Campus information intelligent pushing method and system based on a card and storage medium

Abstract

The application relates to the technical field of information pushing, in particular to a campus information intelligent pushing method and system based on a card and a storage medium. The method obtains an event vector of student behavior through a card; obtains a change degree of attention according to changes of the event vector of the current behavior and the neighborhood behavior of the student; obtains a content conversion degree according to the behavior similarity of the student and the students in the similar group of the student and the difference of the change degree of attention; obtains a change degree of attention deviation according to the difference of the basic information of the student and the current similar student and the difference of the attention condition of the current behavior in the current time period; obtains a current guidance degree according to the content conversion degree and the change degree of attention deviation, and further obtains the weight of each element in a collaborative filtering behavior matrix in a collaborative filtering algorithm. Through real-time and accurate dynamic adjustment of the weight of the element in the collaborative filtering behavior matrix, the accuracy and efficiency of intelligent information pushing on the student are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information pushing, in particular to a campus information intelligent pushing method and system based on a campus card and a storage medium. BACKGROUND

[0002] With the deepening of the construction of smart campus, colleges and universities generally use the "campus card" system to integrate student behavior data on campus, covering consumption, access control, borrowing, attendance and other types of scenarios, providing a data basis for campus information management. The campus card data implies key information such as user preferences, living habits and interest tendencies, creating conditions for precise campus information services (such as course notifications, competition activities, and internship recruitment pushing). At present, the mainstream campus recommendation system matches similar user groups by analyzing student historical behavior data (such as frequent access to the library, consumption in specific places) and using collaborative filtering algorithms to achieve personalized pushing of campus information.

[0003] However, the existing collaborative filtering algorithm relies on historical behavior data for student behavior modeling, ignoring the dynamic evolution of student focus over time. For example, students may focus on course arrangements and textbook acquisition at the beginning of the semester, and later shift their focus to competition registration, sports activities or club information. This makes it difficult to identify and respond to focus shifts in a timely manner, and the content recommended to students by the collaborative filtering algorithm lags behind actual needs, while the relevance of the pushed information is poor, affecting information reach efficiency and service experience. SUMMARY

[0004] In order to solve the technical problem that the existing collaborative filtering algorithm ignores the dynamic evolution of student focus over time, making it difficult to identify and respond to focus shifts in a timely manner, and making the pushed information inaccurate, the purpose of the present application is to provide a campus information intelligent pushing method and system based on a campus card and a storage medium, and the technical solution adopted is as follows:

[0005] In a first aspect, an embodiment of the present application provides a campus information intelligent pushing method based on a campus card, which comprises the following steps:

[0006] Obtain the event vector of each behavior of each student and the basic information of each student through the campus card information of each student in real time;

[0007] According to the change of the event vector of the current behavior of each student and the event vector of the neighborhood behavior of the current behavior of each student, obtain the focus change degree of the current behavior of each student;

[0008] According to the behavior of each student in the current time period, obtain the behavior similar group of each student; according to the behavior similarity and the focus change degree difference between each student and each student in the behavior similar group of each student in the current time period, obtain the content conversion degree of the current behavior of each student;

[0009] obtaining a current similar student of each student according to a similarity of an event vector of a current behavior of each student to each other student, and obtaining a focus deviation degree of the current behavior of each student according to a difference in basic information of each student to each current similar student of the student and a difference in a focus on the current behavior in a current time period;

[0010] obtaining a current guidance degree of each student according to the content conversion degree and the focus deviation degree of the current behavior of each student, and obtaining a weight of each element in a collaborative filtering behavior matrix in a collaborative filtering algorithm based on the current guidance degree of each student to each student in a behavior similar group of the student, to determine an intelligent push information of each student at present.

[0011] Further, the focus change degree obtaining method is:

[0012] for any student, arranging the current behavior of the student and the neighborhood behavior of the current behavior according to a time sequence to obtain a reference behavior sequence of the student;

[0013] taking a length of a modulus of a difference in an event vector of each behavior in the reference behavior sequence to a previous adjacent behavior of the behavior as a change analysis value of the corresponding behavior;

[0014] taking a normalized result of a mean value of the change analysis value as the focus change degree of the current behavior of the student.

[0015] Further, the content conversion degree obtaining method is:

[0016] for any student, arranging an event vector of a behavior of the student in a current time period according to a time sequence of the corresponding behavior to obtain a current behavior vector sequence of the student;

[0017] taking a cosine similarity of the current behavior vector sequence of the student to a target student in a behavior similar group of the student as a current similarity degree of the student to the target student;

[0018] taking a difference in the focus change degree of the student to the target student as a current reference difference of the student to the target student;

[0019] taking a product of the current similarity degree and the current reference difference as a current deviation degree of the student to the target student;

[0020] taking a normalized result of a sum of the current deviation degree of the student to each target student as the content conversion degree of the current behavior of the student.

[0021] Further, the method for obtaining the attention deviation degree comprises the following steps:

[0022] For any student, a representative degree of the current behavior of the student is obtained according to the occurrence of the current behavior of the student in the current time period and the attention change degree of the current behavior of the student;

[0023] For any current similar student of the student, a result of negative correlation and normalization of a vector difference corresponding to the basic information of the student and the current similar student is taken as a basic information similarity degree of the student and the current similar student;

[0024] A difference of the representative degree of the current behavior of the student and the current similar student is taken as a current behavior representative difference of the student and the current similar student;

[0025] A product of the basic information similarity degree and the current behavior representative difference is taken as an attention deviation analysis value of the student and the current similar student;

[0026] An average of the attention deviation analysis values of the student and all current similar students of the student is taken as the attention deviation degree of the current behavior of the student.

[0027] Further, the method for obtaining the representative degree comprises the following steps:

[0028] A ratio of the number of occurrences of the current behavior of the student in the current time period to the total number of behaviors of the student in the current time period is taken as a first characteristic value;

[0029] A product of the first characteristic value and a result of negative correlation and normalization of the attention change degree of the current behavior of the student is taken as the representative degree of the current behavior of the student.

[0030] Further, the method for obtaining the current guidance degree comprises the following steps:

[0031] A product of the content conversion degree of the current behavior of each student and the attention deviation degree is taken as the current guidance degree of each student.

[0032] Further, the method for obtaining the behavior similar group comprises the following steps:

[0033] According to the behaviors of each student in the current time period, a behavior similar group of each student in the current time period is obtained through a collaborative filtering algorithm.

[0034] Further, the method for obtaining the current similar student comprises the following steps:

[0035] For any student, a result of normalization of a vector difference of the current behavior of the student and the current behavior of each other student is taken as a current behavior similarity analysis value of the student and each other student.

[0036] When the current behavior similarity analysis value is less than the preset behavior similarity threshold value, the corresponding student is taken as the current similar student of the student.

[0037] In a second aspect, another embodiment of the present application provides a campus information intelligent pushing system based on a card, which comprises:

[0038] A data acquisition module is configured to acquire an event vector of each behavior of each student and basic information of each student in real time through the card information of each student.

[0039] A concern change degree acquisition module is configured to acquire a concern change degree of the current behavior of each student according to a change of the event vector of the current behavior of each student and the event vector of the neighboring behavior of the current behavior.

[0040] A content conversion degree acquisition module is configured to acquire a behavior similar group of each student according to the behavior of each student in a current time period; and acquire a content conversion degree of the current behavior of each student according to a behavior similarity and a concern change degree difference between each student and each student in the behavior similar group of the student in the current time period.

[0041] A concern offset degree acquisition module is configured to acquire a current similar student of each student according to a similarity of the event vector of the current behavior of each student and the event vector of the current behavior of other students; and acquire a concern offset degree of the current behavior of each student according to a difference in the basic information between each student and each current similar student of the student and a difference in the attention received by the current behavior in the current time period.

[0042] A data processing module is configured to acquire a current guidance degree of each student according to the content conversion degree and the concern offset degree of the current behavior of each student; acquire a weight of each element in a collaborative filtering behavior matrix in a collaborative filtering algorithm based on the current guidance degree of each student and each student in the behavior similar group of the student; and determine an intelligent pushing information of each student in the current time period.

[0043] In a third aspect, another embodiment of the present application provides a computer readable storage medium, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above methods when executing the computer program.

[0044] The present application has the following beneficial effects:

[0045] The application firstly obtains the attention change degree of the current behavior of each student according to the change of the event vector of the neighborhood behavior of the current behavior of each student, which reflects the possibility of the change of the current behavior of each student; in order to accurately analyze whether the current behavior of each student changes, so as to accurately recommend the campus information of each student and reduce irrelevant behavior recommendation, the content conversion degree of the current behavior of each student is obtained according to the behavior similarity and the difference in the attention change degree between each student and each student in the behavior similar group of each student, which further reflects the change of the current behavior of each student; in order to more accurately analyze whether the current behavior of each student changes, the attention deviation degree of the current behavior of each student is obtained according to the difference in the basic information between each student and each current similar student and the difference in the attention of the current behavior in the current time period, which further reflects the change of the current behavior of each student; then, the current orientation degree of each student is obtained according to the content conversion degree and the attention deviation degree of the current behavior of each student, which accurately reflects the possibility of the deviation of the current behavior of each student, dynamically identifies the dominant attention direction of the current stage of the student, improves the relevance and timeliness of the information push, and effectively avoids the problems of push content lag and irrelevant push; then, the weight of each element in the collaborative filtering behavior matrix in the collaborative filtering algorithm is obtained based on the current orientation degree of each student and each student in the behavior similar group of each student, which realizes the dynamic adjustment of the weight in the collaborative filtering behavior matrix and effectively improves the ability of the campus management system to balance the modeling between the long-term and short-term behaviors of the student; then, the intelligent push information of each student is accurately and efficiently determined, which effectively improves the relevance of the push campus information content and the acceptance of the student and improves the student experience. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0047] Figure 1 A schematic flow chart of a campus information intelligent push method based on a card is provided for an embodiment of the present application.

[0048] Figure 2 A campus information intelligent push system structure diagram based on a card is provided for an embodiment of the present application.

[0049] Figure 3 A schematic diagram of a computer device is provided for an embodiment of the present application. Detailed Implementation

[0050] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation methods, structures, features, and effects of the campus information intelligent push method, system, and storage medium based on a smart card system proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0052] The following description, in conjunction with the accompanying drawings, details the specific solutions for the intelligent campus information push method, system, and storage medium based on the all-in-one card provided by this invention.

[0053] Example 1:

[0054] This invention proposes a method for intelligent campus information push based on a campus card system. Please refer to [link / reference]. Figure 1 The diagram illustrates a schematic flowchart of a campus information intelligent push method based on a smart card system, according to an embodiment of the present invention. The method includes the following steps:

[0055] Step S1: Obtain the event vector of each student's behavior and the basic information of each student in real time through each student's campus card information.

[0056] Specifically, the campus management system can obtain the event vector of each student's actions and each student's basic information in real time from each student's campus card information. It should be noted that an action includes consumption data (such as purchase records at print shops, supermarkets, canteens, etc.), access control card swipe records (such as entry and exit data for libraries, dormitories, teaching buildings, laboratories, etc.), book borrowing records, class attendance data, library seat reservation records, and registration data for various campus activities, competitions, lectures, etc. Each action also includes a unique student identifier (such as student ID), action type, time, location, device number, and other auxiliary information. The data related to each student's actions are constructed into a vector, namely the event vector of each action. Each event vector has the same length, and the elements at the same position in each event vector correspond to the same data type. Basic information includes the corresponding student's student ID, department, age, and gender.

[0057] In order to accurately analyze the recent behavior of each student and make more reasonable recommendations for each student in the campus management system, the embodiment only analyzes the unnecessary behavior of each student, wherein the unnecessary behavior is the personal arrangement activities of the student in addition to the necessary behavior such as attending classes and eating; when a student focuses on a behavior, the behavior trajectory of the student usually presents obvious focusing characteristics, such as frequently entering and exiting a specific place and concentrating on participating in related matters, and if the student turns to focus on another event due to external incentives (such as teacher suggestions, social influences or personal planning), the behavior pattern of the student will also change. For example, the student originally frequently enters the library to read, but now wants to prepare for a certain subject competition, and the student may turn to a more quiet and closed self-study room for targeted learning.

[0058] Step S2: According to the change of the event vector of the current behavior of each student and the event vector of the neighboring behavior of the current behavior, the degree of focus change of the current behavior of each student is obtained.

[0059] Specifically, when the focus of a student shifts, the behavior pattern of the student will gradually adjust, which is manifested as a series of new behaviors different from the original behavior path, and if a plurality of behaviors are deviated from the previous mode, it indicates that the content of the focus of the student is undergoing substantial changes, and the greater the deviation, the more obvious the focus change. Therefore, according to the change of the event vector of the current behavior of each student and the event vector of the neighboring behavior of the current behavior, the degree of focus change of the current behavior of each student is obtained. The greater the degree of focus change, the greater the possibility of change of the current behavior of the corresponding student. In the embodiment, the three historical behaviors of each student in time sequence closest to the current behavior of the student are all regarded as the neighboring behavior of the current behavior of the student. The implementer can set the neighboring behavior of the current behavior of each student according to the actual situation, which is not limited herein.

[0060] Preferably, in one implementation manner of the embodiment, the method for obtaining the degree of focus change is as follows: for any student, the current behavior of the student and the neighboring behavior of the current behavior are arranged according to the time sequence from front to back to obtain the reference behavior sequence of the student; the length of the event vector difference between each behavior in the reference behavior sequence and the previous adjacent behavior is taken as the change analysis value of the corresponding behavior; when the change analysis values are all greater, it indicates that the current plurality of behaviors are deviated, which indirectly indicates that the focus change of the current behavior of the student is more obvious, and then the embodiment takes the normalized result of the mean value of the change analysis values as the degree of focus change of the current behavior of the student. In the embodiment, the mean value of the change analysis values is normalized by the norm normalization function.

[0061] Thus, the degree of focus change of the current behavior of each student is obtained.

[0062] Step S3: obtaining a behavior similar group of each student according to the behavior of each student in the current time period; obtaining the content conversion degree of the current behavior of each student according to the behavior similarity and the difference in the degree of attention change between each student and each student in the behavior similar group of the student in the current time period.

[0063] Specifically, under the similar academic stage, professional background and life rhythm, part of the students tend to have strong similarity in behavior. When the degree of attention change of the current behavior of a student and the current behavior of other students similar in behavior has obvious difference, it means that the current behavior of the student has a greater possibility of content change. Therefore, the embodiment first obtains the behavior similar group of each student according to the behavior of each student in the current time period, accurately selects the students similar in behavior corresponding to each student in the current time period; and then obtains the content conversion degree of the current behavior of each student according to the behavior similarity and the difference in the degree of attention change between each student and each student in the behavior similar group of the student in the current time period. The greater the content conversion degree, the more likely the attention content of the current behavior of the corresponding student has changed, and the subsequent recommended behavior of the corresponding student should consider the bias of the current behavior. It should be noted that the duration of the current time period in the embodiment is set to 7 days, and the implementer can set the size of the current time period according to the actual situation, which is not limited here, but the end time of the current time period must be the current time.

[0064] Preferably, in an implementable manner of the embodiment, the method for obtaining the similar group is: obtaining the behavior similar group of each student in the current time period by a collaborative filtering algorithm according to the behavior of each student in the current time period. The collaborative filtering algorithm is a known technology and will not be described here.

[0065] Preferably, in an implementable manner of the present embodiment, the content conversion degree acquisition method is as follows: for any student, arrange the event vector of the student's behavior in the current time period according to the time sequence from the front to the back of the corresponding behavior, obtain the current behavior vector sequence of the student, which accurately represents the student's behavior in the current time period; take each student in the behavior similar group of the student as a target student, for any target student, acquire the cosine similarity between the current behavior vector sequence of the student and the target student as the current similarity degree between the student and the target student; it should be noted that if the length of the current behavior vector sequence of the student and the target student is different, 0 is used to supplement the current behavior vector sequence with shorter length. The greater the current similarity degree, the more similar the overall behavior of the student and the target student in the current time period, and the greater the difference in the attention change degree of the current behavior of the student and the target student, the more accurate the student's current behavior content change. Further, the absolute value of the difference between the attention change degree of the student and the target student is taken as the current reference difference between the student and the target student; then the product of the current similarity degree and the current reference difference is taken as the current deviation degree between the student and the target student; the greater the current deviation degree, the more the current behavior of the student deviates; in order to more accurately represent the content change of the current behavior of the student, the sum of the current deviation degree of the student and each target student is normalized, and the result is taken as the content conversion degree of the current behavior of the student. The present embodiment normalizes the sum of the current deviation degree of the student and each target student by the norm normalization function.

[0066] At this point, the content conversion degree of the current behavior of each student is obtained.

[0067] Step S4: According to the similarity of the event vector of the current behavior of each student and other students, obtain the current similar students of each student; according to the difference in basic information between each student and each of its current similar students, and the difference in attention received by the current behavior in the current time period, obtain the attention deviation degree of the current behavior of each student.

[0068] Specifically, in order to more accurately analyze whether the current behavior of each student has changed, the present embodiment further obtains the current similar students of each student according to the similarity of the event vector of the current behavior of each student and other students. When the basic information of a student and its current similar students is more similar, and the performance of the current behavior in the current time period is less similar, it means that the current behavior of the student is more likely to change. Further, the present embodiment obtains the attention deviation degree of the current behavior of each student according to the difference in basic information between each student and each of its current similar students, and the difference in attention received by the current behavior in the current time period. The greater the attention deviation degree, the more likely the current behavior of the corresponding student deviates.

[0069] Preferably, in one implementable manner of the present embodiment, the method for obtaining the current similar student is: for any student, the result of normalizing the length of the event vector difference between the current behavior of the student and the current behavior of each other student as the current behavior similarity analysis value between the student and each other student; the present embodiment normalizes the length of the event vector difference between the current behavior of the student and the current behavior of each other student by the norm normalization function. The smaller the current behavior similarity analysis value, the more similar the current behavior of the student and the corresponding student, and then the present embodiment sets the preset behavior similarity threshold value to 0.2, and the implementer can set the size of the preset behavior similarity threshold value according to the actual situation, which is not limited here. When the current behavior similarity analysis value is less than the preset behavior similarity threshold value, the corresponding student is taken as the current similar student of the student.

[0070] Up to now, the current similar student of each student is obtained.

[0071] Preferably, in one implementable manner of the present embodiment, the method for obtaining the attention offset degree is: for any student, obtaining the representative degree of the current behavior of the student according to the occurrence of the current behavior of the student in the current time period and the attention change degree of the current behavior of the student; the greater the representative degree, the more representative and the more representative the current behavior of the student. Wherein, the method for obtaining the representative degree is: taking the ratio of the number of times of the current behavior of the student in the current time period to the total number of behaviors of the student in the current time period as a first characteristic value; the greater the first characteristic value, the higher the frequency of the occurrence of the current behavior of the student in the current time period, the more representative the current behavior of the student; the smaller the attention change degree of the current behavior of the student, the more representative the current behavior of the student is indirectly reflected; and then the present embodiment takes the product of the first characteristic value and the negative correlation and normalized result of the attention change degree of the current behavior of the student as the representative degree of the current behavior of the student. Wherein, the present embodiment takes the inverse of the attention change degree of the current behavior of the student as the power of an exponential function with a natural constant as the base, and the output result of the exponential function is the negative correlation and normalized result of the attention change degree of the current behavior of the student.

[0072] For any current similar student of the student, the result of negative correlation and normalization of the length of the vector difference corresponding to the basic information of the student and the basic information of the current similar student is taken as the basic information similarity degree between the student and the current similar student. The greater the basic information similarity degree is, the more the basic information of the student is the same as that of the current similar student. The embodiment takes the similarity number of the length of the vector difference corresponding to the basic information of the student and the basic information of the current similar student as the power of an exponential function with a natural constant as the base number, and the output result of the exponential function is the result of negative correlation and normalization of the length of the vector difference corresponding to the basic information of the student and the basic information of the current similar student. It should be noted that the vector corresponding to the basic information of each student is a vector formed after the basic information of each student is converted into data, wherein the length of the vector corresponding to the basic information of each student is certainly the same, and the types of basic information corresponding to the elements at the same position in different vectors are certainly the same;

[0073] When the basic information of the student is more the same as that of the current similar student, and the difference between the representative degrees of the current behaviors of the student and the current similar student is greater, it is more indicated that the content of the current behavior of the student has changed; the absolute value of the difference between the representative degrees of the current behaviors of the student and the current similar student is taken as the current behavior representative difference between the student and the current similar student; the product of the basic information similarity degree and the current behavior representative difference is taken as the attention deviation analysis value between the student and the current similar student; the greater the attention deviation analysis value is, the greater the deviation reflected by the current similar student in the current behavior of the student is; in order to accurately represent the deviation in the current behavior of the student, the mean value of the attention deviation analysis values of the student and all current similar students of the student is taken as the attention deviation degree of the current behavior of the student.

[0074] Up to now, the attention deviation degree of the current behavior of each student is obtained.

[0075] Step S5: According to the content conversion degree and the attention deviation degree of the current behavior of each student, the current guidance degree of each student is obtained; based on the current guidance degree of each student in the behavior similar group of each student, the weight of each element in the collaborative filtering behavior matrix in the collaborative filtering algorithm is obtained, and the current intelligent push information of each student is determined.

[0076] Specifically, it is known that the collaborative filtering algorithm uses time decay weighting to model the historical behavior of students, which does not closely match the actual trend of the content that students pay attention to over time, making it difficult to respond to the shift of the content that students pay attention to in a timely manner, resulting in a lag or insufficient relevance of the content pushed to students according to the existing collaborative filtering algorithm. In order to improve the accuracy of the content pushed to students, the embodiment is directed to the current focus of students to dynamically adjust the weight of the collaborative filtering algorithm to achieve more accurate information matching. It is known that the behavior data of the student group in the closed environment of the campus has the characteristics of similar structure, consistent time sequence and strong comparability. By comparing the current behavior trajectories of similar student groups, the current focus of the students can be effectively predicted. When the content conversion degree and the focus deviation degree of the current behavior of a student are both greater, it means that the change of the current behavior of the student compared to the similar student group is more obvious, which indirectly indicates that the current focus of the student is more oriented. Therefore, the current orientation degree of each student is obtained according to the content conversion degree and the focus deviation degree of the current behavior of each student. The greater the current orientation degree, the stronger the orientation of the current focus of the corresponding student. The method for obtaining the current orientation degree is that the product of the content conversion degree and the focus deviation degree of the current behavior of each student is taken as the current orientation degree of each student. The value range of the current orientation degree is 0 to 1.

[0077] At this point, the current orientation degree of each student is obtained.

[0078] In order to accurately recommend the behavior of each student in real time and improve the recognition of the campus management system by students, the current orientation degree of each student is taken as a weight to dynamically determine the weight of the corresponding element of each student in the collaborative filtering behavior matrix in the collaborative filtering algorithm, to realize real-time dynamic adjustment of the weight in the collaborative filtering behavior matrix, and to accurately and efficiently determine the current intelligent push information of each student. For example, when the current behavior of a student (such as entering the library or registering for a science and technology competition) shows a greater possibility of focus shift, the corresponding element of the student in the collaborative filtering matrix needs to be given a higher weight, so that the behavior has a stronger orientation in the similar user matching and recommendation result. By introducing the "behavior orientation weighting mechanism", a sensitive response to the shift of the focus of students is realized, thereby improving the accuracy and timeliness of campus information push. It should be noted that the elements in the collaborative filtering behavior matrix are the behaviors of each student in the current time period in the behavior similar group of the corresponding student. The collaborative filtering behavior matrix in the collaborative filtering algorithm and the weight of each element in the matrix are known techniques and will not be described in detail.

[0079] In summary, the embodiment obtains the event vector of the student behavior through the card, obtains the attention change degree according to the change of the event vector of the current behavior and the neighborhood behavior of the student, obtains the content conversion degree according to the behavior similarity and the difference of the attention change degree between the student and the students in the behavior similar group of the student, obtains the attention deviation degree according to the difference of the basic information between the student and the current similar student of the student and the difference of the attention condition of the current behavior in the current time period, obtains the current guidance degree according to the content conversion degree and the attention deviation degree, and further obtains the weight of each element in the collaborative filtering behavior matrix in the collaborative filtering algorithm. Through the real-time and accurate dynamic adjustment of the weight of the element in the collaborative filtering behavior matrix, the accuracy and efficiency of the intelligent information push to the student are effectively improved.

[0080] Embodiment 2

[0081] The application further provides a campus information intelligent push system based on the card, please refer to Figure 2 , which shows a campus information intelligent push system structure diagram based on the card provided by one embodiment of the application, and the system comprises a data acquisition module 10, an attention change degree acquisition module 20, a content conversion degree acquisition module 30, an attention deviation degree acquisition module 40 and a data processing module 50.

[0082] The data acquisition module 10 is used for acquiring the event vector of each behavior of each student and the basic information of each student in real time through the card information of each student.

[0083] The attention change degree acquisition module 20 is used for acquiring the attention change degree of the current behavior of each student according to the change of the event vector of the current behavior and the neighborhood behavior of each student.

[0084] The content conversion degree acquisition module 30 is used for acquiring the behavior similar group of each student according to the behavior of each student in the current time period, and acquiring the content conversion degree of the current behavior of each student according to the behavior similarity and the difference of the attention change degree between each student and each student in the behavior similar group of the student in the current time period.

[0085] The attention deviation degree acquisition module 40 is used for acquiring the current similar student of each student according to the event vector similarity of the current behavior of each student and other students, and acquiring the attention deviation degree of the current behavior of each student according to the difference of the basic information between each student and each current similar student of the student and the difference of the attention condition of the current behavior in the current time period.

[0086] The data processing module 50 is configured to obtain the current guidance degree of each student according to the content conversion degree and the attention deviation degree of the current behavior of each student, and obtain the weight of each element in the collaborative filtering behavior matrix in the collaborative filtering algorithm based on the current guidance degree of each student in the similar group of the behavior of each student, and determine the current intelligent push information of each student.

[0087] It should be noted that: the system provided in the above embodiment is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the campus information intelligent push system based on a card and the campus information intelligent push method based on a card provided in the above embodiment belong to the same concept, and the specific implementation process is described in the method embodiment, which will not be repeated here.

[0088] Embodiment 3:

[0089] The application further provides a computer device, please refer to Figure 3 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein the processor 402 executes the computer program 403, so that the computer device can execute any of the above-mentioned campus information intelligent push methods based on a card.

[0090] Embodiment 4:

[0091] The application further provides a computer readable storage medium, the computer readable storage medium stores computer program code, when the computer program code runs on the computer, the computer executes the above-mentioned related method steps to realize the campus information intelligent push method based on a card provided in the above-mentioned embodiment.

[0092] Embodiment 5:

[0093] The application further provides a computer program product, when the computer program product runs on the computer, the computer executes the above-mentioned related steps to realize the campus information intelligent push method based on a card provided in the above-mentioned embodiment.

[0094] Among them, the device, computer readable storage medium, computer program product or chip provided by the embodiment are used to execute the corresponding method provided above, so the beneficial effects they can achieve can refer to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0095] It is to be noted that the sequential order of the above-described embodiments of the present application only for the purpose of description, but not the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0096] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

Claims

1. A campus information intelligent push method based on a card, characterized in that, The method comprises the following steps: Real-time acquisition of an event vector of each behavior of each student and basic information of each student through the one-card information of each student; Acquisition of a focus change degree of the current behavior of each student according to the current behavior of each student and the change of the event vector of the neighboring behavior of the current behavior of each student; Acquisition of a behavior similar group of each student according to the behavior of each student in the current time period; acquisition of a content conversion degree of the current behavior of each student according to the behavior similarity and the focus change degree difference between each student and each student in the behavior similar group of each student in the current time period; Acquisition of a current similar student of each student according to the event vector similarity of the current behavior of each student and the current behavior of each other student; acquisition of a focus deviation degree of the current behavior of each student according to the basic information difference between each student and each current similar student of each student and the difference in the focus situation of the current behavior in the current time period; Acquisition of a current guidance degree of each student according to the content conversion degree and the focus deviation degree of the current behavior of each student; acquisition of the weight of each element in the collaborative filtering behavior matrix in the collaborative filtering algorithm based on the current guidance degree of each student and each student in the behavior similar group of each student, to determine the intelligent push information of each student in the current. The acquisition method of the focus change degree is as follows: For any student, arrange the current behavior of the student and the neighboring behavior of the current behavior according to the time sequence to obtain a reference behavior sequence of the student; Take the length of the difference between the event vector of each behavior and the previous adjacent behavior in the reference behavior sequence as the change analysis value of the corresponding behavior; Take the normalized result of the mean value of the change analysis value as the focus change degree of the current behavior of the student.

2. The method for intelligent push of campus information based on a card according to claim 1, characterized in that, The acquisition method of the content conversion degree is as follows: For any student, arrange the event vector of the behavior of the student in the current time period according to the time sequence of the corresponding behavior to obtain a current behavior vector sequence of the student; Take the cosine similarity of the current behavior vector sequence of the student and the target student as the current similarity degree between the student and the target student for any target student in the behavior similar group of the student; Take the difference between the focus change degrees of the student and the target student as the current reference difference between the student and the target student; Take the product of the current similarity degree and the current reference difference as the current deviation degree between the student and the target student; Take the normalized result of the sum of the current deviation degrees between the student and each target student as the content conversion degree of the current behavior of the student.

3. The method as claimed in claim 1, wherein the method is characterized in that, The acquisition method of the focus deviation degree is as follows: For any student, according to the occurrence of the current behavior of the student in the current time period and the focus change degree of the current behavior of the student, the representative degree of the current behavior of the student is obtained; For any current similar student of the student, take the length of the vector difference corresponding to the basic information of the student and the current similar student as the basic information similarity degree between the student and the current similar student after negative correlation and normalization. a difference between the student and the current similar student in the representative degree of the current behavior of the current similar student is taken as a current behavior representative difference between the student and the current similar student; a product of the basis information similarity degree and the current behavior representative difference is taken as an attention deviation analysis value between the student and the current similar student; an average of the attention deviation analysis values between the student and all the current similar students of the student is taken as an attention shift degree of the current behavior of the student.

4. The campus information intelligent push method based on a smart card system as described in claim 3, characterized in that, The method for obtaining the representative degree comprises: a ratio between a number of times of occurrence of the current behavior of the student in a current time period and a total number of behaviors of the student in the current time period is taken as a first feature value; a product of the first feature value and a result of negative correlation and normalization of the attention shift degree of the current behavior of the student is taken as the representative degree of the current behavior of the student.

5. The campus information intelligent push method based on a smart card system as described in claim 1, characterized in that, The method for obtaining the current guidance degree comprises: a product of the content conversion degree of the current behavior of each student and the attention shift degree is taken as the current guidance degree of each student.

6. The method of claim 1, wherein the method further comprises: receiving a request for the information from the user; and transmitting the information to the user in response to the request. 5 The method for obtaining the behavior similar group comprises: a behavior similar group of each student in a current time period is obtained through a collaborative filtering algorithm according to behaviors of each student in the current time period.

7. The campus information intelligent push method based on a smart card system as described in claim 1, characterized in that, The method for obtaining the current similar student comprises: for any student, a result of normalization of a module length of an event vector difference between the current behavior of the student and the current behavior of each other student is taken as a current behavior similarity analysis value between the student and each other student; when the current behavior similarity analysis value is less than a preset behavior similarity threshold value, the corresponding student is taken as a current similar student of the student.

8. A campus information intelligent push system based on a card, characterized in that, The system comprises: a data acquisition module configured to acquire, in real time, an event vector of each behavior of each student and basis information of each student through a campus card of each student; an attention shift degree acquisition module configured to acquire an attention shift degree of a current behavior of each student according to a change of the event vector of the current behavior of each student and a neighborhood behavior of the current behavior of each student; a content conversion degree acquisition module configured to acquire a behavior similar group of each student according to behaviors of each student in a current time period, and acquire a content conversion degree of the current behavior of each student according to a behavior similarity in the current time period and a difference in the attention shift degree between each student and each student in the behavior similar group of the student; an attention deviation degree acquisition module configured to acquire a current similar student of each student according to a similarity of the event vector of the current behavior of each student and the current behavior of each other student, and acquire an attention deviation degree of the current behavior of each student according to a difference in the basis information between each student and each current similar student of the student and a difference in attention of the current behavior in the current time period; a data processing module configured to acquire a current guidance degree of each student according to the content conversion degree and the attention deviation degree of the current behavior of each student, acquire a weight of each element in a collaborative filtering behavior matrix in a collaborative filtering algorithm based on the current guidance degree of each student and each student in the behavior similar group of the student, and determine intelligent push information of the student at present. The method for obtaining the attention shift degree comprises: For any student, arranging the student's current behavior and the neighborhood behaviors of the current behavior according to time sequence to obtain a reference behavior sequence of the student; Taking the length of the event vector difference between each behavior in the reference behavior sequence and its previous adjacent behavior as a change analysis value of the corresponding behavior; Taking the result of normalizing the mean of the change analysis values as a degree of attention change of the student's current behavior.

9. A computer-readable storage medium comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor, when executing the computer program, implements the steps of the campus information intelligent push method based on the campus card in any one of claims 1-7.

Images