Student solitary assessment method and electronic equipment

Abstract

The invention discloses a student isolated assessment method and electronic equipment, and the method comprises the steps: determining first intimacy among various clusters according to the consumption data of students contained in the to-be-clustered various clusters; and then, according to the first intimacy among the various clusters, clustering the various clusters, determining the number of the clustered target clusters, and when the number is greater than a preset first number threshold value, continuing clustering until the number of the clustered target clusters is not greater than the preset first number threshold value. At the moment, clustering is finished, if the target class cluster with the student number smaller than the preset second number threshold value exists, the student number in the target class cluster is small, it is indicated that the possibility that the students in the target class cluster are isolated is high, and it is determined that the students in the target class cluster have the isolated risk. According to the method, the objective consumption data of the students are combined, the students with the isolated risk are screened out through clustering, and the accuracy of student isolated evaluation is improved.

Description

Technical Field

[0001] The present application relates to the technical field of smart campus management, and in particular to a student loneliness assessment method and electronic device. Background Art

[0002] As a special social and cultural group, students are in an important period of life development. Students who feel withdrawn cannot maintain normal interpersonal communication with others. This is an unhealthy social behavior pattern and a self-psychological state that needs to be corrected.

[0003] In the prior art, when evaluating students' loneliness, regular mental health assessment questionnaires are generally used to assess whether students are suspected of being lonely. The problem with the prior art is that students generally have resistance and boredom towards mental health assessment questionnaires, and the results obtained from the questionnaire survey may not be the students' true thoughts, making the accuracy of the student loneliness assessment poor. Summary of the invention

[0004] The present application provides a student loneliness assessment method and electronic device to solve the problem of poor accuracy of student loneliness assessment in the prior art.

[0005] In a first aspect, the present application provides a method for assessing student loneliness, the method comprising:

[0006] Determine the first intimacy between the various clusters according to the consumption data of the students included in the various clusters to be clustered; wherein the consumption data includes consumption time data and consumption location data;

[0007] Clustering the various clusters according to the first intimacy between the various clusters, and determining the number of target clusters after clustering;

[0008] If the number is greater than a preset first quantity threshold, the target cluster after clustering is used as each cluster to be clustered, and clustering is continued until the number of target clusters after clustering is no greater than the preset first quantity threshold; if the number is not greater than the preset first quantity threshold, and there is a target cluster containing a number of students less than a preset second quantity threshold, it is determined that the students contained in the target cluster are at risk of being withdrawn.

[0009] The above technical solution has the following advantages or beneficial effects:

[0010] In the present application, the first intimacy between the various clusters to be clustered is determined based on the consumption data of the students included in the various clusters to be clustered; then, the various clusters are clustered based on the first intimacy between the various clusters, and the number of target clusters after clustering is determined. When the number is greater than the preset first quantity threshold, clustering continues until the number of target clusters after clustering is no greater than the preset first quantity threshold. At this point, clustering ends. If there is a target cluster containing a number of students less than the preset second quantity threshold, since the number of students in the target cluster is small, it indicates that the students in the target cluster are more likely to be withdrawn, so it is determined that the students included in the target cluster are at risk of being withdrawn. The present application combines the students' objective consumption data, screens out students at risk of being withdrawn through clustering, and improves the accuracy of student withdrawal assessment.

[0011] In an optional implementation, determining the first intimacy between the various clusters to be clustered according to the consumption data of the students included in the various clusters includes:

[0012] For any first cluster and second cluster in the various clusters, the second intimacy between the first student and the second student is determined based on the consumption data of the first student included in the first cluster and the consumption data of the second student included in the second cluster; the first intimacy between the first cluster and the second cluster is determined based on the second intimacy.

[0013] The above technical solution has the following advantages or beneficial effects:

[0014] In the present application, when determining the first intimacy between the clusters, for any first cluster and second cluster, the second intimacy between the students is first determined based on the consumption data of the students included in the first cluster and the consumption data of the students included in the second cluster. Then, based on the second intimacy of the students included in the first cluster and the second cluster, the first intimacy between the first cluster and the second cluster is determined. This improves the accuracy of determining the first intimacy between the clusters.

[0015] In an optional implementation, the process of determining the second intimacy between the first student and the second student includes:

[0016] Determine the common consumption data of the first student and the second student according to the consumption data of the first student and the consumption data of the second student; wherein the common consumption data includes at least one of the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions, and the number of respective consumptions; wherein, if the first student and the second student consume at the same consumption location within a preset time window, it is determined that the first student and the second student consume once together;

[0017] A second intimacy between the first student and the second student is determined based on the common consumption data of the first student and the second student.

[0018] In an optional implementation manner, if the common consumption data includes the number of common consumption times, the average time interval of common consumption, the minimum time interval of common consumption, and the number of respective consumption times, determining the second intimacy between the first student and the second student according to the common consumption data of the first student and the second student includes:

[0019] Substitute the number of times the first student and the second student consume together, the average time interval of common consumption, the minimum time interval of common consumption, and the number of times each consumes into the following formula to determine the second intimacy between the first student and the second student;

[0020]

[0021] In the formula, i represents the first student, j represents the second student, P i，j The second closest degree, OM i，j is the number of joint consumption, mean i，j is the average time interval of joint consumption, min i，j is the minimum time interval for joint consumption, CM i is the consumption frequency of the first student, CM j The number of consumptions of the second student.

[0022] The above technical solution has the following advantages or beneficial effects:

[0023] In this application, firstly, the common consumption data of the first student and the second student is determined based on the consumption data of the first student and the consumption data of the second student, and then the second intimacy of the first student and the second student is determined based on the common consumption data. Specifically, based on the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions and the number of consumptions of each student, the second intimacy of the first student and the second student is determined based on the formula The second intimacy between the first student and the second student is determined, thereby improving the accuracy of determining the second intimacy.

[0024] In an optional implementation, determining the first intimacy between the first cluster and the second cluster according to the second intimacy includes:

[0025] If the first cluster and the second cluster each include a student, determining the second intimacy as the first intimacy between the first cluster and the second cluster;

[0026] If at least one of the first cluster and the second cluster contains at least two students, obtain the second intimacy between each student in the first cluster and each student in the second cluster, and determine the first intimacy between the first cluster and the second cluster in at least one of the following ways;

[0027] The minimum intimacy among the acquired second intimacy is used as the first intimacy of the first cluster and the second cluster;

[0028] The maximum intimacy among the acquired second intimacy is used as the first intimacy of the first cluster and the second cluster;

[0029] The average intimacy of each second intimacy obtained is used as the first intimacy of the first cluster and the second cluster;

[0030] The variance intimacy among the obtained second intimacy is used as the first intimacy of the first cluster and the second cluster.

[0031] The above technical solution has the following advantages or beneficial effects:

[0032] In the present application, for the case where the first cluster and the second cluster each contain one student, the second intimacy is determined as the first intimacy of the first cluster and the second cluster. For the case where at least one of the first cluster and the second cluster contains at least two students, first obtain the second intimacy of each student in the first cluster and each student in the second cluster, and then determine the first intimacy of the first cluster and the second cluster by at least one of the minimum value, maximum value, average value and variance. This improves the accuracy of determining the first intimacy of the first cluster and the second cluster.

[0033] In an optional implementation, clustering the various clusters according to the first intimacy between the various clusters includes:

[0034] According to the first intimacy between the various clusters, a maximum first intimacy is determined; and the clusters corresponding to the maximum first intimacy are clustered.

[0035] The above technical solution has the following advantages or beneficial effects:

[0036] In the present application, after determining the first intimacy between the clusters, during clustering, the cluster corresponding to the largest first intimacy is selected for clustering, that is, the clusters corresponding to the largest first intimacy are clustered into one cluster, thereby ensuring the accuracy of clustering.

[0037] In an optional implementation, if the first intimacy of the first cluster and the second cluster is determined respectively by using at least two of the above methods, and the number of target clusters corresponding to each method is not greater than the preset first number threshold, determining that the students included in the target cluster have the risk of loneliness includes:

[0038] Determine the students included in the target cluster as candidate withdrawn students;

[0039] For the candidate withdrawn student, if the candidate withdrawn student exists in at least two target clusters, it is determined that the candidate withdrawn student has a risk of being withdrawn.

[0040] The above technical solution has the following advantages or beneficial effects:

[0041] In order to improve the accuracy of the student's lonely assessment, in this application, if the first intimacy of the first cluster and the second cluster is determined respectively by at least two of the above methods, and the number of target clusters corresponding to each method is not greater than the preset first quantity threshold, the target clusters are obtained. At this time, the students included in the target cluster are first determined as candidate lonely students. Then, the candidate lonely students present in at least two target clusters are determined to be at risk of loneliness. Thereby improving the accuracy of the student's lonely assessment.

[0042] In an optional embodiment, the method further includes:

[0043] For students who are at risk of becoming withdrawn, first warning information is outputted to indicate that the students are at high risk of becoming withdrawn.

[0044] The above technical solution has the following advantages or beneficial effects:

[0045] In the present application, the students included in the target cluster are determined as candidate lonely students; for the candidate lonely students, if the candidate lonely students exist in at least two target clusters, it is determined that the candidate lonely students have a lonely risk. And it indicates that the lonely risk is high. Therefore, the first warning information for characterizing that the student has a high lonely risk is output. Thereby improving the accuracy of the lonely warning.

[0046] In an optional embodiment, the method further includes:

[0047] For students who are at risk of becoming isolated, the isolation risk level corresponding to the student is determined based on the number of students included in the target cluster to which the student belongs, and a second warning information corresponding to the isolation risk level is output; wherein, the fewer the number of students included in the target cluster, the higher the corresponding isolation risk level.

[0048] The above technical solution has the following advantages or beneficial effects:

[0049] For students who are determined to be at risk of loneliness and only exist in one target cluster, first determine the loneliness risk level corresponding to the student based on the number of students included in the target cluster to which the student belongs. The smaller the number, the higher the risk of loneliness. Therefore, the smaller the number of students included in the target cluster, the higher the corresponding loneliness risk level. Among them, the correspondence between different quantities and loneliness risk levels can be saved in advance. For example, the loneliness risk level corresponding to quantity 1 is high. The loneliness risk level corresponding to quantity 2 or 3 is medium. The loneliness risk level corresponding to quantity 4 or 5 is low. If it exceeds 5, it is considered that there is no loneliness risk. Then output the second warning information corresponding to the loneliness risk level. Thereby further improving the accuracy of the loneliness risk warning.

[0050] In a second aspect, the present application provides a device for assessing student loneliness risk, the device comprising:

[0051] A first determination module, configured to determine a first degree of intimacy between various clusters to be clustered according to consumption data of students included in the various clusters to be clustered; wherein the consumption data includes consumption time data and consumption location data;

[0052] A second determination module is used to cluster the various clusters according to the first intimacy between the various clusters, and determine the number of target clusters after clustering;

[0053] The clustering evaluation module is used to, if the number is greater than a preset first quantity threshold, use the target cluster after clustering as each cluster to be clustered, and continue clustering until the number of target clusters after clustering is no greater than the preset first quantity threshold; if the number is no greater than the preset first quantity threshold, and there is a target cluster containing a number of students less than a preset second quantity threshold, it is determined that the students contained in the target cluster are at risk of being withdrawn.

[0054] The first determination module is specifically used to determine the second intimacy between any first cluster and second cluster in the various clusters based on the consumption data of the first student included in the first cluster and the consumption data of the second student included in the second cluster; and determine the first intimacy between the first cluster and the second cluster based on the second intimacy.

[0055] The first determination module is specifically used to determine the common consumption data of the first student and the second student based on the consumption data of the first student and the consumption data of the second student; wherein the common consumption data includes at least one of the number of common consumptions, the average time interval of common consumption, the minimum time interval of common consumption and the respective consumption times; wherein, if within a preset time window, the first student and the second student consume at the same consumption location, it is determined that the first student and the second student have consumed together once; based on the common consumption data of the first student and the second student, the second intimacy between the first student and the second student is determined.

[0056] A first determination module is specifically configured to, if the common consumption data includes the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions and the number of respective consumptions, substitute the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions and the number of respective consumptions of the first student and the second student into the following formula according to the common consumption data of the first student and the second student, so as to determine the second intimacy between the first student and the second student;

[0057] In the formula, i represents the first student, j represents the second student, P i，j The second closest degree, OM i，j is the number of joint consumption, mean i，j is the average time interval of joint consumption, min i，j is the minimum time interval for joint consumption, CM i is the consumption frequency of the first student, CM j The number of consumptions of the second student.

[0058] The first determination module is specifically used to determine the second intimacy as the first intimacy of the first cluster and the second cluster if the first cluster and the second cluster respectively contain one student; if at least one of the first cluster and the second cluster contains at least two students, obtain the second intimacy of each student in the first cluster with each student in the second cluster, and determine the first intimacy of the first cluster and the second cluster in at least one of the following ways; use the minimum intimacy among the obtained second intimacy as the first intimacy of the first cluster and the second cluster; use the maximum intimacy among the obtained second intimacy as the first intimacy of the first cluster and the second cluster; use the average intimacy of the obtained second intimacy as the first intimacy of the first cluster and the second cluster; use the variance intimacy among the obtained second intimacy as the first intimacy of the first cluster and the second cluster.

[0059] The second determination module is specifically configured to determine the maximum first intimacy according to the first intimacy between the various clusters; and cluster the clusters corresponding to the maximum first intimacy.

[0060] The clustering evaluation module is specifically used to respectively determine the first intimacy of the first cluster and the second cluster by using at least two of the above-mentioned methods, and respectively obtain target clusters whose number of target clusters corresponding to each method is not greater than the preset first number threshold; determine the students included in the target cluster as candidate withdrawn students; for the candidate withdrawn student, if the candidate withdrawn student exists in at least two target clusters, determine that the candidate withdrawn student is at risk of being withdrawn.

[0061] The device also includes:

[0062] The early warning module is used to output first early warning information for students who are at risk of being withdrawn, which is used to indicate that the students are at high risk of being withdrawn.

[0063] The early warning module is also used to determine the loneliness risk level corresponding to students who are at risk of loneliness according to the number of students included in the target cluster to which the students belong, and output second early warning information corresponding to the loneliness risk level; wherein, the fewer the number of students included in the target cluster, the higher the corresponding loneliness risk level.

[0064] In a third aspect, the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0065] Memory, used to store computer programs;

[0066] The processor is used to implement the method when executing the program stored in the memory.

[0067] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the described method is implemented.

[0068] In a fifth aspect, the present application provides a computer program product, wherein the computer program product comprises an executable program, and the executable program is executed by a processor to implement the described method. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 Schematic diagram of the first type of student loneliness assessment process provided for this application;

[0071] Figure 2 A schematic diagram of the process of determining the first intimacy between various clusters provided in this application;

[0072] Figure 3 A schematic diagram of a process for determining a second degree of intimacy between a first student and a second student provided in the present application;

[0073] Figure 4 A schematic diagram of the second student loneliness assessment process provided for this application;

[0074] Figure 5 Schematic diagram of the process of determining that students included in the target cluster are at risk of loneliness for this application;

[0075] Figure 6 A schematic diagram of the third student loneliness assessment process provided for this application;

[0076] Figure 7 A schematic diagram of the fourth student loneliness assessment process provided for this application;

[0077] Figure 8 Schematic diagram of the clustering process provided for this application;

[0078] Fig. 9 A flow chart of the student withdrawal assessment provided for this application;

[0079] Fig.10 A schematic diagram of the student loneliness assessment obtained by clustering in various ways provided for this application;

[0080] Fig.11 Schematic diagram of the target cluster provided for this application;

[0081] Fig.12 A schematic diagram of the structure of the student loneliness assessment device provided for this application;

[0082] Fig.13 This is a schematic diagram of the electronic device structure provided in this application. DETAILED DESCRIPTION

[0083] In order to make the purpose and implementation method of the present application clearer, the exemplary implementation method of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0084] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings.

[0085] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0086] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0087] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0089] For the convenience of explanation, the above description has been made in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

[0090] The present application provides a method for detecting suspected loneliness based on student consumption records, which belongs to the field of student mental health / computer science and technology.

[0091] Through the daily consumption records of students, we can analyze the mental health problems that students may have, reduce students' resistance, and capture a more realistic mental health status. We can analyze the consumption records of students in multiple intervals, and combine the changes in the consumption records of students in multiple time periods to comprehensively analyze the mental health status of students. While improving the accuracy of locating lonely students, we can also track the development of students' mental health. Through the consumption records during meals, we can judge the intimacy between students, and then use the intimacy relationship to identify students who are suspected of being lonely. We can analyze the student consumption data through a variety of clustering methods, and combine the list of suspected lonely students analyzed by a variety of methods to further identify the suspected lonely students and improve the accuracy of the suspected lonely detection algorithm. By combining the algorithm model with engineering practice, the provider of the school's smart education service is also the data collector, and can collect more realistic student consumption data. Through the analysis of the data, we can pay in-depth attention to students' mental health issues.

[0092] This application analyzes students' daily consumption records to locate students who may have mental health problems, providing a new solution for discovering students' mental health problems. The intimacy between student A and student B is calculated separately, and the suspected lonely students are further located based on this intimacy value. The student consumption data is analyzed through multiple clustering strategies (minimum, maximum, average and variance), which further improves the accuracy of locating suspected lonely students.

[0093] The student loneliness assessment process provided by this application is described in detail below with reference to the accompanying drawings.

[0094] Figure 1 The first student loneliness assessment process diagram provided for this application includes the following steps:

[0095] S101: Determine a first degree of intimacy between various clusters to be clustered according to consumption data of students included in the various clusters to be clustered; wherein the consumption data includes consumption time data and consumption location data;

[0096] S102: clustering the various clusters according to the first intimacy between the various clusters, and determining the number of target clusters after clustering;

[0097] S103: If the number is greater than a preset first number threshold, the target cluster after clustering is used as each cluster to be clustered, and clustering is continued until the number of target clusters after clustering is no greater than the preset first number threshold; if the number is no greater than the preset first number threshold, and there is a target cluster containing a number of students less than a preset second number threshold, it is determined that the students contained in the target cluster are at risk of being withdrawn.

[0098] The student loneliness assessment method provided in this application is applied to electronic devices, which may be PCs, computers, servers and other devices.

[0099] In the present application, each student is first regarded as a cluster to be clustered, that is, the number of students is the same as the number of clusters to be clustered. Then, the first intimacy between each cluster is determined based on the consumption data of the students contained in each cluster. Optionally, the intimacy between two students can be determined based on the students' consumption data. Optionally, the consumption data includes consumption time data and consumption location data. If the consumption time data of two students are similar and the consumption location data are the same, it means that the intimacy between the two students is high. Otherwise, it means that the intimacy between the two students is low. Optionally, the intimacy between the two students can be used as the first intimacy of the cluster to which they belong.

[0100] Then, according to the first intimacy between each cluster, each cluster is clustered to determine the number of target clusters after clustering. Optionally, the first intimacy can be sorted in descending order, and the two clusters with the largest first intimacy can be selected as one class for each clustering, or a set number of clusters with the highest intimacy can be selected as one class. After each clustering, the number of target clusters after clustering is determined; then it is determined whether the number is greater than the preset first quantity threshold. The preset first quantity threshold is, for example, 10, 20, etc. If the number is greater than the preset first quantity threshold, the target cluster after clustering is used as the cluster to be clustered, and clustering is continued until the number of target clusters after clustering is not greater than the preset first quantity threshold, at which time the clustering is completed. Then it is determined whether there is a target cluster with a number of students less than the preset second quantity threshold in the target clusters obtained after clustering. The preset second quantity threshold is, for example, 2, 3, 5, etc. If so, it is determined that the students in the target cluster with a number of students less than the preset second quantity threshold are at risk of being withdrawn.

[0101] In the present application, the first intimacy between the various clusters to be clustered is determined based on the consumption data of the students included in the various clusters to be clustered; then, the various clusters are clustered based on the first intimacy between the various clusters, and the number of target clusters after clustering is determined. When the number is greater than the preset first quantity threshold, clustering continues until the number of target clusters after clustering is no greater than the preset first quantity threshold. At this point, clustering ends. If there is a target cluster containing a number of students less than the preset second quantity threshold, since the number of students in the target cluster is small, it indicates that the students in the target cluster are more likely to be withdrawn, so it is determined that the students included in the target cluster are at risk of being withdrawn. The present application combines the students' objective consumption data, screens out students at risk of being withdrawn through clustering, and improves the accuracy of student withdrawal assessment.

[0102] Figure 2The schematic diagram of the process of determining the first intimacy between various clusters provided in this application includes the following steps:

[0103] S201: for any first cluster and any second cluster in the various clusters, determining a second intimacy between the first student and the second student according to consumption data of a first student included in the first cluster and consumption data of a second student included in the second cluster;

[0104] S202: Determine a first intimacy between the first cluster and the second cluster according to the second intimacy.

[0105] In the present application, when determining the first intimacy between the clusters, for any first cluster and second cluster, the second intimacy between the students is first determined based on the consumption data of the students included in the first cluster and the consumption data of the students included in the second cluster. Then, based on the second intimacy of the students included in the first cluster and the second cluster, the first intimacy between the first cluster and the second cluster is determined. This improves the accuracy of determining the first intimacy between the clusters.

[0106] Figure 3 The schematic diagram of the process of determining the second intimacy between the first student and the second student provided in the present application includes the following steps:

[0107] S301: determining common consumption data of the first student and the second student according to the consumption data of the first student and the consumption data of the second student; wherein the common consumption data includes at least one of the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions, and the number of respective consumptions; wherein if the first student and the second student consume at the same consumption location within a preset time window, it is determined that the first student and the second student have consumed together once;

[0108] S302: Determine a second intimacy between the first student and the second student based on the common consumption data of the first student and the second student.

[0109] In an optional implementation manner, if the common consumption data includes the number of common consumption times, the average time interval of common consumption, the minimum time interval of common consumption, and the number of respective consumption times, determining the second intimacy between the first student and the second student according to the common consumption data of the first student and the second student includes:

[0110] Substitute the number of times the first student and the second student consume together, the average time interval of common consumption, the minimum time interval of common consumption, and the number of times each consumes into the following formula to determine the second intimacy between the first student and the second student;

[0111]

[0112] In the formula, i represents the first student, j represents the second student, P i，j The second closest degree, OM i，j is the number of joint consumption, mean i，j is the average time interval of joint consumption, min i，j is the minimum time interval for joint consumption, CM i is the consumption frequency of the first student, CM j The number of consumptions of the second student.

[0113] In this application, firstly, the common consumption data of the first student and the second student is determined based on the consumption data of the first student and the consumption data of the second student, and then the second intimacy of the first student and the second student is determined based on the common consumption data. Specifically, based on the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions and the number of consumptions of each student, the second intimacy of the first student and the second student is determined based on the formula The second intimacy between the first student and the second student is determined, thereby improving the accuracy of determining the second intimacy.

[0114] In an optional implementation, determining the first intimacy between the first cluster and the second cluster according to the second intimacy includes:

[0115] If the first cluster and the second cluster respectively include a student, the second intimacy is determined as the first intimacy of the first cluster and the second cluster.

[0116] For example, the first cluster includes student a, and the second cluster includes student b. The second intimacy between student a and student b is determined, and the second intimacy is used as the first intimacy between the first cluster and the second cluster.

[0117] If at least one of the first cluster and the second cluster contains at least two students, obtain the second intimacy between each student in the first cluster and each student in the second cluster, and determine the first intimacy between the first cluster and the second cluster in at least one of the following ways;

[0118] Method 1: Using the minimum intimacy among the acquired second intimacy as the first intimacy of the first cluster and the second cluster.

[0119] For example, the first cluster includes students a and b, and the second cluster includes student C. The second intimacy between student a and student c is determined, and the second intimacy between student b and student c is determined, and then the minimum value of the two second intimacy is selected to obtain the minimum intimacy, which is used as the first intimacy of the first cluster and the second cluster.

[0120] For another example, the first cluster includes students a and b, and the second cluster includes students c and d. The second intimacy between students a and c is determined, the second intimacy between students b and c is determined, the second intimacy between students a and d is determined, and the second intimacy between students b and d is determined. Then the minimum value of these four second intimacy is selected to obtain the minimum intimacy, and the minimum intimacy is used as the first intimacy of the first cluster and the second cluster.

[0121] Method 2: using the maximum intimacy among the acquired second intimacy as the first intimacy of the first cluster and the second cluster.

[0122] For example, the first cluster includes students a and b, and the second cluster includes student C. The second intimacy between student a and student c is determined, and the second intimacy between student b and student c is determined, and then the maximum value of the two second intimacy is selected to obtain the maximum intimacy, which is used as the first intimacy of the first cluster and the second cluster.

[0123] For another example, the first cluster includes students a and b, and the second cluster includes students c and d. The second intimacy between students a and c is determined, the second intimacy between students b and c is determined, the second intimacy between students a and d is determined, and the second intimacy between students b and d is determined. Then the maximum value of these four second intimacy is selected to obtain the maximum intimacy, and the maximum intimacy is used as the first intimacy of the first cluster and the second cluster.

[0124] Method three: using the average intimacy of each second intimacy obtained as the first intimacy of the first cluster and the second cluster.

[0125] For example, the first cluster includes students A and B, and the second cluster includes student C. The second intimacy between student A and student C is determined, and the second intimacy between student B and student C is determined, and then the average of the two second intimacy is determined to obtain the average intimacy, which is used as the first intimacy of the first cluster and the second cluster.

[0126] For another example, the first cluster includes students a and b, and the second cluster includes students c and d. The second intimacy between students a and c is determined, the second intimacy between students b and c is determined, the second intimacy between students a and d is determined, and the second intimacy between students b and d is determined. Then the average of these four second intimacy is determined to obtain the average intimacy, which is used as the first intimacy of the first cluster and the second cluster.

[0127] Method 4: Using the variance intimacy of each acquired second intimacy as the first intimacy of the first cluster and the second cluster.

[0128] For example, the first cluster includes students a and b, and the second cluster includes student C. The second intimacy between student a and student c is determined, and the second intimacy between student b and student c is determined, and then the variance value is determined according to the two second intimacy to obtain the variance intimacy, which is used as the first intimacy of the first cluster and the second cluster.

[0129] For another example, the first cluster includes students a and b, and the second cluster includes students c and d. The second intimacy between students a and c is determined, the second intimacy between students b and c is determined, the second intimacy between students a and d is determined, and the second intimacy between students b and d is determined. Then, the variance value is determined based on the four second intimacy to obtain the variance intimacy, which is used as the first intimacy of the first cluster and the second cluster.

[0130] In the present application, for the case where the first cluster and the second cluster each contain one student, the second intimacy is determined as the first intimacy of the first cluster and the second cluster. For the case where at least one of the first cluster and the second cluster contains at least two students, first obtain the second intimacy of each student in the first cluster and each student in the second cluster, and then determine the first intimacy of the first cluster and the second cluster by at least one of the minimum value, maximum value, average value and variance. This improves the accuracy of determining the first intimacy of the first cluster and the second cluster.

[0131] It should be noted that the present application includes but is not limited to the above four methods for determining the first intimacy between the first cluster and the second cluster. Other calculation methods can also be used as methods for determining the first intimacy between the first cluster and the second cluster.

[0132] Figure 4 The second student loneliness assessment process diagram provided for this application includes the following steps:

[0133] S401: Determine a first degree of intimacy between various clusters to be clustered according to consumption data of students included in the various clusters to be clustered; wherein the consumption data includes consumption time data and consumption location data;

[0134] S402: determining a maximum first intimacy according to the first intimacy between the clusters; clustering the clusters corresponding to the maximum first intimacy to determine the number of target clusters after clustering;

[0135] S403: If the number is greater than a preset first number threshold, the target cluster after clustering is used as each cluster to be clustered, and clustering is continued until the number of target clusters after clustering is no greater than the preset first number threshold; if the number is no greater than the preset first number threshold, and there is a target cluster containing a number of students less than a preset second number threshold, it is determined that the students contained in the target cluster are at risk of being withdrawn.

[0136] In the present application, after determining the first intimacy between the clusters, during clustering, the cluster corresponding to the largest first intimacy is selected for clustering, that is, the clusters corresponding to the largest first intimacy are clustered into one cluster, thereby ensuring the accuracy of clustering.

[0137] Figure 5 A schematic diagram of the process of determining whether students included in the target cluster are at risk of loneliness provided for this application includes the following steps:

[0138] S501: If the first intimacy of the first cluster and the second cluster is determined respectively by using at least two of the above methods, and the number of target clusters corresponding to each method is not greater than the preset first number threshold, the students included in the target cluster are determined as candidate lonely students;

[0139] S502: For the candidate withdrawn student, if the candidate withdrawn student exists in at least two target clusters, it is determined that the candidate withdrawn student has a risk of withdrawal.

[0140] For example, through the above method 1, cluster the various clusters according to the first intimacy between the various clusters, and determine the number of target clusters after clustering; if the number is greater than the preset first number threshold, the target cluster after clustering is used as the various clusters to be clustered, and clustering is continued through the above method 1 until the number of target clusters after clustering is not greater than the preset first number threshold. In this way, target cluster 1, target cluster 2, and target cluster 3 are obtained.

[0141] For another example, through the above method 2, cluster the various clusters according to the first intimacy between the various clusters, and determine the number of target clusters after clustering; if the number is greater than the preset first number threshold, the target clusters after clustering are used as the various clusters to be clustered, and clustering is continued through the above method 2 until the number of target clusters after clustering is not greater than the preset first number threshold. In this way, target clusters 4, 5, and 6 are obtained.

[0142] Students included in target cluster 1, target cluster 2, target cluster 3, target cluster 4, target cluster 5, and target cluster 6 are considered candidate lonely students. For example, candidate student A belongs to target cluster 1 and target cluster 5, and it is determined that candidate student A has a lonely risk. For another example, candidate student B only belongs to target cluster 2, and it can be determined that candidate student B does not have a lonely risk.

[0143] In order to improve the accuracy of the student's lonely assessment, in this application, if the first intimacy of the first cluster and the second cluster is determined respectively by at least two of the above methods, and the number of target clusters corresponding to each method is not greater than the preset first quantity threshold, the target clusters are obtained. At this time, the students included in the target cluster are first determined as candidate lonely students. Then, the candidate lonely students present in at least two target clusters are determined to be at risk of loneliness. Thereby improving the accuracy of the student's lonely assessment.

[0144] Figure 6 The third student loneliness assessment process diagram provided for this application includes the following steps:

[0145] S601: If the first intimacy of the first cluster and the second cluster is determined respectively by using at least two of the above methods, and the number of target clusters corresponding to each method is not greater than the preset first number threshold, the students included in the target cluster are determined as candidate lonely students;

[0146] S602: for the candidate withdrawn student, if the candidate withdrawn student exists in at least two target clusters, determining that the candidate withdrawn student has a withdrawn risk;

[0147] S603: For students who are at risk of becoming withdrawn, output first warning information for indicating that the students are at high risk of becoming withdrawn.

[0148] In the present application, the students included in the target cluster are determined as candidate lonely students; for the candidate lonely students, if the candidate lonely students exist in at least two target clusters, it is determined that the candidate lonely students have a lonely risk. And it indicates that the lonely risk is high. Therefore, the first warning information for characterizing that the student has a high lonely risk is output. Thereby improving the accuracy of the lonely warning.

[0149] Figure 7 The fourth student loneliness assessment process diagram provided for this application includes the following steps:

[0150] S701: Determine a first degree of intimacy between various clusters to be clustered according to consumption data of students included in the various clusters to be clustered; wherein the consumption data includes consumption time data and consumption location data;

[0151] S702: Clustering the various clusters according to the first intimacy between the various clusters, and determining the number of target clusters after clustering;

[0152] S703: If the number is greater than a preset first number threshold, the target cluster after clustering is used as each cluster to be clustered, and clustering is continued until the number of target clusters after clustering is no greater than the preset first number threshold; if the number is no greater than the preset first number threshold, and there is a target cluster containing a number of students less than a preset second number threshold, it is determined that the students contained in the target cluster are at risk of being withdrawn;

[0153] S704: For students at risk of loneliness, determine the loneliness risk level corresponding to the student according to the number of students included in the target cluster to which the student belongs, and output second warning information corresponding to the loneliness risk level; wherein, the fewer the number of students included in the target cluster, the higher the corresponding loneliness risk level.

[0154] For students who are determined to be at risk of loneliness and only exist in one target cluster, first determine the loneliness risk level corresponding to the student based on the number of students included in the target cluster to which the student belongs. The smaller the number, the higher the risk of loneliness. Therefore, the smaller the number of students included in the target cluster, the higher the corresponding loneliness risk level. Among them, the correspondence between different quantities and loneliness risk levels can be saved in advance. For example, the loneliness risk level corresponding to quantity 1 is high. The loneliness risk level corresponding to quantity 2 or 3 is medium. The loneliness risk level corresponding to quantity 4 or 5 is low. If it exceeds 5, it is considered that there is no loneliness risk. Then output the second warning information corresponding to the loneliness risk level. Thereby further improving the accuracy of the loneliness risk warning.

[0155] The student loneliness assessment process provided by this application first collects data. The student campus card dining consumption data is exported from the school data storage platform. The data should include: student number, consumption time, unit name, name, consumption amount, consumption location code, consumption location name, and window number. Among them:

[0156] Student ID: It is the unique identifier of the student in the school. The specific student can be located by the student ID, which is unique.

[0157] Consumption time: records the time of this consumption. The time format is "YYYY-MM-DDHH-MM-SS".

[0158] Unit name: indicates which college the student belongs to, and is unique.

[0159] Name: Name as shown on the student’s ID card or other nationally recognized identification document.

[0160] Consumption amount: The amount spent on this consumption, in yuan.

[0161] Name of consumption location: The name of the location where this consumption took place should be unique and indicate that this consumption was in the school cafeteria and on which floor.

[0162] Consumption location code: The code of the location where this consumption took place, which identifies the location code of the restaurant floor and is unique.

[0163] Window number: The window selected for this consumption, which is unique.

[0164] Then, data preprocessing is performed. The obtained student dining consumption data is further processed so that it can be used by the model. The specific operations are as follows:

[0165] The data is grouped by student ID, and the dining records of each student are counted. Students whose dining frequency < (time span / 7) are screened out, that is, the number of dining frequency at school is too few, and it is impossible to determine whether the student is lonely through dining data. Among them: "7" means 7 days a week, that is, the counted students should have at least one meal at school per week; the time span is the latest dining date - the earliest dining date of the currently selected dining data.

[0166] After grouping the data, the groups are arranged in ascending order by student ID, and the groups are arranged in order of dining time. Then, the consumption data of each group is traversed, and the consumption records within 30 minutes are identified as one dining record. The first consumption record is used as the time of this dining record, and redundant data is deleted.

[0167] Then, we make a judgment on whether the two students ate together. We perform calculation and analysis on the preprocessed data to calculate whether each student ate together with other students. In this stage, we assume that two students' two dining records within three minutes are considered to be a common dining, which means that the two students may have eaten together.

[0168] Calculation of the intimacy value between students. At this stage, it is believed that the intimacy between students is reflected in the dining records as follows: the number of times student A and student B eat together. The more times they eat together, the closer their relationship is; the frequency of student A and student B eating together. The higher the frequency of their eating together, the closer their relationship is; the shortest time interval between student A and student B eating together. The shorter the shortest time interval between their eating together, the closer their relationship is. In addition, whether student A and student B have the opportunity to eat together also depends on the number of times they eat in the cafeteria. Therefore, at this stage, the above four indicators are calculated in a coordinated manner to obtain the intimacy value between students. The calculation formula is shown below:

[0169]

[0170] Among them, i,j represent student i and student j respectively, P i,j is the intimacy value between student i and student j, OM i,j and OM i,j represents the number of times student i and student j eat together, CM i and CM j represents the number of times student i and student j eat in the cafeteria, mean i,j and mean j,i represents the average time interval between students i and j eating together, min i,j and min j,i represents the minimum time interval between students i and j eating together in the cafeteria. i and CM j The values ​​of are not exactly the same, but the other indicators are the same, so the formula can be further simplified as follows:

[0171]

[0172] Multi-method combined cluster analysis.

[0173] In this stage, cluster analysis is performed on the dining records of students, with the intimacy value P between students as i,j The "distance" between cluster i and cluster j during clustering is merged according to the distance, and clusters with closer distances are merged first. The distance between new clusters during merging is calculated using four methods: minimum value, maximum value, average value, and minimum variance. The clustering results under the four calculation methods are retained and output when the specified number of clusters is merged, and there is still only one student in the cluster. The four output results are compared, and the clusters that appear more than or equal to 2 times in the four output results are selected, and the student information represented by the cluster is returned to remind relevant teachers or leaders to pay attention to the mental health of the student, providing a new way for mental health teachers to capture students' mental health.

[0174] Combined analysis of multiple interval results. In this stage, the results of the suspected loneliness prediction in multiple time intervals will be analyzed comprehensively and the prediction results will be returned. Based on the prediction results in different intervals, the students' loneliness status in the school year, semester, and the last month can be analyzed to pay attention to the changes in students' mental health and track the effects of mental health intervention.

[0175] The execution process of a method for suspected loneliness detection based on student dining data is as follows:

[0176]

[0177]

[0178] The above process is explained by taking the example of outputting suspected loneliness when the target cluster contains only one student.

[0179] Figure 8 Schematic diagram of the clustering process provided for this application, Figure 8 The horizontal axis is the student ID, and the vertical axis is the similarity. Each vertical line represents a student. If the tops of two vertical lines are connected, it means they are clustered into one category.

[0180] Fig. 9 The student loneliness assessment flow chart provided for this application is as follows Fig. 9 As shown, first determine whether the number of times student i has eaten at school during this period is greater than the threshold. If not, delete the student's record. If yes, add the student to the set of students suspected of being lonely. After all students are traversed, a set of students suspected of being lonely is obtained. Calculate the common consumption data of student i and student j; calculate the intimacy between student i and student j based on the common consumption data. Traverse all students to obtain the intimacy between any two students. Perform cluster analysis based on the intimacy between each student; output the list of suspected lonely students.

[0181] Fig.10 A schematic diagram of obtaining a student loneliness assessment by clustering in various ways provided for this application. Fig.10 As shown, the consumption data of each student is preprocessed, and then the common consumption is judged, and then the intimacy is calculated. Then, cluster analysis is performed in different ways, and finally the suspected lonely students are determined according to different cluster analysis results.

[0182] Fig.11 Schematic diagram of the target cluster provided for this application, Fig.11 For illustration only, discrete points ( Fig.11 The students corresponding to the points contained in the triangle in the figure are suspected to be withdrawn students.

[0183] Fig.12 The schematic diagram of the student loneliness assessment device provided for this application includes:

[0184] A first determination module 121 is used to determine the first intimacy between the various clusters to be clustered according to the consumption data of the students included in the various clusters to be clustered; wherein the consumption data includes consumption time data and consumption location data;

[0185] A second determination module 122, configured to cluster the various clusters according to the first intimacy between the various clusters, and determine the number of target clusters after clustering;

[0186] The clustering evaluation module 123 is used to, if the number is greater than a preset first quantity threshold, use the target cluster after clustering as each cluster to be clustered, and continue clustering until the number of target clusters after clustering is no greater than the preset first quantity threshold; if the number is no greater than the preset first quantity threshold, and there is a target cluster containing a number of students less than a preset second quantity threshold, it is determined that the students contained in the target cluster are at risk of being withdrawn.

[0187] The first determination module 121 is specifically used to determine the second intimacy between the first student and the second student according to the consumption data of the first student included in the first cluster and the consumption data of the second student included in the second cluster for any first cluster and second cluster in the various clusters;

[0188] A first intimacy between the first cluster and the second cluster is determined according to the second intimacy.

[0189] The first determination module 121 is specifically used to determine the common consumption data of the first student and the second student based on the consumption data of the first student and the consumption data of the second student; wherein the common consumption data includes at least one of the number of common consumptions, the average time interval of common consumption, the minimum time interval of common consumption and the respective consumption times; wherein, if within a preset time window, the first student and the second student consume at the same consumption location, it is determined that the first student and the second student have consumed together once; based on the common consumption data of the first student and the second student, the second intimacy between the first student and the second student is determined.

[0190] The first determination module 121 is specifically configured to, if the common consumption data includes the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions and the number of respective consumptions, substitute the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions and the number of respective consumptions of the first student and the second student into the following formula according to the common consumption data of the first student and the second student, so as to determine the second intimacy between the first student and the second student;

[0191] In the formula, i represents the first student, j represents the second student, P i，j The second closest degree, OM i，j is the number of joint consumption, mean i，j is the average time interval of joint consumption, min i，j is the minimum time interval for joint consumption, CM i is the consumption frequency of the first student, CM j The number of consumptions of the second student.

[0192] The first determination module 121 is specifically used to determine the second intimacy as the first intimacy of the first cluster and the second cluster if the first cluster and the second cluster respectively contain one student; if at least one of the first cluster and the second cluster contains at least two students, obtain the second intimacy of each student in the first cluster with each student in the second cluster, and determine the first intimacy of the first cluster and the second cluster in at least one of the following ways; use the minimum intimacy among the obtained second intimacy as the first intimacy of the first cluster and the second cluster; use the maximum intimacy among the obtained second intimacy as the first intimacy of the first cluster and the second cluster; use the average intimacy of the obtained second intimacy as the first intimacy of the first cluster and the second cluster; use the variance intimacy among the obtained second intimacy as the first intimacy of the first cluster and the second cluster.

[0193] The second determination module 122 is specifically configured to determine the maximum first intimacy according to the first intimacy between the various clusters; and cluster the clusters corresponding to the maximum first intimacy.

[0194] The clustering evaluation module 123 is specifically used to respectively determine the first intimacy of the first cluster and the second cluster by using at least two of the above-mentioned methods, and respectively obtain target clusters whose number of target clusters corresponding to each method is not greater than the preset first number threshold; determine the students included in the target cluster as candidate lonely students; and for the candidate lonely student, if the candidate lonely student exists in at least two target clusters, determine that the candidate lonely student is at risk of loneliness.

[0195] The device also includes:

[0196] The early warning module 124 is used to output first early warning information for students who are at risk of being withdrawn, which is used to indicate that the students are at high risk of being withdrawn.

[0197] The early warning module 124 is also used to determine the loneliness risk level corresponding to students who are at risk of loneliness according to the number of students included in the target cluster to which the students belong, and output second early warning information corresponding to the loneliness risk level; wherein, the fewer the number of students included in the target cluster, the higher the corresponding loneliness risk level.

[0198] The present application also provides an electronic device, such as Fig.13 As shown, it includes: a processor 131, a communication interface 132, a memory 133 and a communication bus 134, wherein the processor 131, the communication interface 132, and the memory 133 communicate with each other through the communication bus 134;

[0199] The memory 133 stores a computer program, and when the program is executed by the processor 131, the processor 131 executes any of the above method steps.

[0200] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0201] The communication interface 132 is used for communication between the above electronic device and other devices.

[0202] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0203] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0204] The present application also provides a computer storage readable storage medium, wherein the computer readable storage medium stores a computer program executable by an electronic device, and when the program runs on the electronic device, the electronic device implements any of the above method steps when executing.

[0205] The present application also provides a computer program product, wherein the computer program product comprises an executable program, and the executable program is executed by a processor to implement the method described.

[0206] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0207] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for assessing student loneliness, characterized in that: The method comprises: Determine the first intimacy between the various clusters according to the consumption data of the students included in the various clusters to be clustered; wherein the consumption data includes consumption time data and consumption location data; Clustering the various clusters according to the first intimacy between the various clusters, and determining the number of target clusters after clustering; If the number is greater than a preset first quantity threshold, the target cluster after clustering is used as each cluster to be clustered, and clustering is continued until the number of target clusters after clustering is no greater than the preset first quantity threshold; if the number is not greater than the preset first quantity threshold, and there is a target cluster containing a number of students less than a preset second quantity threshold, it is determined that the students contained in the target cluster are at risk of being withdrawn.

2. The method according to claim 1, characterized in that The step of determining the first intimacy between the various clusters to be clustered according to the consumption data of the students included in the various clusters to be clustered comprises: For any first cluster and second cluster in the various clusters, the second intimacy between the first student and the second student is determined based on the consumption data of the first student included in the first cluster and the consumption data of the second student included in the second cluster; the first intimacy between the first cluster and the second cluster is determined based on the second intimacy.

3. The method according to claim 2, characterized in that The process of determining the second intimacy between the first student and the second student includes: Determine the common consumption data of the first student and the second student according to the consumption data of the first student and the consumption data of the second student; wherein the common consumption data includes at least one of the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions, and the number of respective consumptions; wherein, if the first student and the second student consume at the same consumption location within a preset time window, it is determined that the first student and the second student consume once together; A second intimacy between the first student and the second student is determined based on the common consumption data of the first student and the second student.

4. The method according to claim 3, characterized in that If the common consumption data includes the number of common consumptions, the average time interval of common consumptions, the minimum time interval of common consumptions, and the number of respective consumptions, determining the second intimacy between the first student and the second student according to the common consumption data of the first student and the second student includes: Substitute the number of times the first student and the second student consume together, the average time interval of common consumption, the minimum time interval of common consumption, and the number of times each consumes into the following formula to determine the second intimacy between the first student and the second student; In the formula, i represents the first student, j represents the second student, P i，j The second intimacy, OM i，j is the number of joint consumption, mean i，j is the average time interval of joint consumption, min i，j is the minimum time interval for joint consumption, CM i is the consumption frequency of the first student, CM j The number of consumptions of the second student.

5. The method according to claim 2, characterized in that Determining the first intimacy between the first cluster and the second cluster according to the second intimacy includes: If the first cluster and the second cluster each include a student, determining the second intimacy as the first intimacy between the first cluster and the second cluster; If at least one of the first cluster and the second cluster contains at least two students, obtain the second intimacy between each student in the first cluster and each student in the second cluster, and determine the first intimacy between the first cluster and the second cluster in at least one of the following ways; The minimum intimacy among the acquired second intimacy is used as the first intimacy of the first cluster and the second cluster; The maximum intimacy among the acquired second intimacy is used as the first intimacy of the first cluster and the second cluster; The average intimacy of each second intimacy obtained is used as the first intimacy of the first cluster and the second cluster; The variance intimacy among the obtained second intimacy is used as the first intimacy of the first cluster and the second cluster.

6. The method according to any one of claims 1 to 5, characterized in that: Clustering the various clusters according to the first intimacy between the various clusters includes: According to the first intimacy between the various clusters, a maximum first intimacy is determined; and the clusters corresponding to the maximum first intimacy are clustered.

7. The method according to claim 5, characterized in that If the first intimacy of the first cluster and the second cluster is determined respectively by using at least two of the above methods, and the number of target clusters corresponding to each method is not greater than the preset first number threshold; Determining that students included in the target cluster are at risk of loneliness includes: Determine the students included in the target cluster as candidate withdrawn students; For the candidate withdrawn student, if the candidate withdrawn student exists in at least two target clusters, it is determined that the candidate withdrawn student has a risk of being withdrawn.

8. The method according to claim 7, characterized in that The method further comprises: For students who are at risk of becoming withdrawn, first warning information is outputted to indicate that the students are at high risk of becoming withdrawn.

9. The method according to claim 1, characterized in that The method further comprises: For students who are at risk of becoming isolated, the isolation risk level corresponding to the student is determined based on the number of students included in the target cluster to which the student belongs, and a second warning information corresponding to the isolation risk level is output; wherein, the fewer the number of students included in the target cluster, the higher the corresponding isolation risk level.

10. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method according to any one of claims 1 to 9 when executing a program stored in a memory.

Images