A Learning Buddy Recommendation Method Based on a Smart Education Terminal

Abstract

The present disclosure provides a method for recommending learning friends based on a smart education terminal, including: obtaining learning data of a first student from the smart education terminal to determine student behavior tags of the first student; performing standardization processing and aggregation processing on the student behavior tags to obtain at least one of a learning participation parameter corresponding to a first tag, a learning efficiency parameter corresponding to a second tag, and a learning type parameter corresponding to a third tag; and performing friend recommendation for the first student based on at least one of the learning participation parameter, the learning efficiency parameter, and the learning type parameter. The method of the present disclosure generates tags of the first student from multiple aspects such as learning behavior, knowledge mastery level, and learning style by obtaining the learning data of the first student, and then performs similarity matching on the tags of different students, so as to perform friend recommendation for the first student according to the similarity matching result, improving the objectivity and accuracy of friend recommendation.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to a method for recommending learning friends based on a smart education terminal. Background Art

[0002] In recent years, with the continuous advancement and development of computer technologies and educational informatization, computer and artificial intelligence technologies have been gradually applied to various daily educational teaching activities. More and more intelligent devices have been gradually applied to teaching scenarios, and students can learn through intelligent devices to provide more convenient learning services for students.

[0003] When students use intelligent devices to learn, they usually can only manually select their own learning tags, which is somewhat subjective. Therefore, when recommending friends for students based on these learning tags, the acceptance rate of students is not high, and learning partners cannot be accurately recommended for students. Therefore, a solution that can objectively recommend friends to students is needed. Summary of the Invention

[0004] The present disclosure provides a method for recommending learning friends based on a smart education terminal.

[0005] According to a first aspect of the present disclosure, there is provided a method for recommending learning friends based on a smart education terminal, the method including: obtaining learning data of a first student from the smart education terminal to determine student behavior tags of the first student, where the student behavior tags include at least one of the following: a first tag, a second tag, and a third tag, wherein the first tag is used to indicate the learning behavior situation of the first student, the second tag is used to indicate the knowledge mastery level of the first student, and the third tag is used to indicate the learning style of the first student; performing a normalization process and an aggregation process on the student behavior tags to obtain at least one of a learning participation parameter corresponding to the first tag, a learning efficiency parameter corresponding to the second tag, and a learning type parameter corresponding to the third tag; and performing friend recommendation for the first student based on at least one of the learning participation parameter, the learning efficiency parameter, and the learning type parameter.

[0006] In some embodiments of the present disclosure, obtaining the learning data of the first student to determine the student behavior tags includes at least one of the following: determining the chat data tag of the first student based on the chat content of the first student in the learning data; determining the learning comprehension tag of the first student based on the degree of understanding of the teaching materials by the first student in the learning data; determining the knowledge point proficiency tag of the first student based on the answering data of the first student for the first question corresponding to the same knowledge point in the learning data; determining the global ability evaluation parameter of the comprehensive evaluation of the first student based on the answering data of the first student for questions of different knowledge points, so as to use the global ability evaluation parameter to compare with a preset threshold to determine the learning type tag of the first student, where the learning type tag includes at least one of the following: advanced challenge type tag, balanced development type tag, and basic cultivation type tag.

[0007] In some embodiments of the present disclosure, determining the knowledge point proficiency tag of the first student based on the answering data of the first student for the first question corresponding to the same knowledge point includes: determining the ratio between the number of completed questions of the first student for the first question and the total number of the first questions as the knowledge point learning progress parameter of the first student, and determining the ratio between the number of correct answers of the first student for the first question and the number of completed questions of the first student for the first question as the knowledge point accuracy parameter of the first student; performing weighted summation on the learning progress parameter and the knowledge point accuracy parameter to determine the first knowledge point proficiency parameter of the first student; when the modification time after the first student answers the first question incorrectly is less than the preset modification time, and / or when the number of times the first student answers the first question correctly is greater than the preset correct number threshold, and the standard deviation of the time interval when the first student answers the first question correctly is greater than the preset standard deviation threshold, it is determined that the first student has a suspicious event; when the number of suspicious events of the first student is greater than or equal to the preset suspicious threshold, performing correction processing on the first knowledge point proficiency parameter to obtain the knowledge point proficiency tag; when the number of suspicious events of the first student is less than the preset suspicious threshold, determining the first knowledge point proficiency parameter as the knowledge point proficiency tag.

[0008] In some embodiments of the present disclosure, performing correction processing on the first knowledge point proficiency parameter to obtain the knowledge point proficiency tag includes: associating the first knowledge point proficiency parameter with the time when the first student answers the first question to obtain a second knowledge point proficiency parameter with a time tag; based on the second knowledge point proficiency parameter, the number of suspicious events corresponding to the time tag, the preset suspicious threshold, the preset suspicious event weight, and the preset steepness parameter, combining the following formula 1 to determine the proficiency correction parameter:

[0009] Formula 1,

[0010] where FraudScore represents the proficiency correction parameter, Represents a preset suspicious event weight. Represents the number of suspicious events corresponding to the time tag. Represents a preset suspicious threshold, and k represents a preset steepness parameter.

[0011] Based on the proficiency correction parameter, combined with the following formula 2, correct the proficiency parameter of the second knowledge point to obtain the proficiency parameter of the third knowledge point.

[0012] Formula 2

[0013] Where M final Represents the proficiency parameter of the third knowledge point, and M t Represents the proficiency parameter of the second knowledge point.

[0014] Based on the proficiency parameter of the third knowledge point, the preset difficulty of the first question, the preset memory retention rate, and the preset interference parameter, combined with the following formula 3, determine the knowledge point proficiency label.

[0015] Formula 3

[0016] Where P represents the knowledge point proficiency label. Represents the preset interference parameter. Represents the preset memory retention rate. Represents the preset difficulty of the t-th first question.

[0017] In some embodiments of the present disclosure, the method further includes: based on the answering accuracy rate of the first question, the average answering time of the first question, the total number of questions of the first question, and the actual answering time of the first question, combined with the following formula 4, determine the calibration difficulty to use the calibration difficulty to replace the preset difficulty.

[0018] Formula 4

[0019] Where Represents the calibration difficulty of the t-th first question, U represents the total number of questions of the first question. Represents the actual answering time of the first question. Represents the average answering time of the first question. Represents the actual answering time of the t-th first question.

[0020] In some embodiments of the present disclosure, based on the answering data of the first student for questions on different knowledge points in the learning data, the global ability evaluation parameters for comprehensively evaluating the first student include: performing smoothing processing and normalization processing on the answering data to obtain standardized answering data; performing weighted summation on the standardized accuracy rate of basic knowledge points and the completion degree of learning basic knowledge points in the standardized answering data to determine the score of basic knowledge points in the standardized answering data; performing weighted summation on the standardized accuracy rate of key knowledge points and the completion degree of learning key knowledge points in the standardized answering data to determine the score of key knowledge points in the standardized answering data; based on the score of basic knowledge points, the score of key knowledge points, and the preset angular difference between the basic knowledge points and the key knowledge points, and combining the following formula 5, determine the global ability evaluation parameters,

[0021] Formula 5,

[0022] where T represents the global ability evaluation parameter, S BP represents the score of basic knowledge points, S IW represents the score of key knowledge points, represents the preset angular difference.

[0023] In some embodiments of the present disclosure, using the global ability evaluation parameter and comparing it with a preset threshold to determine the learning type label of the first student includes: when the global ability evaluation parameter is less than the first evaluation preset value, determining the learning type label as an advanced challenge type label; when the global ability evaluation parameter is less than the second evaluation preset value and greater than the third evaluation preset value, determining the learning type label as a balanced development type label; when the global ability evaluation parameter is greater than the fourth evaluation preset value, determining the learning type label as a basic cultivation type label, where the first evaluation preset value is greater than the second evaluation preset value, the second evaluation preset value is greater than the third evaluation preset value, and the third evaluation preset value is greater than the fourth evaluation preset value.

[0024] In some embodiments of the present disclosure, performing standardization processing and aggregation processing on the student behavior labels to obtain at least one of the learning participation parameter corresponding to the first label, the learning efficiency parameter corresponding to the second label, and the learning type parameter corresponding to the third label includes: dividing the first label and the second label into positive labels and negative labels, and performing binary encoding on the third label to obtain an encoded label; performing weighted summation on the positive labels and negative labels corresponding to the first label to obtain the learning participation parameter; performing weighted summation on the positive labels and negative labels corresponding to the second label to obtain the learning efficiency parameter; mapping the encoded label according to the preset encoding mapping rule to obtain the learning type parameter.

[0025] In some embodiments of the present disclosure, the friend recommendation for the first student based on at least one of the learning participation parameter, the learning efficiency parameter, and the learning type parameter includes: according to the preset parameter requirements of the first student, recommending a second student whose learning participation parameter, learning efficiency parameter, and learning type parameter meet the preset recommendation parameter requirements to the first student; and / or performing a global matching process on the learning participation parameter, the learning efficiency parameter, and the learning type parameter to determine the label score of the first student, and based on the label score of the first student and the preset label weight, determining the label similarity between the first students, so as to perform friend recommendation for the first student according to the label similarity.

[0026] In some embodiments of the present disclosure, performing a global matching process on the learning participation parameter, the learning efficiency parameter, and the learning type parameter to determine the label score of the first student includes: based on the learning participation parameter, the learning efficiency parameter, and the learning type parameter, combining the following formula 6 to determine the label score of the first student:

[0027] Formula 6

[0028] where Match_Score represents the label score, X_Score represents the learning participation parameter, Y_Score represents the learning efficiency parameter, Z_Coeff represents the learning type parameter, and μ1, μ2, and μ3 represent the preset parameter weights.

[0029] In some embodiments of the present disclosure, based on the label score of the first student and the preset label weight, determining the label similarity between the first students to perform friend recommendation for the first student according to the label similarity includes: based on the label score of the first student and the preset label weight, combining the following formula 7 to determine the label similarity between the first students

[0030] Formula 7

[0031] where Sim(u, v) represents the label similarity between student u and student v, u k represents the label score of student u in vector form, v k represents the label score of student v in vector form, and w k represents the preset label weight; when the label similarity is greater than the preset similarity threshold, perform friend recommendation for the first student.

[0032] In summary, a learning buddy recommendation method based on a smart education terminal proposed by the present disclosure includes: obtaining learning data of a first student from the smart education terminal to determine student behavior tags of the first student, where the student behavior tags include at least one of the following: a first tag, a second tag, and a third tag. The first tag is used to indicate the learning behavior of the first student, the second tag is used to indicate the knowledge mastery of the first student, and the third tag is used to indicate the learning style of the first student. Standardize and aggregate the student behavior tags to obtain at least one of a learning participation parameter corresponding to the first tag, a learning efficiency parameter corresponding to the second tag, and a learning type parameter corresponding to the third tag. Based on at least one of the learning participation parameter, the learning efficiency parameter, and the learning type parameter, recommend a buddy for the first student. The method of the present disclosure can objectively generate a learning profile of the first student by obtaining the learning data of the first student and generating tags of the first student from multiple aspects such as learning behavior, knowledge mastery, and learning style according to the learning data of the first student, and then perform similarity matching on the tags of different students, and recommend a buddy for the first student according to the similarity matching result, improving the objectivity and accuracy of buddy recommendation.

[0033] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0035] Figure 1 is a schematic flowchart of a learning buddy recommendation method based on a smart education terminal provided by an embodiment of the present disclosure;

[0036] Figure 2 is a schematic flowchart of another learning buddy recommendation method based on a smart education terminal provided by an embodiment of the present disclosure;

[0037] Figure 3 is a schematic flowchart of another learning buddy recommendation method based on a smart education terminal provided by an embodiment of the present disclosure;

[0038] Figure 4 is a schematic flowchart of another learning buddy recommendation method based on a smart education terminal provided by an embodiment of the present disclosure;

[0039] Figure 5 is a schematic flowchart of another learning buddy recommendation method based on a smart education terminal provided by an embodiment of the present disclosure;

[0040] Figure 6 Schematic flowchart of another learning buddy recommendation method based on a smart education terminal provided by an embodiment of the present disclosure;

[0041] Figure 7 Schematic flowchart of another learning buddy recommendation method based on a smart education terminal provided by an embodiment of the present disclosure;

[0042] Figure 8 Schematic structural diagram of a learning buddy recommendation device based on a smart education terminal provided by an embodiment of the present disclosure;

[0043] Figure 9 Schematic hardware structure diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0044] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.

[0045] In recent years, with the continuous advancement and development of computer technology and educational informatization, computer and artificial intelligence technologies have gradually been applied to various daily educational teaching activities. More and more intelligent devices have been gradually applied to teaching scenarios, and students can learn through intelligent devices to provide more convenient learning services for students.

[0046] When students use intelligent devices to learn, they usually can only manually select their own learning tags, which is somewhat subjective. Therefore, when recommending buddies to students based on these learning tags, the acceptance rate of students is not high, and it cannot accurately recommend learning partners to students. Therefore, a solution that can objectively recommend buddies to students is needed.

[0047] To solve the problems in the related art, a learning buddy recommendation method based on a smart education terminal proposed by the present disclosure generates tags for a first student from multiple aspects such as learning behavior, knowledge mastery level, and learning style by obtaining the learning data of the first student, and then performs similarity matching on the tags of different students to recommend buddies to the first student according to the similarity matching result, improving the objectivity and accuracy of buddy recommendation.

[0048] Next, a learning buddy recommendation method based on a smart education terminal according to an embodiment of the present disclosure is described with reference to the accompanying drawings.

[0049] Figure 1The following is a schematic flowchart of a learning buddy recommendation method based on an intelligent education terminal provided by an embodiment of the present disclosure. As Figure 1 shown, the method includes:

[0050] Step 101: Obtain the learning data of the first student from the intelligent education terminal to determine the student behavior labels of the first student.

[0051] In some embodiments, the intelligent education terminal can be implemented based on hardware devices (such as tablet computers, smart whiteboards), or can be based on software applications installed on ordinary computers or mobile devices. Generally, these intelligent education terminals can be connected to cloud services to achieve functions such as accessing rich educational resources and data synchronization. In other words, the intelligent education terminal can record the processes of the first student doing questions, learning, reviewing, etc. during the process of the first student doing exercises and learning, so as to store the learning data of the first student.

[0052] In some embodiments, the student behavior labels include at least one of the following: the first label, the second label, and the third label. Among them, the first label is used to indicate the learning behavior of the first student, the second label is used to indicate the knowledge mastery of the first student, and the third label is used to indicate the learning style of the first student.

[0053] It should be understood that the student behavior labels can include at least one of the first label, the second label, and the third label, or can include other labels other than the first label, the second label, and the third label.

[0054] In other words, any label that can be used to indicate aspects such as the learning progress and learning habits of the first student can be used as a student behavior label.

[0055] In some embodiments, the first label can include one or more sub-labels, the second label can include one or more sub-labels, and the third label can include one or more sub-labels.

[0056] In some embodiments, the learning data can include, but is not limited to, the chat content of the first student, the understanding degree of the first student for the textbook, the answer data of the first student, etc.

[0057] In some embodiments, the behavior labels of the first student can be determined by clustering, statistical processing, etc. of the learning data of the first student.

[0058] Step 102: Perform standardization processing and aggregation processing on the student behavior labels to obtain at least one of the learning participation parameter corresponding to the first label, the learning efficiency parameter corresponding to the second label, and the learning type parameter corresponding to the third label.

[0059] In some embodiments, student behavior tags can be classified into categories such as positive tags, negative tags, learning types, etc., so as to achieve the aggregation processing of student behavior data.

[0060] In some embodiments, the aggregated student behavior tags can be normalized to achieve the standardization processing of student behavior tags.

[0061] In some embodiments, the student behavior tags after standardization processing and aggregation processing are determined as at least one of a learning participation parameter, a learning efficacy parameter, and a learning type parameter, where the learning participation parameter corresponds to the first tag, the learning efficacy parameter corresponds to the second tag, and the learning type parameter corresponds to the third tag.

[0062] Step 103: Based on at least one of the learning participation parameter, the learning efficacy parameter, and the learning type parameter, perform friend recommendation for the first student.

[0063] In some embodiments, according to the preset parameter requirements of the first student, a second student whose learning participation parameter, learning efficacy parameter, and learning type parameter meet the preset recommendation parameter requirements can be recommended to the first student.

[0064] Exemplarily, the preset parameter requirements of the first student are: expecting to recommend a student with a learning participation parameter of A1, a learning efficacy parameter of A2, and a learning type parameter of A3. Then, a second student with a learning participation parameter of A1, a learning efficacy parameter of A2, and a learning type parameter of A3 can be recommended to the first student.

[0065] In some instances, perform global matching processing on the learning participation parameter, the learning efficacy parameter, and the learning type parameter to determine the label score of the first student, and based on the label score of the first student and the preset label weight, determine the label similarity between the first students. When the label similarity between the first students is greater than the preset threshold, the first students with the label similarity greater than the preset threshold can be recommended to each other.

[0066] In some embodiments, when performing friend recommendation, according to the preset learning grid diagram, the student who is the closest to the first student in the preset grid diagram and meets the friend recommendation requirements can be recommended to the first student. The preset learning grid diagram is formed by the learning behavior paths of students. The coordinate points of students in the preset learning grid diagram can indicate the learning behaviors of students (such as learning habits, learning progress, etc.). The closer the distance between students in the preset learning grid diagram, the more similar the learning behaviors of students.

[0067] In summary, the present disclosure proposes a method for recommending learning friends based on a smart education terminal, including: obtaining learning data of a first student from the smart education terminal to determine student behavior tags of the first student; performing standardization processing and aggregation processing on the student behavior tags to obtain at least one of a learning participation parameter corresponding to a first tag, a learning efficiency parameter corresponding to a second tag, and a learning type parameter corresponding to a third tag; and recommending friends for the first student based on at least one of the learning participation parameter, the learning efficiency parameter, and the learning type parameter. The method of the present disclosure generates tags for the first student from multiple aspects such as learning behavior, knowledge mastery, and learning style by obtaining the learning data of the first student, and then performs similarity matching on the tags of different students, and recommends friends for the first student according to the similarity matching result, improving the objectivity and accuracy of friend recommendation.

[0068] As a possible implementation, as Figure 2 shown in the flowchart of another method for recommending learning friends based on a smart education terminal. On the basis of the above embodiments, step 101 is further explained, including the following steps:

[0069] Step 201: Determine the chat data tag of the first student based on the chat content of the first student in the learning data.

[0070] In some embodiments, it is possible to determine the learning online duration tag of the first student based on whether the chat content of the first student in the learning data belongs to a preset knowledge base and the duration of the first student's answering questions; in other words, the duration corresponding to the chat content of the first student belonging to the preset knowledge base can be added to the duration of the first student's answering questions, and the summation result can be determined as the learning online duration tag of the first student.

[0071] In some embodiments, it is possible to count the number of times the student in the learning data initiates a learning help request, and determine the counted number as the help request number tag of the first student.

[0072] In some embodiments, it is possible to count the number of times the student in the learning data solves a learning help request, and determine the counted number as the effective solution number tag of the first student.

[0073] In some embodiments, it is possible to determine the response efficiency tag of the first student based on the response duration when the student in the learning data receives a learning help request and the total duration between initiating a learning help request and solving the learning help request.

[0074] Among them, the above help request number tag, effective solution number tag, response efficiency tag, and learning online duration tag can all belong to the chat data tag, and among them, the chat data tag can belong to the first tag.

[0075] Step 202: Determine the learning and understanding label of the first student based on the understanding level of the first student in the learning data for the teaching materials.

[0076] In some embodiments, the answering accuracy label of the first student can be determined based on the answering data of the first student in the learning data for the same questions.

[0077] In some embodiments, the learning progress label of the first student can be determined based on the learning progress of the first student in the learning data for the teaching material content.

[0078] In some embodiments, the answering duration label of the first student can be determined based on the duration of the first student's first attempt to answer the same question in the learning data.

[0079] In some embodiments, the knowledge point proficiency label of the first student can be determined based on the answering data of the first student for the first question corresponding to the same knowledge point in the learning data.

[0080] Among them, the answering accuracy label, the learning progress label, and the answering duration label can all belong to the learning and understanding label, and among them, the learning and understanding label can belong to the second label.

[0081] Step 203: Determine the knowledge point proficiency label of the first student based on the answering data of the first student for the first question corresponding to the same knowledge point in the learning data.

[0082] In some embodiments, the knowledge point proficiency label can also belong to the second label.

[0083] Specifically, in some embodiments, the knowledge point accuracy parameter and the knowledge point learning progress parameter of the first student can be determined according to the answering data of the first student for the first question corresponding to the same knowledge point (such as the number of correct answers of the first student, the total number of questions answered by the first student, etc.); and the learning progress parameter and the knowledge point accuracy parameter are fused to determine the first knowledge point proficiency parameter of the first student, and it is determined whether the first student has cases of plagiarism or cheating, so as to determine the knowledge point proficiency label according to the judgment result, thereby improving the accuracy of label determination. Among them, the judgment rules can be as follows:

[0084] When the modification time after the first student answers the first question incorrectly is less than the preset modification time, and / or when the number of times the first student answers the first question correctly is greater than the preset correct number threshold, and the standard deviation of the time interval when the first student answers the first question correctly is greater than the preset standard deviation threshold, it is determined that the first student has a suspicious event once;

[0085] When the number of suspicious events of the first student is greater than or equal to the preset suspicious threshold, the first knowledge point proficiency parameter is corrected to obtain the knowledge point proficiency label;

[0086] When the number of suspicious events of the first student is less than the preset suspicious threshold, the proficiency parameter of the first knowledge point is determined as the knowledge point proficiency label.

[0087] Step 204: Based on the answering data of the first student for different knowledge point questions in the learning data, determine the global ability evaluation parameter of the comprehensive evaluation of the first student, so as to use the global ability evaluation parameter to compare with the preset threshold to determine the learning type label of the first student.

[0088] In some embodiments, the learning type label includes at least one of the following: an advanced challenge type label, a balanced development type label, and a basic cultivation type label. Among them, the learning type label can belong to the third label.

[0089] In some embodiments, the learning type label of the first student can be determined according to the answering situation of the first student for questions of different difficulties in the answering data.

[0090] For example, if the first student only answers questions of higher difficulty and has a high accuracy rate (greater than the preset threshold), then the learning type label of the first student can be determined as the advanced challenge type label.

[0091] Specifically, in some embodiments, when the global ability evaluation parameter is less than the first evaluation preset value, the learning type label is determined as the advanced challenge type label;

[0092] When the global ability evaluation parameter is less than the second evaluation preset value and greater than the third evaluation preset value, the learning type label is determined as the balanced development type label;

[0093] When the global ability evaluation parameter is greater than the fourth evaluation preset value, the learning type label is determined as the basic cultivation type label, where the first evaluation preset value is greater than the second evaluation preset value, the second evaluation preset value is greater than the third evaluation preset value, and the third evaluation preset value is greater than the fourth evaluation preset value.

[0094] In summary, the present disclosure proposes a method for recommending learning friends based on a smart education terminal, including: determining the chat data label of the first student based on the chat content of the first student in the learning data; determining the learning understanding label of the first student based on the understanding degree of the first student on the teaching materials in the learning data; determining the knowledge point proficiency label of the first student based on the answering data of the first student on the first question corresponding to the same knowledge point in the learning data; determining the global ability evaluation parameter of the comprehensive evaluation of the first student based on the answering data of the first student on the questions of different knowledge points, so as to use the global ability evaluation parameter to compare with a preset threshold to determine the learning type label of the first student, where the learning type label includes at least one of the following: advanced challenge type label, balanced development type label, and basic cultivation type label. The method of the present disclosure can determine the behavior labels of students from multiple perspectives through different data in the learning data, improve the diversity of student labels, and lay a foundation for realizing accurate friend recommendation.

[0095] As a possible implementation, as Figure 3 shown in the flowchart of another method for recommending learning friends based on a smart education terminal. On the basis of the above embodiments, further determining the knowledge point proficiency label of the first student based on the answering data of the first student on the first question corresponding to the same knowledge point in the learning data includes the following steps:

[0096] Step 301: Determine the knowledge point learning progress parameter of the first student as the ratio between the number of completed questions of the first student on the first question and the total number of the first questions, and determine the knowledge point accuracy parameter of the first student as the ratio between the number of correctly answered questions of the first student on the first question and the number of completed questions of the first question.

[0097] In some embodiments, the knowledge point learning progress parameter can be determined by the following formula:

[0098]

[0099] where Q represents the knowledge point learning progress parameter, q k represents the total number of the first questions, and q done represents the number of completed questions of the first question.

[0100] Step 302: Perform weighted summation on the learning progress parameter and the knowledge point accuracy parameter to determine the first knowledge point proficiency parameter of the first student.

[0101] In some embodiments, the first knowledge point proficiency parameter can be determined by the following formula:

[0102]

[0103] where Ccoverage represents the proficiency parameter of the first knowledge point, and P represents the learning progress parameter. represents a preset weight.

[0104] Step 303: When the modification time after the first student answers the first question incorrectly is less than the preset modification time, and / or when the number of times the first student answers the first question correctly is greater than the preset correct number threshold, and the standard deviation of the time intervals when the first student answers the first question correctly is greater than the preset standard deviation threshold, it is determined that the first student has a suspicious event.

[0105] In some embodiments, by defining suspicious events, it is determined whether the first student has abnormal behaviors such as cheating and copying during learning or question-solving, so as to judge whether it is necessary to correct the proficiency parameter of the first knowledge point.

[0106] Step 304: When the number of suspicious events of the first student is greater than or equal to the preset suspicious threshold, perform a correction process on the proficiency parameter of the first knowledge point to obtain a knowledge point proficiency label.

[0107] In some embodiments, when the number of suspicious events of the first student is greater than or equal to the preset suspicious threshold, it is determined that the first student has an abnormal behavior. At this time, a correction process is performed on the proficiency parameter of the first knowledge point, and a knowledge point proficiency label is determined according to the corrected proficiency parameter of the first knowledge point. For details, see Figure 4 the embodiments shown.

[0108] Step 305: When the number of suspicious events of the first student is less than the preset suspicious threshold, determine the proficiency parameter of the first knowledge point as the knowledge point proficiency label.

[0109] In some embodiments, when the number of suspicious events of the first student is less than the preset suspicious threshold, it is determined that the first student has no abnormal behavior. At this time, the proficiency parameter of the first knowledge point can be determined as the knowledge point proficiency label.

[0110] In summary, according to a learning friend recommendation method based on a smart education terminal proposed by the present disclosure, by determining the number of suspicious events of the first student, different methods are used to determine the knowledge point proficiency label, which improves the accuracy of the knowledge point proficiency label and lays a foundation for realizing accurate friend recommendation.

[0111] As a possible implementation, as Figure 4 shown in the flowchart of another learning friend recommendation method based on a smart education terminal, on the basis of the above embodiments, step 304 is further explained, including the following steps:

[0112] Step 401: Associate the proficiency parameter of the first knowledge point with the time taken by the first student to answer the first question to obtain a second knowledge point proficiency parameter with a time tag.

[0113] In some embodiments, when the number of suspicious events of the first student is greater than or equal to a preset suspicious threshold, it indicates that the first student has studied the first knowledge point for a relatively long time. Therefore, in order to determine whether the first student will forget the first knowledge point over time, it is necessary to associate the proficiency parameter of the first knowledge point with the time taken by the first student to answer the first question.

[0114] For example, use to represent the proficiency parameter of the first knowledge point of the first student at time t.

[0115] Step 402: Determine a proficiency correction parameter based on the second knowledge point proficiency parameter, the number of suspicious events corresponding to the time tag, the preset suspicious threshold, the preset suspicious event weight, and the preset steepness parameter.

[0116] In some embodiments, the proficiency correction parameter can be determined based on the second knowledge point proficiency parameter, the number of suspicious events corresponding to the time tag, the preset suspicious threshold, the preset suspicious event weight, and the preset steepness parameter, in combination with the following formula 1:

[0117] Formula 1,

[0118] where FraudScore represents the proficiency correction parameter, represents the preset suspicious event weight, represents the number of suspicious events corresponding to the time tag, represents the preset suspicious threshold, and k represents the preset steepness parameter.

[0119] Step 403: Correct the second knowledge point proficiency parameter based on the proficiency correction parameter to obtain a third knowledge point proficiency parameter.

[0120] In some embodiments, the second knowledge point proficiency parameter can be corrected based on the proficiency correction parameter, in combination with the following formula 2, to obtain a third knowledge point proficiency parameter.

[0121] Formula 2,

[0122] where Mfinal represents the third knowledge point proficiency parameter, and Mt represents the second knowledge point proficiency parameter.

[0123] Step 404: Determine a knowledge point proficiency label based on the third knowledge point proficiency parameter, the preset difficulty of the first question, the preset memory retention rate, and the preset interference parameter.

[0124] In some instances, based on the proficiency parameter of the third knowledge point, the preset difficulty of the first question, the preset memory retention rate, and the preset interference parameter, in combination with the following formula 3, the knowledge point proficiency label can be determined:

[0125] Formula 3

[0126] where P represents the knowledge point proficiency label, represents the preset interference parameter, represents the preset memory retention rate, represents the preset difficulty of the t-th first question.

[0127] In some embodiments, the calibrated difficulty can also be determined based on the answering accuracy rate of the first question, the average answering time of the first question, the total number of questions of the first question, and the actual answering time of the first question, in combination with the following formula 4, so as to use the calibrated difficulty to replace the preset difficulty, thereby dynamically determining the difficulty of the first question using the actual question-solving data of the first student, so as to improve the accuracy and objectivity of the determination of the knowledge point proficiency label:

[0128] Formula 4

[0129] where represents the calibrated difficulty of the t-th first question, U represents the total number of questions of the first question, represents the actual answering time of the first question, represents the average answering time of the first question, represents the actual answering time of the t-th first question.

[0130] As a possible implementation, as shown in Figure 5 the flowchart of another learning friend recommendation method based on a smart education terminal, on the basis of the above embodiments, further explaining the global ability evaluation parameter for determining the comprehensive evaluation of the first student based on the answering data of the first student for different knowledge point questions, including the following steps:

[0131] Step 501, perform smoothing processing and normalization processing on the answering data to obtain standardized answering data.

[0132] In some embodiments, the answering data can be smoothed by introducing Bayesian smoothing, but not limited to this. Any processing method that can avoid extreme values in the answering data can be the above-mentioned smoothing processing.

[0133] In some embodiments, the smoothed answering data can be mapped to the interval [0, 1], so as to achieve normalization processing, and the answering data after smoothing processing and normalization processing is determined as the standardized answering data.

[0134] In some embodiments, due to the different levels of difficulty of the knowledge points answered by the first student, the standardized answer data can be divided into standardized basic knowledge point data and standardized key knowledge point data. Among them, the standardized basic knowledge point data can include: the accuracy rate of standardized basic knowledge points and the completion degree of learning standardized basic knowledge points; the standardized key knowledge point data can include: the accuracy rate of standardized key knowledge points and the completion degree of learning standardized key knowledge points.

[0135] Step 502: Perform a weighted sum of the accuracy rate of standardized basic knowledge points and the completion degree of learning standardized basic knowledge points in the standardized answer data to determine the score of basic knowledge points in the standardized answer data.

[0136] In some embodiments, the accuracy rate of standardized basic knowledge points can be determined based on the basic knowledge point questions answered by the first student and the basic knowledge point questions answered correctly by the first student.

[0137] Step 503: Perform a weighted sum of the accuracy rate of standardized key knowledge points and the completion degree of learning standardized key knowledge points in the standardized answer data to determine the score of key knowledge points in the standardized answer data.

[0138] In some embodiments, the accuracy rate of standardized key knowledge points can be determined based on the key knowledge point questions answered by the first student and the key knowledge point questions answered correctly by the first student.

[0139] Step 504: Based on the score of basic knowledge points, the score of key knowledge points, and the preset angular difference between the basic knowledge points and the key knowledge points, determine the global ability evaluation parameter.

[0140] In some embodiments, the global ability evaluation parameter can be determined by combining the following formula 5 based on the score of basic knowledge points, the score of key knowledge points, and the preset angular difference between the basic knowledge points and the key knowledge points.

[0141] Formula 5

[0142] where T represents the global ability evaluation parameter, S BP represents the score of basic knowledge points, S IW represents the score of key knowledge points, represents the preset angular difference.

[0143] As a possible implementation, as Figure 6 shown in the flowchart of another learning buddy recommendation method based on a smart education terminal, on the basis of the above embodiments, step 102 is further explained, including the following steps:

[0144] Step 601: Divide the first label and the second label into positive and negative labels, and perform binary encoding on the third label to obtain an encoded label.

[0145] In some embodiments, as shown in Table 1, the first label and the second label can be divided into positive and negative labels, and binary encoding can be performed on the third label:

[0146]

[0147] Table 1

[0148] Among them, for the classification indicators shown in the table, one-hot encoding is used, that is, the value of Z1 balanced development type is 1, and the values of basic cultivation type and advanced challenge type are both 0.

[0149] In some embodiments, the positive and negative labels in the table can also be standardized through a normalization formula to facilitate the determination of the learning participation parameter.

[0150] Step 602: Perform weighted summation on the positive and negative labels corresponding to the first label to obtain the learning participation parameter.

[0151] In some embodiments, the positive and negative labels corresponding to the first label can be weighted and summed through the following formula to obtain the learning participation parameter:

[0152]

[0153] Among them, X_Score represents the learning participation parameter, X norm represents the positive and negative labels corresponding to the first label, and α represents the preset weight.

[0154] Step 603: Perform weighted summation on the positive and negative labels corresponding to the second label to obtain the learning efficiency parameter.

[0155] In some embodiments, the positive and negative labels corresponding to the second label can be weighted and summed through the following formula to obtain the learning efficiency parameter:

[0156]

[0157] Among them, Y_Score represents the learning efficiency parameter, Y norm represents the positive and negative labels corresponding to the second label, and β represents the preset weight.

[0158] Step 604: Map the encoded label according to the preset encoding mapping rule to obtain the learning type parameter.

[0159] In some embodiments, the encoding label may be mapped according to the following preset encoding mapping rules to obtain the learning type parameter:

[0160] ,

[0161] where Z_Coeff represents the learning type parameter.

[0162] As a possible implementation, as Figure 7 shown in the flowchart of another learning buddy recommendation method based on the intelligent education terminal, on the basis of the above embodiments, the friend recommendation for the first student according to the label similarity is further explained, including the following steps:

[0163] Step 701, based on the learning participation parameter, the learning efficiency parameter, and the learning type parameter, and combined with the following formula 6, determine the label score of the first student.

[0164] In some embodiments, the label score of the first student may be determined based on the learning participation parameter, the learning efficiency parameter, and the learning type parameter, and combined with the following formula 6:

[0165] Formula 6,

[0166] where Match_Score represents the label score, X_Score represents the learning participation parameter, Y_Score represents the learning efficiency parameter, Z_Coeff represents the learning type parameter, and μ1, μ2, and μ3 represent the preset parameter weights.

[0167] Step 702, based on the label score of the first student and the preset label weight, and combined with the following formula 7, determine the label similarity between the first students.

[0168] In some embodiments, the label score of the first student may be vectorized to obtain the label score in vector form, and then based on the label score in vector form and the preset label weight, and combined with the following formula 7, determine the label similarity between the first students.

[0169] Formula 7,

[0170] where Sim(u,v) represents the label similarity between student u and student v, u k represents the label score of student u in vector form, v k represents the label score of student v in vector form, and w k represents the preset label weight.

[0171] In some embodiments, the preset label weight may also be dynamically updated according to the following formula to improve the accuracy of label similarity determination.

[0172]

[0173] Among them, represents the updated preset label weight, is the preset learning rate, AcceptRatek n represents the acceptance rate of the first user for the nth type of label.

[0174] Step 703: When the label similarity is greater than the preset similarity threshold, perform friend recommendation for the first student.

[0175] In some embodiments, when the label similarity is greater than the preset similarity threshold, it indicates that the learning behaviors of the first students are relatively similar. At this time, mutual recommendation is performed for the first students whose label similarity is greater than the preset similarity threshold.

[0176] In summary, a learning friend recommendation method based on a smart education terminal is publicly provided. Labels of the first student are generated from multiple aspects such as learning behavior, knowledge mastery, and learning style, and then the label similarities of different students are matched, so as to perform friend recommendation for the first student according to the similarity matching result, improving the objectivity and accuracy of friend recommendation.

[0177] Corresponding to the above-mentioned learning friend recommendation method based on a smart education terminal, the present invention also proposes a learning friend recommendation device based on a smart education terminal. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be elaborated in the present invention.

[0178] Figure 8 is a schematic structural diagram of a learning friend recommendation device provided by an embodiment of the present disclosure. As Figure 8 shown, the device includes:

[0179] A determination unit 810, configured to obtain learning data of a first student from a smart education terminal to determine student behavior labels of the first student. The student behavior labels include at least one of the following: a first label, a second label, and a third label. Among them, the first label is used to indicate the learning behavior of the first student, the second label is used to indicate the knowledge mastery of the first student, and the third label is used to indicate the learning style of the first student;

[0180] A processing unit 820, configured to perform normalization processing and aggregation processing on the student behavior labels to obtain at least one of a learning participation parameter corresponding to the first label, a learning efficiency parameter corresponding to the second label, and a learning type parameter corresponding to the third label;

[0181] A recommendation unit 830 for recommending friends to a first student based on at least one of a learning participation parameter, a learning efficacy parameter, and a learning type parameter.

[0182] In some embodiments of the present disclosure, the determination unit 810 is further configured to: determine a chat data label of the first student based on the chat content of the first student in the learning data; determine a learning comprehension label of the first student based on the degree of understanding of the teaching materials by the first student in the learning data; determine a knowledge point proficiency label of the first student based on the answering data of the first student for the first question corresponding to the same knowledge point in the learning data; determine a global ability evaluation parameter for the comprehensive evaluation of the first student based on the answering data of the first student for questions of different knowledge points in the learning data, so as to use the global ability evaluation parameter to compare with a preset threshold to determine a learning type label of the first student, where the learning type label includes at least one of the following: an advanced challenge type label, a balanced development type label, and a basic cultivation type label.

[0183] In some embodiments of the present disclosure, the determination unit 810 is further configured to: determine the ratio between the number of completed questions of the first student for the first question and the total number of the first questions as the knowledge point learning progress parameter of the first student, and determine the ratio between the number of correct answers of the first student for the first question and the number of completed questions of the first student for the first question as the knowledge point accuracy parameter of the first student; perform weighted summation on the learning progress parameter and the knowledge point accuracy parameter to determine the first knowledge point proficiency parameter of the first student; when the modification time after the first student answers the first question incorrectly is less than a preset modification time, and / or when the number of times the first student answers the first question correctly is greater than a preset correct answer threshold, and the standard deviation of the time interval for the first student to answer the first question correctly is greater than a preset standard deviation threshold, determine that the first student has a suspicious event; when the number of suspicious events of the first student is greater than or equal to a preset suspicious threshold, perform a correction process on the first knowledge point proficiency parameter to obtain a knowledge point proficiency label; when the number of suspicious events of the first student is less than the preset suspicious threshold, determine the first knowledge point proficiency parameter as the knowledge point proficiency label.

[0184] In some embodiments of the present disclosure, the determination unit 810 is further configured to: perform a correction process on the first knowledge point proficiency parameter to obtain a knowledge point proficiency label, including:

[0185] Associate the first knowledge point proficiency parameter with the time when the first student answers the first question to obtain a second knowledge point proficiency parameter with a time label;

[0186] Based on the second knowledge point proficiency parameter, the number of suspicious events corresponding to the time label, the preset suspicious threshold, the preset suspicious event weight, and the preset steepness parameter, and in combination with the following formula 1, determine a proficiency correction parameter:

[0187] Formula 1,

[0188] where FraudScore represents the proficiency correction parameter, represents the preset suspicious event weight, represents the number of suspicious events corresponding to the time tag, represents the preset suspicious threshold, and k represents the preset steepness parameter;

[0189] Based on the proficiency correction parameter, combined with the following Formula 2, the proficiency parameter of the second knowledge point is corrected to obtain the proficiency parameter of the third knowledge point;

[0190] Formula 2,

[0191] where Mfinal represents the proficiency parameter of the third knowledge point, and Mt represents the proficiency parameter of the second knowledge point,

[0192] Based on the proficiency parameter of the third knowledge point, the preset difficulty of the first question, the preset memory retention rate, and the preset interference parameter, combined with the following Formula 3, the knowledge point proficiency label is determined:

[0193] Formula 3,

[0194] where P represents the knowledge point proficiency label, represents the preset interference parameter, represents the preset memory retention rate, represents the preset difficulty of the t-th first question.

[0195] In some embodiments of the present disclosure, the determining unit 810 is further configured to: based on the answering accuracy rate of the first question, the average answering time of the first question, the total number of questions of the first question, and the actual answering time of the first question, combined with the following Formula 4, determine the calibration difficulty to replace the preset difficulty with the calibration difficulty:

[0196] Formula 4,

[0197] where, represents the calibration difficulty of the t-th first question, U represents the total number of questions of the first question, represents the actual answering time of the first question, represents the average answering time of the first question, represents the actual answering time of the t-th first question.

[0198] In some embodiments of the present disclosure, the determining unit 810 is further configured to: perform smoothing processing and normalization processing on the answering data to obtain normalized answering data;

[0199] Weighted sum of the accuracy rate of standardized basic knowledge points and the completion degree of learning standardized basic knowledge points in the standardized answer data to determine the score of basic knowledge points of the standardized answer data;

[0200] Weighted sum of the accuracy rate of standardized key knowledge points and the completion degree of learning standardized key knowledge points in the standardized answer data to determine the score of key knowledge points of the standardized answer data;

[0201] Based on the score of basic knowledge points, the score of key knowledge points, and the preset angular difference between the basic knowledge points and the key knowledge points, combined with the following formula 5, determine the global ability evaluation parameter,

[0202] Formula 5,

[0203] where T represents the global ability evaluation parameter, S BP represents the score of basic knowledge points, S IW represents the score of key knowledge points, represents the preset angular difference.

[0204] In some embodiments of the present disclosure, the determination unit 810 is further configured to: when the global ability evaluation parameter is less than the first evaluation preset value, determine that the learning type label is an advanced challenge type label;

[0205] When the global ability evaluation parameter is less than the second evaluation preset value and greater than the third evaluation preset value, determine that the learning type label is a balanced development type label;

[0206] When the global ability evaluation parameter is greater than the fourth evaluation preset value, determine that the learning type label is a basic cultivation type label, where the first evaluation preset value is greater than the second evaluation preset value, the second evaluation preset value is greater than the third evaluation preset value, and the third evaluation preset value is greater than the fourth evaluation preset value.

[0207] In some embodiments of the present disclosure, the processing unit 820 is further configured to: divide the first label and the second label into positive labels and negative labels, and perform binary encoding on the third label to obtain an encoded label; perform weighted summation on the positive labels and negative labels corresponding to the first label to obtain a learning participation parameter; perform weighted summation on the positive labels and negative labels corresponding to the second label to obtain a learning efficiency parameter; map the encoded label according to a preset encoding mapping rule to obtain a learning type parameter.

[0208] In some embodiments of the present disclosure, the recommendation unit 830 is further configured to: recommend a second student whose learning participation parameter, learning efficacy parameter, and learning type parameter meet the preset recommendation parameter requirements to the first student according to the preset parameter requirements of the first student; and / or

[0209] perform global matching processing on the learning participation parameter, the learning efficacy parameter, and the learning type parameter to determine the label score of the first student, and determine the label similarity between the first students based on the label score of the first student and the preset label weight, so as to perform friend recommendation on the first students according to the label similarity.

[0210] In some embodiments of the present disclosure, the recommendation unit 830 is further configured to: determine the label score of the first student based on the learning participation parameter, the learning efficacy parameter, and the learning type parameter in combination with the following formula 6:

[0211] Formula 6

[0212] where Match_Score represents the label score, X_Score represents the learning participation parameter, Y_Score represents the learning efficacy parameter, Z_Coeff represents the learning type parameter, and μ1, μ2, and μ3 represent the preset parameter weights.

[0213] In some embodiments of the present disclosure, the recommendation unit 830 is further configured to: determine the label similarity between the first students based on the label score of the first student and the preset label weight in combination with the following formula 7

[0214] Formula 7

[0215] where Sim(u,v) represents the label similarity between student u and student v, u k represents the label score of student u in vector form, v k represents the label score of student v in vector form, and w k represents the preset label weight; when the label similarity is greater than the preset similarity threshold, perform friend recommendation on the first students.

[0216] It should be noted that the foregoing explanations of the method embodiments also apply to the apparatus of this embodiment, with the same principle, and will not be limited in this embodiment.

[0217] Based on the method as described above Figures 1 to 7 shown, correspondingly, this embodiment also provides a computer program product, including a computer program, where the computer program, when executed by a processor, implements the method as described above Figures 1 to 5 shown.

[0218] Based on the method as described above Figures 1 to 7The method described above, correspondingly, this embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the method as described above Figures 1 to 5 shown.

[0219] Based on such an understanding, the technical solution of this application can be embodied in the form of a software product. This software product can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0220] As Figure 9 shown is a schematic hardware structure diagram of an electronic device according to the present invention, including:

[0221] At least one processor 901; and,

[0222] A memory 902 communicatively connected to at least one of the processors 901; wherein,

[0223] The memory 902 stores instructions executable by at least one of the processors. The instructions are executed by at least one of the processors so that at least one of the processors can execute a learning friend recommendation method based on a smart education terminal as described above.

[0224] Figure 9 Taking one processor 901 as an example.

[0225] The electronic device may further include: an input device 903 and a display device 904.

[0226] The processor 901, the memory 902, the input device 903, and the display device 904 may be connected by a bus or other means. In the figure, the connection by a bus is taken as an example.

[0227] The memory 902, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the review content generation method in the embodiments of this application. For example, Figure 1 、 Figure 2 And Figure 3 the method flow shown. The processor 901 executes various functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in the memory 902, that is, implements a learning friend recommendation method based on a smart education terminal in the above embodiments.

[0228] The memory 902 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. The data storage area may store data created according to the use of the review content generation method, etc. In addition, the memory 902 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 902 may optionally include a memory remotely disposed relative to the processor 901, and these remote memories may be connected to the device executing the review content generation method through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0229] The input device 903 may receive user clicks and generate signal inputs related to user settings and function controls of the review content generation method. The display device 904 may include a display device such as a display screen.

[0230] When the one or more modules are stored in the memory 902 and run by the one or more processors 901, they execute a learning buddy recommendation method based on an intelligent education terminal in any of the above method embodiments.

[0231] Optionally, the above physical device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, sensors, an audio circuit, a WI-FI module, etc. The user interface may include a display screen (Display) and an input unit such as a keyboard, etc. Optionally, the user interface may further include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0232] Those skilled in the art can understand that the above physical device structure provided in this embodiment does not limit the physical device, and it may include more or fewer components, or combine certain components, or have different component arrangements.

[0233] The storage medium may further include an operating system and a network communication module. The operating system is a program for managing the hardware and software resources of the above physical device and supports the operation of information processing programs and other software and / or programs. The network communication module is used to implement communication between components inside the storage medium and communication between other hardware and software in the information processing physical device.

[0234] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary general hardware platform, or can be implemented by hardware.

[0235] It should be noted that, in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0236] The above are only specific embodiments of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments described herein, but rather will be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A learning friend recommendation method based on a smart education terminal, characterized in that, The method includes: Obtaining the learning data of a first student from the intelligent education terminal to determine the student behavior labels of the first student, where the student behavior labels include at least one of the following: a first label, a second label, and a third label. Among them, the first label is used to indicate the learning behavior situation of the first student, the second label is used to indicate the knowledge mastery level of the first student, and the third label is used to indicate the learning style of the first student; among them, the second label includes a knowledge point proficiency label. Performing standardization processing and aggregation processing on the student behavior labels to obtain at least one of a learning participation parameter corresponding to the first label, a learning efficacy parameter corresponding to the second label, and a learning type parameter corresponding to the third label. Based on at least one of the learning participation parameter, the learning efficacy parameter, and the learning type parameter, performing friend recommendation for the first student. Among them, obtaining the learning data of the first student to determine the student behavior labels includes: Based on the answering data of the first student for the first question corresponding to the same knowledge point in the learning data, determining the knowledge point proficiency label of the first student. Among them, based on the answering data of the first student for the first question corresponding to the same knowledge point in the learning data, determining the knowledge point proficiency label of the first student includes: Determining the ratio between the number of completed questions of the first student for the first question and the total number of the first questions as the knowledge point learning progress parameter of the first student, and determining the ratio between the number of correctly answered questions of the first student for the first question and the number of completed questions of the first student for the first question as the knowledge point accuracy parameter of the first student. Performing weighted summation on the learning progress parameter and the knowledge point accuracy parameter to determine the first knowledge point proficiency parameter of the first student. When the modification time after the first student answers the first question incorrectly is less than a preset modification time, and / or when the number of times the first student answers the first question correctly is greater than a preset correct number threshold, and the standard deviation of the time interval when the first student answers the first question correctly is greater than a preset standard deviation threshold, it is determined that the first student has a suspicious event once. When the number of suspicious events of the first student is greater than or equal to a preset suspicious threshold, performing correction processing on the first knowledge point proficiency parameter to obtain the knowledge point proficiency label. When the number of suspicious events of the first student is less than the preset suspicious threshold, determining the first knowledge point proficiency parameter as the knowledge point proficiency label.

2. The method according to claim 1, characterized in that The obtaining of the learning data of the first student to determine the student behavior labels further includes at least one of the following: Based on the chat content of the first student in the learning data, determining the chat data label of the first student. Based on the understanding degree of the first student for the teaching material in the learning data, determining the learning understanding label of the first student. Based on the answering data of the first student for questions on different knowledge points in the learning data, determine the global ability evaluation parameter of the comprehensive evaluation of the first student, so as to use the global ability evaluation parameter to compare with a preset threshold to determine the learning type label of the first student. Among them, the learning type label includes at least one of the following: advanced challenge type label, balanced development type label, and basic cultivation type label.

3. The method according to claim 1, characterized in that, The method of correcting the proficiency parameter of the first knowledge point to obtain the proficiency label of the knowledge point includes: Associate the proficiency parameter of the first knowledge point with the time taken by the first student to answer the first question to obtain a second knowledge point proficiency parameter with a time label. Based on the second knowledge point proficiency parameter, the number of suspicious events corresponding to the time label, the preset suspicious threshold, the preset suspicious event weight, and the preset steepness parameter, and combining the following formula 1, determine the proficiency correction parameter. Formula 1, Among them, FraudScore represents the proficiency correction parameter, represents the preset suspicious event weight, represents the number of suspicious events corresponding to the time tag, represents the preset suspicious threshold, and k represents the preset steepness parameter; Based on the proficiency correction parameter, and combining the following formula 2, correct the second knowledge point proficiency parameter to obtain a third knowledge point proficiency parameter. Formula 2, Among them, M final represents the proficiency parameter of the third knowledge point, M t represents the proficiency parameter of the second knowledge point, Based on the third knowledge point proficiency parameter, the preset difficulty of the first question, the preset memory retention rate, and the preset interference parameter, and combining the following formula 3, determine the proficiency label of the knowledge point. Formula 3, where P represents the proficiency label of the knowledge point, represents the preset interference parameter, represents the preset memory retention rate, represents the preset difficulty of the t-th first question.

4. The method according to claim 3, wherein The method further includes: Based on the answering accuracy rate of the first question, the average answering time of the first question, the total number of questions of the first question, and the actual answering time of the first question, and combining the following formula 4, determine the calibration difficulty, so as to use the calibration difficulty to replace the preset difficulty. Formula 4 Among them, represents the calibration difficulty of the t-th first question, U represents the total number of questions of the first question, represents the actual answering time of the first question, represents the average answering time of the first question, represents the actual answering time of the t-th first question.

5. The method according to claim 2, characterized in that The method of determining the global ability evaluation parameter of the comprehensive evaluation of the first student based on the answering data of the first student for questions on different knowledge points in the learning data includes: Perform smoothing processing and normalization processing on the answering data to obtain standardized answering data. Perform weighted summation on the standardized accuracy rate of basic knowledge points and the learning completion degree of standardized basic knowledge points in the standardized answering data to determine the basic knowledge point score of the standardized answering data. Perform weighted summation on the standardized accuracy rate of key knowledge points and the learning completion degree of standardized key knowledge points in the standardized answering data to determine the key knowledge point score of the standardized answering data. Based on the basic knowledge point score, the key knowledge point score, and the preset angular difference between the basic knowledge point and the key knowledge point, and combining the following formula 5, determine the global ability evaluation parameter. Formula 5, Among them, T represents the global ability evaluation parameter, and S BP represents the score of the basic knowledge points, and S IW represents the score of the key knowledge points, represents the preset angular difference.

6. The method according to claim 1, characterized in that, The method of performing standardization processing and aggregation processing on the student behavior label to obtain at least one of the learning participation parameter corresponding to the first label, the learning efficiency parameter corresponding to the second label, and the learning type parameter corresponding to the third label includes: Divide the first label and the second label into positive labels and negative labels, and perform binary encoding on the third label to obtain an encoded label. Perform weighted summation on the positive label and the negative label corresponding to the first label to obtain the learning participation parameter. Perform a weighted sum of the positive and negative tags corresponding to the second tag to obtain the learning efficiency parameter; Map the encoded tag according to a preset encoding mapping rule to obtain the learning type parameter.

7. The method according to claim 1, wherein The friend recommendation for the first student based on at least one of the learning participation parameter, the learning efficiency parameter, and the learning type parameter includes: According to the preset parameter requirements of the first student, recommend the second student whose learning participation parameter, learning efficiency parameter, and learning type parameter meet the preset recommendation parameter requirements to the first student; and / or Perform a global matching process on the learning participation parameter, the learning efficiency parameter, and the learning type parameter to determine the tag score of the first student, and based on the tag score of the first student and a preset tag weight, determine the tag similarity between the first students, so as to perform friend recommendation for the first student according to the tag similarity.

8. The method according to claim 7, wherein The global matching process on the learning participation parameter, the learning efficiency parameter, and the learning type parameter to determine the tag score of the first student includes: Based on the learning participation parameter, the learning efficiency parameter, and the learning type parameter, combine the following formula 6 to determine the tag score of the first student: Formula 6 Wherein, the Match_Score represents the tag score, the X_Score represents the learning participation parameter, the Y_Score represents the learning efficiency parameter, the Z_Coeff represents the learning type parameter, and μ1, μ2, and μ3 represent preset parameter weights.

9. The method according to claim 7, wherein The determination of the tag similarity between the first students based on the tag score of the first student and a preset tag weight, so as to perform friend recommendation for the first student according to the tag similarity includes: Based on the tag score of the first student and a preset tag weight, combine the following formula 7 to determine the tag similarity between the first students Formula 7 Among them, Sim(u, v) represents the label similarity between student u and student v, where u k represents the label score of student u in vector form, and v k represents the label score of student v in vector form, and w k represents the preset label weight; When the tag similarity is greater than a preset similarity threshold, perform friend recommendation for the first student.

Images