Перегляд за Автор "Leshchynskyi, Volodymyr"
Зараз показуємо 1 - 11 з 11
Результатів на сторінці
Налаштування сортування
Документ Construction of patterns of user preferences dynamics for explanations in the recommender system(Національний технічний університет "Харківський політехнічний інститут", 2021) Chalyi, Serhii; Leshchynskyi, VolodymyrThe subject of study in the article is the processes of constructing explanations in recommendation systems. Objectives. The goal is to develop a method of constructing patterns that reflect the dynamics of user preferences and provide an opportunity to form an explanation of the recommended list of items, taking into account changes in the user’s requirements of the recommendation system. Construction of explanations taking into account the dynamics of changes in consumer preferences makes it possible to increase user confidence in the results of the intelligent system. Tasks: structuring models of temporal patterns of parallel-alternative and sequential-alternative users’ choice of the recommendation system; development of a method for constructing patterns of changing user preferences using process mining technology; experimental verification of the method for constructing patterns of changing consumer preferences. The approaches used are: temporal logics, which determine the approaches to the description of the temporal ordering of a set of events. The following results are obtained. The structuring of models of temporal patterns of parallel-alternative and sequential-alternative users’ choice of the recommendation system is performed; developed and performed an experimental test of the method of constructing patterns of user preferences dynamics. Conclusions. The scientific novelty of the results is as follows. The method of dynamics patterns construction of users’ preferences for the formation of explanations concerning the recommended list of subjects is offered. The method sequentially generates a set of ordered events, each of which reflects the choice of the subject by a group of users at a certain time interval, and also builds a graph representation of the patterns of user preferences through intellectual analysis of processes. The patterns obtained as a result of the method consist of time-ordered pairs of events that reflect the knowledge of changing user preferences over time. Further use of such dependencies as elements of the knowledge base makes it possible based on probabilistic inference to build a set of alternative explanations for the received recommendation, and then arrange these explanations according to the probability of their implementation for the recommended list of subjects.Документ Designing explanations in the recommender systems based on the principle of a black box(Національний технічний університет "Харківський політехнічний інститут", 2019) Chalyi, Serhii; Leshchynskyi, Volodymyr; Leshchynska, IrinaThe subject matter of the article is the process of designing of explanations in the recommender system. The goalis to develop a conceptual model for designing explanations in recommender systems based on the black box principle. Such a model binds the conditions, the result and the constraints on the choice of objects from the user's position.The user should receive justification of the recommendations taking into account context-oriented possibilities of using the proposed objects.Tasks: to adapt the principle of a black box to the task of constructing explanations in the recommender system; to develop a conceptual scheme for constructing explanations according to the functional principle; to develop a conceptual model for the designing of explanations based on the principle of a black box.The principle used is: functional, or the principle of a black box.The following resultsare obtained. The principle of the black box to the problem of constructing explanations in the recommender system was adapted. The conceptual scheme of constructing explanations on the basis of a functional principle is developed, taking into account both the properties of objects and the sequences of their use. The conceptual model of the explanation based on the black boxprinciple is developed.Conclusions.Scientific novelty of the results is as follows.The conceptual model for constructing explanations with recommendations on the functional principle or the principle of a black box is proposed. The model takes into account the characteristics of subjects and consumers, information on the use of objects in the subjectarea, as well as recommendations in the form of a list of objects.The advantage of using the proposed model lies in the fact that it takes into account the methods of applying the recommended objects for constructing explanations. This creates conditions for personalizing recommendations in cases of a cold start of the recommender system, as well as artificial increase in the ratings of individual items.Документ A dynamic explanation model for human-computer interface(Національний технічний університет "Харківський політехнічний інститут", 2020) Chalyi, Serhii; Leshchynskyi, Volodymyr; Leshchynska, IrynaThe scientific novelty of the results is as follows. A temporal approach to constructing explanations for the operation of an intelligent system is proposed. The approach describes explanation as a process consisting of a temporally ordered sequence of facts. The order of time for pairs of facts is determined by temporal rules. Such rules may define the explanation process with varying degrees of detail over time, depending on the request for clarification. Detailed explanations reflect the subject area model and include the basic and alternative sequences of actions performed by the intelligent system. The explanation of the basic patterns of the intelligent system makes it possible to interpret the limitations that affect the obt ained solution. The explanation of the system as a whole provides an implicit reflection of the key causal relationships, which allows you to get a simplified interpretation of the results of the intelligent system. A dynamic model of describing explanations based on temporal knowledge for use in the human-computer interface is proposed. The model takes into account the description of actions in the subject area, the patterns of these actions, as well as generalized causal relationships between such patterns. The model provides an opportunity to present the dynamics of the process of functioning of the intelligent system with the required level of detail, as well as change the level of detail to clarify the explanation at the request of the user.Документ Hierarchical representation of causal relationships to detail explanations in intelligent systems(Національний технічний університет "Харківський політехнічний інститут", 2021) Chalyi, Serhii; Leshchynskyi, VolodymyrThe subject of research in the article is the processes of constructing explanations in intelligent systems based on the use of causal dependencies. The aim is to develop a hierarchical representation of causal relationships between the actions of an intelligent system to form an explanation of the process of the system's operation with a given degree of generalization or detailing. Representation of the hierarchy of cause-and-effect relationships allows you to form an explanation at a given level of detail using the input data in the form of a temporally ordered sequence of events reflecting the known actions of an intelligent system. Tasks: structuring the hierarchy of cause-and-effect relationships for known variants of the decision-making process in an intelligent information system, considering the temporal ordering of the corresponding actions; development of a model of a multi-level representation of causal dependencies for description for explanations in an intelligent system. The approaches used are: counterfactual analysis of causality, used to describe alternative dependencies for possible decision-making options; linear temporal logic to reflect the temporal aspect of causation. The following results were obtained. A generalized hierarchy of cause-and-effect relationships is highlighted for the known variants of the process of obtaining recommendations in an intelligent information system based on the temporal ordering of the corresponding decision-making actions. A model of hierarchical representation of causal dependencies has been developed to describe explanations in an intellectual system with a given degree of detail. Conclusions. The scientific novelty of the results obtained is as follows. A model of hierarchical representation of time-ordered causal relationships is proposed to describe the explanations of the operation of an intelligent system with a given degree of detail. At the top level of the hierarchy, the model defines a generalized causal relationship between the event of using the input data and the event of the result of the system's operation. This connection describes the current task that the intelligent information system solves. At the lower level, cause-and-effect relationships are set between events sequential in time, between which there are no other events. At intermediate levels of the hierarchical representation, the causal dependencies of pairs of events are determined, between which there are other events. The developed model creates conditions for constructing explanations with a given degree of detailing of the actions of the decision-making process in an intelligent system. The model also provides the ability to describe early and late anticipation of alternative sequences of the decision-making process by describing causal dependencies for events between which there are other events.Документ Knowledge representation in the recommendation system based on the white box principle(Національний технічний університет "Харківський політехнічний інститут", 2019) Chalyi, Serhii; Leshchynskyi, VolodymyrThe subject matter of the article is the construction of a rating list of goods and services in recommendation systems. The goalis to develop a knowledge representation model in recommendation systems using the white box principle. Such a model contains knowledge about the possible sequences of choosing restrictions on the properties of goods and services according to user preferences. The recommender system should provide a reasonable choice of the object according to the requirements of the user, subject to restrictions on the key properties of this object. Tasks: to structure the process of applying the principles of black and white boxes when building recommendations based on the use of a knowledge base; develop knowledge representations according to the principle of the white box in order to combine a static description of the properties of objects and a description of possible sequences for clarifying the requirements for the properties of these objects. The principles usedare: the principle of the white box, which provides an account of requirements that take into account the properties of the constituent elements of the object selected by the consumer. The following resultsare obtained. The key features of the processes of forming recommendations on the principles of black and white boxes based on the use of the knowledge base are highlighted. The knowledge representationis developed according to the principle of the white box, which allows taking into account both the properties ofobjects and the process of their selection by the consumer. Conclusions. The scientific novelty of the results is as follows. A model for representing knowledge in a recommendation system according to the principle of a white box is proposed. The declarative aspect of this representation of knowledge is implemented in the form of predicates that define restrictions on the values of the properties of objects offered to the consumer. The procedural aspect is implemented in the form of adapted temporal dependencies that specify the sequence of refinement of time limits. This model combines the advantages of approaches based on the similarity of customer requirements and the similarity of product characteristics, which makes it possible to adjust recommendations online for a cold start situation. With this adjustment, it is advisable to use the similarity of the user selection processes for given requirements for goods.Документ Multilevel personalization of explanations in recommender systems(Національний технічний університет "Харківський політехнічний інститут", 2020) Chalyi, Serhii; Leshchynskyi, Volodymyr; Leshchynska, IrinaThe scientific novelty of the results is as follows. A formal description of the explanations of the recommended personal list of objects in the form of a hierarchy of levels of data, information, knowledge and meta-knowledge about user behavior and characteristics of objects is proposed. At the data level, a description of the variables and their values is given, taking into account the instant of occurrence of these values. Information at the next level is represented by the relationships between individual facts. Knowledge is represented by causal or temporal explanatory rules that generalize the relationship of the informat ion level to a subset of facts. Meta-knowledge sets the key patterns that determine the benefits and relevance of the proposed choice for the user of the recommendation system. In a practical aspect, the proposed formalization of explanations determines the typical sequence of constructing and personalizing multilevel explanations regarding recommendations, taking into account the characteristics of the subject area.Документ Possible evaluation of the correctness of explanations to the end user in an artificial intelligence system(Національний технічний університет "Харківський політехнічний інститут", 2023) Chalyi, Serhii; Leshchynskyi, VolodymyrThe subject of this paper is the process of evaluation of explanations in an artificial intelligence system. The aim is to develop a method for forming a possible evaluation of the correctness of explanations for the end user in an artificial intelligence system. The evaluation of the correctness of explanations makes it possible to increase the user's confidence in the solution of an artificial intelligence system and, as a result, to create conditions for the effective use of this solution. Aims: to structure explanations according to the user's needs; to develop an indicator of the correctness of explanations using the theory of possibilities; to develop a method for evaluating the correctness of explanations using the possibilities approach. The approaches used are a set-theoretic approach to describe the elements of explanations in an artificial intelligence system; a possibility approach to provide a representation of the criterion for evaluating explanations in an intelligent system; a probabilistic approach to describe the probabilistic component of the evaluation of explanations. The following results are obtained. The explanations are structured according to the needs of the user. It is shown that the explanation of the decision process is used by specialists in the development of intelligent systems. Such an explanation represents a complete or partial sequence of steps to derive a decision in an artificial intelligence system. End users mostly use explanations of the result presented by an intelligent system. Such explanations usually define the relationship between the values of input variables and the resulting prediction. The article discusses the requirements for evaluating explanations, considering the needs of internal and external users of an artificial intelligence system. It is shown that it is advisable to use explanation fidelity evaluation for specialists in the development of such systems, and explanation correctness evaluation for external users. An explanation correctness assessment is proposed that uses the necessity indicator in the theory of possibilities. A method for evaluation of explanation fidelity is developed. Conclusions. The scientific novelty of the obtained results is as follows. A possible method for assessing the correctness of an explanation in an artificial intelligence system using the indicators of possibility and necessity is proposed. The method calculates the necessity of using the target value of the input variable in the explanation, taking into account the possibility of choosing alternative values of the variables, which makes it possible to ensure that the target value of the input variable is necessary for the explanation and that the explanation is correct.Документ Probabilistic counterfactual causal model for a single input variable in explainability task(Національний технічний університет "Харківський політехнічний інститут", 2023) Chalyi, Serhii; Leshchynskyi, VolodymyrThe subject of research in this article is the process of constructing explanations in intelligent systems represented as black boxes. The aim is to develop a counterfactual causal model between the values of an input variable and the output of an artificial intelligence system, considering possible alternatives for different input variable values, as well as the probabilities of these alternatives. The goal is to explain the actual outcome of the system's operation to the user, along with potential changes in this outcome according to the user's requirements based on changes in the input variable value. The intelligent system is considered as a "black box." Therefore, this causal relationship is formed using possibility theory, which allows accounting for the uncertainty arising due to the incompleteness of information about changes in the states of the intelligent system in the decision-making process. The tasks involve: structuring the properties of a counterfactual explanation in the form of a causal dependency; formulating the task of building a potential counterfactual causal model for explanation; developing a possible counterfactual causal model. The employed approaches include: the set-theoretic approach, used to describe the components of the explanation construction process in intelligent systems; the logical approach, providing the representation of causal dependencies between input data and the system's decision. The following results were obtained. The structuring of counterfactual causal dependency was executed. A comprehensive task of constructing a counterfactual causal dependency was formulated as a set of subtasks aimed at establishing connections between causes and consequences based on minimizing discrepancies in input data values and deviations in the decisions of the intelligent system under conditions of incomplete information regarding the functioning process of the system. A potential counterfactual causal model for a single input variable was developed. Conclusions. The scientific novelty of the obtained results lies in the proposal of a potential counterfactual causal model for a single input variable. This model defines a set of alternative connections between the values of the input variable and the obtained result based on estimates of the possibility and necessity of using these variables to obtain a decision from the intelligent system. The model enables the formation of a set of dependencies that explain to the user the importance of input data values for achieving an acceptable decision for the user.Документ Temporal representation of causality in the construction of explanations in intelligent systems(Національний технічний університет "Харківський політехнічний інститут", 2020) Chalyi, Serhii; Leshchynskyi, VolodymyrThe subject matter of the article are the processes of constructing explanations in intelligent systems. Objectives. The goal is to develop a temporal representation of causality in order to provide a description of the process of the intelligent system as part of the explanation, taking into account the temporal aspect. As a result, it providesan opportunity to increase user confidence in the results of the intelligent system. Tasks: structuring of causal dependences taking into account the decision-making process in the intellectual system and its state; development of a temporal model of causality for explanations in the intellectual system. The approaches usedare: approaches to the description of causality between the elements of the system on the basis of causal relationships, on the basis of probabilistic dependencies, as well as on the basis of the physical interaction of its elements. The following resultswere obtained. The structuring of causal dependences for construction of explanations with allocation of causal, probabilistic communications, and also dependences between acondition of intellectual system and the recommendations received in this system is executed. A model of causal dependences inan intelligent system is proposed to construct explanations for the recommendations of this system. Conclusions. The scientific novelty of the results is as follows. The model of causal dependences which are intended for construction of the explanation in intellectual system is offered. This explanation consists of a chain of causal relationships that reflect the sequence of decision-making over time. The model covers the limitations and conditions of the formation of the result of the intellig ent system. Constraints are represented by causal relationships between key performance actions. Restrictions must be true for all explanations where they are used. Conditions determine the probable relationships between such actions in the intellectual system. The model takes into account the influence of key parameters of the state of the intelligent system on the achievement ofthe result. The presented model provides an explanation with varying degrees of detail based on the definition of the temporalsequence of actions, as well as taking into account changes in the states of the intelligent system.Документ Temporal representation of the essences of the subject area for the construction of explanations in intelligent systems(Національний технічний університет "Харківський політехнічний інститут", 2022) Chalyi, Serhii; Leshchynskyi, VolodymyrThe subject of research in the article is the processes of constructing explanations in intelligent systems using causal relationships. The aim is to develop a representation of the entities of the subject area, taking into account the temporal aspect in order to represent the binary relations in time between the properties of the same entity. The construction of temporal relations between the properties of entities makes it possible to determine the probabilistic causal relationships between the states of these entities and use these dependencies to form explanations for the implemented decision-making process in the intelligent system, taking into account possible alternatives. Tasks: structuring the objects of the subject area, taking into account their essential properties for the decision-making process, including temporal; definition of classes of essences of subject area; determination of equivalence classes of entities of the subject area taking into account changes in the properties of these entities over time; development of a temporal model of representation of essences of subject area for construction of explanations in intellectual systems on the basis of definition of dependences in time between properties of essences. The approaches used are: set-theoretic approach, which is used to describe the classes of entities and classes of equivalence of entities of the subject area; linear temporal logic, which provides a representation of the relationship between entities in the temporal aspect. The following results were obtained. The structuring of the objects of the subject area is performed taking into account their properties, which are used in the decision-making process in the intellectual system; defined classes of entities; the classes of equivalence of entities of the subject area are defined as a kind of class of entities with the same values of key attributes, which makes it possible to take into account changes in these values over time; a temporal model of representation of the essences of the subject area is developed, which takes into account their static, dynamic properties and properties of time. Conclusions. The scientific novelty of the results is as follows. An equivalence class for entities is distinguished, which contains entities with the same key static properties and different dynamic properties considering the time of their change, which allows to reflect changes in the state of the entity in the decision-making process in the intelligent system. The temporal model of representation of essences of subject area which contains classes of equivalence of essences, and also temporal communications between properties of elements of these classes is offered. The selection of classes of equivalence of entities makes it possible to present the decision-making process in the intellectual system in the form of a sequence of temporal connections between the properties of entities of the subject area, and to form on this basis casual relationships between states of entities.Документ Temporal-oriented model of causal relationship for constructing explanations for decision-making process(Національний технічний університет "Харківський політехнічний інститут", 2022) Chalyi, Serhii; Leshchynskyi, VolodymyrThe subject of research in the article is the decision-making process in intelligent systems. The goal is to develop a model of the causal relationship between the states of the decision-making process in an intelligent information system, taking into account the temporal aspect of this process, in order to build cause-and-effect relationships between the actions of the process and further use these dependencies to form explanations for the sequence of actions to obtain a decision. The formation of causal relations between the states of the decision-making process makes it possible to substantiate the sequence of actions of this process, considering incomplete information regarding external influences on this process. Tasks: structuring the decision-making process in an intelligent information system as a specialized business process; development of a three-element model of the causal relationship between the states of the decision-making process, considering the temporal aspect of this process; substantiation of the possibility of using three-element relationships to build causal dependencies for decision making in intelligent systems. The approaches used are: the set-theoretical approach used to describe the elements of the decision-making process in intelligent systems; a logical approach that provides a representation of the relationship between the states of the decision-making process; probabilistic approach to describe the probabilistic component of the decision-making process. The following results are obtained. The decision-making process in an intelligent information system was structured as a specialized business process that, using additional information from the user, turns the input data into a result that is valuable for this user; a three-element model of the causal relationship between the states of the decision-making process is proposed, which makes it possible to take into account external influences on the process; using a probabilistic approach, the possibility of using three-element causal relations to describe the decision-making process in intelligent systems is substantiated, taking into account uncontrolled external influences. Conclusions. The scientific novelty of the obtained results is as follows. A three-element model of the causal relationship between the states of the decision-making process is proposed, based on a model of a temporal rule of the "future" type, containing a state-cause, a state-effect and an intermediate state that reflects external influences. The model makes it possible to build a base of causeand-effect dependencies for the decision-making process in an intelligent information system, considering external influences and use these dependencies to build explanations for this process.