1. A course recommendation method, comprising:

acquiring user information of a user to be recommended;

analyzing the user information of the user to be recommended to obtain learning attribute information corresponding to the user to be recommended; wherein the learning attribute information comprises one or more of access login preference information, access contact preference information, course preference information, and learning state transition information;

carrying out comprehensive portrait analysis on the user to be recommended according to the learning attribute information corresponding to the user to be recommended to obtain a course recommendation result corresponding to the user to be recommended;

and outputting the course recommendation result to the user to be recommended.

2. The method according to claim 1, wherein the analyzing the user information of the user to be recommended to obtain the access login preference information corresponding to the user to be recommended comprises:

acquiring all login records corresponding to the user to be recommended from the user information; the login record comprises login time and logout time;

and determining login preference information corresponding to the user to be recommended according to all login records corresponding to the user to be recommended.

3. The method of claim 2, wherein the login record further comprises a login device type and a learning entry type;

the analyzing the user information of the user to be recommended to obtain the access contact preference information corresponding to the user to be recommended comprises:

and determining contact preference information corresponding to the user to be recommended according to the login equipment type in each login record, and determining entry preference information corresponding to the user to be recommended according to the learning entry type in each login record.

4. The method according to claim 3, wherein the determining the contact preference information corresponding to the user to be recommended according to the login device type in each login record comprises:

determining login times corresponding to the login equipment types based on the login equipment types in the login records;

and determining the contact preference information corresponding to the user to be recommended according to the login times corresponding to the types of the login equipment.

5. The method as claimed in claim 1, wherein the analyzing the user information of the user to be recommended to obtain the course preference information corresponding to the user to be recommended includes:

acquiring historical course access information from the user information, wherein the historical course access information comprises historical access courses and learning course duration and course types corresponding to the historical access courses;

determining the course learning preference duration corresponding to the user to be recommended according to the learning course duration corresponding to the historical access course;

and determining the course type preference corresponding to the user to be recommended according to the course type corresponding to the historical access course.

6. The method according to any one of claims 1 to 5, wherein the performing comprehensive portrait analysis on the user to be recommended according to the learning attribute information corresponding to the user to be recommended to obtain a course recommendation result corresponding to the user to be recommended includes:

and inputting the learning attribute information corresponding to the user to be recommended to a target network model, so that the target network model performs comprehensive portrait analysis based on the learning attribute information to obtain a course recommendation result corresponding to the user to be recommended.

7. A course recommending apparatus, comprising:

the information acquisition module is used for acquiring the user information of the user to be recommended;

the processing module is used for analyzing the user information of the user to be recommended to obtain learning attribute information corresponding to the user to be recommended; wherein the learning attribute information comprises one or more of access login preference information, access contact preference information, course preference information, and learning state transition information;

the processing module is further used for carrying out comprehensive portrait analysis on the user to be recommended according to the learning attribute information corresponding to the user to be recommended to obtain a course recommendation result corresponding to the user to be recommended;

the processing module is further used for outputting the course recommending result to the user to be recommended.

8. An electronic device, comprising: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the course recommendation method of any of claims 1-6.

9. A computer-readable storage medium having stored thereon computer-executable instructions which, when executed by a processor, implement the course recommendation method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the course recommendation method of any one of claims 1 to 6.

Background

The enterprise online learning platform is based on the Internet technology, adopts an open online learning platform mode, takes learning resources as a core, and meets various training scene requirements of enterprises. With the popularization and deep application of the internet, an enterprise online learning platform becomes an important way for internal education and knowledge sharing.

At present, in order to meet the learning requirements of all employees, an enterprise online learning platform usually shows all network courses, i.e., training contents. When a user wants to learn a course, the user needs to search a target network course from network courses provided by the enterprise online learning platform, namely, search a required network course.

However, the target network course is determined inefficiently and the user experience is low due to the fact that the user is required to manually search the target network course.

Disclosure of Invention

The embodiment of the invention provides a course recommending method and device, and aims to solve the technical problem of low course determining efficiency in the prior art.

In a first aspect, an embodiment of the present invention provides a course recommendation method, where the method includes:

acquiring user information of a user to be recommended;

analyzing the user information of the user to be recommended to obtain learning attribute information corresponding to the user to be recommended; wherein the learning attribute information comprises one or more of access login preference information, access contact preference information, course preference information, and learning state transition information;

carrying out comprehensive portrait analysis on the user to be recommended according to the learning attribute information corresponding to the user to be recommended to obtain a course recommendation result corresponding to the user to be recommended;

and outputting the course recommendation result to the user to be recommended.

In a possible design, the analyzing the user information of the user to be recommended to obtain the access login preference information corresponding to the user to be recommended includes:

acquiring all login records corresponding to the user to be recommended from the user information; the login record comprises login time and logout time;

and determining login preference information corresponding to the user to be recommended according to all login records corresponding to the user to be recommended.

In one possible design, the login record further includes a login device type and a learning entry type;

the analyzing the user information of the user to be recommended to obtain the access contact preference information corresponding to the user to be recommended comprises:

and determining contact preference information corresponding to the user to be recommended according to the login equipment type in each login record, and determining entry preference information corresponding to the user to be recommended according to the learning entry type in each login record.

In a possible design, the determining, according to the login device type in each login record, the contact preference information corresponding to the user to be recommended includes:

determining login times corresponding to the login equipment types based on the login equipment types in the login records;

and determining the contact preference information corresponding to the user to be recommended according to the login times corresponding to the types of the login equipment.

In a possible design, the analyzing the user information of the user to be recommended to obtain the course preference information corresponding to the user to be recommended includes:

acquiring historical course access information from the user information, wherein the historical course access information comprises historical access courses and learning course duration and course types corresponding to the historical access courses;

determining the course learning preference duration corresponding to the user to be recommended according to the learning course duration corresponding to the historical access course;

and determining the course type preference corresponding to the user to be recommended according to the course type corresponding to the historical access course.

In a possible design, the comprehensively analyzing the portrait of the user to be recommended according to the learning attribute information corresponding to the user to be recommended to obtain a course recommendation result corresponding to the user to be recommended, including:

and inputting the learning attribute information corresponding to the user to be recommended to a target network model, so that the target network model performs comprehensive portrait analysis based on the learning attribute information to obtain a course recommendation result corresponding to the user to be recommended.

In a second aspect, an embodiment of the present invention provides a course recommending apparatus, including:

the information acquisition module is used for acquiring the user information of the user to be recommended;

the processing module is used for analyzing the user information of the user to be recommended to obtain learning attribute information corresponding to the user to be recommended; wherein the learning attribute information comprises one or more of access login preference information, access contact preference information, course preference information, and learning state transition information;

the processing module is further used for carrying out comprehensive portrait analysis on the user to be recommended according to the learning attribute information corresponding to the user to be recommended to obtain a course recommendation result corresponding to the user to be recommended;

the processing module is further used for outputting the course recommending result to the user to be recommended.

In one possible design, the processing module is further to:

acquiring all login records corresponding to the user to be recommended from the user information; the login record comprises login time and logout time;

and determining login preference information corresponding to the user to be recommended according to all login records corresponding to the user to be recommended.

In one possible design, the login record further includes a login device type and a learning entry type;

the processing module is further configured to:

and determining contact preference information corresponding to the user to be recommended according to the login equipment type in each login record, and determining entry preference information corresponding to the user to be recommended according to the learning entry type in each login record.

In one possible design, the processing module is further to:

determining login times corresponding to the login equipment types based on the login equipment types in the login records;

and determining the contact preference information corresponding to the user to be recommended according to the login times corresponding to the types of the login equipment.

In one possible design, the processing module is further to:

acquiring historical course access information from the user information, wherein the historical course access information comprises historical access courses and learning course duration and course types corresponding to the historical access courses;

determining the course learning preference duration corresponding to the user to be recommended according to the learning course duration corresponding to the historical access course;

and determining the course type preference corresponding to the user to be recommended according to the course type corresponding to the historical access course.

In one possible design, the processing module is further to:

and inputting the learning attribute information corresponding to the user to be recommended to a target network model, so that the target network model performs comprehensive portrait analysis based on the learning attribute information to obtain a course recommendation result corresponding to the user to be recommended.

In a third aspect, an embodiment of the present invention provides an electronic device, including: at least one processor and memory;

the memory stores computer-executable instructions;

the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the course recommendation method as set forth above in the first aspect and in various possible designs of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the course recommendation method according to the first aspect and various possible designs of the first aspect is implemented.

In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the course recommendation method according to the first aspect and the various possible designs of the first aspect is implemented.

The invention provides a course recommending method and a course recommending device, which are characterized in that when user information of a user to be recommended is acquired, the course recommending of the user to be recommended is indicated, the user information of the user to be recommended is analyzed, so that learning attribute information corresponding to the user to be recommended is obtained, wherein the learning attribute information comprises one or more of access login preference information, access contact preference information, course preference information and learning state transfer information, and namely the learning attribute information represents the preference condition of the user. When learning attribute information corresponding to a user to be recommended is obtained, comprehensive portrait analysis is carried out on the user to be recommended based on the learning attribute information, namely, multidimensional comprehensive intelligent analysis is carried out to determine courses which are interested by the user to be recommended, namely, required target courses, so that course recommendation results corresponding to the user to be recommended are obtained, and the course recommendation results are pushed to the user to be recommended, so that the user to be recommended can directly learn corresponding target courses based on the course recommendation results, the user does not need to manually search for the target courses, namely, the user does not need to search for the required courses, automatic determination of the target courses is achieved, determination efficiency of the target courses is improved, and user experience is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a schematic view of a scenario of a course recommendation method according to an embodiment of the present invention;

FIG. 2 is a first flowchart illustrating a course recommendation method according to an embodiment of the present invention;

FIG. 3 is a second flowchart illustrating a course recommendation method according to an embodiment of the present invention;

FIG. 4 is a block diagram of a course recommending apparatus according to an embodiment of the present invention;

fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

With the continuous popularization and application of the internet and the mobile terminal, more and more enterprises adopt an online learning mode, provide an enterprise online learning platform for employees by constructing an enterprise internal training ecosystem, and meet the training requirements of the enterprise internal to the employees.

In the prior art, in order to meet the learning requirements of all employees, an online enterprise learning platform usually displays all courses, i.e., training contents, such as employee enrollment training, welfare training, and business-related training contents, on the online enterprise learning platform. Different employees have different work contents and business directions and different learning interests for different courses, and a user needs to search all courses, namely target courses, required by the user from all the courses provided by the enterprise online learning platform. However, since the user needs to manually search for the target course, the course searching efficiency is low, and the user experience is reduced.

Therefore, in view of the above problems, the technical idea of the present invention is to consider learning data, that is, learning attribute information reflecting learning trend and potential requirements of a student, and perform multi-angle intelligent analysis, that is, comprehensive portrait analysis, on the learning attribute information of a user based on a learning data analysis model to determine a course required by the user, that is, a target course, to achieve automatic determination of the target course, without manual search by the user, to improve determination efficiency of the target course, to achieve personalized recommendation of the course, and to improve user experience.

The following describes the technical solutions of the present disclosure and how to solve the above technical problems in detail by specific examples. Several of these specific examples may be combined with each other below, and some of the same or similar concepts or processes may not be repeated in some examples. Examples of the present disclosure will now be described with reference to the accompanying drawings.

Fig. 1 is a schematic view of a scenario of a course recommendation method according to an embodiment of the present invention, as shown in fig. 1, an electronic device 101 provides multiple types of courses (for example, course 1), and when a user needs to learn, a target course may be selected from the courses provided by the electronic device 101, that is, a required course is selected.

Alternatively, the electronic device 101 may be a computer, a mobile terminal (e.g., a tablet), or the like.

Fig. 2 is a flowchart illustrating a first method for recommending courses according to an embodiment of the present invention, where an executing subject in the embodiment may be the electronic device shown in fig. 1. As shown in fig. 2, the method includes:

s201, obtaining user information of a user to be recommended.

In this embodiment, after determining the user to be recommended, that is, after determining the identifier of the user to be recommended, indicating that the network course, that is, the target course, required by the user to be recommended needs to be determined, the user information of the user to be recommended is obtained, so that the user information is used to determine the preference condition of the user, and thus the interested course is determined, that is, the target course corresponding to the user to be recommended is determined.

Optionally, when the user to be recommended is determined, the determination may be performed based on the user list directly, that is, the user in the user list is used as the user to be recommended.

In addition, the user to be recommended may also be determined from the users based on the user information of all employees, that is, the users corresponding to the enterprise online learning platform, for example, the user to be recommended may be determined based on the user information of the users, and the user with the activity value being very inactive and the access behavior level being less access behavior may be used as the user to be recommended. Of course, the user to be recommended may be determined from the user, which may be determined in other manners, for example, the user with higher recommendation value is used as the user to be recommended, and this is not limited herein.

S202, analyzing the user information of the user to be recommended to obtain learning attribute information corresponding to the user to be recommended. Wherein the learning attribute information includes one or more of access login preference information, access contacts preference information, lesson preference information, and learning state transition information.

In this embodiment, after the user to be recommended is determined, that is, after the user information of the user to be recommended is obtained, for each user to be recommended, the user of the user to be recommended is analyzed to determine the historical behavior condition of the user to be recommended, that is, the learning preference condition of the user to be recommended is determined, so that the learning attribute information corresponding to the user to be recommended is obtained.

Wherein the learning attribute information includes one or more of access login preference information, access contacts preference information, lesson preference information, and learning state transition information.

Wherein, the access login preference information comprises the login situation and the learning situation of the user, which can reflect the learning activity and the learning stickiness of the user.

The access contact preference information comprises login contact preference information and learning entry preference information of the user, and the login contact preference information and the learning entry preference information can reflect learning access preference conditions of the user.

The course preference information comprises information such as course category preference, course keyword preference, course learning completion rate and the like, and can reflect the course preference condition of the user.

Wherein the learning state transition information represents a learning state change trajectory of the user.

S203, carrying out comprehensive portrait analysis on the user to be recommended according to the learning attribute information corresponding to the user to be recommended to obtain a course recommendation result corresponding to the user to be recommended.

In this embodiment, for each user to be recommended, after learning attribute information corresponding to the user to be recommended is obtained, portrait analysis, that is, multidimensional data analysis, is performed on the user to be recommended based on the learning attribute information corresponding to the user to be recommended, so as to determine a course required by the user to be recommended, that is, a course recommendation result corresponding to the user to be recommended is obtained, where the course recommendation result includes a target course identifier, that is, an identifier of the course required by the user.

In addition, the user information of the user to be recommended may further include basic attribute information, where the basic attribute information represents basic information of the user to be recommended, for example, a department to which the user to be recommended belongs. Correspondingly, when the comprehensive portrait analysis is performed on the user to be recommended, the basic attribute information corresponding to the user to be recommended can be combined.

And S204, pushing the course recommendation result to a user to be recommended.

In this embodiment, after obtaining a course recommendation result corresponding to a user to be recommended, that is, after determining a course including a course required by the user to be recommended, that is, a course recommendation result of a target course, the course recommendation result is sent to a user terminal corresponding to the user to be recommended, so that the course recommendation result is pushed to the user to be recommended, so that the user to be recommended can directly know the target course, that is, the course required to be learned by the user, and can directly learn the target course, the user to be recommended does not need to search the target course according to the condition of the user, the efficiency of determining the target course is improved, and the efficiency of online learning of the user is improved.

In this embodiment, the enterprise online learning platform recommends a network course, i.e., a target course, required by the user to the user based on the learning attribute information of the user, so as to implement personalized recommendation of the target course, provide reference for online learning of the user, and implement accurate operation of the enterprise online learning platform.

As can be seen from the above description, when the user information of the user to be recommended is obtained, it indicates that course recommendation needs to be performed on the user to be recommended, the user information of the user to be recommended is analyzed to obtain learning attribute information corresponding to the user to be recommended, where the learning attribute information includes one or more of access login preference information, access contact preference information, course preference information, and learning state transition information, that is, the learning attribute information represents a preference condition of the user. When learning attribute information corresponding to a user to be recommended is obtained, comprehensive portrait analysis is carried out on the user to be recommended based on the learning attribute information, namely, multidimensional comprehensive intelligent analysis is carried out to determine courses which are interested by the user to be recommended, namely, required target courses, so that course recommendation results corresponding to the user to be recommended are obtained, and the course recommendation results are pushed to the user to be recommended, so that the user to be recommended can directly learn corresponding target courses based on the course recommendation results, the user does not need to manually search for the target courses, namely, the user does not need to search for the required courses, automatic determination of the target courses is achieved, determination efficiency of the target courses is improved, and user experience is improved.

Fig. 3 is a schematic flow diagram of a course recommendation method according to an embodiment of the present invention, in which on the basis of the embodiment of fig. 2, when performing comprehensive portrait analysis on a user to be recommended based on learning attribute information corresponding to the user to be recommended, a data analysis model, that is, a target network may be used to perform comprehensive portrait analysis, and this process will be described below with reference to a specific embodiment. As shown in fig. 3, the method includes:

s301, obtaining user information of the user to be recommended.

S302, analyzing the user information of the user to be recommended to obtain learning attribute information corresponding to the user to be recommended. Wherein the learning attribute information includes one or more of access login preference information, access contacts preference information, lesson preference information, and learning state transition information.

Optionally, the access login preference information includes login preference information, learning preference information, and access preference information. The access contact preference information includes contact preference information and entry preference information. The course preference information includes course learning preference duration and course type preference.

Correspondingly, the process of determining the learning state transition information corresponding to the user to be recommended includes:

the user state corresponding to the first period is obtained from the user information, and the learning state corresponding to the second period is obtained, wherein the first period and the second period are adjacent learning periods (for example, one month). And determining the user state transition type corresponding to the user to be recommended according to the user states corresponding to the first period and the second period.

Optionally, the user state includes a valid learning state, a login state, a sleep state, and an invalid state.

When the user state of the user in a certain learning period is a learning state, the user is indicated to have an over-learning behavior in the learning period;

when the user state of the user in a certain learning period is the login state, the user is indicated to have the login behavior in the learning period, but not to have the learning behavior.

When the user state of the user in a certain learning period is in a dormant state, it indicates that the user is a valid user having no login behavior in the learning period (the user's delete flag is no at the end of the month).

When the user state of the user in a certain learning period is an invalid state: indicating that the current status of the user is invalid, such as an expired account or a staff member.

Optionally, when the user state transition type corresponding to the user to be recommended is determined according to the user states corresponding to the first period and the second period, the user state corresponding to the first period and the transition type corresponding to the second period are searched from the preset learning state transition table, and are determined as the user state transition type. The format table 1 of the preset learning state transition table shows:

TABLE 1 learning state transition Table

For example, when the user state corresponding to the first period is the sleep state and the user state corresponding to the second period is also the sleep state, it is determined that the user state transition type is the sleep maintenance type.

Correspondingly, the process of determining the access login preference information corresponding to the user to be recommended comprises the following steps:

and acquiring all login records corresponding to the user to be recommended from the user information. The login record comprises login time and logout time. And determining login preference information corresponding to the user to be recommended according to all login records corresponding to the user to be recommended. Obtaining learning duration corresponding to a user to be recommended from user information

Wherein the login preference information includes a login preference period indicating a period in which the user logs in the most number of times. Correspondingly, the preset login time period to which the login time belongs in each login record is obtained, the number of the login time included in the preset time period is determined as the login frequency corresponding to the preset time period, and the preset time period with the highest login frequency is used as the login preference time period.

Optionally, accessing the login preference information further comprises learning a preference period. The log-in record further includes a learning start time and a learning end time. Correspondingly, the preset time interval to which the learning starting time in each login record belongs is obtained, the number of the learning starting times included in the preset time interval is determined as the learning times corresponding to the preset time interval, and the preset time interval with the highest learning times is used as the learning preference time interval.

In addition, optionally, the access login preference information further includes the following types of information:

login number preference type: let a be the total login times/total number of sub-organizers corresponding to the user to be recommended, and determine the type of login times preference corresponding to the user to be recommended according to the value of a, for example, 1.2 or more is high, 0.8-1.2 is medium, and 0.8 or less is low.

Login duration preference type: and determining the login duration preference type of the user to be recommended according to the value A, wherein the login duration preference type is determined by the value A, and the login duration preference type is, for example, 1.2 or more high, 0.8-1.2 medium, and 0.8 or less low.

Learning number preference type: let a be the total learning frequency corresponding to the user to be recommended/the total learning frequency of the sub-organizer, and determine the learning frequency preference type to which the user to be recommended belongs according to the value a, for example, 1.2 or more is high, 0.8-1.2 is medium, and 0.8 or less is low.

Learning duration preference type: let a be the total learning duration/total learning duration of the sub-organizer corresponding to the user to be recommended, and determine the learning duration preference type to which the user to be recommended belongs according to the value a, for example, 1.2 or more is high, 0.8-1.2 is medium, and 0.8 or less is low.

Access period preference type: and combining and calculating the login times and the learning times in each preset time period, namely calculating the weighted sum of the login times and the learning times corresponding to each preset time period, and taking the time period with the maximum weighted sum as the preference type of the access time period.

And the access frequency preference type is the weighted sum of the total login frequency and the total learning frequency/the average number of access times of the region corresponding to the user to be recommended, and preference description is performed according to a proportional value, namely the access frequency preference type corresponding to the user to be recommended is determined, wherein the preference type is high for more than 1.2, medium for 0.8-1.2 and low for less than 0.8.

Access duration preference type: the preference description is carried out according to a proportional value, namely the preference type of the access duration corresponding to the user to be recommended is determined, for example, the preference type is higher by more than 1.2, medium by 0.8-1.2 and low by less than 0.8.

Learning completion rate: the learning completion rate of one student, i.e. the user, is the number of completed courses/the number of all courses with learning records (incomplete + completed).

Learning completion degree: the learning completion rate is defined based on a value of the learning completion rate, for example, the learning completion rate is low at 0 to 60%, medium at 60 to 90%, and high at 90% or more.

Active value: defining an active value Act_i(login times/average login times of the sub-organization in the month + learning times/average learning times of the sub-organization in the month + login time length/average learning time length)/4And I is the number of sub-organizers. The use area is more reasonable than the people in the whole country.

Activity level: defined in terms of activity values, e.g., less than 0.9 for low activity, 0.9-1.1 for moderate activity, and greater than 1.1 for high activity. The segmentation values may need to be adjusted according to the actual data.

Viscosity grade: the number of activity levels that were high in the last 6 months is calculated based on the activity level, and may be classified into, for example, high viscosity, medium viscosity, and low viscosity, and the viscosity is high if 4 or more, and is normal if 2 to 3, and is low if less than 2. The interval definition is front opening and back closing.

The sub-organization is a user to be recommended, namely an organization to which the user belongs, and the corresponding related information can be obtained from a database.

The login duration is determined according to the exit time and the login time in the login record, namely, the difference value between the exit time and the login time is used as the login duration.

The learning duration is determined according to the learning ending time and the learning starting time in the login record, namely, the difference value between the learning ending time and the learning starting time is used as the login duration.

In any embodiment, optionally, the login record further includes a login device type and/or a learning entry type. The login device type represents the device type used by the user to be recommended when the user logs in the system at this time. The type of the learning entry represents the learning entry to which the course belongs when the user to be recommended learns the course this time.

Specifically, the login device type includes a PC (Personal Computer) type, an APP (application) type, and the like.

Specifically, the types of learning entries include learning entries such as public classes, special districts, and examinations.

Correspondingly, analyzing the user information of the user to be recommended to obtain the access contact preference information corresponding to the user to be recommended, and the method comprises the following steps:

and determining contact preference information corresponding to the user to be recommended according to the login equipment type in each login record, and/or determining entry preference information corresponding to the user to be recommended according to the learning entry type in each login record.

The contact preference information comprises a contact preference type which indicates a user to be recommended, namely the user likes to use the enterprise online learning platform through the contact preference type, namely the user generally logs in/learns through the contact preference type.

The entrance preference information comprises an entrance preference type which represents a user to be recommended, namely the user likes to learn courses corresponding to the entrance preference type.

Further, optionally, determining contact preference information corresponding to the user to be recommended according to the login device type in each login record, including:

and determining login times corresponding to the login equipment types based on the login equipment types in the login records. And determining contact preference information, namely contact preference types, corresponding to the user to be recommended according to the login times corresponding to the types of the login equipment.

Specifically, login records corresponding to a user to be recommended within a certain period of time are obtained, and the login device types in all the obtained login records are counted to obtain the number of the login records corresponding to each login device type. And taking the number of login records corresponding to the login equipment type as the login times corresponding to the login equipment type, and taking the login equipment type with the maximum login times as the contact preference type.

Further, optionally, determining entry preference information corresponding to the user to be recommended according to the type of the learned entry in each login record, including:

and determining the learning entry times corresponding to the learning entry types based on the learning entry types in the login records. And determining the learning entry preference information corresponding to the user to be recommended, namely the entry preference type, according to the learning entry times corresponding to the learning entry types.

Specifically, login records corresponding to a user to be recommended within a certain period of time are obtained, and learning entry types in all the obtained login records are counted to obtain the number of the login records corresponding to each learning entry type. And taking the number of login records corresponding to the login equipment type as the learning entry frequency corresponding to the learning entry type, and taking the learning entry type with the maximum learning entry frequency as the entry preference type.

In addition, optionally, the access contact preference information further includes the following types of preference information:

the contact registration times are in proportion: the log-in times corresponding to a certain log-in equipment type in a certain period are compared and recorded as QA1_iLet QA1_iThe login times corresponding to the login device type/the total login times of the trainee.

Entry login frequency ratio: the number of learning access times is counted as QB1, wherein the learning access times is in proportion to the corresponding learning entry type in a certain period_jLet QB1_jLearning entry times/total number of entries of trainees corresponding to the learning entry type.

The contact login time is in proportion: the login duration is the ratio of the login duration corresponding to a certain login equipment type in a certain period.

Entry login time ratio: the login duration is the ratio of the login duration corresponding to a certain login equipment type in a certain period.

Correspondingly, the process of determining the course preference information corresponding to the user to be recommended includes:

and acquiring historical course access information from the user information, wherein the historical course access information comprises the historical access course, and the learning course time length and the course type corresponding to the historical access course.

And determining the course learning preference duration corresponding to the user to be recommended according to the learning course duration corresponding to the historical access course.

And determining the course type preference corresponding to the user to be recommended according to the course type corresponding to the historical access course.

The history access course represents a course which is learned by a user, and the learning course time length corresponding to the history access course represents the learning time length when the history access course is learned, namely the learning time length of the history access course. The course type corresponding to the historical access course represents the type of the historical access course.

Specifically, the lesson types include one or more of a superior instructor live type, a general instructor live type, an internal instructor lesson type, and an external instructor lesson type. Correspondingly, when the course type preference corresponding to the user to be recommended is determined according to the course types corresponding to the historical access courses, the course types corresponding to all the historical access courses corresponding to the user to be recommended are counted, and the access times corresponding to all the course types corresponding to the user to be recommended are obtained. And selecting one or more course types with the highest access times as course type preferences corresponding to the user to be recommended.

The course type preference corresponding to the user to be recommended represents the course type preferred by the user to be recommended. The access times corresponding to the course types represent the number of courses of which the types learned by the user to be recommended are the course types.

In addition, optionally, all history access courses corresponding to the user to be recommended are all courses learned by the user to be recommended in a history time period.

Specifically, when the course learning preference duration is determined, the maximum learning course duration is selected from the learning course durations corresponding to all history access courses and determined as the course learning preference duration, or the learning course durations corresponding to all history access courses are counted to obtain the repetition number corresponding to each learning course duration, and the learning course duration with the maximum repetition number is determined as the course learning preference duration.

The course learning preference duration corresponding to the user to be recommended represents the duration that the user to be recommended prefers to learn the course, namely the duration that the user to be recommended can learn when learning the course.

In addition, optionally, the course preference information corresponding to the user to be recommended may further include other types of information, for example, a course duration preference, a course completion rate preference, and the like.

Specifically, the course duration preference: obtaining the course time corresponding to the historical access course, wherein the course time refers to the course that the user has learnedThe duration of the lesson. Segmenting the history access courses according to the course time length, A1, A2 and …, for example, taking the course with the course time length of 0-30 minutes from A1 and taking the course with the course time length of 30-50 minutes from A2; respectively storing the lessons learned by the user in A1, A2 and … within a certain time period, and enabling N to be_i=A_iThe number of courses in, take max { N }_iThe corresponding course time interval is taken as the course time preference of the student, or N is taken_iThe higher value of the plurality of periods is taken as the lesson duration preference.

Specifically, the course completion rate preference: the course completion rate refers to the completion rate of each course that a user, i.e., a student, learns, i.e., the completion rate corresponding to the history access course. Recording the course completion rate corresponding to the historical access course as P, and defining as follows: p = min { K,1}, where K = the current user's time duration/class duration for the class. The course completion rate preference is defined as an interval value, C1, C2, …, e.g., the current student's course completion rate preference is 70-80%. The subsequent calculation method is the same as the course duration preference.

It should be noted that, in the technical solution of the present disclosure, the acquisition, storage, application, and the like of the personal information of the related user all conform to the track of relevant laws and regulations, and do not violate the good custom of the public order.

S303, inputting the learning attribute information corresponding to the user to be recommended into the target network model, so that the target network model performs comprehensive portrait analysis based on the learning attribute information to obtain a course recommendation result corresponding to the user to be recommended.

In this embodiment, after learning attribute information corresponding to a user to be recommended is obtained, the learning attribute information is input to a trained learning attribute portrait model, that is, a target network model, so that the target network model performs comprehensive portrait analysis, that is, multidimensional intelligent analysis, on the learning attribute information to determine a portrait of the user, that is, to determine a learning condition preferred by the user, for example, a preferred course, so as to obtain a course recommendation result corresponding to the user to be recommended, and output the course recommendation result.

Alternatively, the network model may be a neural network model, for example, a convolutional neural network module.

The target network model is obtained by training the basic network model, and the training process is similar to the training process of the existing model, i.e. the basic network model is trained by using sample data, which is not described herein again.

S304, obtaining a course recommendation result corresponding to the user to be recommended and output by the target network model, and pushing the course recommendation result to the user to be recommended.

In this embodiment, after obtaining the course recommendation result corresponding to the user to be recommended, the target network model outputs the course recommendation result. And the electronic equipment acquires the course recommendation result output by the target network model and pushes the course recommendation result to the corresponding user to be recommended.

In addition, optionally, when determining the course recommendation result corresponding to the user to be recommended based on the learning attribute information corresponding to the user to be recommended, the course recommendation result may also be determined by using the attribute result mapping table, that is, the course corresponding to the learning attribute information is searched and determined as the target course, so as to generate the course recommendation result including the target course.

In addition, optionally, after the course recommendation result corresponding to the user to be recommended is obtained, the course recommendation result may also be stored in the relevant database.

In this embodiment, after learning attribute information corresponding to a user to be recommended is acquired, a target network model is used to perform data analysis on the learning attribute information to realize portrait analysis, so that a course recommendation result suitable for the user to be recommended is determined, and accurate and rapid course recommendation is realized.

Fig. 4 is a schematic structural diagram of a course recommending apparatus according to an embodiment of the present invention, and as shown in fig. 4, the course recommending apparatus 400 includes: an information acquisition module 401 and a processing module 402.

The information obtaining module 401 is configured to obtain user information of a user to be recommended.

The processing module 402 is configured to analyze user information of the user to be recommended to obtain learning attribute information corresponding to the user to be recommended. Wherein the learning attribute information includes one or more of access login preference information, access contacts preference information, lesson preference information, and learning state transition information.

The processing module 402 is further configured to perform comprehensive portrait analysis on the user to be recommended according to the learning attribute information corresponding to the user to be recommended, so as to obtain a course recommendation result corresponding to the user to be recommended.

The processing module 402 is further configured to output the course recommendation result to the user to be recommended.

In one possible design, the processing module 402 is further configured to:

and acquiring all login records corresponding to the user to be recommended from the user information. The login record comprises login time and logout time.

And determining login preference information corresponding to the user to be recommended according to all login records corresponding to the user to be recommended.

In one possible design, the login record further includes a login device type and a learning entry type.

The processing module 402 is further configured to:

and determining contact preference information corresponding to the user to be recommended according to the login equipment type in each login record, and determining entry preference information corresponding to the user to be recommended according to the learning entry type in each login record.

In one possible design, the processing module 402 is further configured to:

and determining login times corresponding to the login equipment types based on the login equipment types in the login records.

And determining contact preference information corresponding to the user to be recommended according to the login times corresponding to the types of the login equipment.

In one possible design, the processing module 402 is further configured to:

and acquiring historical course access information from the user information, wherein the historical course access information comprises the historical access course, and the learning course time length and the course type corresponding to the historical access course.

And determining the course learning preference duration corresponding to the user to be recommended according to the learning course duration corresponding to the historical access course.

And determining the course type preference corresponding to the user to be recommended according to the course type corresponding to the historical access course.

In one possible design, the processing module 402 is further configured to:

and inputting the learning attribute information corresponding to the user to be recommended to the target network model so that the target network model performs comprehensive portrait analysis based on the learning attribute information to obtain a course recommendation result corresponding to the user to be recommended.

The course recommending device provided by the embodiment of the invention can realize the course recommending method of the embodiment, the realization principle and the technical effect are similar, and the details are not repeated here.

Fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention. As shown in fig. 5, the electronic device 500 of the present embodiment includes: a processor 501 and a memory 502;

memory 502 for storing computer execution instructions;

the processor 501 is configured to execute computer-executable instructions stored in the memory to implement the steps performed by the receiving device in the above embodiments. Reference may be made in particular to the description relating to the method embodiments described above.

Alternatively, the memory 502 may be separate or integrated with the processor 501.

When the memory 502 is provided separately, the electronic device further comprises a bus 503 for connecting said memory 502 and the processor 501.

An embodiment of the present invention further provides a computer-readable storage medium, where a computer executing instruction is stored in the computer-readable storage medium, and when a processor executes the computer executing instruction, the course recommendation method as described above is implemented.

An embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the course recommendation method as described above is implemented.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the modules is only one logical division, and other divisions may be realized in practice, for example, a plurality of modules may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit. The unit formed by the modules can be realized in a hardware form, and can also be realized in a form of hardware and a software functional unit.

The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present application.

It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.

The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc.

The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.

The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic device or host device.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.