An identity recognition management method and related equipment for interactive education

Abstract

The present invention provides an identity recognition management method and related equipment for interactive education, which are applied to the field of data processing technology. The present application pre-processes a training sample set to generate a training sample set with target feature data; processes a preset identity recognition matching model based on the training sample set with target feature data to generate a target identity recognition matching model; processes the biometric information of a target user to generate the identity information of the target user and the emotional information of the target user; processes a target event set that matches the target user to generate the training purpose information of the target user; processes the training purpose information of the target user, the identity information of the target user, the emotional information of the target user and the target location information based on the target identity recognition matching model to generate the training impact factor of the target user; processes the training impact factor of the target user to generate the training warning information of the target user.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an identity recognition management method and related equipment for interactive education. Background Art

[0002] Under the traditional education model, teachers can only perceive students' learning status through visual observation during the teaching process. They cannot understand each student's real-time classroom emotional state and it is difficult to give true feedback on students' listening status in class, resulting in low teaching efficiency. In addition, roll call and sign-in waste time. Although it is currently possible to sign-in through mobile phone positioning, the positioning is too flexible, which provides a lot of room for students to skip classes. There is also the phenomenon of students substituting for classes. Students are prone to inattention, drowsiness, whispering, etc. in class. There is also the situation where physical discomfort cannot be discovered in time. Traditional face recognition and voice recognition are no longer reliable enough. For classrooms with larger areas, there are differences in student positions and individuals, making it difficult to fully play their role.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The purpose of this application is to provide an identity recognition management method and related equipment for interactive education, which at least to some extent overcomes the problems existing in the prior art, by obtaining a variety of information of the target user, including biometrics, target event sets, target location information and training sample sets. The training sample set is preprocessed to generate target feature data, and a preset identity recognition matching model is obtained and further processed to obtain a target identity recognition matching model. The target user's biometric information is processed to obtain identity and emotional information, and the target event set is processed to obtain training purpose information. Based on the target identity recognition matching model, a training impact factor is generated by integrating various aspects of information, and the training impact factor is then processed to obtain training warning information. This method realizes comprehensive management of user training and risk warning.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0006] According to one aspect of the present application, there is provided an identity recognition management method for interactive education, comprising: obtaining biometric information of a target user, a target event set matching the target user, target location information and a training sample set, wherein the target location information includes location information of the target user at the target location, and the training sample set includes historical environmental factor information of the target location and real-time teaching factor information of other locations adjacent to the target location; preprocessing the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors affecting user training; obtaining a preset identity recognition matching model, wherein the preset identity recognition matching model is generated based on historical teaching factor information of other locations; processing the preset identity recognition matching model based on the training sample set with target feature data to generate a target biometric information. A target identification and matching model is used; the biometric information of the target user is processed to generate the identity information of the target user and the emotional information of the target user; the target event set matching the target user is processed to generate the training purpose information of the target user; based on the target identity identification and matching model, the training purpose information of the target user, the identity information of the target user, the emotional information of the target user and the target location information are processed to generate the training influence factor of the target user, wherein the training influence factor of the target user includes the attendance information of the target user and the training result information of the target user; based on the target identity identification and matching model, the training influence factor of the target user is processed to generate the training warning information of the target user, wherein the training warning information of the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user.

[0007] Another aspect of the present application is an identity recognition management device for interactive education, characterized in that it includes: an acquisition module, used to acquire biometric information of a target user, a target event set matching the target user, target location information and a training sample set, wherein the target location information includes location information of the target user at the target location, and the training sample set includes historical environmental factor information of the target location and real-time teaching factor information of other locations adjacent to the target location; acquiring a preset identity recognition matching model, wherein the preset identity recognition matching model is generated based on historical teaching factor information of other locations; a processing module, used to pre-process the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors affecting user training; and processing the preset identity recognition matching model based on the training sample set with target feature data. Processing is performed to generate a target identity recognition matching model; the biometric information of the target user is processed to generate the identity information of the target user and the emotional information of the target user; the target event set matching the target user is processed to generate the training purpose information of the target user; based on the target identity recognition matching model, the training purpose information of the target user, the identity information of the target user, the emotional information of the target user and the target location information are processed to generate a training influence factor of the target user, wherein the training influence factor of the target user includes the attendance information of the target user and the training result information of the target user; based on the target identity recognition matching model, the training influence factor of the target user is processed to generate training warning information of the target user, wherein the training warning information of the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user.

[0008] According to another aspect of the present application, an electronic device is characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the identity recognition management method for implementing the above-mentioned interactive education by executing the executable instructions.

[0009] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the identity recognition management method for interactive education is implemented.

[0010] According to another aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a third processor, the above-mentioned identity recognition management method for interactive education is implemented.

[0011] The present application provides an interactive education identity recognition management method and related equipment, in which a server obtains the target user's biometric information, target event set, target location information and training sample set. The target location information includes the user's location, and the training sample set covers the historical environmental factors of the target location and the real-time teaching factors of the adjacent locations. Then, the training sample set is preprocessed. The original feature library is determined by feature extraction, and then the training set and the verification set are generated. The verification set is processed by a preset classifier to obtain a prediction result, and the training set is processed by a preset algorithm to obtain a verification set-class prediction result. The two are combined to generate target feature data that characterizes the risk factors affecting user training.

[0012] Then, obtain the preset identity recognition matching model generated based on the historical teaching factor information of other places. And use the training sample set with target feature data for processing. Generate the influencing factors of expression features and obtain the preset expression mapping table, generate the original feature library after comprehensive processing, further generate several feature data sets, and finally generate the target identity recognition matching model. Processing the biometric information of the target user can obtain identity information and emotional information. Processing the target event set can generate the access frequency and training time period of the target training course, and generate training preference information in combination with historical training information, and then obtain training purpose information.

[0013] Based on the target identity recognition matching model, the training purpose information, identity information, emotion information and target location information are processed to generate the attribute information of the training content to be trained. The training content matching degree is generated by combining the user emotion and identity information. The training influencing factors are then combined with the target location information to generate attendance information and training result information. Finally, the training influencing factors are processed to generate training abnormal features and correlation co-occurrence frequencies, and then the training progress value is generated. By comparing with the preset training progress value, training warning information is generated to characterize the deviation value between the training results and the expected effect. This method realizes comprehensive management and risk warning of user training through comprehensive processing of multi-faceted information.

[0014] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flow chart showing an identity recognition management method for interactive education provided by an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the structure of an identity recognition management device for interactive education provided by an embodiment of the present application is shown;

[0017] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0018] Figure 4 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0019] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0020] Combine the following Figure 1 To describe the identity recognition management method of interactive education according to the exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the embodiments of the present application are not limited in this respect. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0021] In one implementation, the present application also proposes an identity recognition management method and related equipment for interactive education. Figure 1 The following schematically shows a flow chart of an interactive education identity recognition management method according to an embodiment of the present application. Figure 1 As shown, the method is applied to a server, comprising:

[0022] S101, obtaining biometric information of a target user, a target event set matching the target user, target location information, and a training sample set.

[0023] In one implementation, it is assumed that the target user is Xiao Zhang, a student who is taking a professional skills training course. Xiao Zhang's biometric information may include fingerprint information, and identity verification is performed through a fingerprint recognition device every time he enters a training venue. For example, a fingerprint recognition access control system is installed at the entrance of the training center. Xiao Zhang can only enter after verifying his fingerprint, which can effectively prevent others from taking classes instead of him. Facial feature information can also be included, and a high-definition camera is used to capture Xiao Zhang's facial image, and his identity is confirmed through facial recognition technology. For example, a monitoring device with facial recognition function is installed in the classroom, which can monitor the identity of the students in real time. Once the facial features are found to be inconsistent with the registered students, the system will issue an alarm.

[0024] Taking the training course attended by Xiao Zhang as an example, the target event set can include Xiao Zhang's sign-in event on the course platform, homework submission event, and classroom interaction event. For example, Xiao Zhang signs in on the course platform every day, and the system will record his sign-in time and location to ensure that he signs in at the training venue himself, rather than someone else signing in on his behalf. If Xiao Zhang actively participates in classroom interaction, such as asking questions and answering questions, these events can also serve as evidence of his participation in the training, reducing the possibility of substitution.

[0025] Assuming that the training is conducted in a large training center, the location information in the target location information can be specific to Xiao Zhang's seat in the training center. For example, Xiao Zhang is assigned to the fifth seat in the third row of classroom A. Through indoor positioning technology, it is possible to monitor in real time whether Xiao Zhang is attending the training in his seat. If it is found that Xiao Zhang's position does not match the system record, there may be a risk of substitution, and the management staff can verify it in time. The historical environmental factor information of the target location can include the impact of the past environmental conditions such as temperature, humidity, and light of the training center on the learning status of trainees. For example, by analyzing historical data, it is found that when the temperature is moderate and the humidity is low, the trainees are more focused and the learning efficiency is higher. Understanding this historical environmental factor information can help managers optimize the training environment, improve the learning enthusiasm of trainees, and reduce the phenomenon of substitution due to environmental discomfort. The real-time teaching factor information of other places adjacent to the target location can include the teaching activities and noise levels in the nearby classrooms. For example, there is an intense group discussion next to Xiao Zhang's classroom, and the noise is loud. At this time, the management staff can take measures to reduce noise interference, ensure that Xiao Zhang and other trainees can focus on their training courses, and reduce the motivation to substitute classes due to external interference.

[0026] The training sample set combines the historical environmental factor information of the target location and the real-time teaching factor information of other locations adjacent to the target location to build a model to predict the behavior of students and identify the risk of class substitution. For example, the historical environmental factor information shows that in an environment with high temperature and high humidity, the student absenteeism rate is high, and there may be a risk of class substitution. The real-time teaching factor information shows that when the teaching activities in the nearby classrooms are too noisy, the students' attention is easily distracted, which may also lead to an increase in the phenomenon of class substitution. By analyzing these training samples, a prediction model can be established to predict the attendance of students and the risk of class substitution based on the current environmental factors and teaching situation, so that managers can take timely measures to improve training efficiency.

[0027] S102, preprocessing the training sample set to generate a training sample set with target feature data.

[0028] In one implementation, feature extraction is performed on the training sample set to determine the original feature library. Assume that we are conducting a user training risk factor analysis for an online learning platform to reduce the phenomenon of class substitution and improve training efficiency. The training sample set contains a large amount of data related to user training, such as the user's login time, learning time, course completion progress, answer accuracy, etc. Through feature extraction technology, we can determine the original feature library from these data. For example, we found that features such as the number of user logins in a week, the distribution of learning time after each login, the completion ratio of different courses, and the average answer accuracy in various tests can be used as part of the original feature library. These features reflect the user's learning habits and learning status, and may be related to training risk factors.

[0029] Process the original feature library to generate training set and validation set. Process the original feature library and divide it into training set and validation set. For example, we can randomly select 70% of the data as the training set for model training; the remaining 30% as the validation set to evaluate the performance of the model. Assuming we have training data for 1,000 users, the training set contains data from 700 users and the validation set contains data from 300 users.

[0030] The validation set is processed based on the preset classifier to generate a prediction result. The preset classifier can be a machine learning algorithm, such as a decision tree, random forest, or support vector machine. Taking random forest as an example, we input the data of the validation set into the random forest classifier, and the classifier will classify and predict each sample in the validation set based on the learned rules. For example, predict whether a user has a risk of class substitution. If the classifier predicts that the user has a high risk of class substitution, it may give a corresponding risk level, such as high risk, medium risk, or low risk.

[0031] The training set is processed based on a preset algorithm to generate a validation set class prediction result. The preset algorithm can be a data mining algorithm, such as a clustering algorithm or an association rule mining algorithm. Taking the clustering algorithm as an example, we perform cluster analysis on the data of the training set and group users with similar characteristics into one group. Then, for each user in the validation set, the most similar cluster group is found based on its characteristics, and the training risk factor of the user is predicted based on the characteristics of the cluster group. For example, if a user's characteristics are similar to a high-risk cluster group, then we can predict that the user also has a high training risk.

[0032] The prediction results and the validation set prediction results are processed to generate target feature data, which are used to characterize the risk factors that affect user training. The prediction results and the validation set prediction results are processed comprehensively to generate target feature data. These target feature data are used to characterize the risk factors that affect user training. For example, if the prediction results and the validation set prediction results both show that a user has irregular login time, short learning time, and low answer accuracy, then we can combine these features as target feature data indicating that the user has training risks. These data can help us further analyze the user's training situation and take corresponding measures to reduce risks, such as strengthening supervision of the user, providing personalized learning suggestions, etc., to reduce class substitution and improve training efficiency.

[0033] S103: Obtain a preset identity recognition matching model.

[0034] In one implementation, assume that we are developing an identity recognition system for a chain training institution to reduce class substitution and improve training efficiency. The preset identity recognition matching model is a tool for identifying user identities. It can determine the real identity of the user by analyzing various characteristics of the user, such as biometrics (fingerprints, facial features, etc.), behavioral characteristics (learning habits, login time, etc.) and environmental characteristics (location of the training venue, surrounding environment, etc.). This model is pre-built and can quickly and accurately identify users during the training process to prevent class substitution. Collect historical teaching factor information: The historical teaching factor information of other venues can include multiple aspects. For example, the attendance records, academic performance distribution, and course participation of students in different training venues. It can also include environmental factors of different venues, such as classroom size, equipment configuration, temperature and humidity, etc. In addition, the teaching style and evaluation of teachers, the interaction between students, etc. can also be used as part of the historical teaching factor information. The collected historical teaching factor information is deeply analyzed to find out the characteristics related to user identity recognition. For example, it is found that some students are more likely to substitute in a specific classroom environment, or that the teaching style of some teachers will affect the participation of students and the accuracy of identity verification. By analyzing this information, we can determine which factors have a significant impact on user identification. Based on the analysis results, we use machine learning algorithms or data mining techniques to generate a preset identification matching model. For example, we can use a decision tree algorithm to determine whether a user's identity is genuine based on factors such as the student's attendance record, academic performance, and classroom environment. Or we can use a clustering algorithm to divide students into different groups and identify possible substitute users based on group characteristics.

[0035] Taking a specific scenario as an example, suppose we have two different training venues A and B. In the historical teaching of venue A, it was found that students were more likely to be absent and substitute in classrooms with higher temperatures. At the same time, historical data from venue B showed that some students had low participation in the courses of specific teachers and were at risk of substitution. By analyzing these historical teaching factor information, we can build a preset identity recognition matching model, which can predict whether there is a risk of substitution based on the temperature of the current training venue, teacher information, and historical behavioral characteristics of the students, and accurately identify the user's identity.

[0036] S104, processing the preset identity recognition matching model based on the training sample set with target feature data to generate a target identity recognition matching model.

[0037] In one embodiment, a training sample set with target feature data is processed to generate expression feature influencing factors, wherein the expression feature influencing factors are generated based on the facial image information of other users. Assume that we are developing a target identity recognition and matching model for an online education platform to ensure the authenticity of the student identity, reduce the phenomenon of class substitution and improve training efficiency. The training sample set contains a large amount of user information with target feature data, including various behavioral data and environmental data of users during the learning process. In order to generate expression feature influencing factors, we first extract the facial image information of other users from the training sample set. For example, in the video course of the platform, the facial images of the students are collected by the camera. These images are analyzed to extract expression features, such as smiling, frowning, and concentration. These expression features may be affected by many factors, such as course difficulty, learning progress, personal emotions, etc. By analyzing the facial image information of a large number of users, we can determine which expression features are related to specific learning situations, thereby generating expression feature influencing factors.

[0038] Get a preset expression mapping table, where the preset expression mapping table is the expression information generated by different users for different scenarios. The preset expression mapping table is the expression information generated by different users for different scenarios. This mapping table can be pre-built through observation and analysis of a large number of users. For example, when a user encounters a difficult problem, he may frown and show a confused expression; when a user understands a knowledge point, he may show a smiling and satisfied expression. The preset expression mapping table corresponds these different expressions to specific learning scenarios to provide a reference for subsequent analysis.

[0039] The factors affecting expression features and the preset expression mapping table are processed to generate the original feature library. The factors affecting expression features and the preset expression mapping table are processed comprehensively to generate the original feature library. This process can be achieved through data fusion and feature extraction technology. For example, the expression features extracted from the training sample set are compared and analyzed with the expression information in the preset expression mapping table to find out the associations and differences between the two. Then, these associations and differences are added to the original feature library as new features. The original feature library may also include other features related to user identity recognition, such as learning habits, behavior patterns, environmental factors, etc.

[0040] The original feature library is processed to generate several feature data sets. The original feature library is further processed to generate several feature data sets. This process can be achieved through technologies such as data partitioning, feature selection, and data conversion. For example, the data in the original feature library is divided according to different feature dimensions to generate multiple feature data sets. Each feature data set can focus on specific aspects, such as facial expression features, learning habits, environmental factors, etc. This can facilitate the subsequent analysis and processing of different features.

[0041] The preset identity recognition matching model is processed based on several feature data sets to generate a target identity recognition matching model. Based on the preset identity recognition matching model, several feature data sets are used to train and optimize it to generate a target identity recognition matching model. For example, the preset identity recognition matching model can be a neural network model based on deep learning. Different feature data sets are input into the model, and the parameters of the model are continuously adjusted through the back propagation algorithm so that the model can better identify the identity of the user. After multiple training and optimization, the accuracy and stability of the model are improved, and finally the target identity recognition matching model is generated. This model can monitor the identity of students in real time on the online education platform, reduce the phenomenon of class substitution, and improve training efficiency.

[0042] S105, processing the biometric information of the target user to generate identity information of the target user and emotion information of the target user.

[0043] In one implementation, assume that we are in a corporate training scenario, and the target user is Xiao Li, an employee who is participating in the training. Xiao Li's biometric information is collected by a high-definition camera installed in the training classroom. By processing this information, Xiao Li's facial features can be extracted, thereby generating initial facial image information. This image information is Xiao Li's facial information within a preset time period (such as the first few minutes after the start of the training course). At the same time, by comparing with the information in the employee database, Xiao Li's identity information can be determined to ensure that the person participating in the training is himself and not someone else's substitute. For example, the camera captures the picture of Xiao Li entering the classroom, and the system immediately recognizes his face and matches it with the photo in the database. After confirming that it is Xiao Li himself, his facial image at this time is recorded as the initial facial image information, and Xiao Li's identity is displayed in the system as "Marketing Department Employee Xiao Li". The preset processing rules may include steps such as image enhancement and feature extraction. The initial facial image information is processed to extract Xiao Li's facial expression features, such as the degree of opening and closing of the eyes, the upward or downward movement of the corners of the mouth, etc. These features will be affected by multiple factors, thereby generating expression feature influencing factors. For example, through image analysis, it was found that Xiao Li's eyes were wide open and the corners of his mouth were slightly raised in the initial state. These characteristics may be affected by his expectations for training, his happy mood and other factors. These factors together constitute the influencing factors of facial expression characteristics.

[0044] The preset emotion recognition model can be an algorithm model based on deep learning, which can analyze Xiao Li's expression changes according to the influencing factors of expression characteristics, and then generate target face image information. This information includes Xiao Li's expression changes during the training process, such as changing from expectation at the beginning to concentration, confusion or fatigue. For example, as the training progresses, the model detects that Xiao Li's eyes gradually narrow and the corners of his mouth slightly turn down, which indicates that he may have encountered a problem or feel tired. The system records these expression changes and generates target face image information, showing that Xiao Li's expression has changed from expectation to confusion. The target face image information is further analyzed to determine Xiao Li's emotional state at different stages and generate the target user's emotional information. For example, based on the expression changes shown in the target face image information, the system determines that Xiao Li has experienced emotional stages such as expectation, concentration, and confusion during the training process, records these emotional states, generates Xiao Li's emotional information, and provides a reference for the trainer to adjust the teaching strategy in time and improve the training effect. At the same time, emotional information can also be used as an indicator to evaluate Xiao Li's enthusiasm and effectiveness in participating in the training.

[0045] S106, processing the target event set matching the target user to generate training purpose information of the target user.

[0046] In one implementation, the target event set that matches the target user is processed to generate the access frequency of the target training course and the training time period of the target training course. Assume that the target user is Xiao Wang, a student of an online learning platform. The target event set contains various event information related to Xiao Wang. By processing this information, the access frequency and training time period of Xiao Wang to the target training course can be determined. For example, by analyzing the log data of the platform, it is found that Xiao Wang has visited the target training course 15 times in the past month. At the same time, it is recorded that Xiao Wang usually studies between 7 and 9 pm. In this way, the access frequency of the target training course is 15 times per month, and the training time period is from 7 to 9 pm.

[0047] Obtain the historical training information of the target user for the target training course. Obtain Xiao Wang's historical training information for the target training course from the database of the learning platform. This may include the course chapters Xiao Wang has previously attended, the homework he has completed, the discussions he has participated in, etc. For example, it is found that Xiao Wang has completed the first three chapters of the target training course and has expressed his views in the discussion area of ​​each chapter. Process the historical training information to generate the training preference information of the target user, where the training preference information of the target user includes the training information of the target user in the historical time period. Analyze Xiao Wang's historical training information and extract his training preference information. The training preference information includes Xiao Wang's training behavior and interest tendency in the historical time period. For example, through analysis, it is found that Xiao Wang pays special attention to the case analysis part in the historical training and often watches the case explanation video repeatedly. At the same time, he also actively participates in group discussions and likes to communicate and interact with other trainees. These behaviors show that Xiao Wang's training preference in the historical time period is to focus on practical cases and interactive communication.

[0048] Based on the training preference information of the target user, the access frequency of the target training course and the training time period of the target training course are processed to generate the training purpose information of the target user. Combined with Xiao Wang's training preference information, the access frequency and training time period of the target training course are comprehensively processed to generate Xiao Wang's training purpose information. For example, considering that Xiao Wang has a high access frequency and likes to study at night, and he also has a preference for case analysis and interactive communication. It can be inferred that Xiao Wang's training purpose may be to use his spare time to study practical cases in depth and improve his professional ability by communicating with others. The training purpose information can provide the platform with personalized learning suggestions and resource recommendations to improve Xiao Wang's learning effect. It also helps the platform to better understand user needs and optimize course settings and services.

[0049] S107: Process the training purpose information of the target user, the identity information of the target user, the emotion information of the target user and the target location information based on the target identity recognition matching model to generate a training influence factor for the target user.

[0050] In one implementation, the training purpose information of the target user is processed based on the target identity recognition matching model to generate attribute information of the content to be trained. Assume that the target user is Xiao Zhang, an employee who is participating in vocational skills training. The target identity recognition matching model first processes Xiao Zhang's training purpose information. The training purpose information may indicate that Xiao Zhang participates in this training to improve specific professional skills, such as data analysis capabilities. By analyzing this information, the model can generate attribute information of the content to be trained. For example, it is determined that the content to be trained mainly involves attributes such as statistical knowledge, the use of data visualization tools, and data analysis case studies.

[0051] Based on the target user's emotional information and identity information, the attribute information of the training content to be trained is processed to generate the training content matching degree, where the training content matching degree is used to characterize the matching relationship between the target user's emotional state and the training content to be trained. If Xiao Zhang's current emotional information shows that he is anxious, it may be because of the high work pressure and the worry about learning new knowledge. The target identity recognition matching model will combine this emotional state and Xiao Zhang's identity information (such as his job position and professional background) to process the attribute information of the training content to be trained. Assume that Xiao Zhang is a marketing specialist who usually deals with market research data. The model will determine that the data analysis training content has a certain relevance to Xiao Zhang's work needs, but his anxiety may affect his absorption of complex statistical knowledge. Therefore, a training content matching degree is generated, such as a matching degree of 70%, indicating that Xiao Zhang's emotional state and work background have a certain degree of matching with the training content to be trained, but there are still some challenges to overcome.

[0052] Based on the target venue information, the training content matching is processed to generate the training impact factor of the target user. The training impact factor of the target user includes the attendance information of the target user and the training result information of the target user. The target venue information includes the classroom environment and surrounding facilities where Xiao Zhang attends the training. If the training venue is noisy, it may further reduce Xiao Zhang's learning effect, thereby affecting the matching of the training content. On the contrary, if the venue is quiet, comfortable and well-equipped, it may improve the matching. The model combines these factors to generate the training impact factor of the target user. For example, Xiao Zhang's attendance information shows that he has attended four training courses in the past week, but his performance in the training is average due to the noise in the venue and personal emotional problems. The training result information may show that he has made some progress in some simple data analysis tasks, but still has difficulties in complex problems. Combining these factors, the training impact factor can reflect Xiao Zhang's overall performance in this training and the degree of influence of various factors on him.

[0053] S108: Process the training influencing factor of the target user based on the target identity recognition matching model to generate training warning information for the target user.

[0054] In one implementation, the training influencing factors of the target user are processed based on the target identity recognition matching model to generate training abnormal features and correlation co-occurrence frequencies. Assume that the target user is Xiao Li, a student participating in programming training. The target identity recognition matching model processes Xiao Li's training influencing factors. Training influencing factors may include Xiao Li's attendance, learning progress, performance at the training venue, etc. By analyzing these factors, the model can identify training abnormal features. For example, if Xiao Li's attendance has become irregular recently, or the error rate in programming exercises has suddenly increased, these can be regarded as training abnormal features. At the same time, the model also calculates the correlation co-occurrence frequency, that is, the probability of these abnormal features appearing at the same time. For example, Xiao Li's irregular attendance and increased error rate occur frequently at the same time, which may indicate that there is some systemic problem that affects his training.

[0055] The training abnormal features and the correlation co-occurrence frequency are processed to generate the training progress value of the target user. The training abnormal features and the correlation co-occurrence frequency are further processed to generate Xiao Li's training progress value. This progress value can comprehensively reflect the gap between Xiao Li's actual status and expected status in training. For example, if Xiao Li's abnormal features are more serious and the co-occurrence frequency is high, then his training progress value may be low. Assume that under normal circumstances, Xiao Li should complete a certain number of programming projects and achieve a certain accuracy rate at this stage, but due to the influence of abnormal features, the number of projects he actually completed is small and the error rate is high, resulting in a training progress value of only 60% of the expected.

[0056] The training progress value of the target user is processed based on the preset training progress value to generate the training warning information of the target user. The training warning information of the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user. The preset training progress value is a standard value set according to the training goal and expected effect. Compare Xiao Li's training progress value with the preset training progress value to generate training warning information. For example, the preset training progress value is 80%, while Xiao Li's actual progress value is only 60%, which is a large deviation. At this time, the system will generate training warning information to remind trainers and managers that there is a large deviation between Xiao Li's training results and the expected effect. The warning information can specifically point out where Xiao Li has problems, such as insufficient attendance resulting in a weak grasp of knowledge, or unclear programming ideas resulting in a high error rate. In this way, timely measures can be taken, such as communicating with Xiao Li to understand the situation, providing additional coaching, or adjusting the training plan to ensure that Xiao Li can get back on track as soon as possible and improve the training effect.

[0057] The target identity recognition matching model includes a calculation formula for obtaining the co-occurrence frequency of correlation, which is:

[0058] ; Where N is the data sample, when training abnormal features and training impact factor When they appear at the same time, ) = 1, otherwise )=0.

[0059] Suppose we are analyzing the training of students on an online learning platform. The abnormal training features here can be the frequent interruption of learning by students, the sudden increase in the error rate of answering questions, the obvious reduction of learning time, etc.; the training influencing factors can include the difficulty of the course, the degree of interference in the learning environment of the students, the recent life pressure of the students, etc. For example, there are 5 different abnormal training features (n=5), which are marked as arrive ; and three training influence factors (m=3), marked as arrive , we need to consider that the training abnormality feature subscript i takes values ​​in the range of n, and the training impact factor subscript j takes values ​​in the range of m. We collected 100 data samples (N=100). For a specific data sample, if the trainee frequently interrupts learning (e.g. ), and the course difficulty is also relatively high (e.g. ), then at this time ( , ) = 1. If in another data sample, the trainees do not have any training abnormal characteristics, or if they have training abnormal characteristics but they do not appear at the same time as any training influencing factor, then ( , )=0. We judge each data sample in turn and calculate the total number of times all training abnormal characteristics and training influencing factors appear at the same time. Assume that after calculation, this total is 30. Then according to the formula, the correlation co-occurrence frequency This result indicates that in all data samples, the frequency of training abnormal features and training influencing factors appearing at the same time is 30%. Through this frequency value, we can evaluate the severity of possible problems in training, and which combinations of training abnormal features and training influencing factors appear more frequently, so as to take targeted measures to improve training results and reduce the phenomenon of class substitution.

[0060] This method aims to reduce the phenomenon of class substitution and improve training efficiency. First, obtain the biometric information of the target user, the target event set, the target location information and the training sample set. The target location information includes the user's location, and the training sample set covers the historical environmental factors of the target location and the real-time teaching factors of the adjacent locations. Then, preprocess the training sample set. Determine the original feature library through feature extraction, and then generate the training set and validation set. Use the preset classifier to process the validation set to obtain the prediction result, and use the preset algorithm to process the training set to obtain the validation set class prediction result. Combine the two to generate the target feature data that characterizes the risk factors affecting user training.

[0061] Then, obtain the preset identity recognition matching model generated based on the historical teaching factor information of other places. And use the training sample set with target feature data for processing. Generate the influencing factors of expression features and obtain the preset expression mapping table, generate the original feature library after comprehensive processing, further generate several feature data sets, and finally generate the target identity recognition matching model. Processing the biometric information of the target user can obtain identity information and emotional information. Processing the target event set can generate the access frequency and training time period of the target training course, and generate training preference information in combination with historical training information, and then obtain training purpose information.

[0062] Based on the target identity recognition matching model, the training purpose information, identity information, emotion information and target location information are processed to generate the attribute information of the training content to be trained. The training content matching degree is generated by combining the user emotion and identity information. The training influencing factors are then combined with the target location information to generate attendance information and training result information. Finally, the training influencing factors are processed to generate training abnormal features and correlation co-occurrence frequencies, and then the training progress value is generated. By comparing with the preset training progress value, training warning information is generated to characterize the deviation value between the training results and the expected effect. This method realizes comprehensive management and risk warning of user training through comprehensive processing of multi-faceted information.

[0063] In one embodiment, if Figure 2As shown, the present application also provides an identity recognition management device for interactive education, comprising:

[0064] The acquisition module 201 is used to acquire the biometric information of the target user, the target event set matching the target user, the target location information and the training sample set, wherein the target location information includes the location information of the target user at the target location, and the training sample set includes the historical environmental factor information of the target location and the real-time teaching factor information of other locations adjacent to the target location; acquire a preset identity recognition matching model, wherein the preset identity recognition matching model is generated based on the historical teaching factor information of other locations;

[0065] The processing module 202 is used to pre-process the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors that affect user training; based on the training sample set with target feature data, the preset identity recognition matching model is processed to generate a target identity recognition matching model; the biometric information of the target user is processed to generate the identity information of the target user and the emotional information of the target user; the target event set that matches the target user is processed to generate the training purpose information of the target user; based on the target identity recognition matching model, the training purpose information of the target user, the identity information of the target user, the emotional information of the target user and the target location information are processed to generate a training influencing factor of the target user, wherein the training influencing factor of the target user includes the attendance information of the target user and the training result information of the target user; based on the target identity recognition matching model, the training influencing factor of the target user is processed to generate training warning information of the target user, wherein the training warning information of the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user.

[0066] The present application embodiment provides an electronic device, such as Figure 3 As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302 and a communication interface 303. The first processor 300, the communication interface 303 and the memory 301 are connected via the bus 302; the memory 301 stores a computer program that can be run on the first processor 300, and when the first processor 300 runs the computer program, it executes the identity recognition management method for interactive education provided in any of the aforementioned embodiments of the present application.

[0067] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0068] The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store a program, and the first processor 300 executes the program after receiving an execution instruction. The identity recognition management method for interactive education disclosed in any implementation of the embodiment of the present application may be applied to the first processor 300, or implemented by the first processor 300.

[0069] The first processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the first processor 300. The above-mentioned first processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in a decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

[0070] The electronic device provided in the above-mentioned embodiments of the present application and the identity recognition management method for interactive education provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0071] The present application embodiment provides a computer-readable storage medium, such as Figure 4 As shown, the computer-readable storage medium 401 stores a computer program, and when the computer program is read and executed by the second processor 402, the identity recognition management method for interactive education as described above is implemented.

[0072] The technical solution of the embodiment of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0073] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the identity recognition management method for interactive education provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0074] An embodiment of the present application provides a computer program product, including a computer program, wherein the computer program is executed by a third processor to implement the method described above.

[0075] The computer program product provided by the above-mentioned embodiments of the present application and the identity recognition management method for interactive education provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0076] It should be noted that, in this application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or still includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0077] Each embodiment in this application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the identity recognition management method, electronic device, electronic device, and readable storage medium embodiment for evaluating interactive education, since they are basically similar to the above-mentioned identity recognition management method embodiment for interactive education, the description is relatively simple, and the relevant parts can be referred to the partial description of the above-mentioned identity recognition management method embodiment for interactive education.

[0078] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application, so the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. An identity recognition management method for interactive education, characterized in that: include: Acquire biometric information of a target user, a target event set matching the target user, target location information, and a training sample set, wherein the target location information includes location information of the target user at the target location, and the training sample set includes historical environmental factor information of the target location and real-time teaching factor information of other locations adjacent to the target location; Preprocessing the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors affecting user training; Obtaining a preset identity recognition matching model, wherein the preset identity recognition matching model is generated based on historical teaching factor information of other places; Processing the preset identity recognition matching model based on the training sample set with target feature data to generate a target identity recognition matching model; Processing the biometric information of the target user to generate identity information of the target user and emotional information of the target user; Processing the target event set that matches the target user to generate training purpose information for the target user; Based on the target identity recognition matching model, the training purpose information of the target user, the identity information of the target user, the emotional information of the target user and the target location information are processed to generate a training influence factor of the target user, wherein the training influence factor of the target user includes the attendance information of the target user and the training result information of the target user; Processing the training influencing factor of the target user based on the target identity recognition matching model to generate training warning information for the target user, wherein the training warning information for the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user; Processing a target event set that matches a target user to generate training purpose information of the target user, including: processing a target event set that matches a target user to generate a target training course access frequency and a target training course training time period; obtaining the target user's historical training information for the target training course; processing the historical training information to generate the target user's training preference information, wherein the target user's training preference information includes the target user's training information within the historical time period; processing the target training course access frequency and the target training course training time period based on the target user's training preference information to generate the target user's training purpose information; The training purpose information of the target user, the identity information of the target user, the emotional information of the target user and the target location information are processed based on the target identity recognition matching model to generate a training influence factor for the target user, including: processing the training purpose information of the target user based on the target identity recognition matching model to generate attribute information of the content to be trained; processing the attribute information of the content to be trained based on the emotional information of the target user and the identity information of the target user to generate a training content matching degree, wherein the training content matching degree is used to characterize the matching relationship between the emotional state of the target user and the content to be trained; processing the training content matching degree based on the target location information to generate a training influence factor for the target user; The training impact factor of the target user is processed based on the target identity recognition matching model to generate training warning information for the target user, including: processing the training impact factor of the target user based on the target identity recognition matching model to generate training abnormality features and correlation co-occurrence frequencies; processing the training abnormality features and the correlation co-occurrence frequencies to generate a training progress value for the target user; processing the training progress value of the target user based on a preset training progress value to generate training warning information for the target user; the target identity recognition matching model includes a calculation formula for obtaining the correlation co-occurrence frequency, and the calculation formula is: ; Where N is the data sample, when training abnormal features and training impact factor When they appear at the same time, ) = 1, otherwise ) = 0, the training abnormal feature subscript i takes values ​​in the range of n, and the training impact factor subscript j takes values ​​in the range of m.

2. The method according to claim 1, characterized in that Preprocessing the training sample set to generate a training sample set with target feature data includes: Extract features from the training sample set and determine the original feature library; Processing the original feature library to generate a training set and a verification set; Processing the verification set based on a preset classifier to generate a prediction result; Processing the training set based on a preset algorithm to generate a prediction result of the validation set; The prediction results and the validation set prediction results are processed to generate target feature data, where the target feature data is used to characterize risk factors that affect user training.

3. The method according to claim 1, characterized in that The preset identity recognition matching model is processed based on the training sample set with target feature data to generate a target identity recognition matching model, including: Processing the training sample set with target feature data to generate expression feature influencing factors, wherein the expression feature influencing factors are generated based on facial image information of other users; Obtaining a preset expression mapping table, wherein the preset expression mapping table is based on expression information generated by different users for different scenarios; Processing the expression feature influencing factors and the preset expression mapping table to generate an original feature library; Processing the original feature library to generate several feature data sets; The preset identity recognition matching model is processed based on a number of feature data sets to generate a target identity recognition matching model.

4. An identity recognition management device for interactive education, characterized in that: The device comprises: An acquisition module is used to acquire biometric information of a target user, a target event set matching the target user, target location information and a training sample set, wherein the target location information includes location information of the target user at the target location, and the training sample set includes historical environmental factor information of the target location and real-time teaching factor information of other locations adjacent to the target location; and to acquire a preset identity recognition matching model, wherein the preset identity recognition matching model is generated based on the historical teaching factor information of other locations; a processing module, configured to pre-process the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors affecting user training; to process the preset identity recognition matching model based on the training sample set with target feature data to generate a target identity recognition matching model; to process the biometric information of the target user to generate the identity information of the target user and the emotional information of the target user; to process the target event set that matches the target user to generate the training purpose information of the target user; to process the training purpose information of the target user, the identity information of the target user, the emotional information of the target user and the target location information based on the target identity recognition matching model to generate a training influencing factor of the target user, wherein the training influencing factor of the target user includes the attendance information of the target user and the training result information of the target user; to process the training influencing factor of the target user based on the target identity recognition matching model to generate training warning information of the target user, wherein the training warning information of the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user; Processing a target event set that matches a target user to generate training purpose information of the target user, including: processing a target event set that matches a target user to generate a target training course access frequency and a target training course training time period; obtaining the target user's historical training information for the target training course; processing the historical training information to generate the target user's training preference information, wherein the target user's training preference information includes the target user's training information within the historical time period; processing the target training course access frequency and the target training course training time period based on the target user's training preference information to generate the target user's training purpose information; The training purpose information of the target user, the identity information of the target user, the emotional information of the target user and the target location information are processed based on the target identity recognition matching model to generate a training influence factor for the target user, including: processing the training purpose information of the target user based on the target identity recognition matching model to generate attribute information of the content to be trained; processing the attribute information of the content to be trained based on the emotional information of the target user and the identity information of the target user to generate a training content matching degree, wherein the training content matching degree is used to characterize the matching relationship between the emotional state of the target user and the content to be trained; processing the training content matching degree based on the target location information to generate a training influence factor for the target user; The training impact factor of the target user is processed based on the target identity recognition matching model to generate training warning information for the target user, including: processing the training impact factor of the target user based on the target identity recognition matching model to generate training abnormality features and correlation co-occurrence frequencies; processing the training abnormality features and the correlation co-occurrence frequencies to generate a training progress value for the target user; processing the training progress value of the target user based on a preset training progress value to generate training warning information for the target user; the target identity recognition matching model includes a calculation formula for obtaining the correlation co-occurrence frequency, and the calculation formula is: ; Where N is the data sample, when training abnormal features and training impact factor When they appear at the same time, ) = 1, otherwise ) = 0, the training abnormal feature subscript i takes values ​​in the range of n, and the training impact factor subscript j takes values ​​in the range of m.

5. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the identity recognition management method for interactive education as described in any one of claims 1 to 3 by executing the executable instructions.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the identity recognition management method for interactive education described in any one of claims 1 to 3 is implemented.

Images