UDC 004.891.2
USING EXPERT SYSTEMS IN EDUCATION1
M.S. Chvanova, I.A. Kiseleva, A.A. Molchanov, A.N. Bozyukova
Tambov State University named after G.R. Derzhavina Russia, Tambov. e-mail: [email protected]
The article discusses the problems of using and developing expert systems in education, as well as specific examples of the use of such systems. The authors consider it necessary to use fuzzy logic apparatus for the design and development of an intelligent subsystem.
Key words: information technology, expert system, fuzzy logic, education system.
A study of research on the problem showed that in the early eighties, an independent direction was formed in research on artificial intelligence, called “expert systems” (ES). Researchers in the field of ES often also use the term “knowledge engineering”, introduced by E. Feigenbaum, to name their discipline. Expert systems (ES) are a set of programs that perform the functions of an expert in solving problems from a certain subject area. The name comes from the fact that they seem to imitate people who are experts.
Each expert system consists of three parts: a very large database of modern data, a subsystem for generating questions, and a set of rules that allow drawing conclusions. Some expert systems can tell you the method they use to reach their conclusion.
In our country, the current state of developments in the field of expert systems can be characterized as a stage of increasing interest among broad layers of economists, financiers, teachers, engineers, doctors, psychologists, programmers, and linguists. Unfortunately, this interest has insufficient material support: a clear lack of textbooks and specialized literature, the lack of character processors and artificial intelligence workstations, limited financial resources.
1 The topic was supported within the framework of the Ministry of Education and Science Program “Conducting scientific research by young scientists - candidates of science” No. 14.B37.21.1141, 2012-2013.
funding of research in this area, the weak domestic market for software products for the development of expert systems, and the high cost of existing ones makes their use and analysis of the effectiveness of application practically inaccessible.
It is well known that the process of creating an expert system requires the participation of highly qualified specialists in the field of artificial intelligence, which so far are produced by a small number of higher educational institutions in the country.
An analysis of theoretical research and teaching practice has shown that insufficient attention is paid to the development of expert systems in the distance education system. Expert systems in the field of education are most often used to build a knowledge base that allows you to reflect the minimum required content of a subject area, taking into account its quantitative and qualitative assessments.
Research in the field of application and development of expert systems in education, we believe, can be divided into three groups. It seems possible to include in the first group authors who study the theoretical and pedagogical aspects of the use of expert systems in education. The second group includes authors who have developed specific expert teaching systems together with teachers based on well-known technologies. The third group includes authors who explore new approaches to creating expert systems in education.
Research in the field of application and development of expert systems in education
research, as we believe, can be divided into three groups. It seems possible to include in the first group authors who study the theoretical and pedagogical aspects of the use of expert systems in education. The second group includes authors who have developed specific expert teaching systems together with teachers based on well-known technologies. The third group includes authors who explore new approaches to creating expert systems in education.
Let us consider the first group of publications analyzing the theoretical and pedagogical aspects of the use of expert systems.
In a study by N.L. Yugova designed the content of specialized training using an expert system. The author considers an expert system for conducting diagnostics based on the levels of training and professional preferences of students, which is implemented on the basis of constructing a frame model of profile educational information, establishing subject-subject relationships between participants in the educational process: student, teacher, cognitive scientist.
N.M. Antipina developed a technology for developing professional methodological skills during independent work of students of pedagogical universities using an expert system. A specialized educational expert system developed by the author is capable of issuing individual tasks of various levels of difficulty during students’ independent work at the computer, developing recommendations on how to complete them, providing assistance in the form of consultations, monitoring the knowledge and skills of students at various stages of their implementation of methodological tasks and etc.
N.L. Kiryukhina developed a model of an expert system for diagnosing students’ knowledge in psychology. The author considers an expert system for solving the problem of diagnosing students’ psychological knowledge, testing hypotheses about the correctness of the student’s answers, and the degree of mastery of material on various topics of the course. I.V. Grechin is implementing a new approach to using an expert system in educational technology.
He proposes a system that, when using feedback interactively, generates and tracks the sequence of a chain of reasoning during learning.
ON THE. Baranova considers the issue of using expert systems in continuing pedagogical education. The expert system structures educational information and creates individual curricula for each student with shortened training periods, which increases the efficiency of the learning, teaching and self-education processes.
A.B. Andreev, V.B. Moiseev, Yu.E. Usachev use expert systems to analyze students’ knowledge in an open education environment. Knowledge quality analysis is carried out using an expert knowledge analysis system. To implement such a system, the authors consider a structural approach to the creation of intelligent teaching and monitoring computer systems. Thus, this approach allows us to develop effective means of analyzing students’ knowledge based on the use of a structural model of educational material. The structural unit of a body of knowledge in the proposed model is a concept that has content and scope.
E.V. Myagkova considers the possibility of using expert systems as information technologies in the field of higher education. According to the author, expertise lies in the presence in the expert teaching system of knowledge on teaching methods, thanks to which it helps teachers teach and students learn. The main goal of implementing an expert teaching system, according to the author of the article, is training and assessment of the student’s current level of knowledge relative to the teacher’s level of knowledge. Thus, a comparison of two gratings (the reference grating, reflecting the teacher’s ideas, and the grating filled in by the student during the dialogue) makes it possible to assess the differences in the ideas of the teacher and the student.
B.M. Moskovkin built a simulation expert system for selecting universities for study. The author has conducted a brief review of foreign research in
the field of modeling decision-making processes about choosing colleges and universities for further education. At the conceptual level, a corresponding simulation expert system was built.
Let's consider the second group of publications, which discuss expert systems developed jointly with teachers for education based on well-known technologies.
E.Yu. Levina has developed an intra-university diagnostics of the quality of education based on an automated expert system, the use of which boils down, in essence, to diagnosing the quality of the educational process at a university, which allows, on the basis of information tools and mathematical methods, to manage databases for carrying out research procedures and analyzing statistics of the results of the educational process , development of recommendations for making management decisions to ensure the quality of education.
M.A. Smirnova has developed an expert system for assessing the quality of pedagogical training of a future teacher, which boils down to assessing the quality of his training at school, which makes it possible to study the level of teacher preparedness.
L.S. Bolotova, based on the technology of situational management expert systems, adaptive distance learning in decision making is implemented. As instrumental software, experimental samples of instrumental problem-based subject-oriented expert systems for situational management of municipalities and small businesses have been developed based on the developed situational simulator.
A computer system for making decisions based on the results of expert assessment in problems of assessing the quality of education, developed by O.G. Berestneva and O.V. Marukhina allows us to highlight the most substantiated statements of expert experts and ultimately use them to prepare various decisions. The universal software product developed by the authors and described in the article makes it possible to most optimally solve the problem of assessing the quality of the educational process based on the results of expert assessment.
E.F. The methodology for using expert systems to adjust the learning process and evaluate the effectiveness of pedagogical software is considered. In the course of the research, the author developed an experimental fragment of a pedagogical software tool for learning the Prolog language for 9th grade secondary school students in order to demonstrate the main points of the developed methodology and its experimental testing. The expert system built into the pedagogical software tool was brought to the level of a demonstration prototype.
An analysis of the literature in this area showed that one of the approaches to creating expert systems is attempts to propose the use of fuzzy logic methods based on the theory of fuzzy sets.
V.S. Toiskin identifies several reasons on the basis of which preference is given to the use of systems with fuzzy logic:
It is conceptually easier to understand;
It is flexible and resistant to inaccurate input data;
It can model nonlinear functions of arbitrary complexity;
It takes into account the experience of specialist experts;
It is based on the natural language of human communication.
I.V. Solodovnikov, O.V. Rogozin, O.V. Shu-ruev consider the general principles of constructing a software complex capable of producing comprehensive student performance in a semester using an expert system, using elements of the fuzzy logic apparatus.
Attending lectures. The attendance score was calculated using the arithmetic average of all available scores;
Work at the seminar. Performance evaluation was carried out in a similar manner;
Carrying out inspection work. The assessment of the performance of test work was carried out taking into account the difficulty coefficient;
Doing homework. Performance assessment was carried out in a similar manner.
To assess academic performance, the authors used linguistic variables: “attended lectures,” “worked at a seminar,” “completed tests,” “did homework.” The characteristics of these variables were the concepts of “activity”, “efficiency”, “assessment”. This approach makes it possible to analyze the student’s work and, based on the formulated criteria, evaluate the effectiveness of the quality of the student’s knowledge.
Based on fuzzy logic models I.V. Samoilo, D.O. Zhukov consider the problem of creating expert systems that make it possible to give recommendations on vocational guidance to a specific applicant.
Group of variables (O) - assessments. In the general case, for a group of variables O we can write O = (O1, O2, O3, ..., Op).
Group of variables (C) - psychological tests aimed at identifying abilities related to learning and intelligence.
Group of variables (V) - characteristics of the student’s personality.
Group of variables (M) - results of diagnosing the student’s area of interest: M = (t1, t2, ..., tk).
Thus, the prototype of such a system made it possible to form a mechanism for managing cathedral selection:
The applicant goes to the start page of the system, enters school grades and (or) enters the results of the unified state exam, the results of current academic performance, the system evaluates the reliability of the result using fuzzy logic;
The user undergoes testing of psychological characteristics of personality and ability to learn, areas of interest with
assessing the reliability of the result using fuzzy logic;
An automated expert system (AES) checks whether a given applicant meets the requirements of the department (educational institution). If “yes”, then with the help of the control educational environment the user’s knowledge is corrected, optimal conditions are created for overcoming the departmental “barrier”, in addition, the user has the opportunity to refuse to fight for the department of interest to him and continue his education at the department in which his achievements allow him;
Subsequent testing takes place every six months. Test results help track the dynamics of a student’s development and choose the optimal strategy for shaping a future professional.
O.A. Melikhov is considering the possibility of implementing an expert system for monitoring the educational process of a university based on a fuzzy approach to modeling intelligent systems. This approach uses “linguistic” variables, the relationships between which are described using fuzzy statements and fuzzy algorithms.
Building a system for monitoring the educational process includes the following stages:
Formulation of learning objectives, determination of the level of requirements of each teacher (higher, intermediate, lower);
Construction of a monitoring system, determination of the degree of training in each discipline. Indicators: discrimination, memorization, understanding, basic skills, knowledge transfer;
Determining the actual effectiveness of a teacher based on indicators of the degree of student learning. The main indicators of a teacher’s effectiveness are the strength, depth and awareness of students’ knowledge. These same indicators determine the quality of education.
DI. Popov in his work examines the intelligent distance learning system (ISDL) “KnowledgeCT” based on Internet technologies, which is planned to be used for educational purposes by the Center for Distance Education. She allows
not only assess knowledge, but also collect data about students, which is necessary to create mathematical models of the student and collect statistics.
Knowledge assessment is carried out using an adaptive testing system based on fuzzy logic methods and algorithms: for each level of complexity, an expert in the discipline (teacher) needs to develop an appropriate set of questions. Such a system allows you to make the learning process more flexible, take into account the individual characteristics of the student and increase the accuracy of assessing the student’s knowledge.
V.M. Kureichik, V.V. Markov, Yu.A. Kravchenko in their work explore an approach to the design of intelligent distance learning systems based on rules and inference technologies based on precedents.
Expert systems model the expert's decision-making process as a deductive process using rule-based inference. The system contains a set of rules, according to which, based on the input data, a conclusion is generated on the adequacy of the proposed model. There is a drawback: the deductive model emulates one of the rarer approaches that an expert follows when solving a problem.
Case-based inference draws conclusions based on the results of searching for analogies stored in the precedent database. This method is effective in situations where the main source of knowledge about a problem or situation is experience rather than theory; solutions are not unique to a particular situation and can be used in others to solve similar problems; the goal of inference is not a guaranteed correct solution, but the best possible one. This inference technology can be implemented using neural network algorithms.
An analysis of the literature on the problem of using expert systems in the distance learning system showed that this area has been little studied and is only developing, as evidenced by the small number of publications of research teachers working in this problem field. Publications in this area are mainly of a predictive nature.
There is interest in distributed intelligent systems in the distance learning system, however, it is not entirely clear how the educational process can be effectively organized so that it leads to the desired quality of education. Apparently, we should talk, first of all, about building pedagogical educational models in the open education system.
In our opinion, the problem is due to the fact that a significant part of researchers in the field of distance learning technologies transfer methods and techniques known in practice, filling distance learning with them. At the same time, it is quite obvious that new technologies in education should be based on the principle of “new tasks”. Advanced technologies bring a new solution, new methods, new approaches, new opportunities not yet known to the education system. It has now become obvious that the “traditional lecture” and “traditional textbook” are ineffective in distance learning. We need organized and targeted access to dynamic systems of up-to-date information, we need “automated consultations” available at any time, we need new ways and techniques for organizing joint project activities, and much more.
To date, some experience has been accumulated in transferring part of the intellectual functions of organizing and conducting the educational process in the open education system to information technology.
So, G.A. Samigulina gives an example of an intelligent expert system for distance learning based on artificial immune systems, which allows, depending on the student’s belonging to a certain group, to assess his intellectual potential and, in accordance with it, quickly provide an individual training program. The output is a comprehensive assessment of knowledge, differentiation of students and a forecast of the quality of the education received. Groups are determined by experts and correspond to certain knowledge, practical skills, creativity, logical thinking, etc. The developed expert system implies the implementation of subsystems:
- “Information subsystem” - development of methods and means of storing information, development of databases, knowledge bases. Includes electronic textbooks, reference books, catalogs, libraries, etc.;
- “Intelligent subsystem” - training the immune network, processing multidimensional data in real time. The use of an algorithm for estimating binding energies based on the properties of homologous peptides makes it possible to reduce errors in predicting an intelligent system, which allows students to be trained in accordance with their individual characteristics;
- “Training subsystem” develops methods, means and forms of presenting educational information, adapted to a specific user, taking into account his individual characteristics. A schedule for completing the volume of required work and deadlines for implementation are drawn up;
- “Control subsystem” is intended for a comprehensive assessment of the student’s knowledge for the purpose of prompt adjustment of the program and learning process.
Thus, as a result of operational analysis of the knowledge of a huge number of students, the learning process can be quickly adjusted, since the expert system offers an individual training program.
An analysis of research into expert systems in the field of distance education showed that this is a new and relevant direction in science, which has been little studied. Often, teachers understand an expert system as testing students in one or another distance education system and examining their knowledge.
So, A.V. Zubov and T.S. Denisova developed complex expert Internet systems for distance learning based on the Finport Training System distance learning system. The system has the ability to develop training courses, conduct training and certification, and at the same time analyze the results and effectiveness of training based on tests developed by highly qualified specialists.
V.G. Nikitaev and E.Yu. Berdnikov developed multimedia chicken-
Systems of distance learning for doctors in histological and cytological diagnostics using expert systems based on the Moodle content management system. The system allows you to add courses to the content and, based on testing, check the level of mastery of the material depending on the students’ response.
Thus, in distance learning systems it is possible to make an expert assessment of knowledge based on test tasks developed by specialists.
At the same time, in our opinion, distance learning technologies require the use of many subsystems to relieve routine workload from organizers and tutors. This load increases due to the fact that a person chooses his own rhythm, pace and time of learning. Individualization requires a developed automated system of “intelligent” tips, assistance, consultations throughout the entire period of distance learning and when using various educational methods and techniques: lectures, practice, project activities, conferences, etc. Only unique questions are addressed to the expert teacher. Based on the analysis of publications and personal practice of organizing distance learning, we came to the conclusion that the above intellectual subsystems can be organized on different theoretical and programmatic basis in the form of separate modules connected to the system. This is due to the fact that subsystems carry different intellectual “loads”: in some cases it is enough to use traditional logic when designing a specific subsystem, and in other cases it is convenient to create a subsystem using fuzzy logic.
Bibliography
1. Andreychikov A.V., Andreychikova O.N. Intelligent information systems. M.: Finance and Statistics, 2006.
2. Yugova N.L. Designing the content of specialized training using an expert system: abstract. dis. ...cand. ped. Sci. Izhevsk, 2006.
3. Antipina N.M. Technology for the formation of professional methodological skills in the course of independent work of teaching students
gical universities using an expert system: dis. ...cand. ped. Sci. M., 2000.
4. Kiryukhina N.L. Model of an expert system for diagnosing students’ knowledge in psychology: dis. ...cand. psychol. Sci. M., 1998.
5. Grechin I.V. A new approach to the expert system in educational technology // News of TRTU. Thematic issue "Intelligent CAD". Taganrog: TRTU, 2001. No. 4.
6. Baranova N.A. On the issue of using expert systems in continuing pedagogical education // Education and Science. 2008. No. 4. P. 24-28.
7. Moiseev V.B., Andreev A.B. Intra-university system for ensuring the quality of training of specialists // Engineering education.
2005. No. 3. P. 62-74.
8. Myagkova E.V. The role and possibility of using
research of expert systems as information technologies in the field of higher education // Information technologies in design and production: scientific and technical
magazine. 2008. No. 1. P. 13-15.
9. Moskovkin V.M. Simulation expert system for choosing universities for training // NTI. Series 2. 2009. No. 10. pp. 19-21.
10. Levina E.Yu. Intra-university diagnostics of teaching quality based on an automated expert system: abstract of thesis. dis. ...cand. ped. Sci. Kazan, 2008.
11. Smirnova M.A. Application of an expert system to assess the quality of pedagogical training of a future teacher: dis. ...cand. ped. Sci. Tula, 1997.
12. Bolotova L.S. [and others] Adaptive distance learning in decision making based on the technology of expert systems of situational systems of situational management of municipalities and small businesses // Scientific research. Vol. 5. Annual report on the main results of research work, 2003. M., 2004.
13. Berestneva O.G., Marukhina O.V. Computer decision-making system based on the results of expert assessment in problems of assessing the quality of education // Materials of the regional scientific and methodological conference “Modern education: systems and practice of quality assurance”, Tomsk, January 29-30. 2002 Tomsk, 2002. pp. 29-30.
14. Snizhko E.A. Methodology for using expert systems to adjust the learning process and assess the effectiveness of teaching staff: dis. ...cand. ped. Sci. St. Petersburg, 1997.
15. Toiskin V.S. Intelligent information systems: textbook. Stavropol: Publishing house SGPI, 2010. Part 2.
16. Expert system for assessing the effectiveness of teaching based on the mathematical apparatus of fuzzy logic / I.V. Solodovnikov [and others] // Quality. Innovation. Education. 2006. No. 1. P. 19-22.
17. Samoilo I.V., Zhukov D.O. Information technologies in ensuring new quality of higher education // Collection of scientific articles. Book 2. Proceedings of the All-Russian scientific and practical conference with international participation “Information technologies in ensuring a new quality of higher education (April 14-15, 2010, Moscow, NUST MISIS).” M.: Research Center for Problems of Quality of Training of Specialists NUST "MISiS", 2010. pp. 89-95.
18. Melikhova O.A., Melikhova Z.A. The use of fuzzy mathematics in modeling artificial intelligence systems // Thematic issue “Intelligent CAD”: in 2 volumes. Taganrog: TRTU Publishing House, 2007. pp. 113-119.
19. Popov D.I. Design of intelligent systems for distance education // News of the Southern Federal University. Series: Technical Sciences. 2001. T. 22. No. 4. P. 325-332.
20. Astanin S.V. [etc.] Intelligent educational environment for distance learning // Artificial Intelligence News. 2003. No. 1.
21. Samigulina G.A. Intelligent expert system of distance learning based on artificial immune systems // Information technologies of modeling and control. 2007. Vol. 9 (43). pp. 1019-1024.
22. Zubov A.V., Denisova T.S. Creation of complex expert Internet systems for distance learning // Informatization of education and science. M.: State Research Institute of Information Technologies and Telecommunications, 2010.
23. Nikitaev V.G., Berdnikovich E.Yu. Development of multimedia distance learning courses for doctors on histological and cytological diagnostics using expert systems // Fundamental Research: Scientific Journal. 2007. No. 12. P. 334-334.
1. Andrejchikov A.V., Andrejchikova O.N. Intel-lektual"nye informacionnye system. M.: Finansy i statistika, 2006.
2. Jugova N.L. Konstruirovanie soderzhanija pro-fil"nogo obuchenija s primeneniem ekspertnoj sis-temy: avtoref. dis. ... kand. ped. nauk. Izhevsk,
3. Antipina N.M. Tehnologija formirovanija profes-sional"nyh metodicheskih umenij v hode samosto-jatel"noj raboty studentov pedagogicheskih vuzov
s primeneniem ekspertnoj systemy: dis. ... kand. ped. nauk. M., 2000.
4. Kirjuhina N.L. Model" ekspertnoj sistemy diag-nostiki znanij studentov po psihologii: dis. ... kand. psihol. nauk. M., 1998.
5. Grechin I.V. Novyj podhod k jekspertnoj sisteme v tehnologii obuchenija // Izvestija TRTU. Tema-ticheskij vypusk "Intellektual"nye SAPR". Taganrog: TRTU, 2001. No. 4. S. 343-344.
6. Baranova N.A. K voprosu o primenenii ekspertnyh sistem v nepreryvnom pedagogicheskom obrazo-vanii // Obrazovanie i nauka. 2008. No. 4. S. 24-28.
7. Moiseev V.B., Andreev A.B. Vnutrivuzovskaja sistema obespechenija kachestva podgotovki specialistov // Inzhenernoe obrazovanie. 2005. No. 3. S. 62-74.
8. Mjagkova E.V. Rol" i vozmozhnost" primenenija
ekspertnyh sistem kak informacionnyh tehnologij v sfere vysshego obrazovanija // Information-nye tehnologii v proektirovanii i proizvodstve: nauchno-tehnicheskij zhurnal. 2008. No. 1.
9. Moskovkin V.M. Imitacionnaja ekspertnaja sistema vybora universitetov dlja obuchenija // NTI. Serija 2. 2009. No. 10. S. 19-21.
10. Levina E.Ju. Vnutrivuzovskaja diagnostika kachestva obuchenija na osnove avtomatizirovan-noj ekspertnoj systemy: avtoref. dis. ... kand. ped. nauk. Kazan", 2008.
11. Smirnova M.A. Primenenie ekspertnoj sistemy dlja ocenki kachestva pedagogicheskoj podgotovki budushhego uchitelja: dis. ... kand. ped. nauk. Tula, 1997.
12. Bolotova L.S. . Adaptivnoe distancionnoe obuchenie prinjatiju reshenij na osnove tehnologii ekspertnyh sistem situacionnogo sistem situacion-nogo upravlenija municipal"nymi obrazovanijami i malym biznesom // Nauchnye issledovanija. Vyp.
5. Ezhegodnyj otchet ob osnovnyh rezul "tatah nauchnoissledovatel"skih rabot, 2003. M., 2004.
13. Berestneva O.G., Maruhina O.V. Komp"juternaja sistema prinjatija reshenij po rezul"tatam jeks-pertnogo ocenivanija v zadachah ocenki kachest-va obrazovanija // Materialy regional"noj nauch-no-metodicheskoj konferencii "Modern ob-razovanie: sistemy i praktika obespechenija ka-chestva", Tomsk, 29-30 Jan. 2002. Tomsk, 2002. S. 29-30.
14. Snizhko E.A. Metodika primenenija jekspertnyh sistem dlja korrektirovki processa obuchenija i ocenki jeffektivnosti PPS: dis. ... kand. ped. nauk. SPb., 1997.
15. Toiskin V.S. Intellectual "nye informacionnye systemy: uchebnoe posobie. Stavropol": Izd-vo SGPI, 2010. Ch. 2.
16. Solodovnikov I.V. Ekspertnaja sistema ocenki jeffektivnosti obuchenija na osnove ma-
tematicheskogo apparata nechetkoj logiki // Kachestvo. Innovacii. Obrazovanie, 2006. No. 1.
17. Samojlo I.V., Zhukov D.O. Informacionnye tehnologii v obespechenii novogo kachestva vys-shego obrazovanija // Sbornik nauchnyh statej. Kn. 2. Trudy Vserossijskoj nauchno-praktiche-skoj konferencii s mezhdunarodnym uchastiem “Informacionnye tehnologii v obespechenii no-vogo kachestva vysshego obrazovanija (14-15 Apr. 2010, Moskva, NITU “MISiS”).” M.: Issledo-vatel "skij centr problem kachestva podgotovki specialistov NITU "MISiS", 2010. S. 89-95.
18. Melihova O.A., Melihova Z.A. Ispol"zovanie nechetkoj matematiki pri modelirovanii sistem iskusstvennogo intellekta // Tematicheskij vypusk "Intellektual"nye SAPR": v 2 t. Taganrog: Izd-vo TRTU, 2007. S. 113-119.
19. Popov D.I. Proektirovanie intellektual "nyh sistem distancionnogo obrazovanija // Izvestija Juzhno-go federal"nogo universiteta. Serija: Technicheskie nauki. 2001. T. 22. No. 4. S. 325-332.
20. Astanin S.V. Intellektual"naja obrazova-tel"naja sreda distancionnogo obuchenija // No-vosti iskusstvennogo intellekta. 2003. No. 1.
21. Samigulina G.A. Intellektual"naja jekspertnaja sistema distancionnogo obuchenija na osnove iskusstvennyh immunnyh sistem // Information-nye tehnologii modelirovanija i upravlenija.
2007. Vyp. 9 (43). S. 1019-1024.
22. Zubov A.V., Denisova T.S. Sozdanie kompleks-nyh ekspertnyh Internet-sistem dlja distancion-nogo obuchenija // Informatizacija obrazovanija i nauki. M.: Gosudarstvennyj nauchnoissledova-tel"skij institut informacionnyh tehnologij i tele-kommunikacij, 2010.
23. Nikitaev V.G., Berdnikovich E.Ju. Razrabotka mul"timedijnyh kursov distancionnogo obuchenija vrachej po gistologicheskoj i citologicheskoj diagnostike s primeneniem ekspertnyh sistem // Fundamental"nye issledovanija: nauchnyj zhur-nal. 2007. No. 12. S. 334-334.
USE OF EXPERT SYSTEMS IN EDUCATION
M.S. Chvanova, I.A. Kiseleva, A.A. Molchanov, A.N. Bozyukova Tambov State University named after G.R. Derzhavin Tambov, Russia. e-mail: [email protected]
The article considers the problems of use and development of expert systems in education, as well as actual examples of use of such systems. The authors consider it necessary to use fuzzy logic to design and develop an intelligent subsystem.
Key words: information technologies, expert system, fuzzy logic, system of education.
Topic 1. EOS as a component of intensive training of specialists.
Lecture 8. Expert learning systems.
Areas of application of expert systems in management.
Cost of expert systems.
Development of expert systems.
Over the past twenty years, specialists in the field of intelligent systems have been conducting active research in the field of creating and using expert systems intended for the field of education. A new class of expert systems has emerged - expert teaching systems - the most promising direction for improving software pedagogical tools in the direction of procedural knowledge.
An expert system is a set of computer software that helps a person make informed decisions. Expert systems use information received in advance from experts - people who are the best specialists in any field.
Expert systems must:
- store knowledge about a specific subject area (facts, descriptions of events and patterns);
- be able to communicate with the user in limited natural language (i.e. ask questions and understand the answers);
- have a set of logical tools for deriving new knowledge, identifying patterns, and detecting contradictions;
- pose a problem upon request, clarify its formulation and find a solution;
- Explain to the user how the solution was obtained.
It is also desirable that the expert system be able to:
- provide information that increases user confidence in the expert system;
- “tell” about yourself, about your own structure
An expert learning system (ETS) is a program that implements one or another pedagogical goal based on the knowledge of an expert in a certain subject area, diagnosing learning and learning management, and also demonstrating the behavior of experts (subject specialists, methodologists, psychologists). The expertise of EOS lies in its knowledge of teaching methods, thanks to which it helps teachers teach and students learn.
The architecture of an expert learning system includes two main components: a knowledge base (a repository of knowledge units) and a software tool for accessing and processing knowledge, consisting of mechanisms for drawing conclusions (decisions), acquiring knowledge, explaining the results obtained, and an intelligent interface.
Data exchange between the student and the EOS is performed by an intelligent interface program that receives the student’s messages and converts them into a knowledge base representation form and, conversely, translates the internal representation of the processing result into the student’s format and outputs the message to the required medium. The most important requirement for organizing a dialogue between a student and an EOS is naturalness, which does not mean literally formulating the student’s needs in natural language sentences. It is important that the sequence of solving the problem is flexible, corresponds to the student’s ideas and is conducted in professional terms.
The presence of a developed system of explanations (SO) is extremely important for EOS working in the field of education. During the learning process, such an EOS will play not only the active role of a “teacher”, but also the role of a reference book, helping the student to study the internal processes occurring in the system using modeling of the application area. A developed communication system consists of two components: active, which includes a set of information messages issued to the student in the process of work, depending on the specific path to solving the problem, completely determined by the system; passive (the main component of SO), focused on the initializing actions of the student.
The active component of the CO is a detailed comment accompanying the actions and results obtained by the system. The passive component of information support is a qualitatively new type of information support, inherent only in knowledge-based systems. This component, in addition to a developed system of HELPs called by the student, has systems for explaining the progress of solving the problem. The system of explanations in existing EOS is implemented in various ways. It can be: a set of information certificates about the state of the system; full or partial description of the path taken by the system along the decision tree; a list of hypotheses being tested (the basis for their formation and the results of their testing); a list of goals that govern the operation of the system and ways to achieve them.
An important feature of a developed communication system is the use of natural language of communication with the learner. The widespread use of “menu” systems allows not only to differentiate information, but also, in developed electronic systems, to judge the level of preparedness of the student, forming his psychological portrait.
However, the learner may not always be interested in the complete output of the solution, which contains many unnecessary details. In this case, the system should be able to select only key points from the chain, taking into account their importance and the level of knowledge of the student. To do this, it is necessary to support a model of the learner’s knowledge and intentions in the knowledge base. If the student continues to not understand the answer received, then the system should, in a dialogue based on the supported model of problematic knowledge, teach him certain fragments of knowledge, i.e. reveal in more detail individual concepts and dependencies, even if these details were not directly used in the conclusion.
Expert system for training
is a software system that implements the learning function based on expert knowledge. EOS capabilities: Network presentation of training courses
Learner models
Generation of security questions and data for analysis of answers to them
Possibility of increasing knowledge bases, skills and abilities
Expert system tasks: provide the student with clear criteria for achieving educational goals (control system),
help him build an optimal individual training schedule.
save the results of previous consultations.
Expert system for solving problems in the subject area being studied
Expert system for diagnosing student errors
Expert system for planning the exercise management process
1. Teaching
Network presentation of training courses
Learner models
Generation of security questions and data for analysis of answers to them
Possibility of increasing knowledge bases, skills and abilities
Expert system tasks: provide the student with clear criteria for achieving educational goals (control system),
help him build an optimal individual training schedule.
save the results of previous consultations.
Expert system for solving problems in the subject area being studied
Expert system for diagnosing student errors
Expert system for planning the exercise management process
1. Teaching
provide the student with clear criteria for achieving educational goals (control system),
help him build an optimal individual training schedule.
save the results of previous consultations.
Expert system for solving problems in the subject area being studied
Expert system for diagnosing student errors
Expert system for planning the exercise management process
1. Teaching
1. Teaching . Creating an environment for knowledge acquisition.
2. Education. Performing the functions of a teacher in presenting the material, monitoring its assimilation and diagnosing errors
3. Monitoring and diagnostics . Providing test questions, evaluating answers and identifying errors.
4. Training . Creating an environment that allows you to acquire and consolidate the required skills and abilities.
Expert Shell
Expert Shell
designed to organize training in the “computer-student” mode. Training as part of the Chopin information and educational environment takes place according to an individual curriculum and at an individual pace. The expert shell in the environment plays the role of an adviser who, based on the student’s real achievements recorded in the database of testing and training results, builds a training plan and makes decisions about the student achieving a certain level of knowledge about the subject area. VIPES – hybrid shell 
VIPES is designed to work online. This shell is multi-user. This system uses a graphical user interface. Subject specialists and teachers are able to independently create and edit knowledge bases for the VIPES shell.
Test Shell
Data Analysis Console
Multi-user ES shell with a visual interface
Training and testing database
File system for test and training course data
Learning Shell
Service module
Testing of initial data
Test Shell
Data Analysis Console
Multi-user ES shell with a visual interface
Training and testing database
File system for test and training course data
Learning Shell
Service module
Testing of initial data includes verification of factual information that serves as the basis for the examination.
Logical testing of the knowledge base consists in detecting logical errors in the production system that do not depend on the subject area; missing and overlapping rules; inconsistent and terminal clauses (inconsistent conditions).
Concept testing
is carried out to check the general structure of the system and take into account all aspects of the problem being solved. 
1. Simplicity of solving the initial problem of building a system.
2. Possibility of adding to the testing system during use.
3. A fairly simple scheme for practical use.
4. Attractiveness for the user due to the time and effort spent on testing knowledge. 
offering several answer options indirectly encourages the user to analyze various solutions and explore the task in more depth.
Reviewing expert system.
One of the ways to solve the problem of intensifying the educational process is to use the latest information technologies in the training and internship of young specialists.
To solve this problem, a project has been developed to create a reviewing expert system that performs the functions of an expert - consultant and teacher at the same time.
An expert system is a program that is designed to simulate human intelligence, experience, and the process of cognition.
With an expert system based on a peer-review approach, the user provides more data as well as his or her own solution or course of action.
The system evaluates the user's plan and provides critical analysis.
The critique includes alternatives, explanations, justifications, warnings, and additional information to consider. 
The reviewing expert system implements two types of abilities: The system can function like a conventional expert system
The system can analyze any of the possible plans proposed by the user in the context of a scenario of possible actions, and produce a practical critical analysis.
The system can function like a conventional expert system
The system can analyze any of the possible plans proposed by the user in the context of a scenario of possible actions, and produce a practical critical analysis.
1. The user enters information regarding the current action and submits his operating plan or set of actions.
2. the entered data is analyzed
3. the user gets the required result.
4. If the user has specified an action plan as unknown, the reviewing expert system will function as a regular expert system and will produce a plan recommended by the expert. 
All expert systems perform different functions, but they pursue one single goal - to compare a given task with the available information in the database and perform the function that the given expert system performs.
What is an expert-learning system?
What are the 3 aspects of expert system testing?
-
Topic 1. EOS as a component of intensive training of specialists.
Lecture 8. Expert learning systems.
Areas of application of expert systems in management.
Cost of expert systems.
Development of expert systems.
Over the past twenty years, specialists in the field of intelligent systems have been conducting active research in the field of creating and using expert systems intended for the field of education. A new class of expert systems has emerged - expert teaching systems - the most promising direction for improving software pedagogical tools in the direction of procedural knowledge.
An expert system is a set of computer software that helps a person make informed decisions. Expert systems use information received in advance from experts - people who are the best specialists in any field.
Expert systems must:
- store knowledge about a specific subject area (facts, descriptions of events and patterns);
- be able to communicate with the user in limited natural language (i.e. ask questions and understand the answers);
- have a set of logical tools for deriving new knowledge, identifying patterns, and detecting contradictions;
- pose a problem upon request, clarify its formulation and find a solution;
- Explain to the user how the solution was obtained.
It is also desirable that the expert system be able to:
- provide information that increases user confidence in the expert system;
- “tell” about yourself, about your own structure
An expert learning system (ETS) is a program that implements one or another pedagogical goal based on the knowledge of an expert in a certain subject area, diagnosing learning and learning management, and also demonstrating the behavior of experts (subject specialists, methodologists, psychologists). The expertise of EOS lies in its knowledge of teaching methods, thanks to which it helps teachers teach and students learn.
The architecture of an expert learning system includes two main components: a knowledge base (a repository of knowledge units) and a software tool for accessing and processing knowledge, consisting of mechanisms for drawing conclusions (decisions), acquiring knowledge, explaining the results obtained, and an intelligent interface.
Data exchange between the student and the EOS is performed by an intelligent interface program that receives the student’s messages and converts them into a knowledge base representation form and, conversely, translates the internal representation of the processing result into the student’s format and outputs the message to the required medium. The most important requirement for organizing a dialogue between a student and an EOS is naturalness, which does not mean literally formulating the student’s needs in natural language sentences. It is important that the sequence of solving the problem is flexible, corresponds to the student’s ideas and is conducted in professional terms.
The presence of a developed system of explanations (SO) is extremely important for EOS working in the field of education. During the learning process, such an EOS will play not only the active role of a “teacher”, but also the role of a reference book, helping the student to study the internal processes occurring in the system using modeling of the application area. A developed communication system consists of two components: active, which includes a set of information messages issued to the student in the process of work, depending on the specific path to solving the problem, completely determined by the system; passive (the main component of SO), focused on the initializing actions of the student.
The active component of the CO is a detailed comment accompanying the actions and results obtained by the system. The passive component of information support is a qualitatively new type of information support, inherent only in knowledge-based systems. This component, in addition to a developed system of HELPs called by the student, has systems for explaining the progress of solving the problem. The system of explanations in existing EOS is implemented in various ways. It can be: a set of information certificates about the state of the system; full or partial description of the path taken by the system along the decision tree; a list of hypotheses being tested (the basis for their formation and the results of their testing); a list of goals that govern the operation of the system and ways to achieve them.
An important feature of a developed communication system is the use of natural language of communication with the learner. The widespread use of “menu” systems allows not only to differentiate information, but also, in developed electronic systems, to judge the level of preparedness of the student, forming his psychological portrait.
However, the learner may not always be interested in the complete output of the solution, which contains many unnecessary details. In this case, the system should be able to select only key points from the chain, taking into account their importance and the level of knowledge of the student. To do this, it is necessary to support a model of the learner’s knowledge and intentions in the knowledge base. If the student continues to not understand the answer received, then the system should, in a dialogue based on the supported model of problematic knowledge, teach him certain fragments of knowledge, i.e. reveal in more detail individual concepts and dependencies, even if these details were not directly used in the conclusion.
Classification of computer training systems
Computer teaching aids are divided into:
· computer textbooks;
- domain-specific environments;
- laboratory workshops;
- simulators;
- knowledge control systems;
- reference books and databases for educational purposes;
- instrumental systems;
- expert learning systems.
Automated learning systems (ATS) are complexes of software, hardware, educational and methodological tools that ensure active learning activities. ATS provide not only teaching specific knowledge, but also checking students’ answers, providing hints, making the material being studied entertaining, etc.
AOS are complex human-machine systems that combine a number of disciplines into one: didactics (the goals, content, patterns and principles of teaching are scientifically substantiated); psychology (the character traits and mental makeup of the student are taken into account); modeling, computer graphics, etc.
The main means of interaction between the student and the AOS is dialogue. The dialogue with the training system can be controlled by both the learner and the system. In the first case, the student himself determines the mode of his work with AOS, choosing a method of studying the material that corresponds to his individual abilities. In the second case, the method and method of studying the material is chosen by the system, presenting the student with frames of educational material and questions to them in accordance with the scenario. The student enters his answers into the system, which interprets their meaning for itself and issues a message about the nature of the answer. Depending on the degree of correctness of the answer, or on the student’s questions, the system organizes the launch of certain paths of the learning scenario, choosing a learning strategy and adapting to the student’s level of knowledge.
Expert training systems (ETS). They implement training functions and contain knowledge from a certain rather narrow subject area. EOS have the ability to explain the strategy and tactics for solving a problem in the subject area being studied and provide monitoring of the level of knowledge, skills and abilities with the diagnosis of errors based on learning results.
Educational databases (UBD) and educational knowledge bases (UBZ), focused on a certain subject area. UDBs allow you to create data sets for a given educational task and select, sort, analyze and process the information contained in these sets. The UBZ, as a rule, contains a description of the basic concepts of the subject area, strategy and tactics for solving problems; a set of proposed exercises, examples and problems in the subject area, as well as a list of possible student errors and information for correcting them; a database containing a list of methodological techniques and organizational forms of training.
Multimedia systems. They allow you to implement intensive methods and forms of training, increase learning motivation through the use of modern means of processing audiovisual information, increase the level of emotional perception of information, and develop the ability to implement various forms of independent information processing activities.
Multimedia systems are widely used to study processes of various natures based on their modeling. Here you can make visible the life of elementary particles of the microworld, invisible to the ordinary eye, when studying physics, talk figuratively and clearly about abstract and n-dimensional worlds, clearly explain how this or that algorithm works, etc. The ability to simulate a real process in color and with sound takes learning to a whole new level.
Systems<Виртуальная реальность>. They are used in solving constructive-graphic, artistic and other problems where it is necessary to develop the ability to create a mental spatial construction of a certain object based on its graphical representation; when studying stereometry and drawing; in computerized simulators of technological processes, nuclear installations, aviation, sea and land transport, where without such devices it is fundamentally impossible to develop the skills of human interaction with modern highly complex and dangerous mechanisms and phenomena.
Educational computer telecommunication networks. They allow for distance learning (DL) - learning at a distance, when the teacher and student are separated spatially and (or) in time, and the educational process is carried out using telecommunications, mainly based on the Internet. Many people at the same time have the opportunity to improve their education at home (for example, adults burdened with business and family concerns, young people living in rural areas or small towns). At any period of his life, a person has the opportunity to remotely acquire a new profession, improve his qualifications and broaden his horizons, and in almost any scientific or educational center in the world.
All main types of computer telecommunications are used in educational practice: e-mail, electronic bulletin boards, teleconferences and other Internet capabilities. DL also provides for the autonomous use of courses recorded on video discs, CDs, etc. Computer telecommunications provide:
- the ability to access various sources of information via the Internet and work with this information;
- the possibility of prompt feedback during a dialogue with the teacher or with other participants in the training course;
- the possibility of organizing joint telecommunications projects, including international teleconferences, the possibility of exchanging opinions with any participant in this course, teacher, consultants, the possibility of requesting information on any issue of interest through teleconferences.
- the ability to implement remote creativity methods, such as participation in remote conferences, remote<мозговой штурм>network creative works, comparative analysis of information on the WWW, distance research, collective educational projects, business games, workshops, virtual excursions, etc.
Collaborative work encourages students to become familiar with different points of view on the problem being studied, to search for additional information, and to evaluate their own results.
Topic 2.3. Presentation software and office programming basics
Topic 2.4.
2.4.11. Training database with the main button form "Training_students" - Download
Database management systems and expert systems
2.4. Database management systems and expert systems
2.4.10. Expert and learning systems
Expert systems are one of the main applications of artificial intelligence. Artificial intelligence is one of the branches of computer science that deals with the problems of hardware and software modeling of those types of human activities that are considered intellectual.
The results of research on artificial intelligence are used in intelligent systems that are capable of solving creative problems belonging to a specific subject area, knowledge about which is stored in the memory (knowledge base) of the system. Artificial intelligence systems are focused on solving a large class of problems, which include the so-called partially structured or unstructured tasks (weakly formalizable or unformalizable tasks).
Information systems used to solve semi-structured problems are divided into two types:
- Creating management reports (performing data processing: searching, sorting, filtering). Decisions are made based on the information contained in these reports.
- Developing possible solution alternatives. Decision making comes down to choosing one of the proposed alternatives.
Information systems that develop solution alternatives can be model or expert:
- Model information systems provide the user with models (mathematical, statistical, financial, etc.) that help ensure the development and evaluation of solution alternatives.
- Expert information systems provide the development and assessment of possible alternatives by the user through the creation of systems based on knowledge obtained from specialist experts.
Expert systems are computer programs that accumulate the knowledge of specialists - experts in specific subject areas, which are designed to obtain acceptable solutions in the process of information processing. Expert systems transform the experience of experts in any particular field of knowledge into the form of heuristic rules and are intended for consultation of less qualified specialists.
It is known that knowledge exists in two forms: collective experience and personal experience. If a subject area is represented by collective experience (for example, higher mathematics), then this subject area does not need expert systems. If in a subject area most of the knowledge is the personal experience of high-level specialists and this knowledge is weakly structured, then such an area needs expert systems. Modern expert systems have found wide application in all spheres of the economy.
The knowledge base is the core of the expert system. The transition from data to knowledge is a consequence of the development of information systems. Databases are used to store data, and knowledge bases are used to store knowledge. Databases, as a rule, store large amounts of data with a relatively low cost, while knowledge bases store small but expensive information sets.
A knowledge base is a body of knowledge described using the selected form of its presentation. Filling the knowledge base is one of the most difficult tasks, which is associated with the selection of knowledge, its formalization and interpretation.
The expert system consists of:
- a knowledge base (as part of working memory and a rule base), designed to store initial and intermediate facts in working memory (it is also called a database) and store models and rules for manipulating models in the rule base;
- a problem solver (interpreter), which ensures the implementation of a sequence of rules for solving a specific problem based on facts and rules stored in databases and knowledge bases;
- explanation subsystem allows the user to get answers to the question: “Why did the system make this decision?”;
- a knowledge acquisition subsystem designed to both add new rules to the knowledge base and modify existing rules;
- user interface, a set of programs that implement the user’s dialogue with the system at the stage of entering information and obtaining results.
Expert systems differ from traditional data processing systems in that they typically use symbolic representation, symbolic inference, and heuristic search for solutions. For solving weakly formalizable or non-formalizable problems, neural networks or neurocomputers are more promising.
The basis of neurocomputers is made up of neural networks - hierarchical organized parallel connections of adaptive elements - neurons, which ensure interaction with objects of the real world in the same way as the biological nervous system.
Great successes in the use of neural networks have been achieved in the creation of self-learning expert systems. The network is configured, i.e. train by passing all known solutions through it and achieving the required answers at the output. The setup consists of selecting the parameters of the neurons. Often they use a specialized training program that trains the network. After training, the system is ready for operation.
If in an expert system its creators pre-load knowledge in a certain form, then in neural networks it is unknown even to the developers how knowledge is formed in its structure in the process of learning and self-learning, i.e. the network is a “black box”.
Neurocomputers, as artificial intelligence systems, are very promising and can be endlessly improved in their development.
Currently, artificial intelligence systems in the form of expert systems and neural networks are widely used in solving financial and economic problems.
What is an expert-learning system?
What are the 3 aspects of expert system testing?
Topic 1. EOS as a component of intensive training of specialists.
Lecture 8. Expert learning systems.
Areas of application of expert systems in management.
Cost of expert systems.
Development of expert systems.
Over the past twenty years, specialists in the field of intelligent systems have been conducting active research in the field of creating and using expert systems intended for the field of education. A new class of expert systems has emerged - expert teaching systems - the most promising direction for improving software pedagogical tools in the direction of procedural knowledge.
An expert system is a set of computer software that helps a person make informed decisions. Expert systems use information received in advance from experts - people who are the best specialists in any field.
Expert systems must:
- store knowledge about a specific subject area (facts, descriptions of events and patterns);
- be able to communicate with the user in limited natural language (i.e. ask questions and understand the answers);
- have a set of logical tools for deriving new knowledge, identifying patterns, and detecting contradictions;
- pose a problem upon request, clarify its formulation and find a solution;
- Explain to the user how the solution was obtained.
It is also desirable that the expert system be able to:
- provide information that increases user confidence in the expert system;
- “tell” about yourself, about your own structure
An expert learning system (ETS) is a program that implements one or another pedagogical goal based on the knowledge of an expert in a certain subject area, diagnosing learning and learning management, and also demonstrating the behavior of experts (subject specialists, methodologists, psychologists). The expertise of EOS lies in its knowledge of teaching methods, thanks to which it helps teachers teach and students learn.
The architecture of an expert learning system includes two main components: a knowledge base (a repository of knowledge units) and a software tool for accessing and processing knowledge, consisting of mechanisms for drawing conclusions (decisions), acquiring knowledge, explaining the results obtained, and an intelligent interface.
Data exchange between the student and the EOS is performed by an intelligent interface program that receives the student’s messages and converts them into a knowledge base representation form and, conversely, translates the internal representation of the processing result into the student’s format and outputs the message to the required medium. The most important requirement for organizing a dialogue between a student and an EOS is naturalness, which does not mean literally formulating the student’s needs in natural language sentences. It is important that the sequence of solving the problem is flexible, corresponds to the student’s ideas and is conducted in professional terms.
The presence of a developed system of explanations (SO) is extremely important for EOS working in the field of education. During the learning process, such an EOS will play not only the active role of a “teacher”, but also the role of a reference book, helping the student to study the internal processes occurring in the system using modeling of the application area. A developed communication system consists of two components: active, which includes a set of information messages issued to the student in the process of work, depending on the specific path to solving the problem, completely determined by the system; passive (the main component of SO), focused on the initializing actions of the student.
The active component of the CO is a detailed comment accompanying the actions and results obtained by the system. The passive component of information support is a qualitatively new type of information support, inherent only in knowledge-based systems. This component, in addition to a developed system of HELPs called by the student, has systems for explaining the progress of solving the problem. The system of explanations in existing EOS is implemented in various ways. It can be: a set of information certificates about the state of the system; full or partial description of the path taken by the system along the decision tree; a list of hypotheses being tested (the basis for their formation and the results of their testing); a list of goals that govern the operation of the system and ways to achieve them.
An important feature of a developed communication system is the use of natural language of communication with the learner. The widespread use of “menu” systems allows not only to differentiate information, but also, in developed electronic systems, to judge the level of preparedness of the student, forming his psychological portrait.
However, the learner may not always be interested in the complete output of the solution, which contains many unnecessary details. In this case, the system should be able to select only key points from the chain, taking into account their importance and the level of knowledge of the student. To do this, it is necessary to support a model of the learner’s knowledge and intentions in the knowledge base. If the student continues to not understand the answer received, then the system should, in a dialogue based on the supported model of problematic knowledge, teach him certain fragments of knowledge, i.e. reveal in more detail individual concepts and dependencies, even if these details were not directly used in the conclusion.
Classification of computer training systems
Computer teaching aids are divided into:
· computer textbooks;
- domain-specific environments;
- laboratory workshops;
- simulators;
- knowledge control systems;
- reference books and databases for educational purposes;
- instrumental systems;
- expert learning systems.
Automated learning systems (ATS) are complexes of software, hardware, educational and methodological tools that ensure active learning activities. ATS provide not only teaching specific knowledge, but also checking students’ answers, providing hints, making the material being studied entertaining, etc.
AOS are complex human-machine systems that combine a number of disciplines into one: didactics (the goals, content, patterns and principles of teaching are scientifically substantiated); psychology (the character traits and mental makeup of the student are taken into account); modeling, computer graphics, etc.
The main means of interaction between the student and the AOS is dialogue. The dialogue with the training system can be controlled by both the learner and the system. In the first case, the student himself determines the mode of his work with AOS, choosing a method of studying the material that corresponds to his individual abilities. In the second case, the method and method of studying the material is chosen by the system, presenting the student with frames of educational material and questions to them in accordance with the scenario. The student enters his answers into the system, which interprets their meaning for itself and issues a message about the nature of the answer. Depending on the degree of correctness of the answer, or on the student’s questions, the system organizes the launch of certain paths of the learning scenario, choosing a learning strategy and adapting to the student’s level of knowledge.
Expert training systems (ETS). They implement training functions and contain knowledge from a certain rather narrow subject area. EOS have the ability to explain the strategy and tactics for solving a problem in the subject area being studied and provide monitoring of the level of knowledge, skills and abilities with the diagnosis of errors based on learning results.
Educational databases (UBD) and educational knowledge bases (UBZ), focused on a certain subject area. UDBs allow you to create data sets for a given educational task and select, sort, analyze and process the information contained in these sets. The UBZ, as a rule, contains a description of the basic concepts of the subject area, strategy and tactics for solving problems; a set of proposed exercises, examples and problems in the subject area, as well as a list of possible student errors and information for correcting them; a database containing a list of methodological techniques and organizational forms of training.
Multimedia systems. They allow you to implement intensive methods and forms of training, increase learning motivation through the use of modern means of processing audiovisual information, increase the level of emotional perception of information, and develop the ability to implement various forms of independent information processing activities.
Multimedia systems are widely used to study processes of various natures based on their modeling. Here you can make visible the life of elementary particles of the microworld, invisible to the ordinary eye, when studying physics, talk figuratively and clearly about abstract and n-dimensional worlds, clearly explain how this or that algorithm works, etc. The ability to simulate a real process in color and with sound takes learning to a whole new level.
Systems<Виртуальная реальность>. They are used in solving constructive-graphic, artistic and other problems where it is necessary to develop the ability to create a mental spatial construction of a certain object based on its graphical representation; when studying stereometry and drawing; in computerized simulators of technological processes, nuclear installations, aviation, sea and land transport, where without such devices it is fundamentally impossible to develop the skills of human interaction with modern highly complex and dangerous mechanisms and phenomena.
Educational computer telecommunication networks. They allow for distance learning (DL) - learning at a distance, when the teacher and student are separated spatially and (or) in time, and the educational process is carried out using telecommunications, mainly based on the Internet. Many people at the same time have the opportunity to improve their education at home (for example, adults burdened with business and family concerns, young people living in rural areas or small towns). At any period of his life, a person has the opportunity to remotely acquire a new profession, improve his qualifications and broaden his horizons, and in almost any scientific or educational center in the world.
All main types of computer telecommunications are used in educational practice: e-mail, electronic bulletin boards, teleconferences and other Internet capabilities. DL also provides for the autonomous use of courses recorded on video discs, CDs, etc. Computer telecommunications provide:
- the ability to access various sources of information via the Internet and work with this information;
- the possibility of prompt feedback during a dialogue with the teacher or with other participants in the training course;
- the possibility of organizing joint telecommunications projects, including international teleconferences, the possibility of exchanging opinions with any participant in this course, teacher, consultants, the possibility of requesting information on any issue of interest through teleconferences.
- the ability to implement remote creativity methods, such as participation in remote conferences, remote<мозговой штурм>network creative works, comparative analysis of information on the WWW, distance research, collective educational projects, business games, workshops, virtual excursions, etc.
Collaborative work encourages students to become familiar with different points of view on the problem being studied, to search for additional information, and to evaluate their own results.
Topic 2.3. Presentation software and office programming basics
Topic 2.4.
2.4.11. Training database with the main button form "Training_students" - Download
Database management systems and expert systems
2.4. Database management systems and expert systems
2.4.10. Expert and learning systems
Expert systems are one of the main applications of artificial intelligence. Artificial intelligence is one of the branches of computer science that deals with the problems of hardware and software modeling of those types of human activities that are considered intellectual.
The results of research on artificial intelligence are used in intelligent systems that are capable of solving creative problems belonging to a specific subject area, knowledge about which is stored in the memory (knowledge base) of the system. Artificial intelligence systems are focused on solving a large class of problems, which include the so-called partially structured or unstructured tasks (weakly formalizable or unformalizable tasks).
Information systems used to solve semi-structured problems are divided into two types:
- Creating management reports (performing data processing: searching, sorting, filtering). Decisions are made based on the information contained in these reports.
- Developing possible solution alternatives. Decision making comes down to choosing one of the proposed alternatives.
Information systems that develop solution alternatives can be model or expert:
- Model information systems provide the user with models (mathematical, statistical, financial, etc.) that help ensure the development and evaluation of solution alternatives.
- Expert information systems provide the development and assessment of possible alternatives by the user through the creation of systems based on knowledge obtained from specialist experts.
Expert systems are computer programs that accumulate the knowledge of specialists - experts in specific subject areas, which are designed to obtain acceptable solutions in the process of information processing. Expert systems transform the experience of experts in any particular field of knowledge into the form of heuristic rules and are intended for consultation of less qualified specialists.
It is known that knowledge exists in two forms: collective experience and personal experience. If a subject area is represented by collective experience (for example, higher mathematics), then this subject area does not need expert systems. If in a subject area most of the knowledge is the personal experience of high-level specialists and this knowledge is weakly structured, then such an area needs expert systems. Modern expert systems have found wide application in all spheres of the economy.
The knowledge base is the core of the expert system. The transition from data to knowledge is a consequence of the development of information systems. Databases are used to store data, and knowledge bases are used to store knowledge. Databases, as a rule, store large amounts of data with a relatively low cost, while knowledge bases store small but expensive information sets.
A knowledge base is a body of knowledge described using the selected form of its presentation. Filling the knowledge base is one of the most difficult tasks, which is associated with the selection of knowledge, its formalization and interpretation.
The expert system consists of:
- a knowledge base (as part of working memory and a rule base), designed to store initial and intermediate facts in working memory (it is also called a database) and store models and rules for manipulating models in the rule base;
- a problem solver (interpreter), which ensures the implementation of a sequence of rules for solving a specific problem based on facts and rules stored in databases and knowledge bases;
- explanation subsystem allows the user to get answers to the question: “Why did the system make this decision?”;
- a knowledge acquisition subsystem designed to both add new rules to the knowledge base and modify existing rules;
- user interface, a set of programs that implement the user’s dialogue with the system at the stage of entering information and obtaining results.
Expert systems differ from traditional data processing systems in that they typically use symbolic representation, symbolic inference, and heuristic search for solutions. For solving weakly formalizable or non-formalizable problems, neural networks or neurocomputers are more promising.
The basis of neurocomputers is made up of neural networks - hierarchical organized parallel connections of adaptive elements - neurons, which ensure interaction with objects of the real world in the same way as the biological nervous system.
Great successes in the use of neural networks have been achieved in the creation of self-learning expert systems. The network is configured, i.e. train by passing all known solutions through it and achieving the required answers at the output. The setup consists of selecting the parameters of the neurons. Often they use a specialized training program that trains the network. After training, the system is ready for operation.
If in an expert system its creators pre-load knowledge in a certain form, then in neural networks it is unknown even to the developers how knowledge is formed in its structure in the process of learning and self-learning, i.e. the network is a “black box”.
Neurocomputers, as artificial intelligence systems, are very promising and can be endlessly improved in their development.
Currently, artificial intelligence systems in the form of expert systems and neural networks are widely used in solving financial and economic problems.
