CN109740048B - A course recommendation method and device - Google Patents

Abstract

The embodiment of the invention discloses a course recommending method and device, relates to the technical field of networks, and can generate recommended courses suitable for students through basic information data, so that the students can recommend the suitable courses to the students in advance when accessing an enterprise online learning platform, and the learning efficiency of the students is improved. The method comprises the following steps: acquiring basic information data; generating at least one first course recommendation list according to the basic information data, wherein each first course recommendation list is generated by one or more items of data in the basic information data; removing courses in at least one first course recommendation list according to a removal strategy to generate at least one second course recommendation list, wherein the first course recommendation list and the second course recommendation list are in one-to-one correspondence; and performing duplication checking and over-threshold processing on at least one second course recommendation list to generate a final course recommendation list. The embodiment of the invention is applied to the network learning system.

Description

A course recommendation method and device

technical field

Embodiments of the present invention relate to the field of network technologies, and in particular, to a method and apparatus for recommending courses.

Background technique

The enterprise online learning platform is based on Internet technology, adopts an open online learning platform model, takes learning resources as the core, meets the needs of various training scenarios of enterprises, builds an enterprise internal training ecosystem, and helps enterprises achieve talent leadership. With the popularization and in-depth application of the Internet, the enterprise online learning platform has become an important way for internal education and knowledge sharing. User behavior data is one of the main basis for guiding the production and operation of the platform. How to conduct effective data analysis is a major problem faced by the platform operation. The modeling process of the behavioral characteristics of network students is to analyze the behaviors of students, acquire and maintain the students' preferences, etc., and finally form a model that reflects the students' personalized needs, knowledge background or preferences. Obtain data on students' interests, needs and all interactive behaviors, and obtain a computable and formatted model of students' behavioral characteristics through analysis and generalization, and continuously record the changes in students' behavior, along with the changes in students' preferences. In turn, the process of changing the model of the learner's behavioral characteristics.

The enterprise online learning platform has multi-level administrator users, who are respectively responsible for a certain range of students' learning behavior management and platform operation. It is necessary to know the students' learning frequency, learning progress, and learning hotspots, and recommend suitable courses to suitable students. . Therefore, there is a demand for student portraits and course recommendations. Student portrait is an effective tool for delineating target students, connecting students' demands and design direction, and has been widely used in various fields. For example, Baidu Mobile Statistics provides comprehensive analysis and visual reports, agile development support, and digital operation and promotion management support in three aspects: student insight, product optimization, and operation promotion, starting from the needs of mobile developers. Mobile statistics can help developers solve the problems of increasingly complex student attributes, more and more changeable student behaviors, faster and faster product generation cycles, and higher and higher promotion costs. However, enterprise online learning platforms are different from social Internet platforms in that they have the characteristics of a relatively fixed range of students and relatively concentrated course resources, and have specific student portraits and recommendation needs. At present, there are few studies on enterprise online learning platforms, and it is impossible to recommend suitable courses to students.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a course recommendation method and device, which can generate recommended courses suitable for students through basic information data, so that students can recommend suitable courses to students in advance when accessing an enterprise online learning platform, thereby improving students' learning efficiency.

To achieve the above object, the present invention adopts the following technical solutions:

In the first aspect, a course recommendation method is provided. The method includes: acquiring basic information data, where the basic information data includes: student position attributes, student age, student's learning courses, the length of time that students study each course, course release time, The keywords of the current time and the current strategic direction of the enterprise; at least one first course recommendation list is generated according to the basic information data, and each first course recommendation list is generated by one or more pieces of data in the basic information data; according to the exclusion strategy, at least one first course recommendation list is generated; A course in the first course recommendation list is excluded, and at least one second course recommendation list is generated, wherein the first course recommendation list corresponds to the second course recommendation list one-to-one; Threshold processing to generate the final course recommendation list.

In the above method, first, basic information data such as the student's position attribute, the student's age, the student's study course, the length of the student's study of each course, the release time of the course, the current time, and the keywords of the company's current strategic direction are obtained; and At least one first course recommendation list is generated according to one or more pieces of data in the basic information data; then, courses in the at least one first course recommendation list are excluded according to the exclusion strategy, and at least one second course recommendation list is generated, wherein The first course recommendation list is in one-to-one correspondence with the second course recommendation list; at least one second course recommendation list is subjected to duplicate checking and over-threshold processing to generate a final course recommendation list. The embodiment of the present invention can generate recommended courses suitable for students through basic information data, so that students can recommend suitable courses to students in advance when they access the enterprise online learning platform, thereby improving the learning efficiency of students.

In a second aspect, a course recommendation device is provided. The device includes: an acquisition unit for acquiring basic information data, where the basic information data includes: the student's position attribute, the student's age, the student's study course, the student's learning time for each course, The release time of the course, the current time, and the keywords of the current strategic direction of the enterprise; the processing unit is used to generate at least one first course recommendation list according to the basic information data obtained by the acquisition unit, and each first course recommendation list consists of the basic information data. One or more pieces of data are generated; the processing unit is further configured to exclude courses in at least one first course recommendation list according to the exclusion strategy, and generate at least one second course recommendation list, wherein the first course recommendation list is the same as the second course recommendation list. The course recommendation lists are in one-to-one correspondence; the processing unit is further configured to perform duplicate checking and over-threshold processing on at least one second course recommendation list to generate a final course recommendation list.

It can be understood that the above-mentioned course recommendation apparatus is used to execute the method corresponding to the first aspect provided above. Therefore, for the beneficial effect that can be achieved, reference may be made to the method corresponding to the above-mentioned first aspect and the following detailed description. The beneficial effects of the corresponding solution will not be repeated here.

In a third aspect, a course recommendation apparatus is provided, the structure of the course recommendation apparatus includes a processor and a memory, the memory is used for coupling with the processor, and saves necessary program instructions and data of the course recommendation apparatus, and the processor is used for executing the memory. The program instructions stored in the device enable the course recommendation apparatus to execute the course recommendation method described in the first aspect.

In a fourth aspect, a computer storage medium is provided, in which computer program codes are stored, and when the computer program codes are executed on the course recommendation apparatus as described in the third aspect, the course recommendation apparatus is made to perform the above-mentioned first aspect. method.

A fifth aspect provides a computer program product, the computer program product stores the above-mentioned computer software instructions, when the computer software instructions are run on the course recommendation device as described in the third aspect, the course recommendation device is made to execute the above-mentioned first method. Procedure for the protocol described in the aspect.

Description of drawings

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

1 is a schematic flowchart of a course recommendation method provided by an embodiment of the present invention;

FIG. 2 is a schematic flowchart of generating a first course recommendation list according to an embodiment of the present invention;

3 is a schematic flowchart of yet another generation of a first course recommendation list provided by an embodiment of the present invention;

4 is a schematic flowchart of performing duplicate checking and over-threshold processing on a course recommendation list according to an embodiment of the present invention;

5 is a schematic structural diagram of a course recommendation device provided by an embodiment of the present invention;

6 is a schematic structural diagram of another course recommendation device provided by an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of still another course recommendation apparatus provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to represent examples, illustrations, or descriptions. Any embodiments or designs described as "exemplary" or "such as" in the embodiments of the present invention should not be construed as preferred or advantageous over other embodiments or designs. Rather, use of words such as "exemplary" or "such as" is intended to present the related concepts in a specific manner.

It should also be noted that, in the embodiment of the present invention, "of", "corresponding (English: corresponding, relevant)" and "corresponding (English: corresponding)" can sometimes be mixed. It should be pointed out that , when not emphasizing the difference, the meaning to be expressed is the same.

In order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and functions. Those skilled in the art can understand that words such as "first" and "second" are not intended to limit the quantity and execution order.

The learning recommendation of the enterprise online learning platform can help students improve the efficiency of course selection and accurate learning. The enterprise online learning platform has multi-level administrator users, who are responsible for a certain range of user learning behavior management and platform operation. It is necessary to understand the user's learning frequency, learning progress, and learning hotspots and other information, and recommend suitable courses to suitable users. . User portraits and recommendation methods have different focuses in different application fields. For example, user portraits in the marketing field mainly focus on the consumption habits of users, and in the field of video recommendation, they mainly focus on users' movie viewing preferences. Therefore, it is necessary to design according to the characteristics of each application scenario. Corresponding user profiles and recommended methods. After retrieval, the existing related technologies are mainly concentrated in the fields of e-commerce and search. For example, Amazon, Ali and Baidu have proposed many implementation methods in this field. There are very few inventions disclosed in the field of online education. The one related to the application scenario is "CN106528656A-A method and system for implementing course recommendation based on student history and real-time learning state parameters-disclosure". The course resource recommendation method and system of the online education platform integrates the massive curriculum resources on the online education platform into a tree-like data structure, and comprehensively considers the professional knowledge system and the academic characteristics of the massive colleges to form a user portrait model. On this basis Use the learning history and learning status of individual colleges to realize classification pattern recognition, and then generate personalized course recommendations from the big data course resource database according to the classification of students and the relevance of courses. However, this method cannot be applied to the enterprise online learning platform. At present, there are few studies on enterprise online learning platforms, and it is impossible to recommend suitable courses to students.

Based on the above technical background and the problems existing in the prior art, referring to FIG. 1 , an embodiment of the present invention provides a course recommendation method, which includes:

S1. Obtain basic information data. The basic information data includes: the student's position attribute, the student's age, the student's study course, the length of the student's study of each course, the release time of the course, the current time, and the keywords of the company's current strategic direction.

S2. Generate at least one first course recommendation list according to the basic information data, and each first course recommendation list is generated from one or more pieces of data in the basic information data.

In an implementation scheme, referring to FIG. 2 , step S2 specifically includes:

S211. Determine the total number of students for each course of the same post according to the post attribute of the trainee and the course of study of the trainee.

S212. Determine the hot courses of the same post according to the total number of students studying each course of the same post, and count the number of hot courses of the same post.

S213. If the number of hot courses in the same position is greater than the first preset threshold, count the age of each hot course in the same position according to the hot courses in the same position, the learning courses of the students, and the age of the students.

S214. Determine the average age of students of each hotspot course in the same position according to the age of the students of each hotspot course in the same position.

S215. Determine the age deviation value according to the following formula, wherein the age deviation value is the age deviation value of each student of the learning hotspot course of the same position:

D _i =|CY _i -Y ₀ |;

Among them, D _i represents the age deviation value, CY _i represents the average age of students in each hot course (i=1, 2, ..., n, n represents the number of hot courses in the same position), Y ₀ represents the students in each hot course age.

S216. Use the hot courses corresponding to the statistical age deviation value less than or equal to the second preset threshold as the first course recommendation list.

In an implementation scheme, referring to FIG. 3 , step S2 further includes the following steps:

S221. If the student's learning time of each course is greater than the preset learning time of each course, determine that the student has completed the course, and count the number of students who have completed each course and the number of students who have completed all the courses.

Exemplarily, the preset study duration of each course may be set to be 80% of the total study duration of each course.

S222. Determine the total number of students for each course according to the learning courses of the students, and determine the number of hot courses and the number of hot courses according to the total number of students for each course.

S223. If the number of hot courses is greater than the third preset threshold, count the number of students in each course, the total study time of all students in each course, and the study time of all courses The number of people and the total study time of all students in all courses.

S224. Perform normalization processing on the number of students who have studied in each course and the number of students who have completed all the courses to generate a normalized number of completed learning in each course.

Exemplarily, the normalized number of completed courses for a certain course = the number of students who have studied in this course/the number of students who have completed all courses.

S225 , normalize the number of learners of each course and the number of learners of all courses to generate the normalized number of learners of each course.

Exemplarily, the normalized number of learners of a certain course=the number of learners of this course/the number of learners of all courses.

S226. Perform normalization processing on the total learning duration of all students of each course and the total learning duration of all students in all courses to generate the normalized learning duration of each course.

Exemplarily, the normalized study time of a certain course=the total study time of all students of this course/the total study time of all students of all courses.

S227: Acquire the time limit value T _j of each course according to the formula T _j =1/(current time-j course release time+1), where j=1, 2, ..., m, m is the number of all courses.

S228: Perform weighting processing on the normalized number of completed learning for each course, the normalized number of learners for each course, the normalized learning duration for each course, and the aging value _Tj of each course to generate a weighted value for each course.

Exemplarily, the weighted value of a certain course=α×the number of normalized study completions of the course+β×the normalized number of learners of the course+γ×the normalized study duration of the course+η×the aging value of the course; Wherein, α+β+γ+η=1, 0≤α, β, γ, η≤1.

In an implementation manner, after step S228, it further includes: S2281, arranging the weighted value of each course in descending order, and taking the weighted value of the top t ranks to generate a weighted value list, and according to the weighted value in the weighted value list The course corresponding to the value generates the first course recommendation list.

In an implementation manner, after step S228, it further includes: S2282, exclude the courses corresponding to the weighted value of each course according to the keywords of the current strategic direction of the enterprise, generate the weighted value of the strategic course, and weight the strategic course Values are sorted, and the courses corresponding to the top k strategic course weights are selected to generate the first course recommendation list.

In an implementation manner, generating at least one first course recommendation list according to the basic information data may further include the following steps:

S231. Acquire the aging value T _j of each course according to the formula T _j =1/(current time-j course release time+1), where j=1, 2, ..., m, m is the number of all courses.

S232. Sort the aging values T _j of all courses from large to small, and select the courses corresponding to the first p-bit aging values T _j to generate the first course recommendation list.

S3. Exclude courses in at least one first course recommendation list according to the exclusion strategy to generate at least one second course recommendation list, wherein the first course recommendation list and the second course recommendation list correspond one-to-one.

The exclusion strategy specifically includes: excluding at least one course in the first course recommendation list whose similarity ratio with the courses already learned by the student exceeds a first preset ratio.

S4. Perform duplicate checking and over-threshold processing on at least one second course recommendation list to generate a final course recommendation list.

For step S4, referring to FIG. 4, the specific implementation is as follows:

S41. Generate at least one third course recommendation list for the same courses in each second course recommendation list, and count the number of courses in all the third course recommendation lists.

S42. If the number of courses in all the third course recommendation lists does not exceed the fifth preset threshold, count the courses in all the third course recommendation lists to generate a final course recommendation list.

If the number of courses in all the third course recommendation lists exceeds the fifth preset threshold, remove the corresponding number of courses from each third course recommendation list according to the second preset ratio according to the course ranking in each third course recommendation list. courses, and generate at least one third course recommendation list with the corresponding number removed.

S43. Count all the courses from which the corresponding number of the third course recommendation list is removed to generate a final course recommendation list.

In an exemplary solution, according to the three first course recommendation lists generated in steps S1, S211-S228, S2281, and S2282, the final course recommendation list generated according to steps S3 and S4 is mainly a standardized course recommendation for student groups. .

In another exemplary solution, the four first course lists generated according to steps S1, S211-S228, S2281, S2282, S231, and S232 are combined with two of the prior art based on student preference method and collaborative filtering method. The first course recommendation list, the final course recommendation list generated according to steps S3 and S4 is mainly for personalized course recommendation for students.

It should be noted that the student preference-based method performs learning recommendation according to the preferences submitted by the students and personal learning history preferences, and generates a first course recommendation list according to the recommendation result. Among them, the preferences submitted by the students refer to the preference information submitted by the students according to the prompts of the enterprise online learning platform when they log in to the learning platform for the first time; the personal learning history preference refers to the user behavior formed by the system according to the students' browsing and learning history courses on the enterprise online learning platform. image information. Based on the collaborative filtering method, the learning recommendation is performed according to the system filtering method, and the first course recommendation list is generated according to the recommendation result. Collaborative filtering refers to using the preferences of a group with similar interests and common experience to recommend information that students are interested in. Collaborative filtering algorithms are widely used in the global Internet field due to their excellent speed and robustness. The specific implementation methods of the student preference-based method and the collaborative filtering method are implemented by reference to the prior art, and are not repeated here.

In the above method, first, basic information data such as the student's position attribute, the student's age, the student's study course, the length of the student's study of each course, the release time of the course, the current time, and the keywords of the company's current strategic direction are obtained; and At least one first course recommendation list is generated according to one or more pieces of data in the basic information data; then, courses in the at least one first course recommendation list are excluded according to the exclusion strategy, and at least one second course recommendation list is generated, wherein The first course recommendation list is in one-to-one correspondence with the second course recommendation list; at least one second course recommendation list is subjected to duplicate checking and over-threshold processing to generate a final course recommendation list. The embodiment of the present invention can generate recommended courses suitable for students through basic information data, so that students can recommend suitable courses to students in advance when they access the enterprise online learning platform, thereby improving the learning efficiency of students.

5, a course recommendation device 50 according to an embodiment of the present invention, the device 50 includes:

The obtaining unit 501 is used to obtain basic information data, the basic information data includes: the student's position attribute, the student's age, the student's study course, the length of the student's study of each course, the course release time, the current time, and the key to the company's current strategic direction word.

The processing unit 502 is configured to generate at least one first course recommendation list according to the basic information data acquired by the acquiring unit 501 , and each first course recommendation list is generated from one or more pieces of data in the basic information data.

The processing unit 502 is further configured to exclude courses in the at least one first course recommendation list according to the exclusion strategy, and generate at least one second course recommendation list, wherein the first course recommendation list corresponds to the second course recommendation list one-to-one.

The processing unit 502 is further configured to perform duplicate checking and over-threshold processing on at least one second course recommendation list to generate a final course recommendation list.

In an exemplary solution, the processing unit 502 is specifically configured to determine the total number of people who study each course in the same position according to the post attribute of the student obtained by the obtaining unit 501 and the study courses of the student.

The processing unit 502 is further configured to determine the hot courses of the same position according to the total number of students studying each course in the same position, and count the number of hot courses of the same position.

The processing unit 502 is further configured to determine that when the number of hot courses in the same post is greater than the first preset threshold, then according to the hot courses in the same post, the learning courses of the students acquired by the acquiring unit 501 and the age of the students acquired by the acquiring unit 501 Count the same posts. The age of students for each hot course.

The processing unit 502 is further configured to determine the average age of the students of each hot course in the same position according to the age of the students of each hot course in the same position.

The processing unit 502 is further configured to determine the age deviation value according to the following formula, wherein the age deviation value is the age deviation value of each student of the learning hotspot course of the same post:

D _i =|CY _i -Y ₀ |;

Among them, D _i represents the age deviation value, CY _i represents the average age of students in each hot course (i=1, 2, ..., n, n represents the number of hot courses in the same position), Y ₀ represents the students in each hot course age.

The processing unit 502 is further configured to count the hot courses corresponding to the age deviation value less than or equal to the second preset threshold as the first course recommendation list.

In an exemplary solution, the processing unit 502 is specifically configured to determine that the duration of the students studying each course is greater than the preset learning duration of each course, then determine that the students have completed the course learning, and count the students who have completed the learning of each course number and the number of students who completed all courses.

The processing unit 502 is further configured to determine the total number of people who study each course according to the learning courses of the students, and determine the number of hot courses and the number of hot courses according to the total number of people who study each course.

The processing unit 502 is further configured to determine that the number of hot courses is greater than the third preset threshold, then according to the learning courses of the students acquired by the acquiring unit 501 and the duration of the students learning each course, count the number of learners of each course, and all of the students in each course. The total study time of students, the number of students in all courses, and the total study time of all students in all courses.

The processing unit 502 is further configured to perform normalization processing on the number of students who have studied in each course and the number of students who have completed all the courses to generate a normalized number of completed learning in each course.

The processing unit 502 is further configured to perform normalization processing on the number of learners in each course and the number of learners in all courses to generate the normalized number of learners in each course.

The processing unit 502 is further configured to perform normalization processing on the total learning duration of all students of each course and the total learning duration of all students in all courses to generate the normalized learning duration of each course.

The processing unit 502 is further configured to obtain the aging value T _j of each course according to the formula T _j =1/(the release time of the j course+1), where j=1, 2, . . . , m is the value of all courses quantity.

The processing unit 502 is further configured to perform weighted processing on the normalized number of completed learning for each course, the normalized number of students for each course, the normalized learning duration for each course, and the aging value T _j of each course to generate each The weighted value of the course.

In an exemplary solution, the processing unit 502 is further configured to rank the weighted value of each course in descending order, and take the weighted value of the top t to generate a weighted value list, according to the weighted value in the weighted value list The course corresponding to the value generates the first course recommendation list.

In an exemplary solution, the processing unit 502 is further configured to exclude the course corresponding to the weighted value of each course according to the keywords of the current strategic direction of the enterprise, generate the weighted value of the strategic course, and weight the strategic course Values are sorted, and the courses corresponding to the top k strategic course weights are selected to generate the first course recommendation list.

In an exemplary solution, the exclusion strategy specifically includes: excluding at least one course in the first course recommendation list whose similarity ratio with the courses already taken by the student exceeds a first preset ratio.

In an exemplary solution, the processing unit 502 is specifically configured to generate at least one third course recommendation list for the same course in each second course recommendation list, and count the number of courses in all the third course recommendation lists .

The processing unit 502 is further configured to determine that the number of courses in all the third course recommendation lists does not exceed the fifth preset threshold, and then count the courses in all the third course recommendation lists to generate a final course recommendation list.

The processing unit 502 is further configured to determine that the number of courses in all the third course recommendation lists exceeds the fifth preset threshold, and then place each third course recommendation list according to the second preset according to the course ranking in each third course recommendation list. A proportion is set to remove a corresponding number of courses, and at least one third course recommendation list from which the corresponding number is removed is generated.

The processing unit 502 is further configured to count all the courses from which the corresponding number of the third course recommendation list is removed to generate a final course recommendation list.

Since the course recommendation apparatus in the embodiments of the present invention can be applied to implement the above method embodiments, the technical effects that can be obtained may also refer to the above method embodiments, and details are not described herein again in the embodiments of the present invention.

In the case of using an integrated unit, FIG. 6 shows a possible schematic structural diagram of the course recommendation apparatus 50 involved in the above embodiment. The course recommendation apparatus 50 includes: a processing module 601 , a communication module 602 and a storage module 603 . The processing module 601 is used to control and manage the actions of the course recommendation apparatus 50 , for example, the processing module 601 is used to support the course recommendation apparatus 50 to execute the processes S211 - S228 , S2281 , S2282 , S3 and S4 in FIG. 3 . The communication module 602 is used to support the communication between the course recommendation device 50 and other entities. The storage module 603 is used for storing program codes and data of the course recommendation apparatus 50 .

The processing module 601 may be a processor or a controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), or an application-specific integrated circuit (application-specific integrated circuit). circuit, ASIC), field programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logical blocks, modules and circuits described in connection with this disclosure. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 602 may be a transceiver, a transceiver circuit, a communication interface, or the like. The storage module 603 may be a memory.

When the processing module 601 is the processor shown in FIG. 7 , the communication module 602 is the transceiver shown in FIG. 7 , and the storage module 603 is the memory shown in FIG. 7 , the course recommendation apparatus 50 involved in the embodiment of the present application may be as follows The course recommendation device 50 .

Referring to FIG. 7 , the course recommendation apparatus 50 includes: a processor 701 , a transceiver 702 , a memory 703 and a bus 704 .

The processor 701, the transceiver 702, and the memory 703 are connected to each other through a bus 704; the bus 704 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus Wait. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

The processor 701 may be a general-purpose central processing unit (Central Processing Unit, CPU), a microprocessor, an application-specific integrated circuit (Application-Specific Integrated Circuit, ASIC), or one or more processors for controlling the execution of the programs of the present application. integrated circuit.

The memory 703 may be Read-Only Memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (Random Access Memory, RAM) or other types of information and instructions that can be stored The dynamic storage device can also be an Electrically Erasable Programmable Read-only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM), or other optical disk storage, optical disk storage ( including compact discs, laser discs, compact discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or capable of carrying or storing desired program code in the form of instructions or data structures and capable of being stored by a computer any other medium taken, but not limited to this. The memory can exist independently and be connected to the processor through a bus. The memory can also be integrated with the processor.

Wherein, the memory 703 is used for storing the application program code for executing the solution of the present application, and the execution is controlled by the processor 701 . The transceiver 702 is configured to receive content input from an external device, and the processor 701 is configured to execute the application code stored in the memory 703, thereby implementing the course recommendation method described in the embodiments of the present application.

It should be understood that, in various embodiments of the present application, the size of the sequence numbers of the above-mentioned processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not be dealt with in the embodiments of the present application. implementation constitutes any limitation.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the above-described devices, devices and units, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other manners. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general purpose computer, special purpose computer, computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server, or data center The transmission is carried out to another website site, computer, server or data center by wire (eg coaxial cable, optical fiber, Digital Subscriber Line, DSL) or wireless (eg infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or data storage devices including one or more servers, data centers, etc. that can be integrated with the medium. The usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVD), or semiconductor media (eg, Solid State Disk (SSD)), and the like.

Embodiments of the present invention also provide a computer program product, which can be directly loaded into a memory and contains software codes, which can implement the above-mentioned course recommendation method after being loaded and executed by a computer.

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited to this. should be covered within the scope of protection of this application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims (14)

1. A course recommendation method, the method comprising:

acquiring basic information data, wherein the basic information data comprises: the post attribute of the student, the age of the student, the learning course of the student, the time length of each learning course of the student, the release time of the course, the current time and the keywords of the current strategic direction of the enterprise;

generating at least one first course recommendation list according to the basic information data, wherein each first course recommendation list is generated by one or more items of data in the basic information data;

removing courses in the at least one first course recommendation list according to a removal strategy to generate at least one second course recommendation list, wherein the first course recommendation list is in one-to-one correspondence with the second course recommendation list;

performing duplicate checking and super-threshold processing on the at least one second course recommendation list to generate a final course recommendation list;

the generating at least one first course recommendation list according to the basic information data specifically includes:

determining the total number of learners of each course on the same post according to the post attributes of the student and the learning courses of the student;

determining hot courses of the same post according to the total number of learners of each course of the same post, and counting the number of the hot courses of the same post;

if the number of the hot courses on the same post is larger than a first preset threshold value, counting the student age of each hot course on the same post according to the hot courses on the same post, the learning courses of the students and the student ages;

determining the average age of the trainees of each hot course in the same post according to the ages of the trainees of each hot course in the same post;

determining an age bias value according to the following formula, wherein the age bias value is an age bias value of each student of the same position learning hotspot course:

D_i＝|CY_i-Y₀|；

wherein D is_iIndicates the age deviation value, CY_iRepresenting the average age of each hot course student, i is 1, 2, …, n, n represents the number of hot courses in the same position, Y₀Representing the student age of each of the hot courses;

and counting the hot course corresponding to the age deviation value smaller than or equal to a second preset threshold value to be used as the first course recommendation list.

2. The course recommendation method as claimed in claim 1, wherein said generating at least one first course recommendation list according to said basic information data specifically comprises:

if the time length of each course learned by the student is greater than the preset learning time length of each course, determining that the student completes the course learning, and counting the number of students completing the course learning and the number of students completing all the course learning;

determining the total number of learners of each course according to the learning courses of the student, and determining hot courses and the number of the hot courses according to the total number of learners of each course;

if the number of the hot courses is larger than a third preset threshold, counting the number of the learning people of each course, the total learning time of all the students of each course, the number of the learning people of all the courses and the total learning time of all the students of all the courses according to the learning courses of the students and the learning time of each course of the students;

normalizing the number of the students who learn in each course and the number of the students who finish learning in all the courses to generate a normalized learning finishing number of each course;

normalizing the number of the learners of each course and the number of the learners of all the courses to generate a normalized number of the learners of each course;

normalizing the total learning time length of all the students of each course and the total learning time length of all the students of all the courses to generate a normalized learning time length of each course;

according to the formula T_jAcquiring the aging value T of each course 1/(the current time-j, the release time of the course +1)_jWherein j is 1, 2, …, m, m is the number of all courses;

the number of learning completion of one learning for each course, the number of learning population for each course, the learning duration for each course, and the aging value T for each course_jAnd performing weighting processing to generate a weighted value of each course.

3. The course recommending method according to claim 2, wherein said learning completion number for each course, said learning population for each course, said learning time length for each course, and said aging value T for each course_jPerforming a weighting process to generate a weighting value for each course, and then:

and arranging the weighted value of each course from big to small, generating a weighted value list by taking the weighted value of the top t, and generating the first course recommendation list according to the course corresponding to the weighted value in the weighted value list.

4. The course recommending method according to claim 2, wherein said learning completion number for each course, said learning population for each course, said learning time length for each course, and said aging value T for each course_jPerforming a weighting process to generate a weight for each courseValues, thereafter also including:

and removing the course corresponding to the weighted value of each course according to the keywords of the current strategic direction of the enterprise, generating the weighted value of the strategic course, sequencing the weighted values of the strategic course, and selecting the course corresponding to the weighted value of the strategic course at the top k positions to generate the first course recommendation list.

5. The course recommendation method of claim 1, wherein the exclusion policy specifically comprises: and excluding the courses with the similarity proportion to the courses already learned by the student exceeding a first preset proportion from the at least one first course recommendation list.

6. The course recommendation method of claim 1, wherein said performing a duplicate checking and super-threshold processing on said second course recommendation list to generate a final course recommendation list comprises:

comparing the courses in each second course recommendation list, removing the same courses, generating at least one third course recommendation list, and counting the number of the courses in all the third course recommendation lists;

if the number of the courses in all the third course recommendation lists does not exceed a fifth preset threshold value, counting the courses in all the third course recommendation lists to generate a final course recommendation list;

if the number of the courses in all the third course recommendation lists exceeds a fifth preset threshold, removing the corresponding number of the courses from each third course recommendation list according to a second preset proportion according to the ranking of the courses in each third course recommendation list, and generating at least one third course recommendation list with the corresponding number removed;

and counting all the courses with the corresponding number of the third course recommendation lists removed to generate a final course recommendation list.

7. A course recommending apparatus, comprising:

an acquisition unit configured to acquire basic information data, the basic information data including: the post attribute of the student, the age of the student, the learning course of the student, the time length of each learning course of the student, the release time of the course, the current time and the keywords of the current strategic direction of the enterprise;

the processing unit is used for generating at least one first course recommendation list according to the basic information data acquired by the acquisition unit, and each first course recommendation list is generated by one or more items of data in the basic information data;

the processing unit is further configured to exclude courses in the at least one first course recommendation list according to an exclusion policy, and generate at least one second course recommendation list, where the first course recommendation list and the second course recommendation list are in one-to-one correspondence;

the processing unit is further configured to perform duplicate checking and super-threshold processing on the at least one second course recommendation list to generate a final course recommendation list;

the processing unit is specifically configured to determine a total number of learners of each course on the same post according to the post attributes of the trainee and the learning courses of the trainee, which are acquired by the acquisition unit;

the processing unit is further used for determining the hot courses on the same post according to the total number of learners of each course on the same post, and counting the number of the hot courses on the same post;

the processing unit is further configured to, when it is determined that the number of the hot-spot courses on the same post is greater than a first preset threshold, count the student age of each hot-spot course on the same post according to the hot-spot course on the same post, the learning course of the student acquired by the acquiring unit, and the student age acquired by the acquiring unit;

the processing unit is further used for determining the average age of each hot-spot course student in the same post according to the ages of the students in each hot-spot course in the same post;

the processing unit is further configured to determine an age deviation value according to the following formula, where the age deviation value is an age deviation value of each student of the same-position learning hotspot course:

D_i＝|CY_i-Y₀|；

wherein D is_iIndicates the age deviation value, CY_iRepresenting the average age of each hot course student, i is 1, 2, …, n, n represents the number of hot courses in the same position, Y₀Representing the student age of each of the hot courses;

the processing unit is further configured to count the hot course corresponding to the age deviation value being less than or equal to a second preset threshold value as the first course recommendation list.

8. The course recommending apparatus of claim 7, comprising:

the processing unit is specifically configured to determine that the learning duration of each course of the student is greater than the preset learning duration of each course, determine that the student completes the course learning, and count the number of students who complete the learning of each course and the number of students who complete the learning of all courses;

the processing unit is further used for determining the total number of learners of each course according to the learning courses of the student, and determining the hot courses and the number of the hot courses according to the total number of learners of each course;

the processing unit is further configured to determine that the number of the hot courses is greater than a third preset threshold, and count the number of learning people of each course, the total learning time of all the students of each course, the number of learning people of all the courses, and the total learning time of all the students of all the courses according to the learning courses of the students and the learning time of each course acquired by the acquisition unit;

the processing unit is further configured to perform normalization processing on the number of students learning in each course and the number of students completing learning in all courses to generate a normalized learning completion number of each course;

the processing unit is further used for carrying out normalization processing on the number of the learners of each course and the number of the learners of all the courses to generate a normalized number of the learners of each course;

the processing unit is further configured to perform normalization processing on the total learning duration of all the students in each course and the total learning duration of all the students in all the courses to generate a normalized learning duration of each course;

the processing unit is also used for processing the data according to a formula T_jAcquiring the aging value T of each course 1/(the current time-j, the release time of the course +1)_jWherein j is 1, 2, …, m is the number of all courses;

the processing unit is further used for counting the number of completed learning in one-to-one mode of each course, the number of learning people in one-to-one mode of each course, the learning duration in one-to-one mode of each course and the aging value T of each course_jAnd performing weighting processing to generate a weighted value of each course.

9. The course recommending apparatus of claim 8, comprising:

the processing unit is further configured to arrange the weighted values of each course from large to small, take the weighted value of t place before ranking to generate a weighted value list, and generate the first course recommendation list according to the course corresponding to the weighted value in the weighted value list.

10. The course recommending apparatus of claim 8, comprising:

the processing unit is further configured to exclude the course corresponding to the weighted value of each course according to the keywords in the current strategic direction of the enterprise, generate a weighted value of strategic courses, sort the weighted values of the strategic courses, and select the first k courses corresponding to the weighted values of the strategic courses to generate the first course recommendation list.

11. The course recommending apparatus of claim 7, wherein said exclusion policy specifically comprises: and excluding the courses with the similarity proportion to the courses already learned by the student exceeding a first preset proportion from the at least one first course recommendation list.

12. The course recommending apparatus of claim 7, comprising:

the processing unit is specifically configured to generate at least one third course recommendation list for the same course in each second course recommendation list, and count the number of courses in all the third course recommendation lists;

the processing unit is further configured to determine that the number of courses in all the third course recommendation lists does not exceed a fifth preset threshold, and count the courses in all the third course recommendation lists to generate a final course recommendation list;

the processing unit is further configured to determine that the number of courses in all the third course recommendation lists exceeds a fifth preset threshold, remove a corresponding number of courses from each third course recommendation list according to a second preset ratio according to the ranking of the courses in each third course recommendation list, and generate at least one third course recommendation list from which the corresponding number is removed;

and the processing unit is also used for counting all the courses with the third course recommendation lists with the corresponding quantity removed to generate a final course recommendation list.

13. A course recommending apparatus, characterized in that said course recommending apparatus comprises a processor and a memory, said memory is used for coupling with said processor and storing the necessary program instructions and data of said course recommending apparatus, said processor is used for executing the program instructions stored in said memory, so that said course recommending apparatus executes the course recommending method according to any one of claims 1-6.

14. A computer storage medium, characterized in that the computer storage medium has stored therein computer program code which, when run on a course recommending apparatus according to claim 13, causes the course recommending apparatus to execute the course recommending method according to any one of claims 1-4.

Images