Method and electronic device for determining members of a learning discussion room

Abstract

The present application discloses a method for determining members of a learning discussion room and an electronic device, which relates to the field of data processing technology. The electronic device can determine the recommendation degree of the second learning object based on the similarity of the learning ability and learning progress of the second learning object and the first learning object, and automatically push the second learning object after the recommendation degree is greater than the recommendation degree threshold. In this way, the first learning object does not need to manually screen the appropriate second learning object, thereby improving the efficiency of the second learning object joining the learning discussion room where the first learning object is located.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method for determining members of a learning discussion room and an electronic device. Background Art

[0002] Students can discuss and study with other students online through online learning discussion rooms to improve their academic performance.

[0003] In the related art, the backend server of the online learning discussion room can create an online learning discussion room in response to a learning discussion room creation request sent by a client. The members of the online learning discussion room include the learning object to which the client belongs. Afterwards, the student to which the client belongs can select a suitable friend from the friend list and invite the friend to join the online learning discussion room.

[0004] However, the above method of inviting friends to join the online learning discussion room is less efficient. Summary of the invention

[0005] The present application provides a method for determining members of a learning discussion room and an electronic device, which can solve the problem of low efficiency of the related art method for inviting friends to join an online learning discussion room. The technical solution is as follows:

[0006] In one aspect, a method for determining members of a learning discussion room is provided, which is applied to an electronic device; the method comprises:

[0007] receiving a member recommendation request, wherein the member recommendation request is used to recommend a learning object for a first learning object to conduct a learning discussion with the first learning object in a learning discussion room;

[0008] In response to the member recommendation request, obtaining object data of the first learning object and each of the plurality of second learning objects, wherein the object data of each learning object includes: learning progress and learning ability of the learning object;

[0009] For each second learning object, determining a learning progress similarity based on the learning progress of the second learning object and the first learning object, and determining a learning ability similarity based on the learning ability of the second learning object and the first learning object;

[0010] Determining a recommendation degree of the second learning object based on the learning progress similarity and the learning ability similarity, wherein the recommendation degree is positively correlated with the learning progress similarity and is correlated with the learning ability similarity;

[0011] If the recommendation degree of the second learning object is greater than the recommendation degree threshold, recommendation information of the second learning object is pushed, where the recommendation information is used to indicate that the second learning object is a learning object that can join the learning discussion room.

[0012] In another aspect, an electronic device is provided, the electronic device comprising: a processor; the processor is configured to:

[0013] receiving a member recommendation request, wherein the member recommendation request is used to recommend a learning object for a first learning object to conduct a learning discussion with the first learning object in a learning discussion room;

[0014] In response to the member recommendation request, obtaining object data of the first learning object and each of the plurality of second learning objects, wherein the object data of each learning object includes: learning progress and learning ability of the learning object;

[0015] For each second learning object, determining a learning progress similarity based on the learning progress of the second learning object and the first learning object, and determining a learning ability similarity based on the learning ability of the second learning object and the first learning object;

[0016] Determining a recommendation degree of the second learning object based on the learning progress similarity and the learning ability similarity, wherein the recommendation degree is positively correlated with the learning progress similarity and is correlated with the learning ability similarity;

[0017] If the recommendation degree of the second learning object is greater than the recommendation degree threshold, recommendation information of the second learning object is pushed, where the recommendation information is used to indicate that the second learning object is a learning object that can join the learning discussion room.

[0018] On the other hand, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for determining members of a learning discussion room as described in the above aspects is implemented.

[0019] On the other hand, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is loaded and executed by a processor to implement the method for determining members of a learning discussion room as described in the above aspects.

[0020] On the other hand, a computer program product comprising instructions is provided. When the computer program product is executed on the computer, the computer is caused to execute the method for determining members of the learning discussion room described in the above aspects.

[0021] The beneficial effects of the technical solution provided by this application include at least:

[0022] The present application provides a method for determining members of a learning discussion room and an electronic device, the electronic device can determine the recommendation degree of the second learning object based on the similarity of the learning ability and learning progress of the second learning object and the first learning object, and automatically push the second learning object after the recommendation degree is greater than the recommendation degree threshold. In this way, the first learning object does not need to manually screen the appropriate second learning object, thereby improving the efficiency of the second learning object joining the learning discussion room where the first learning object is located.

[0023] Furthermore, since the recommendation degree is positively correlated with the learning progress similarity and the learning ability similarity is correlated, it can be determined that the learning progress of the pushed second learning object is equivalent to the learning progress of the first learning object, and the learning ability is equivalent to or stronger than the learning ability of the first learning object, thereby facilitating effective discussion and learning between the first learning object and the second learning object. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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 creative work.

[0025] Figure 1 It is a flow chart of a method for determining members of a learning discussion room provided in an embodiment of the present application;

[0026] Figure 2 It is a schematic diagram of an implementation environment involved in a method for determining members of a learning discussion room provided in an embodiment of the present application;

[0027] Figure 3 This is an interface diagram of a mobile terminal sending a member recommendation request to an electronic device provided by an embodiment of the present application;

[0028] Figure 4 is a flow chart of another method for determining members of a learning discussion room provided in an embodiment of the present application;

[0029] Figure 5 This is a schematic diagram of an interface for determining target invitation conditions provided in an embodiment of the present application;

[0030] Figure 6 This is a schematic diagram of an interface for determining target invitation conditions provided in an embodiment of the present application;

[0031] Figure 7This is a schematic diagram of an interface for adding a learning task provided in an embodiment of the present application;

[0032] Figure 8 This is a schematic diagram of a task punch-in interface provided in an embodiment of the present application;

[0033] Fig. 9 This is a schematic diagram of an interface for conducting discussion and learning in a learning and discussion room provided in an embodiment of the present application;

[0034] Fig.10 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0035] Fig.11 It is a software structure block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0037] The present application embodiment provides a method for determining members of a learning discussion room, which can be applied to an electronic device. Optionally, the electronic device can be a mobile terminal or a server. The mobile terminal can be a mobile phone, a tablet or a laptop. The server can be a single server, or a server cluster composed of several servers, or a cloud computing service center. Figure 1 , the method comprising:

[0038] Step 101: Receive a member recommendation request.

[0039] In the embodiment of the present application, if the electronic device is a server, see Figure 2 , the electronic device can establish a communication connection with the mobile terminal. The mobile terminal can be installed with a learning application, and the background server of the learning application can be the electronic device. Figure 3 , the application interface of the learning application may display an object recommendation control 01, and the first learning object (e.g., a student) or the parent of the first learning object may touch the object recommendation control 01. The mobile terminal may send a member recommendation request to the server in response to the touch operation on the object recommendation control 01. Accordingly, the electronic device may receive the member recommendation request.

[0040] The member recommendation request is used to indicate a learning object recommended to the first learning object for learning and discussing with the first learning object in the learning discussion room. The member recommendation request may carry the identifier of the first learning object. The identifier of the first learning object may be a user account logged in to the learning application. The learning discussion room may be created by the background server of the learning application in response to a creation request sent by the mobile terminal of the first learning object.

[0041] If the electronic device is a mobile terminal, after the first learning object or the parent of the first learning object touches the object recommendation control displayed by the learning application installed in the mobile terminal, the mobile terminal can receive a member recommendation request triggered by the touch operation on the object recommendation control.

[0042] Step 102: In response to a member recommendation request, obtain object data of a first learning object and each of a plurality of second learning objects.

[0043] The object data of each learning object includes: the learning progress and learning ability of the learning object.

[0044] In an embodiment of the present application, the learning progress of each learning object may include: the sub-progress of each subject in the learning object's study of multiple subjects. The teaching material of each subject may include: multiple course units, and each course unit in the multiple course units may include multiple chapters. The sub-progress of each learning object in learning any subject may at least be represented by the arrangement sequence number of the latest course unit of the teaching material of the subject learned by the learning object in the multiple course units. For example, the sub-progress may be represented by the arrangement sequence number of the latest course unit of the subject learned by the learning object in the multiple course units, and the arrangement sequence number of the latest chapter of the latest course unit learned in the multiple chapters. It can be understood that the multiple chapters are all chapters in the latest course unit.

[0045] The learning ability of each learning object can be represented by the total number of learning tasks completed by the learning object within the target time. Alternatively, the learning ability can be a numerical value determined based on the score of the target test questions completed by the learning object. For example, the numerical value can be the score.

[0046] Step 103: For each second learning object, determine the learning progress similarity based on the learning progress of the second learning object and the first learning object, and determine the learning ability similarity based on the learning ability of the second learning object and the first learning object.

[0047] In the embodiment of the present application, for each second learning object, the electronic device can use a similarity calculation formula to process the learning progress of the second learning object and the learning progress of the first learning object, and process the learning ability of the second learning object and the learning ability of the first learning object to obtain the learning progress similarity and learning ability similarity of the second learning object and the first learning object. The similarity calculation formula can be one of the following calculation formulas: Pearson similarity calculation formula, cosine similarity calculation formula.

[0048] Alternatively, for the similarity of learning progress, the electronic device may first determine the intersection of the multiple subjects studied by the second learning object and the multiple subjects studied by the first learning object, and the intersection includes at least one target subject. Then, for each target subject in the at least one target subject, the electronic device may determine the similarity of the sub-progress of the second learning object and the first learning object in learning the target subject. Afterwards, the electronic device may determine the similarity of the learning progress of the second learning object and the first learning object based on the mean of the similarities of the sub-progress of the at least one target subject. The learning progress similarity may be positively correlated with the mean.

[0049] For the learning ability similarity, the electronic device may first determine the total number of learning tasks completed by the second learning object within the target time, and the total number of learning tasks completed by the first learning object within the target time. Then, the electronic device may determine the difference between the total number of learning tasks completed by the second learning object within the target time and the total number of learning tasks completed by the first learning object within the target time. Afterwards, the electronic device may determine the learning ability similarity between the first learning object and the second learning object based on the difference, and the learning ability similarity is negatively correlated with the absolute value of the difference.

[0050] Step 104: Determine the recommendation degree of the second learning object based on the learning progress similarity and learning ability similarity between the second learning object and the first learning object.

[0051] Among them, the recommendation degree of the second learning object is positively correlated with the learning progress similarity and is related to the learning ability similarity. For example, the recommendation degree of the second learning object may be positively correlated with the learning ability similarity. Accordingly, the second learning object pushed by the electronic device is equivalent to the learning ability of the first learning object. Alternatively, the recommendation degree of the second learning object may be negatively correlated with the learning ability similarity, and the learning ability of the second learning object is stronger than the learning ability of the first learning object. Accordingly, the learning ability of the second learning object pushed by the electronic device is stronger than the learning ability of the first learning object.

[0052] Optionally, the electronic device may directly perform a weighted summation on the learning progress similarity and learning ability similarity between the first learning object and the second learning object, thereby obtaining the recommendation degree of the second learning object.

[0053] Step 105: If the recommendation degree of the second learning object is greater than the recommendation degree threshold, push the recommendation information of the second learning object.

[0054] The recommendation information is used to indicate that the second learning object is a learning object that can join the learning discussion room. The recommendation information of the second learning object may include: a user account of the second learning object's mobile terminal that logs into the learning application.

[0055] After obtaining the recommendation degree of the second learning object, the electronic device can compare the recommendation degree of the second learning object with the recommendation degree threshold. If the electronic device determines that the recommendation degree of the second learning object is greater than the recommendation degree threshold, the recommendation information of the second learning object can be pushed.

[0056] In an embodiment of the present application, if the electronic device is a server, the server may send recommendation information of a second learning object whose recommendation degree is greater than a recommendation degree threshold to a mobile terminal for display by the mobile terminal, and the mobile terminal is a mobile terminal that sends a member recommendation request. If the electronic device is a mobile terminal, the mobile terminal may directly display the recommendation information of the second learning object whose recommendation degree is higher than the recommendation degree threshold to push the recommendation information.

[0057] In summary, the embodiment of the present application provides a method for determining members of a learning discussion room, where the electronic device can determine the recommendation degree of the second learning object based on the similarity of the learning ability and learning progress of the second learning object and the first learning object, and automatically push the second learning object after the recommendation degree is greater than the recommendation degree threshold. In this way, the first learning object does not need to manually screen suitable second learning objects, thereby improving the efficiency of the second learning object joining the learning discussion room where the first learning object is located.

[0058] Furthermore, since the recommendation degree is positively correlated with the learning progress similarity and the learning ability similarity is correlated, it can be determined that the learning progress of the pushed second learning object is equivalent to the learning progress of the first learning object, and the learning ability is equivalent to or stronger than the learning ability of the first learning object, thereby facilitating effective discussion and learning between the first learning object and the second learning object.

[0059] Figure 4 This is a flowchart of another method for determining members of a learning discussion room provided in an embodiment of the present application.

[0060] See also Figure 4 , the method may include:

[0061] Step 201: Receive a member recommendation request.

[0062] In the embodiment of the present application, taking the electronic device as a server as an example, the process of the electronic device receiving a member recommendation request is exemplarily described:

[0063] See also Figure 2 , the electronic device can establish a communication connection with the mobile terminal. The mobile terminal can be installed with a learning application, and the background server of the learning application can be the electronic device. Figure 3 , the object recommendation control 01 can be displayed in the application interface of the learning application.

[0064] The first learning object or the parent of the first learning object can touch the object recommendation control 01. The mobile terminal can send a member recommendation request to the server in response to the touch operation on the object recommendation control 01. Accordingly, the electronic device can receive the member recommendation request.

[0065] The member recommendation request is used to indicate a learning object recommended to the first learning object for learning and discussing with the first learning object in the learning discussion room. The member recommendation request may carry the identifier of the first learning object. The identifier of the first learning object may be a user account logged in to the learning application. The learning discussion room may be created by the background server of the learning application in response to a creation request sent by the mobile terminal of the first learning object.

[0066] In an embodiment of the present application, the electronic device may also obtain the target capability condition that the learning capability of the second learning object that the first learning object wishes to recommend must meet, and push the second learning object whose learning capability meets the target capability condition. Optionally, if the electronic device is a server, the target capability condition may be determined by the mobile terminal and sent to the server. For example, the member recommendation request sent by the mobile terminal to the server may also include the target capability condition.

[0067] For example, the application interface of the learning application installed in the mobile terminal can also display capability condition selection controls corresponding to multiple candidate capability conditions, as well as description information of each capability condition selection control. Figure 3 , the multiple capability condition selection controls include: a first capability condition selection control 021 corresponding to a first candidate capability condition, and a second capability condition selection control 031 corresponding to a second candidate capability condition. The first candidate capability condition means that the learning capability of the second learning object is equivalent to the learning capability of the first learning object. The second candidate capability condition means that the learning capability of the second learning object is stronger than the learning capability of the first learning object.

[0068] from Figure 3It can also be seen that the first description information 022 of the first ability condition selection control 021 and the second description information 032 of the second ability condition selection control 031 can both be text. The first description information 022 can be: after the control is selected, the learning ability of the learning object recommended to you is equivalent to your learning ability. The second description information 032 can be: after the control is selected, the learning ability of the learning object recommended to you is stronger than your learning ability.

[0069] like Figure 3 As shown, the first learning object touches the first capability condition selection control 021, so the mobile terminal can determine the first candidate capability condition as the target capability condition in response to the first learning object's touch operation on the first capability condition selection control 021. Afterwards, the mobile terminal can send a member recommendation request including the target capability condition to the electronic device in response to the touch operation on the object recommendation control 01.

[0070] Step 202: In response to a member recommendation request, obtain object data of a first learning object and each of a plurality of second learning objects.

[0071] The object data of each learning object includes: the learning progress and learning ability of the learning object.

[0072] In an embodiment of the present application, the learning progress of each learning object may include: the sub-progress of the learning object in learning each of the multiple subjects. The teaching material of each subject may include: multiple course units, and each of the multiple course units may include multiple chapters. The sub-progress of each learning object in learning any subject may at least be represented by the arrangement sequence number of the latest course unit of the teaching material of the subject learned by the learning object in the multiple course units. For example, the sub-progress may be represented by the arrangement sequence number of the latest course unit of the subject learned by the learning object in the multiple course units, and the arrangement sequence number of the latest chapter of the latest course unit learned in the multiple chapters.

[0073] The learning ability of each learning object can be represented by the total number of learning tasks completed by the learning object within the target time. Alternatively, the learning ability can be a numerical value determined based on the score of the target test questions completed by the learning object. For example, the numerical value can be the score.

[0074] Step 203: For each second learning object, determine the learning progress similarity based on the learning progress of the second learning object and the first learning object, and determine the learning ability similarity based on the learning ability of the second learning object and the first learning object.

[0075] In an embodiment of the present application, for each second learning object, the electronic device can determine the intersection of multiple subjects learned by the first learning object and multiple subjects learned by the second learning object. The intersection includes: at least one target subject. Then, for each target subject in the at least one target subject, the electronic device can determine the similarity between the sub-progress of the second learning object and the first learning object in learning the target subject. Afterwards, the electronic device can determine the similarity of the learning progress of the second learning object and the first learning object based on the mean of the similarity of the sub-progress of at least one target subject. The learning progress similarity may be positively correlated with the mean.

[0076] If the sub-progress of the first learning object and the second learning object in learning the target subject is the same, the similarity of the sub-progress of the target subject is the target value. If the sub-progress of the first learning object and the second learning object in learning the target subject is different, the similarity of the sub-progress of the target subject is a value less than the target value. The target value may be pre-stored in the electronic device, for example, the target value may be 1.

[0077] Taking the sub-progress of each learning object in learning each subject as represented by the arrangement sequence number of the latest course unit learned by the learning object in multiple course units, and the arrangement sequence number of the latest chapter learned in the latest course unit in multiple chapters as an example, an exemplary description is given of the electronic device determining the similarity of the sub-progress of the second learning object and the first learning object in learning the target subject.

[0078] The electronic device can determine a first value based on the arrangement sequence number of the latest course unit of the target subject learned by the second learning object in multiple course units, and the similarities and differences between the arrangement sequence number of the latest course unit of the target subject learned by the first learning object in multiple course units, and determine a second value based on the arrangement sequence number of the latest chapter in the latest course unit learned by the second learning object in multiple chapters, and the similarities and differences between the arrangement sequence number of the latest chapter in the latest course unit learned by the first learning object in multiple chapters. Afterwards, the electronic device can perform a weighted sum of the first value and the second value to obtain the similarity of the sub-progress of the second learning object and the first learning object in learning the target subject. Among them, the weight of the course unit and the weight of the chapter can be pre-stored by the electronic device, and the sum of the weight of the course unit and the weight of the chapter can be a specified value.

[0079] Optionally, the first value and the second value may be one of the following values: 0 and 1. The specified value may be 1. For example, the weight of a course unit may be 0.3, and the weight of a chapter may be 0.7.

[0080] Assume that the total number of at least one target subject is I (I is an integer greater than or equal to 1), the sub-progress of the first learning object learning the i-th target subject among the I target subjects includes: i Units, and AD i Ad in the course unit i Chapter, the second learning object learns the BD i Units, and BD i Bd of the course units i Then, the similarity P between the second learning object and the first learning object in learning the i-th target subject is i The following formula can be satisfied:

[0081]

[0082] Among them, c1 is the weight of the course unit and c2 is the weight of the chapter.

[0083] Satisfies the following formula:

[0084]

[0085] Satisfies the following formula:

[0086]

[0087] According to the above formulas (1) to (3), if the specified value is 1, then if the electronic device determines that the second learning object has learned the latest course unit of the i-th target subject, the arrangement number BD in the multiple course units is i , and the sequence number AD of the latest course unit of the target subject learned by the first learning object among multiple course units i The same, and the latest chapter in the latest course unit learned by the second learning object is the sequence number Bd among multiple chapters i , and the sequence number of the latest chapter in the latest course unit learned by the first learning object among multiple chapters Ad i If the second learning object and the first learning object have the same sub-progress, then it can be determined that the similarity between the sub-progress of learning the target subject by the second learning object and the first learning object is 1.

[0088] If the electronic device determines that the second learning object has learned the latest course unit of the i-th target subject, the arrangement sequence number BD among the multiple course units i , and the sequence number AD of the latest course unit of the target subject learned by the first learning object among multiple course units iThe same as the last chapter in the last course unit learned by the second learning object is numbered Bd among the multiple chapters. i , and the sequence number of the latest chapter in the latest course unit learned by the first learning object among multiple chapters Ad i If they are different, it can be determined that the similarity between the sub-progress of the second learning object and the first learning object in learning the target subject is c1.

[0089] If the electronic device determines that the second learning object has learned the latest course unit of the i-th target subject, the arrangement sequence number BD among the multiple course units i , and the sequence number AD of the latest course unit of the target subject learned by the first learning object among multiple course units i Different from the second learning object, the latest chapter in the latest course unit learned by the second learning object is ranked in the multiple chapters. i , and the sequence number of the latest chapter in the latest course unit learned by the first learning object among multiple chapters Ad i If the sub-progress of the second learning object and the first learning object in learning the target subject are the same, it can be determined that the similarity between the sub-progress of the second learning object and the first learning object in learning the target subject is c2.

[0090] If the electronic device determines that the second learning object has learned the latest course unit of the i-th target subject, the arrangement sequence number BD among the multiple course units i , and the sequence number AD of the latest course unit of the target subject learned by the first learning object among multiple course units i Different from the second learning object, the latest chapter in the latest course unit learned by the second learning object is ranked in the multiple chapters. i , and the sequence number of the latest chapter in the latest course unit learned by the first learning object among multiple chapters Ad i If the sub-progress of the second learning object and the first learning object in learning the target subject are the same, it can be determined that the similarity between the sub-progress of the second learning object and the first learning object in learning the target subject is 0.

[0091] Furthermore, according to the above formula (1), it can be determined that the similarity between the learning progress of each second learning object and the first learning object can satisfy the following formula:

[0092]

[0093] In the embodiment of the present application, the learning ability of each object is the total number of learning tasks completed by the learning object within the target time. Based on this, the process of the electronic device determining the similarity of learning ability based on the learning ability of the second learning object and the first learning object may include:

[0094] The electronic device first determines the total number of learning tasks completed by the second learning object within the target time, and the difference between the total number of learning tasks completed by the first learning object within the target time. Then, the electronic device can determine the learning ability similarity between the second learning object and the first learning object based on the difference. The learning ability similarity is negatively correlated with the absolute value of the difference.

[0095] For example, the learning ability similarity S between the second learning object and the first learning object may satisfy the following formula:

[0096]

[0097] Wherein, Am is the total number of learning tasks completed by the first learning object within the target time, and Bm is the total number of learning tasks completed by the second learning object within the target time. M is the maximum value of the total number of learning tasks completed by multiple learning objects within the target time. The multiple learning objects include: a first learning object and multiple second learning objects.

[0098] In an embodiment of the present application, in the process of recommending a learning object for a first learning object to be used for learning and discussing with the first learning object, the electronic device may also consider the interest similarity and social similarity between the first learning object and each second learning object to ensure that the recommended second learning object is more reliable. Accordingly, the object data of each learning object may also include: information on the learning object's interest in multiple different types of learning tasks, and the number of interactions with other learning objects. In addition, the electronic device may also perform the following steps:

[0099] Step 204: Determine the interest similarity between the second learning object and the first learning object based on the interest information of the second learning object in the multiple different types of learning tasks and the interest information of the first learning object in the multiple different types of learning tasks.

[0100] The multiple different types of learning tasks may include at least two of the following types: reading learning tasks, sports learning tasks, and art learning tasks. For example, the multiple different types of learning tasks may include: reading learning tasks, sports learning tasks, and art learning tasks.

[0101] The information of interest of each learning object in a reading learning task may include: the interest level of the learning object in books of different book types and / or the interest level of the learning object in different book authors. The information of interest of each learning object in a sports learning task may include: the interest level of the learning object in sports of different sports types. The information of interest of each learning object in an art learning task may include: the interest level of the learning object in art activities of different art types.

[0102] The learning object's interest level in books of any book type (or any book author, or sports of any sport type, or artistic activities of any art type) can be represented by a numerical value, and the numerical value is positively correlated with the learning object's interest level in books of any book type (or any book author, or sports of any sport type, or artistic activities of any art type).

[0103] In an embodiment of the present application, the book type may be one of the following types: literature, science fiction, suspense, finance, philosophy, economics, sports, geography, etc. The book author may be one of a plurality of different book authors. Accordingly, the interest information of each learning object in a reading learning task may be represented by a first eigenvector and / or a second eigenvector. Among them, the dimension (also referred to as the length) of the first eigenvector may be equal to the total number of a plurality of different book types, and each eigenvalue in the first eigenvector may represent the degree of interest of the learning object in a book of a book type. The dimension of the second eigenvector may be equal to the total number of a plurality of different book authors, and each eigenvalue in the second eigenvector may represent the degree of interest of the learning object in a book author.

[0104] The type of sports can be one of the following types: rope skipping, badminton, table tennis, gymnastics, basketball, swimming, etc. Correspondingly, the interest information of each learning object in the sports learning task can be represented by a third eigenvector. The dimension of the third eigenvector can be equal to the total number of multiple different sports types, and each eigenvalue in the third eigenvector can represent the interest degree of the learning object in a sports type.

[0105] The art type of the art activity can be one of the following types: dance, drama, calligraphy, seal carving, song, etc. Correspondingly, the interest information of each learning object in the art learning task can be represented by a fourth eigenvector. The dimension of the fourth eigenvector can be equal to the total number of multiple different art types, and each eigenvalue in the fourth eigenvector can represent the interest degree of the learning object in an art activity of an art type.

[0106] In the embodiment of the present application, for each learning object, the electronic device can obtain multiple learning plans for the learning object, each learning plan can include at least one learning task, and each learning task has a task name that can reflect the type of the learning task. For example, the task name of a certain learning task is: read "Journey to the West" for 30 minutes, or swim for 30 minutes, or practice dancing for 30 minutes.

[0107] Afterwards, the electronic device can obtain the learning object's interest level in different types of books, interest level in different book authors, interest level in different types of sports, and interest level in different types of art activities based on the task name of each learning task in multiple learning tasks, thereby obtaining the learning object's interest information in different types of learning tasks.

[0108] The embodiment of the present application takes determining the interest information of the learning object in a sports learning task as an example to exemplarily illustrate how an electronic device determines the interest information based on the task names of multiple learning tasks.

[0109] For each of the multiple learning tasks, the electronic device can analyze the task name of the learning task to obtain the type of the learning task. Then, for each sports learning task, the electronic device can determine the sport type corresponding to the sports learning task. Afterwards, the electronic device can count the number of sports learning tasks whose sport type is the target sport type, and use the number to characterize the learning subject's interest in the sport of the target sport type, thereby obtaining a third feature vector. Among them, the target sport type is any one of a plurality of different sport types.

[0110] The electronic device determines the learning object's interest information for reading learning tasks and art learning tasks, and can refer to the implementation process of determining the learning object's interest information for sports learning tasks, which will not be repeated in the embodiments of the present application.

[0111] It is understandable that the aforementioned multiple learning tasks of the learning object may all be learning tasks that the learning object has completed, so that the accuracy of the determined learning object's interest information for different types of learning tasks can be ensured to be high.

[0112] It should be noted that before determining the first eigenvector, the mobile terminal needs to set the arrangement order of multiple book types; before determining the second eigenvector, the mobile terminal needs to set the arrangement order of multiple book authors; before determining the third eigenvector, the mobile terminal needs to set the arrangement order of multiple sports types; before determining the fourth eigenvector, the mobile terminal needs to set the arrangement order of multiple art types.

[0113] Assume that the multiple different types of learning tasks include: reading learning tasks, sports learning tasks and art learning tasks, and the learning object's interest information on the reading learning tasks is represented by the first feature vector and the second feature vector of the learning object. Then, after obtaining the first feature vector to the second feature vector of each learning object, in an optional implementation, for each second learning object, the electronic device can directly use a similarity calculation algorithm to process the first feature vector to the fourth feature vector of the second learning object and the first feature vector to the fourth feature vector of the first learning object, so as to obtain the interest similarity between the second learning object and the first learning object.

[0114] In another optional implementation, for each feature vector in the multiple feature vectors of each second learning object, the electronic device can determine the feature vector and a corresponding feature vector from the multiple feature vectors of the first learning object, and count the number of target feature value pairs from the corresponding two feature vectors. Wherein, the two eigenvalues ​​in the target feature value pair are equal and not 0, one of the two eigenvalues ​​is one of the two feature vectors, and the other eigenvalue is another eigenvalue in the two feature vectors. And the arrangement order of the one eigenvalue in the one feature vector is equal to the arrangement order of the other eigenvalue in the other feature vector.

[0115] Afterwards, the electronic device may determine the interest similarity between the second learning object and the first learning object based on the sum of the number of target feature value pairs of the plurality of feature vectors of the second learning object and the corresponding feature vectors in the first learning object. The interest similarity is positively correlated with the sum.

[0116] For example, the interest similarity may be positively correlated with a first ratio, which is a ratio of the sum value to a reference value. The reference value may be the total number of multiple feature values ​​included in multiple feature vectors of the learning object. Alternatively, the reference value may be the total number of multiple candidate feature value pairs in multiple feature vectors of the first learning object and the second learning object.

[0117] Among them, both eigenvalues ​​in each candidate eigenvalue pair are not 0, one of the two eigenvalues ​​is located in the eigenvector of the first learning object, and the other eigenvalue is located in the corresponding eigenvector of the second learning object. And the arrangement order of the one eigenvalue in the eigenvector where it is located is the same as the arrangement order of the other eigenvalue in the eigenvector where it is located.

[0118] Optionally, the object data of each learning object may also include the learning information of the learning object. Before determining the interest similarity between the second learning object and the first learning object, for each of the plurality of second learning objects and the first learning object, the electronic device may also extract a plurality of different interest keywords of the learning object from the learning information of the learning object recorded in the learning application. Furthermore, for each interest keyword, the electronic device may determine the criticality of the interest keyword in the learning information of the learning object based on the word frequency and inverse document frequency of the interest keyword.

[0119] Then, for each second learning object, the electronic device can determine the intersection of multiple interest keywords of the second learning object and multiple interest keywords of the first learning object, and the intersection can include at least one target keyword. In addition, the electronic device can determine the similarity of interest keywords between the second learning object and the first learning object based on the criticality of at least one target keyword of the second learning object and the criticality of at least one target keyword of the first learning object, and determine the similarity of interest information between the second learning object and the first learning object based on the interest information of the second learning object for multiple different types of learning tasks and the interest information of the first learning object for multiple different types of learning tasks. Afterwards, the electronic device can determine the similarity of interest between the second learning object and the first learning object based on the interest keyword similarity and the interest information similarity.

[0120] The interest similarity is positively correlated with the interest keyword similarity and the interest information similarity. The learning information of the learning object may include at least one of the following information: the learning plan of the learning object, and the discussion information between the learning object and other learning objects. For example, the learning information of the learning object may include: the learning plan of the learning object, and the discussion information between the learning object and other learning objects.

[0121] Since the electronic device also considers the similarity of interest keywords between the second learning object and the first learning object during the process of determining the interest similarity between the second learning object and the first learning object, it can ensure that the accuracy of determining the interest similarity is high.

[0122] Optionally, the electronic device may perform a weighted summation of the interest keyword similarity and the interest information similarity between the second learning object and the first learning object to obtain the interest similarity between the second learning object and the first learning object. The sum of the weight of the interest keyword similarity and the weight of the interest information similarity may be 1. For example, the weight of the interest keyword similarity and the weight of the interest information similarity may both be 0.5.

[0123] In an embodiment of the present application, if the number of at least one target keyword is multiple, the electronic device needs to set the ranking of multiple target keywords before determining the similarity of the interest keywords of the second learning object and the first learning object. Then, the electronic device can obtain the fifth feature vector based on the ranking and the criticality of the multiple target keywords of the first learning object, and obtain the sixth feature vector based on the ranking and the criticality of the multiple target keywords of the second learning object. Afterwards, the electronic device can use a similarity calculation algorithm to process the fifth feature vector and the sixth feature vector to obtain the similarity of the interest keywords of the second learning object and the first learning object. Among them, the dimensions of the fifth feature vector and the sixth feature vector are both equal to the total number of the multiple target keywords.

[0124] Optionally, the similarity calculation algorithm may be one of the following algorithms: Pearson similarity calculation algorithm and cosine similarity calculation algorithm. For example, if the similarity calculation algorithm is a chord similarity calculation algorithm, the similarity W of the interest keywords between the second learning object and the first learning object may satisfy the following formula:

[0125]

[0126] In formula (6), u j is the criticality of the jth target keyword among the J target keywords of the first learning object. J is an integer greater than or equal to 1, and j is an integer greater than or equal to 1 and less than or equal to J. j is the criticality of the jth target keyword among the J target keywords of the second learning object.

[0127] Optionally, the electronic device may process the learning information of each learning object using a term frequency-inverse document frequency (TF-IDF) algorithm to obtain the term frequency and inverse document frequency of each interest keyword of each learning object, and obtain the criticality in the learning information of the learning object based on the term frequency and inverse document frequency. The term frequency f of any interest keyword among the multiple interest keywords of each learning object may satisfy the following formula:

[0128]

[0129] Among them, r is the number of times any interest keyword appears in the learning information of the learning object, and R is the sum of the number of times multiple different interest keywords of the learning object appear in the learning information of the learning object, that is, the total number of all interest keywords extracted from the learning information of the learning object.

[0130] The inverse document frequency g of any interest keyword among multiple interest keywords of each learning object can satisfy the following formula:

[0131]

[0132] Wherein, log is a logarithmic function, and T is the total number of all interest keywords extracted by the electronic device from the learning information of all learning objects.

[0133] Step 205: Determine the social similarity between the first learning object and the second learning object based on the number of interactions between the first learning object and the second learning object.

[0134] The social similarity is positively correlated with the number of interactions. That is, the more interactions the first learning object has with the second learning object, the higher the social similarity between the first learning object and the second learning object. The fewer interactions the first learning object has with the second learning object, the lower the social similarity between the first learning object and the second learning object.

[0135] Optionally, the electronic device may determine the interaction heat between the first learning object and the second learning object based on the number of interactions between the first learning object and the second learning object and the sum of the number of interactions between the first learning object and each of the plurality of third learning objects. Thereafter, the electronic device may determine the social similarity between the second learning object and the first learning object based on the interaction heat.

[0136] The interaction heat may be positively correlated with the number of interactions and may be negatively correlated with the sum value. The social similarity may be positively correlated with the interaction heat. Each third learning object is a friend of the first learning object, that is, the user account logged in to the learning application of each third learning object is a friend account of the user account of the first learning object.

[0137] Optionally, the interaction heat H between the first learning object and the second learning object may satisfy the following formula:

[0138]

[0139] Among them, h(A,B) is the number of interactions between the first learning object and the second learning object, h total is the sum of the number of interactions between the first learning object and each third learning object.

[0140] In an embodiment of the present application, the number of interactions between the first learning object and the second learning object (or the third learning object) may refer to: the number of interactions between the first learning object and the second learning object (or the third learning object) within a reference period before receiving the member recommendation request. The reference period may refer to: a period closest to the moment when the member recommendation request is received and having a reference duration. The reference duration may be pre-stored by the electronic device. For example, the reference period may be the last two months. In this way, the accuracy of the determined interaction heat between the second learning object and the first learning object can be ensured to be high, thereby ensuring the accuracy of the determined social similarity between the second learning object and the first learning object to be high.

[0141] Optionally, in the process of determining the social similarity between the second learning object and the first learning object, the electronic device may also consider the social relationship similarity between the second learning object and the first learning object to ensure that the accuracy of the determined social similarity between the second learning object and the first learning object is high. Based on this, the electronic device can determine the social similarity between the second learning object and the first learning object based on the interaction heat between the second learning object and the first learning object, as well as the social relationship similarity. The social similarity is also positively correlated with the social relationship similarity.

[0142] In an embodiment of the present application, the electronic device may obtain multiple first friend accounts of the user account of the first learning object, and multiple second friend accounts of the user account of the second learning object. Then, the electronic device may determine the first total number of at least one friend account included in the intersection of the multiple first friend accounts and the multiple second friend accounts, and determine the second total number of multiple friend accounts included in the union of the multiple first friend accounts and the multiple second friend accounts. Afterwards, the electronic device may determine the social relationship similarity between the second learning object and the first learning object based on the second ratio of the first total number to the second total number. The social relationship similarity is positively correlated with the second ratio.

[0143] It can be seen that the electronic device can determine the similarity of the social relationship between the second learning object and the first learning object according to the number of common friends of the first learning object and the second learning object.

[0144] Optionally, before determining the similarity of the social relationship between the second learning object and the first learning object, the electronic device may also obtain multiple first fan accounts of the user account of the first learning object, and multiple second fan accounts of the user account of the second object, and determine a third total number of at least one fan account included in the intersection of the multiple first fan accounts and the multiple second fan accounts, and a fourth total number of multiple fan accounts included in the union of the multiple first fan accounts and the multiple second fan accounts. Then, the electronic device may determine a third ratio of the third total number to the fourth total number. Thereafter, the electronic device may determine the similarity of the social relationship between the second learning object and the first learning object based on the second ratio and the third ratio. The social relationship similarity is also positively correlated with the third ratio.

[0145] It can be understood that the friend accounts of each learning object's user account refer to user accounts that are different from the user account and follow each other. The fan accounts of each learning object's user account refer to user accounts that follow the user account but are not followed by the user account.

[0146] According to the above description, when the electronic device determines the social relationship similarity between the second learning object and the first learning object, it can also consider the number of fans of the learning object, thereby ensuring that the accuracy of determining the social relationship similarity is high.

[0147] Optionally, the electronic device may perform a weighted summation of the second ratio and the third ratio to obtain the social relationship similarity between the second learning object and the first learning object. The weight of the second ratio and the weight of the third ratio may be pre-stored by the electronic device. And the sum of the weight of the second ratio and the weight of the third ratio may be a specified value. For example, the weight of the second ratio may be 0.6, and the weight of the third ratio may be 0.4.

[0148] For example, the social relationship similarity N between the second learning object and the first learning object may satisfy the following formula:

[0149]

[0150] Wherein, n1 is the weight of the second ratio, x is the first total number of at least one friend account included in the intersection of the plurality of first friend accounts and the plurality of second friend accounts, X is the second total number of multiple friend accounts included in the union of the plurality of first friend accounts and the plurality of second friend accounts. n2 is the weight of the third ratio, y is the third total number of at least one fan account included in the intersection of the plurality of first fan accounts and the plurality of second fan accounts, and Y is the fourth total number of multiple fan accounts included in the union of the plurality of first fan accounts and the plurality of second fan accounts.

[0151] Step 206: Determine the recommendation degree of the second learning object based on the learning progress similarity, the learning ability similarity, the interest similarity and the social similarity.

[0152] The recommendation degree is positively correlated with the learning progress similarity, interest similarity and social similarity. And is related to the learning ability similarity. Since the electronic device comprehensively considers the learning progress similarity, learning ability similarity, interest similarity and social similarity between the second learning object and the first learning object when determining the recommendation degree of the second learning object, it can ensure that the recommendation degree of the determined second learning object is high.

[0153] In the embodiment of the present application, if the target ability condition of the learning ability of the recommended second learning object is: equivalent to the learning ability of the first learning object, then the recommendation degree of the second learning object is positively correlated with the similarity of the learning ability. If the target ability condition of the learning ability of the recommended second learning object is: the learning ability is stronger than the learning ability of the first learning object, then the recommendation degree of the second learning object is negatively correlated with the similarity of the learning ability.

[0154] Optionally, if the recommendation degree of the second learning object is positively correlated with the learning ability similarity, the electronic device can perform a weighted summation of the learning progress similarity, learning ability similarity, interest similarity and social similarity between the second learning object and the first learning object to obtain the recommendation degree of the second learning object. Among them, the weight of the learning progress similarity, the weight of the learning ability similarity, the weight of the interest similarity and the weight of the social similarity can all be pre-stored in the electronic device. And the sum of the weight of the learning progress similarity, the weight of the learning ability similarity, the weight of the interest similarity and the weight of the social similarity can be a specified value. For example, the specified value can be 1.

[0155] If the recommendation degree of the second learning object is negatively correlated with the learning ability similarity, the electronic device can first compare the learning ability of the second learning object with the learning ability of the first learning object. If the electronic device determines that the learning ability of the second learning object is weaker than that of the first learning object, it can directly determine that the second learning object does not meet the recommendation condition. If the electronic device determines that the learning ability of the second learning object is stronger than that of the first learning object, it can first determine the target difference based on the similarity of the learning ability of the second learning object and the first learning object. The target difference is negatively correlated with the learning ability similarity. Afterwards, the electronic device can perform a weighted summation of the learning progress similarity, interest similarity, social similarity and target difference between the second learning object and the first learning object to obtain the recommendation degree of the second learning object.

[0156] Among them, the target difference E can satisfy the following formula:

[0157] E=1-S Formula (11)

[0158] Optionally, the electronic device may also obtain attribute information of each learning object, and the attribute information may at least include: the area where the learning object is located. For example, the attribute information may include: the gender, age, grade, class and area of ​​the learning object.

[0159] The electronic device may also determine the distance between the second learning object and the first learning object according to the area where the second learning object is located and the area where the first learning object is located. Afterwards, the electronic device may determine the recommendation degree of the second learning object according to the learning progress similarity, learning ability similarity, interest similarity, social similarity and distance between the second learning object and the first learning object. The recommendation degree may also be negatively correlated with the distance.

[0160] Step 207: If the recommendation degree of the second learning object is greater than the recommendation degree threshold, push the recommendation information of the second learning object.

[0161] The recommendation information is used to indicate that the second learning object is a learning object that can join the learning discussion room. The recommendation information of the second learning object may include: a user account of the second learning object's mobile terminal that logs into the learning application.

[0162] After obtaining the recommendation degree of the second learning object, the electronic device may compare the recommendation degree of the second learning object with the recommendation degree threshold. If the electronic device determines that the recommendation degree of the second learning object is greater than the recommendation degree threshold, the recommendation information of the second learning object may be pushed. The recommendation degree threshold may be pre-stored by the electronic device.

[0163] In an embodiment of the present application, if the electronic device is a server, the server may send recommendation information of a second learning object whose recommendation degree is greater than a recommendation degree threshold to a mobile terminal, and the mobile terminal is a mobile terminal that sends a member recommendation request.

[0164] It is understandable that if the number of second learning objects determined by the electronic device to have a recommendation degree greater than the recommendation degree threshold is multiple, the electronic device can push the recommendation information of the multiple second learning objects in the form of a list. The recommendation information of the multiple second learning objects recorded in the list can be arranged in descending order according to the recommendation degree.

[0165] In an embodiment of the present application, after the mobile terminal of the first learning object obtains the recommendation information of the second learning object whose recommendation degree is higher than the recommendation degree threshold, the recommendation information of the second learning object can be displayed. Afterwards, the mobile terminal of the first learning object can send an invitation request to the mobile terminal of the second learning object in response to the touch operation on the recommendation information, so as to invite the second learning object to join the learning discussion room and discuss learning with the first learning object. The members of the learning discussion room include the first learning object.

[0166] Alternatively, after the mobile terminal of the first learning object obtains the recommendation information of the second learning object whose recommendation degree is higher than the recommendation degree threshold, it can automatically send an invitation request to the mobile terminal of the second learning object based on the recommendation information to invite the second learning object to join the learning discussion room and discuss learning with the first learning object. In this way, on the one hand, the efficiency of inviting the second learning object to join the learning discussion room can be improved, and on the other hand, the operation of the first learning object is simplified, thereby improving the user experience.

[0167] Optionally, in the process of automatically sending the invitation request to the mobile terminal of the second learning object, the mobile terminal of the first learning object may also display the recommendation information of the second learning object.

[0168] Optionally, the mobile terminal of the first learning object may automatically send an invitation request to the mobile terminal of the second learning object that meets the target invitation condition. The target invitation condition may be determined by the mobile terminal of the first learning object from a plurality of candidate invitation conditions. The plurality of candidate invitation conditions may include: the second learning object and the first learning object are in the same school; the second learning object and the first learning object are in the same grade.

[0169] For example, see Figure 5 After the mobile terminal of the first learning object obtains the recommendation information of the second learning object whose recommendation degree is higher than the recommendation degree threshold, it can display the first invitation condition selection control 041 corresponding to the first alternative invitation condition (the second learning object and the first learning object are in the same school), the second invitation condition selection control 051 corresponding to the second alternative invitation condition (the second learning object and the first learning object are in the same grade), the description information 042 of the first invitation condition selection control 041, the description information 052 of the second invitation condition selection control 051 and the invitation control 06.

[0170] from Figure 5 It can also be seen that the description information 042 of the first invitation condition selection control 041 can be text: It can be: After the selection control is selected, the second learning object in the same school as you is automatically invited to discuss and learn with you. The description information 052 of the second invitation condition selection control 051 can be text: After the selection control is selected, the second learning object in the same grade as you is automatically invited to discuss and learn with you.

[0171] See also Figure 5 If the first learning object does not touch the first invitation condition selection control 041 and the second invitation condition selection control 051, but directly touches the invitation control 06, the mobile terminal can respond to the touch operation on the invitation control 06 and directly send an invitation request to the mobile terminals of all second learning objects whose recommendation degree is greater than the recommendation degree threshold.

[0172] See also Figure 6 , if the first learning object touches the first invitation condition selection control 041, the mobile terminal can determine the target invitation condition as: the second learning object and the first learning object are in the same school in response to the touch operation on the first invitation condition selection control 041. Afterwards, when the mobile terminal receives the touch operation on the invitation control 06, it can filter out the second learning object that is in the same school as the first learning object from all the second learning objects whose recommendation degree is greater than the recommendation degree threshold, and automatically send an invitation request to the mobile terminal of the second learning object that is in the same school as the first learning object.

[0173] In the embodiment of the present application, the learning task of each learning object can be created for the learning object by the parent or teacher of the learning object. Figure 7 , the creation process of learning tasks is illustrated as follows:

[0174] See also Figure 7 The task adding interface of the learning application installed in the mobile terminal may display a task input control 071, a task start execution time setting control 072, an end execution time setting control 073, a task execution reminder time setting control 074, multiple quick task controls 075, and an addition completion control 076. Each quick task control 075 displays the word "a task".

[0175] The mobile terminal may acquire a learning task in response to an input operation in the task input control 071. Alternatively, the mobile terminal may determine a task displayed in any of the multiple quick task controls 075 as a learning task in response to a touch operation on the quick task control 075.

[0176] Then, the mobile terminal can respond to the touch operation of the control 072 for setting the start execution time of the task, the control 073 for setting the end execution time, and the control 074 for setting the reminder time of the task in sequence, and determine the start execution time, end execution time, and reminder time of the learning task. After that, the mobile terminal can respond to the touch operation of the add completion control 076, and then generate the learning task to be executed by the learning object.

[0177] In addition, from Figure 7 It can be seen that the mobile terminal can also display the start execution time, the end execution time, and the default time of the reminder time, which is 00:00.

[0178] In the embodiment of the present application, after completing any learning task, the learning subject can check in for the task through the mobile terminal. Figure 8 , explain the process of learning objects to check in for tasks:

[0179] The learning application can display a task check-in interface, which includes: an input control 081 for the learning task, a photo control 082, a delete control 083, and a check-in completion control 084. After the learning subject completes a learning task, the learning task can be input into the input control 081. The mobile terminal can obtain the learning task in response to a touch operation on the input control 081. Then, the mobile terminal can enable the camera in response to a touch operation on the photo control 082. At this time, the learning subject can control the mobile terminal to capture the completion result of the learning task and obtain a result image. In addition, the mobile terminal can also display the result image.

[0180] Afterwards, the mobile terminal can record the completion result of the learning task in response to the touch operation on the punch-in completion control 084. If the learning object needs to delete the result image, the learning object can also touch the result image to select the result image. Afterwards, the learning object can touch the delete control 083, and the mobile terminal can delete the result image in response to the touch operation on the delete control 083.

[0181] In the embodiment of the present application, each learning object in the same learning discussion room can discuss and study not only through text messages, but also through video calls. And during the process of each learning object discussing and studying through video calls, the mobile terminal can also display the text messages of each learning object.

[0182] For example, see Fig. 9 When the various learning objects in the mathematics learning discussion room are discussing and learning through video calls and text messages, the mobile terminal of each learning object participating in the discussion and learning can display the video images collected by the mobile terminal of each learning object participating in the discussion and learning, the text messages of each learning object, the text message input control 09, the voice input control 10, and the exit control 11. In addition, while displaying the text messages, the mobile terminal can also display the announcement of the learning discussion room and the reminder messages of the members of the learning discussion room to join.

[0183] If the learning object needs to discuss and study through text messages, the input operation can be performed in the text message input control 09. Accordingly, the mobile terminal can obtain the text message input by the learning object in response to the input operation. If the learning object needs to discuss and study through a video call, the voice input control 10 can be touched. Accordingly, the mobile terminal can respond to the voice input control 10 and enable the microphone to collect the voice of the learning object. If the learning object needs to exit the current video call, the exit control 11 can be touched. Accordingly, the mobile terminal of the learning object can respond to the touch operation on the exit control 11 to exit the current video call.

[0184] It should be noted that the order of the steps of the method for determining members of the learning discussion room provided in the embodiment of the present application can be appropriately adjusted, and the steps can also be increased or decreased accordingly according to the situation. For example, step 205 can also be deleted according to the situation. Any technician familiar with the technical field can easily think of a method of variation within the technical scope disclosed in this application, which should be included in the protection scope of this application, so it will not be repeated.

[0185] In summary, the embodiment of the present application provides a method for determining members of a learning discussion room, where the electronic device can determine the recommendation degree of the second learning object based on the similarity of the learning ability and learning progress of the second learning object and the first learning object, and automatically push the second learning object after the recommendation degree is greater than the recommendation degree threshold. In this way, the efficiency of the second learning object joining the learning discussion room where the first learning object is located is improved.

[0186] Furthermore, since the recommendation degree is positively correlated with the learning progress similarity and the learning ability similarity is correlated, it can be determined that the learning progress of the pushed second learning object is equivalent to the learning progress of the first learning object, and the learning ability is equivalent to or stronger than the learning ability of the first learning object, thereby facilitating effective discussion and learning between the first learning object and the second learning object.

[0187] The present application embodiment also provides an electronic device, which can be used to execute the member determination method of the learning discussion room provided by the above method embodiment. Fig.10 The electronic device 110 may include a processor 1101, wherein the processor 1101 is configured to:

[0188] receiving a member recommendation request, the member recommendation request being used to indicate a recommendation for a first learning object to be used for conducting a learning discussion with the first learning object in a learning discussion room;

[0189] In response to a member recommendation request, obtaining object data of a first learning object and each of a plurality of second learning objects, wherein the object data of each learning object includes: learning progress and learning ability of the learning object;

[0190] For each second learning object, determining a learning progress similarity based on the learning progress of the second learning object and the first learning object, and determining a learning ability similarity based on the learning ability of the second learning object and the first learning object;

[0191] Based on the learning progress similarity and the learning ability similarity, determining the recommendation degree of the second learning object, wherein the recommendation degree is positively correlated with the learning progress similarity and is correlated with the learning ability similarity;

[0192] If the recommendation degree of the second learning object is greater than the recommendation degree threshold, the second learning object recommendation information is pushed, and the recommendation information is used to indicate that the second learning object is a learning object that can join the learning discussion room.

[0193] Optionally, the learning progress of the learning object includes: sub-progress of each subject in multiple subjects. The processor 1101 can be used to:

[0194] Determine at least one target subject, where the at least one target subject is the intersection of a plurality of subjects studied by the first learning object and a plurality of subjects studied by the second learning object;

[0195] For each target subject in the at least one target subject, determining a similarity between the second learning object and the sub-progress of the first learning object in learning the target subject;

[0196] Determine the similarity of the learning progress of the second learning object and the first learning object according to the average of the similarities of the sub-progresses of at least one target subject;

[0197] Among them, if the sub-progress of the target subject studied by the first learning object and the second learning object is the same, the similarity of the sub-progress of the target subject is the target value; if the sub-progress of the target subject studied by the first learning object and the second learning object is different, the similarity of the sub-progress of the target subject is a value less than the target value.

[0198] Optionally, the total number of at least one target subject is I, where I is an integer greater than or equal to 1. Each target subject includes multiple course units, and each course unit includes multiple chapters. The sub-progress of the first learning object learning the i-th target subject among the i-th target subjects includes: i Units, and AD i Ad in the course unit i The sub-progress of the first learning object learning the i-th target subject includes: iUnits, and BD i Bd of the course units i The learning progress of the second learning object is similar to that of the first learning object to the degree P that satisfies:

[0199]

[0200] satisfy:

[0201]

[0202] satisfy:

[0203]

[0204] Among them, c1 is the weight of the course unit and c2 is the weight of the chapter.

[0205] Optionally, the learning ability of each object is represented by the total number of learning tasks completed within the target time. The processor 1101 can be used to:

[0206] Determine the difference between the total number of learning tasks completed by the second learning object within the target time and the total number of learning tasks completed by the first learning object within the target time;

[0207] The learning ability similarity is determined based on the difference, and the learning ability similarity is negatively correlated with the absolute value of the difference.

[0208] Optionally, the recommendation degree is positively correlated with the learning ability similarity;

[0209] Alternatively, the learning ability of the second learning object is stronger than that of the first learning object, and the recommendation degree is negatively correlated with the similarity of learning ability.

[0210] Optionally, the object data of each learning object also includes: information about the learning object's interest in multiple different types of learning tasks. The processor 1101 may also be used to:

[0211] For each second learning object, based on the second learning object's interest information for a plurality of different types of learning tasks and the first learning object's interest information for a plurality of different types of learning tasks, determine the interest similarity between the second learning object and the first learning object;

[0212] Based on the learning progress similarity and the learning ability similarity, determining the recommendation degree of the second learning object includes:

[0213] Based on the learning progress similarity, the learning ability similarity and the interest similarity, the recommendation degree of the second learning object is determined, and the recommendation degree is also positively correlated with the interest similarity.

[0214] Optionally, the object data of each learning object also includes: the number of interactions between the learning object and other learning objects. The processor 1101 may also be used to:

[0215] Based on the number of interactions between the first learning object and the second learning object, determining the social similarity between the first learning object and the second learning object, where the social similarity is positively correlated with the number of interactions;

[0216] Based on the learning progress similarity, learning ability similarity and interest similarity, the recommendation degree of the second learning object is determined, including:

[0217] Based on the learning progress similarity, learning ability similarity, interest similarity and social similarity, the recommendation degree of the second learning object is determined, and the recommendation degree is also positively correlated with the social similarity.

[0218] Optionally, the processor 1101 may be configured to:

[0219] The learning progress similarity, learning ability similarity, interest similarity and social similarity are weightedly summed to obtain the recommendation degree of the second learning object.

[0220] In summary, the embodiment of the present application provides an electronic device that can determine the recommendation degree of the second learning object based on the similarity of the learning ability and learning progress of the second learning object and the first learning object, and automatically push the second learning object after the recommendation degree is greater than the recommendation degree threshold. In this way, the first learning object does not need to manually screen the appropriate second learning object, thereby improving the efficiency of the second learning object joining the learning discussion room where the first learning object is located.

[0221] Furthermore, since the recommendation degree is positively correlated with the learning progress similarity and the learning ability similarity is correlated, it can be determined that the learning progress of the pushed second learning object is equivalent to the learning progress of the first learning object, and the learning ability is equivalent to or stronger than the learning ability of the first learning object, thereby facilitating effective discussion and learning between the first learning object and the second learning object.

[0222] like Fig.10 As shown, the electronic device 110 provided in the embodiment of the present application may also include: a display unit 130, a radio frequency (RF) circuit 150, an audio circuit 160, a wireless fidelity (Wi-Fi) module 170, a Bluetooth module 180, a power supply 190 and a camera 121 and other components.

[0223] Among them, the camera 121 can be used to capture static pictures or videos. The object generates an optical picture through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the processor 1101 to convert it into a digital picture signal.

[0224] The processor 1101 is the control center of the electronic device 110. It uses various interfaces and lines to connect various parts of the entire terminal. It executes various functions of the electronic device 110 and processes data by running or executing software programs stored in the memory 140 and calling data stored in the memory 140. In some embodiments, the processor 1101 may include one or more processing units; the processor 1101 may also integrate an application processor and a baseband processor, wherein the application processor mainly processes an operating system, a user interface, and an application program, and the baseband processor mainly processes wireless communications. It is understandable that the above-mentioned baseband processor may not be integrated into the processor 1101. In the present application, the processor 1101 can run an operating system and an application program, can control the user interface display, and can implement the member determination method of the learning discussion room provided in the embodiment of the present application. In addition, the processor 1101 is coupled to the input unit and the display unit 130.

[0225] The display unit 130 may be used to receive input digital or character information, generate signal input related to user settings and function control of the electronic device 110, and optionally, the display unit 130 may also be used to display information input by the user or information provided to the user and a graphical user interface (GUI) of various menus of the electronic device 110. The display unit 130 may include a display screen 131 disposed on the front of the electronic device 110. The display screen 131 may be configured in the form of a liquid crystal display, a light emitting diode, etc. The display unit 130 may be used to display various graphical user interfaces described in the present application.

[0226] The display unit 130 includes a touch screen 132 disposed on the front of the electronic device 110. The display screen 131 can be used to display preview images. The touch screen 132 can collect user touch operations on or near it, such as clicking a button, dragging a scroll box, etc. Among them, the touch screen 132 can be covered on the display screen 131, or the touch screen 132 can be integrated with the display screen 131 to realize the input and output functions of the electronic device 110, and the integration can be simply called a touch display screen.

[0227] The memory 140 can be used to store software programs and data. The processor 1101 executes various functions and data processing of the electronic device 110 by running the software programs or data stored in the memory 140. The memory 140 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. The memory 140 stores an operating system that enables the electronic device 110 to run. In the present application, the memory 140 can store an operating system and various application programs, and can also store code for executing the member determination method of the learning discussion room provided in the embodiment of the present application.

[0228] The RF circuit 150 can be used to receive and send signals during the process of sending and receiving information or making calls. It can receive downlink data from the base station and hand it over to the processor 1101 for processing; it can send uplink data to the base station. Generally, the RF circuit includes but is not limited to antennas, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer and other devices.

[0229] The audio circuit 160, the speaker 161, and the microphone 162 can provide an audio interface between the user and the electronic device 110. The audio circuit 160 can transmit the electrical signal converted from the received audio data to the speaker 161, which is converted into a sound signal for output. The electronic device 110 can also be equipped with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 162 converts the collected sound signal into an electrical signal, which is received by the audio circuit 160 and converted into audio data, and then the audio data is output to the RF circuit 150 to be sent to, for example, another terminal, or the audio data is output to the memory 140 for further processing. In the present application, the microphone 162 can obtain the user's voice.

[0230] Wi-Fi is a short-range wireless transmission technology. The electronic device 110 can help users send and receive emails, browse web pages, and access streaming media through the Wi-Fi module 170, which provides users with wireless broadband Internet access.

[0231] The Bluetooth module 180 is used to exchange information with other Bluetooth devices having Bluetooth modules through the Bluetooth protocol. For example, the electronic device 110 can establish a Bluetooth connection with a wearable electronic device (such as a smart watch) that also has a Bluetooth module through the Bluetooth module 180 to exchange data.

[0232] The electronic device 110 also includes a power supply 190 (such as a battery) for supplying power to various components. The power supply can be logically connected to the processor 1101 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption. The electronic device 110 can also be configured with a power button for turning on and off the terminal, as well as locking the screen and other functions.

[0233] The electronic device 110 may include at least one sensor 1110, such as a motion sensor 11101, a distance sensor 11102, and a temperature sensor 11103. The electronic device 110 may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor.

[0234] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the mobile terminal and each device described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0235] Fig.11 It is a software structure diagram of the mobile terminal provided in the embodiment of the present application. The layered architecture divides the software into several layers, each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom, namely, the application layer, the application framework layer, the Android runtime environment (android runtime, ART) and the system library, and the kernel layer.

[0236] The application layer can include a series of application packages. Fig.11 As shown, the application package may include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message, etc. The application framework layer provides an application programming interface (API) and programming framework for the applications in the application layer. The application framework layer includes some predefined functions.

[0237] like Fig.11 As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0238] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0239] Content providers are used to store and retrieve data and make it accessible to applications. The data may include videos, pictures, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0240] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.

[0241] The phone manager is used to provide communication functions for the electronic device 110, such as management of call status (including connecting, hanging up, etc.).

[0242] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0243] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt tone is emitted, the communication terminal vibrates, and the indicator light flashes.

[0244] Android runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system.

[0245] The core library consists of two parts: one part is the function that needs to be called by the Java language, and the other part is the Android core library.

[0246] The application layer and the application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.

[0247] The system library may include multiple functional modules, such as surface manager, media libraries, 3D graphics processing library (such as openGL ES), 2D graphics engine (such as SGL), etc.

[0248] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

[0249] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0250] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, synthesis, and layer processing.

[0251] A 2D graphics engine is a drawing engine for 2D drawings.

[0252] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.

[0253] An embodiment of the present application provides an electronic device, which may include a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for determining members of a learning discussion room provided in the above embodiment is implemented, for example Figure 1 or Figure 4 The method shown.

[0254] The embodiment of the present application provides a computer-readable storage medium in which a computer program is stored. The computer program is loaded by a processor and executes the member determination method of the learning discussion room provided in the above embodiment, for example Figure 1 or Figure 4 The method shown.

[0255] The present application also provides a computer program product including instructions. When the computer program product is run on a computer, the computer executes the method for determining members of a learning discussion room provided in the above method embodiment. For example, Figure 1 or Figure 4 The method shown.

[0256] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0257] It should be understood that the "and / or" mentioned in this article indicates that there may be three relationships. For example, A and / or B may indicate that A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated with each other are in an "or" relationship. In addition, the term "at least one" in this application means one or more, and the term "plurality" in this application means two or more.

[0258] In this application, the terms "first", "second", etc. are used to distinguish the same or similar items with substantially the same role and function. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there a limit on the number and execution order. For example, without departing from the scope of the various examples described, a first learning object can be referred to as a second learning object, and similarly, a second learning object can be referred to as a first learning object.

[0259] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions. For example, the object data of the learning objects involved in this application are all obtained with full authorization.

[0260] The above description is only an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining members of a learning discussion room, characterized in that: Applied to electronic equipment; the method comprises: receiving a member recommendation request, wherein the member recommendation request is used to recommend a learning object for a first learning object to conduct a learning discussion with the first learning object in a learning discussion room; In response to the member recommendation request, obtaining object data of the first learning object and each of the plurality of second learning objects, wherein the object data of each learning object includes: learning progress, learning ability, learning information, information about the learning object's interest in a plurality of different types of learning tasks, and the number of interactions between the learning object and other learning objects; the learning information includes the learning plan of the learning object and discussion information between the learning object and other learning objects, wherein the learning plan includes at least one learning task; For each second learning object, determining a learning progress similarity based on the learning progress of the second learning object and the first learning object, and determining a learning ability similarity based on the learning ability of the second learning object and the first learning object; extracting a plurality of different interest keywords of the learning object from the learning information of the learning object; Determining the criticality of the interest keyword in the learning information of the learning object based on the word frequency and the inverse document frequency of the interest keyword; For each second learning object, determining an intersection of a plurality of interest keywords of the second learning object and a plurality of interest keywords of the first learning object; the intersection includes at least one target keyword; Determining the similarity of the interest keywords of the second learning object and the first learning object based on the criticality of at least one target keyword of the second learning object and the criticality of at least one target keyword of the first learning object; Determining similarity between the interest information of the second learning object and the interest information of the first learning object for a plurality of different types of learning tasks based on the interest information of the second learning object for a plurality of different types of learning tasks; Determining the interest similarity between the second learning object and the first learning object based on the interest keyword similarity and the interest information similarity; Determining the social similarity between the second learning object and the first learning object based on the interaction heat and social relationship similarity between the first learning object and the second learning object; The interaction heat satisfies: Wherein, h(A,B) is the number of interactions between the first learning object and the second learning object, and h total is the sum of the number of interactions between the first learning object and each of a plurality of third learning objects, where the third learning objects are friend accounts of the user account of the first learning object; The social relationship similarity satisfies: Wherein, x is a first total number of at least one friend account included in the intersection of multiple first friend accounts of the user account of the first learning object and multiple second friend accounts of the user account of the second learning object, X is a second total number of multiple friend accounts included in the union of the multiple first friend accounts and the multiple second friend accounts, n1 is a weight of a second ratio, and the second ratio is a ratio of the first total number to the second total number; y is a third total number of at least one fan account included in the intersection of multiple first fan accounts of the user account of the first learning object and multiple second fan accounts of the user account of the second learning object, Y is a fourth total number of multiple fan accounts included in the union of the multiple first fan accounts and the multiple second fan accounts, n2 is a weight of a third ratio, and the third ratio is a ratio of the third total number to the fourth total number; Determine a recommendation degree of the second learning object based on the learning progress similarity, the learning ability similarity, the interest similarity and the social similarity, wherein the recommendation degree is positively correlated with the learning progress similarity, the learning ability similarity, the interest similarity and the social similarity; If the recommendation degree of the second learning object is greater than the recommendation degree threshold, recommendation information of the second learning object is pushed, where the recommendation information is used to indicate that the second learning object is a learning object that can join the learning discussion room.

2. The method according to claim 1, characterized in that The learning progress of the learning object includes: a sub-progress of each subject in a plurality of subjects; and determining the similarity of the learning progress based on the learning progress of the second learning object and the learning progress of the first learning object includes: Determine at least one target subject, where the at least one target subject is the intersection of a plurality of subjects studied by the first learning object and a plurality of subjects studied by the second learning object; For each target subject of the at least one target subject, determining a similarity between the sub-progress of the second learning object and the first learning object in learning the target subject; Determine the similarity of the learning progress of the second learning object and the first learning object according to the average of the similarities of the sub-progresses of the at least one target subject; Among them, if the first learning object and the second learning object have the same sub-progress in learning the target subject, the similarity of the sub-progress of the target subject is the target value; if the first learning object and the second learning object have different sub-progress in learning the target subject, the similarity of the sub-progress of the target subject is a value less than the target value.

3. The method according to claim 2, characterized in that The total number of the at least one target subject is 1, where 1 is an integer greater than or equal to 1; each target subject includes a plurality of course units, and each course unit includes a plurality of chapters; The sub-progress of the first learning object learning the i-th target subject in the i-th target subject includes: i course units, and the AD i Ad in the course unit i The sub-progress of the second learning object learning the i-th target subject includes: the BD-th subject learned by the second learning object i Units, and the BD i Bd of the course units i chapters; the learning progress of the second learning object is similar to that of the first learning object to the degree that: satisfy: satisfy: Among them, c1 is the weight of the course unit, and c2 is the weight of the chapter.

4. The method according to claim 1, characterized in that: The learning ability of each of the subjects is represented by the total number of learning tasks completed within the target duration; Determining the learning ability similarity based on the learning ability of the second learning object and the learning ability of the first learning object includes: Determine a difference between the total number of learning tasks completed by the second learning object within the target time period and the total number of learning tasks completed by the first learning object within the target time period; The learning ability similarity is determined based on the difference, and the learning ability similarity is negatively correlated with the absolute value of the difference.

5. The method according to claim 1, characterized in that The determining the recommendation degree of the second learning object based on the learning progress similarity, the learning ability similarity, the interest similarity and the social similarity includes: The learning progress similarity, the learning ability similarity, the interest similarity and the social similarity are weightedly summed to obtain the recommendation degree of the second learning object.

6. An electronic device, characterized in that: The electronic device comprises: a processor; the processor is used for: receiving a member recommendation request, wherein the member recommendation request is used to recommend a learning object for a first learning object to conduct a learning discussion with the first learning object in a learning discussion room; In response to the member recommendation request, obtaining object data of the first learning object and each of the plurality of second learning objects, wherein the object data of each learning object includes: learning progress, learning ability, learning information, information about the learning object's interest in a plurality of different types of learning tasks, and the number of interactions between the learning object and other learning objects; the learning information includes the learning plan of the learning object and discussion information between the learning object and other learning objects, wherein the learning plan includes at least one learning task; For each second learning object, determining a learning progress similarity based on the learning progress of the second learning object and the first learning object, and determining a learning ability similarity based on the learning ability of the second learning object and the first learning object; extracting a plurality of different interest keywords of the learning object from the learning information of the learning object; Determining the criticality of the interest keyword in the learning information of the learning object based on the word frequency and the inverse document frequency of the interest keyword; For each second learning object, determining an intersection of a plurality of interest keywords of the second learning object and a plurality of interest keywords of the first learning object; the intersection includes at least one target keyword; Determining the similarity of the interest keywords of the second learning object and the first learning object based on the criticality of at least one target keyword of the second learning object and the criticality of at least one target keyword of the first learning object; Determining similarity between the interest information of the second learning object and the interest information of the first learning object for a plurality of different types of learning tasks based on the interest information of the second learning object for a plurality of different types of learning tasks; Determining the interest similarity between the second learning object and the first learning object based on the interest keyword similarity and the interest information similarity; Determining the social similarity between the second learning object and the first learning object based on the interaction heat and social relationship similarity between the first learning object and the second learning object; The interaction heat satisfies: Wherein, h(A,B) is the number of interactions between the first learning object and the second learning object, and h total is the sum of the number of interactions between the first learning object and each of a plurality of third learning objects, where the third learning objects are friend accounts of the user account of the first learning object; The social relationship similarity satisfies: Wherein, x is a first total number of at least one friend account included in the intersection of multiple first friend accounts of the user account of the first learning object and multiple second friend accounts of the user account of the second learning object, X is a second total number of multiple friend accounts included in the union of the multiple first friend accounts and the multiple second friend accounts, n1 is a weight of a second ratio, and the second ratio is a ratio of the first total number to the second total number; y is a third total number of at least one fan account included in the intersection of multiple first fan accounts of the user account of the first learning object and multiple second fan accounts of the user account of the second learning object, Y is a fourth total number of multiple fan accounts included in the union of the multiple first fan accounts and the multiple second fan accounts, n2 is a weight of a third ratio, and the third ratio is a ratio of the third total number to the fourth total number; Determine a recommendation degree of the second learning object based on the learning progress similarity, the learning ability similarity, the interest similarity and the social similarity, wherein the recommendation degree is positively correlated with the learning progress similarity, the learning ability similarity, the interest similarity and the social similarity; If the recommendation degree of the second learning object is greater than the recommendation degree threshold, recommendation information of the second learning object is pushed, where the recommendation information is used to indicate that the second learning object is a learning object that can join the learning discussion room.

7. The electronic device according to claim 6, characterized in that: The learning progress of the learning object includes: a sub-progress of each subject in a plurality of subjects; and the processor is used for: Determine at least one target subject, where the at least one target subject is the intersection of a plurality of subjects studied by the first learning object and a plurality of subjects studied by the second learning object; For each target subject of the at least one target subject, determining a similarity between the sub-progress of the second learning object and the first learning object in learning the target subject; Determine the similarity of the learning progress of the second learning object and the first learning object according to the average of the similarities of the sub-progresses of the at least one target subject; Among them, if the first learning object and the second learning object have the same sub-progress in learning the target subject, the similarity of the sub-progress of the target subject is the target value; if the first learning object and the second learning object have different sub-progress in learning the target subject, the similarity of the sub-progress of the target subject is a value less than the target value.

Images