An education application recommendation method and device, equipment, storage medium and product

Abstract

This application discloses an educational application recommendation method, apparatus, device, storage medium, and product. The method includes: calculating a first degree of interest of an enterprise in its accessed educational applications based on the enterprise's location and historical behavioral data of the enterprise's accessed educational applications; wherein the historical behavioral data includes at least one of the following: historical usage behavior data and historical browsing behavior data; calculating interest similarity between enterprises based on the first degree of interest; predicting a second degree of interest of a target enterprise in its unaccessed educational applications based on the interest similarity; and making recommendations for the target enterprise based on the second degree of interest. The embodiments of this application can meet the personalized recommendation needs of enterprises for educational applications.

Description

Technical Field

[0001] This application relates to the field of recommendation technology, and in particular to a method, apparatus, device, storage medium, and product for recommending educational applications. Background Technology

[0002] Educational companies can subscribe to educational applications through mobile cloud platforms and use them in the cloud. However, the current recommendation and display of educational applications relies on manually configured sorting rules, which are usually based on the platform's own marketing needs and do not take into account the interests and preferences of enterprise users, making it difficult to meet the personalized recommendation needs of enterprises for educational applications. Summary of the Invention

[0003] This application provides a method, apparatus, device, storage medium, and product for recommending educational applications, in order to address the problem that existing technologies do not take into account the interests and preferences of enterprise users, making it difficult to meet the personalized recommendation needs of enterprises for educational applications.

[0004] To achieve the above objectives, embodiments of this application provide an educational application recommendation method, including: Based on the region where the enterprise is located and the enterprise's historical behavior data on its accessed educational applications, the enterprise's first level of interest in its accessed educational applications is calculated; wherein, the historical behavior data includes at least one of the following: historical usage behavior data and historical browsing behavior data; Calculate the interest similarity between enterprises based on the first interest score; Based on the interest similarity, predict the target company's second interest in its unaccessed educational applications; Recommendations are made for the target companies based on the second level of interest.

[0005] As an improvement to the above solution, the step of calculating the enterprise's first level of interest in its accessed educational applications based on the enterprise's location and its historical behavioral data on accessed educational applications includes: Based on the company's location, the degree of interest in the company's accessed educational applications can be obtained from the region where the company is located. Based on the historical usage data of the educational applications accessed by the enterprise, the usage volume of the educational applications accessed by the enterprise is statistically analyzed, and the usage volume is normalized. Based on the historical browsing behavior data of enterprises in their accessed educational applications, the number of views of enterprises in their accessed educational applications is counted, and the number of views is normalized. The first interest level is obtained based on the stated level of interest, the normalized usage, and the normalized pageviews.

[0006] As an improvement to the above scheme, the step of calculating the interest similarity between enterprises based on the first interest level includes: Construct an interest matrix using the first interest score as matrix elements; Based on the interest matrix, the interest similarity between enterprises is calculated using the cosine similarity algorithm.

[0007] As an improvement to the above scheme, the step of predicting the target enterprise's second level of interest in its unaccessed educational applications based on the interest similarity includes: Based on the interest similarity, one or more companies that are most similar to the target company are selected to form a candidate company set. The second interest level is predicted based on the interest level of each enterprise in the candidate enterprise set in the unaccessed educational applications of the target enterprise.

[0008] As an improvement to the above scheme, the step of predicting the second interest degree based on the interest degree of each enterprise in the candidate enterprise set for the unaccessed educational applications of the target enterprise includes: Calculate the average interest level based on the interest level of each enterprise in the candidate enterprise set towards the unaccessed educational applications of the target enterprise; The average interest level is used as the second interest level.

[0009] As an improvement to the above solution, the step of recommending the target enterprise based on the second degree of interest includes: Based on the second level of interest, one or more unaccessed educational applications with the highest level of interest are selected and recommended to the target enterprise.

[0010] To achieve the above objectives, embodiments of this application also provide an educational application recommendation device, comprising: The first calculation module is used to calculate the enterprise's first level of interest in its accessed educational applications based on the enterprise's location and the enterprise's historical behavior data in its accessed educational applications; wherein, the historical behavior data includes at least one of the following: historical usage behavior data and historical browsing behavior data; The second calculation module is used to calculate the interest similarity between enterprises based on the first interest degree; The prediction module is used to predict the target enterprise's second level of interest in its unaccessed educational applications based on the interest similarity. The recommendation module is used to make recommendations for the target company based on the second degree of interest.

[0011] To achieve the above objectives, this application also provides an educational application recommendation device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the educational application recommendation method as described above.

[0012] To achieve the above objectives, embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program; wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the educational application recommendation method as described above.

[0013] To achieve the above objectives, embodiments of this application also provide a computer program product, including a computer program / instructions, which, when executed by a processor, implement the educational application recommendation method as described above.

[0014] Compared with existing technologies, the educational application recommendation method, apparatus, device, storage medium, and product provided in this application calculate a company's first level of interest in its accessed educational applications based on the company's location and historical behavioral data of its accessed educational applications. The historical behavioral data includes at least one of the following: historical usage behavior data and historical browsing behavior data. Based on the first level of interest, an interest similarity between companies is calculated. Based on the interest similarity, a second level of interest of the target company in its unaccessed educational applications is predicted. Based on the second level of interest, recommendations are made to the target company. Therefore, this application combines the company's location and historical behavioral data of its accessed educational applications to obtain the company's interest in educational applications, and recommends educational applications based on this interest, thus meeting the personalized recommendation needs of companies for educational applications. Attached Figure Description

[0015] Figure 1 This is a flowchart of an educational application recommendation method provided in an embodiment of this application; Figure 2 This is a structural block diagram of an educational application recommendation device provided in an embodiment of this application; Figure 3 This is a structural block diagram of an educational application recommendation device provided in an embodiment of this application. Detailed Implementation

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0017] In the description of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0018] In this application description, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0019] In this application description, the terms "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The term "based on" means "at least partially based on." The term "according to" means "at least partially according to." The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments." The term "and / or" means at least one of the connected objects, such as A and / or B, indicating three cases: including only A, only B, and both A and B. Unless otherwise stated, the term "multiple" means two or more.

[0020] See Figure 1 , Figure 1 This is a flowchart of an educational application recommendation method provided in an embodiment of this application. The educational application recommendation method includes: S1. Calculate the enterprise's first level of interest in its accessed educational applications based on the enterprise's location and its historical behavior data; wherein, the historical behavior data includes at least one of the following: historical usage behavior data and historical browsing behavior data; S2. Calculate the interest similarity between enterprises based on the first interest degree; S3. Based on the interest similarity, predict the target company's second interest in its unaccessed educational applications; S4. Recommend the target company based on the second degree of interest.

[0021] It is worth noting that "visited educational applications" refers to educational applications that users within the enterprise have accessed, while "unvisited educational applications" refers to educational applications that users within the enterprise have not accessed. This application's embodiment combines the enterprise's location and historical behavioral data regarding its visited educational applications to predict the target enterprise's secondary interest in its unvisited educational applications. Based on this secondary interest, it recommends educational applications to the target enterprise, thus meeting the enterprise's personalized recommendation needs for educational applications.

[0022] In one optional embodiment, calculating the enterprise's first level of interest in its accessed educational applications based on the enterprise's location and its historical behavioral data on accessed educational applications includes: Based on the company's location, the degree of interest in the company's accessed educational applications can be obtained from the region where the company is located. Based on the historical usage data of the educational applications accessed by the enterprise, the usage volume of the educational applications accessed by the enterprise is statistically analyzed, and the usage volume is normalized. Based on the historical browsing behavior data of enterprises in their accessed educational applications, the number of views of enterprises in their accessed educational applications is counted, and the number of views is normalized. The first interest level is obtained based on the stated level of interest, the normalized usage, and the normalized pageviews.

[0023] Understandably, a mapping relationship between regions and the degree of interest in educational applications is pre-defined. Generally, different enterprises within the same region (such as a province) use educational applications with high similarity. This mapping relationship can be designed based on distance; the closer two enterprises are, the more similar their degree of interest in the same educational application. The range of region and degree of interest in educational applications is: greater than or equal to 0 and less than or equal to 1, with higher values ​​indicating greater interest. For example, influenced by factors such as economic development level, educational policy orientation, and actual regional needs, there are significant regional differences in the selection of educational applications among different provinces. For instance, if regions are divided into developed eastern provinces (Beijing, Shanghai, Zhejiang, Jiangsu, Guangdong, etc.), central provinces (Henan, Hubei, Hunan, Anhui, Jiangxi, etc.), and western and northeastern provinces (Sichuan, Shaanxi, Yunnan, Guizhou, Heilongjiang, Jilin, etc.), the degree of interest in a particular educational application in eastern provinces ranges from 0.7 to 1.0, in central provinces from 0.4 to 0.7, and in western and northeastern provinces from 0.1 to 0.4.

[0024] enterprise In its own accessed educational applications usage This refers to: within a preset time window (e.g., one day), enterprises All users within the app have access to the educational application. The cumulative number of times or duration of usage behavior. (Enterprise) The statistical rule for a user's usage behavior is as follows: If a user performs any business operations such as viewing details, adding data, deleting data, or modifying data after opening the application, this is counted as one usage behavior for that user. In other words, any multiple actions involving business operations performed after launching the application are considered a single usage behavior.

[0025] enterprise In its own accessed educational applications Page views This refers to: within a preset time window (e.g., one day), enterprises All users within the app have access to the educational application. The cumulative number of browsing activities or the duration of browsing time. (Enterprise) The statistical rules for a user's browsing behavior are as follows: If a user opens the application and only performs pure browsing operations such as switching pages, refreshing pages, and scrolling pages, without performing business operations such as viewing details, adding data, deleting data, or modifying data, this is counted as one browsing behavior for that user. In other words, all pure browsing operations performed after launching the application are counted as one browsing behavior. Furthermore, to filter out abnormal behaviors such as automated access and high-frequency browsing, only browsing behaviors with a dwell time exceeding a set threshold (e.g., 2 seconds) are counted.

[0026] Let's take the cumulative number of occurrences as an example. Suppose a certain company... Some users , and By collecting data from the enterprise's data points User behavior logs for the application, statistics of users The accessed educational application was opened 3 times within the preset time window. If one of these actions involves a purely browsing-based activity with a dwell time exceeding 2 seconds, and two actions involve business-related activities, then the user is considered a valid user. For accessed educational applications The page views are 1, and the user... For accessed educational applications The usage is 2, users and Using the same statistical method, we obtained user data. For accessed educational applications Page views and usage, as well as users For accessed educational applications The number of page views and usage. Then the enterprise... Educational applications have been accessed. Pageviews for users For accessed educational applications Page views + users For accessed educational applications Page views + users For accessed educational applications Page views, businesses Educational applications have been accessed. Usage for users For accessed educational applications Usage + Users For accessed educational applications Usage + Users For accessed educational applications Usage.

[0027] For example, the enterprise is calculated according to the following formula. For the educational applications that have been accessed First interest :

[0028]

[0029]

[0030]

[0031]

[0032] In the formula, Indicates enterprise In its own accessed educational applications Usage Indicates enterprise users in For accessed educational applications Usage Indicates enterprise The user set. Indicates enterprise In its own accessed educational applications The normalized value of usage. Indicates enterprise The collection of educational applications that have been accessed. Indicates enterprise In its own accessed educational applications Usage. Indicates enterprise In its own accessed educational applications Page views Indicates enterprise users in For accessed educational applications Page views. Indicates enterprise In its own accessed educational applications The normalized value of pageviews, Indicates enterprise In its own accessed educational applications Page views. Indicates enterprise The region has access to educational applications. The level of interest. , , This represents the weighting coefficients.

[0033] In an optional embodiment, calculating the interest similarity between enterprises based on the first interest level includes: Construct an interest matrix using the first interest score as matrix elements; Based on the interest matrix, the interest similarity between enterprises is calculated using the cosine similarity algorithm.

[0034] In one specific embodiment, the constructed interest matrix is ​​shown in Table 1. Indicates enterprise For educational applications The first level of interest.

[0035] Table 1

[0036] The cosine similarity calculation method is to calculate the similarity between enterprises. and enterprises The interest is considered as two n-dimensional vectors consisting of the enterprise's initial interest level and the first interest level. The geometric angle between the two vectors is then calculated. The larger the angle, the lower the similarity of interests between the two enterprises. When the angle is 90 degrees, it means the two enterprises have no shared interest in visited educational applications. When the angle is 0 degrees, it means the two enterprises have exactly the same interest in visited educational applications, and the similarity of interests between the two enterprises is at its maximum.

[0037] Based on the cosine similarity algorithm, enterprises and enterprises Interest similarity between The calculation formula is as follows:

[0038] in, Indicates enterprise For accessed educational applications First level of interest Indicates enterprise For accessed educational applications First level of interest Indicates enterprise and enterprises A shared collection of accessed educational applications. Indicates enterprise The collection of educational applications that have been accessed. Indicates enterprise The collection of educational applications that have been accessed.

[0039] After the calculation is completed, the top m companies with the highest interest similarity to the target company are selected by the Top-N method to form a candidate company set. That is, one or more companies that are most similar to the target company are obtained to form a candidate company set.

[0040] In an optional embodiment, predicting the second interest level based on the interest level of each enterprise in the candidate enterprise set for the unaccessed educational application of the target enterprise includes: Based on the interest similarity, one or more companies that are most similar to the target company are selected to form a candidate company set. The second interest level is predicted based on the interest level of each enterprise in the candidate enterprise set in the unaccessed educational applications of the target enterprise.

[0041] This application addresses the problem of unpredictable behavior of target companies towards candidate educational applications by mining the interest similarity between companies and using the interest of companies most similar to the target company in candidate educational applications. This makes the prediction results more closely match the target company's true preferences.

[0042] In one optional embodiment, predicting the target enterprise's second level of interest in its unaccessed educational applications based on the interest similarity includes: Calculate the average interest level based on the interest level of each enterprise in the candidate enterprise set for the unaccessed educational applications. The average interest level is used as the second interest level.

[0043] Specifically, the target company is calculated according to the following formula. Unaccessible educational applications Second interest :

[0044] in, Indicates to the target company Similar sets of candidate companies It is any one of the candidate companies in the set of companies. Indicates the target company Unaccessible educational applications Indicates enterprise For those who have not accessed educational applications interest Represents the set of candidate companies The number of Chinese companies.

[0045] In one optional embodiment, recommending the target enterprise based on the second degree of interest includes: Based on the second level of interest, one or more unaccessed educational applications with the highest level of interest are selected and recommended to the target enterprise.

[0046] This application utilizes the Top-N method to recommend educational applications that the target enterprise has not yet accessed, thus meeting the personalized needs of users.

[0047] See Figure 2 , Figure 2 This is a structural block diagram of an educational application recommendation device 10 provided in an embodiment of this application. The educational application recommendation device 10 includes: The first calculation module 11 is used to calculate the enterprise's first level of interest in its accessed educational applications based on the enterprise's location and the enterprise's historical behavior data in its accessed educational applications; wherein the historical behavior data includes at least one of the following: historical usage behavior data and historical browsing behavior data; The second calculation module 12 is used to calculate the interest similarity between enterprises based on the first interest degree; Prediction module 13 is used to predict the target enterprise's second interest in its unaccessed educational applications based on the interest similarity. The recommendation module 14 is used to make recommendations for the target enterprise based on the second interest level.

[0048] Optionally, the step of calculating the enterprise's initial interest in its accessed educational applications based on the enterprise's location and historical behavioral data of the enterprise's accessed educational applications includes: Based on the company's location, the degree of interest in the company's accessed educational applications can be obtained from the region where the company is located. Based on the historical usage data of the educational applications accessed by the enterprise, the usage volume of the educational applications accessed by the enterprise is statistically analyzed, and the usage volume is normalized. Based on the historical browsing behavior data of enterprises in their accessed educational applications, the number of views of enterprises in their accessed educational applications is counted, and the number of views is normalized. The first interest level is obtained based on the stated level of interest, the normalized usage, and the normalized pageviews.

[0049] Optionally, calculating the interest similarity between enterprises based on the first interest level includes: Construct an interest matrix using the first interest score as matrix elements; Based on the interest matrix, the interest similarity between enterprises is calculated using the cosine similarity algorithm.

[0050] Optionally, predicting the target enterprise's second level of interest in its unaccessed educational applications based on the interest similarity includes: Based on the interest similarity, one or more companies that are most similar to the target company are selected to form a candidate company set. The second interest level is predicted based on the interest level of each enterprise in the candidate enterprise set in the unaccessed educational applications of the target enterprise.

[0051] Optionally, predicting the second interest level based on the interest level of each enterprise in the candidate enterprise set for the unaccessed educational applications of the target enterprise includes: Calculate the average interest level based on the interest level of each enterprise in the candidate enterprise set towards the unaccessed educational applications of the target enterprise; The average interest level is used as the second interest level.

[0052] Optionally, the step of recommending the target enterprise based on the second degree of interest includes: Based on the second level of interest, one or more unaccessed educational applications with the highest level of interest are selected and recommended to the target enterprise.

[0053] It is worth noting that the working process of each module in the educational application recommendation device 10 described in this application embodiment can refer to the working process of the educational application recommendation method described in the above embodiment, and will not be repeated here.

[0054] This application provides an educational application recommendation device 10 that calculates a company's first level of interest in its accessed educational applications based on the company's location and historical behavioral data of its accessed educational applications. The historical behavioral data includes at least one of the following: historical usage behavior data and historical browsing behavior data. Based on the first level of interest, the device calculates the interest similarity between companies. Based on the interest similarity, it predicts a second level of interest of the target company in its unaccessed educational applications. Based on the second level of interest, it makes recommendations to the target company. Therefore, this application combines the company's location and historical behavioral data of its accessed educational applications to obtain the company's interest in educational applications, and recommends educational applications based on this interest, thus meeting the company's personalized recommendation needs for educational applications.

[0055] Furthermore, this application also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the educational application recommendation method as described in any of the above embodiments.

[0056] Furthermore, this application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the educational application recommendation method as described in any of the above embodiments.

[0057] See Figure 3 , Figure 3This is a structural block diagram of an educational application recommendation device 20 provided in an embodiment of this application. The educational application recommendation device 20 includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, it implements the steps in the above-described educational application recommendation method embodiments. Alternatively, when the processor 21 executes the computer program, it implements the functions of each module / unit in the above-described device embodiments.

[0058] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the educational application recommendation device 20.

[0059] The educational application recommendation device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of the educational application recommendation device 20 and does not constitute a limitation on the device. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the educational application recommendation device 20 may also include input / output devices, network access devices, buses, etc.

[0060] The processor 21 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 21 is the control center of the educational application recommendation device 20, connecting all parts of the educational application recommendation device 20 via various interfaces and lines.

[0061] The processor 21 can be any one of a CPU (Central Processing Unit), GPU (Graphics Processing Unit), TPU (Tensor Processing Unit), NPU (Neural Network Processing Unit), DPU (Deep Learning Processing Unit), APU (Accelerated Processing Unit), and GPGPU (General-Purpose Computing on Graphics Processing Unit). The processor 21 is the control center of the educational application recommendation device 20, connecting various parts of the electronic device via various interfaces and lines.

[0062] The memory 22 can be used to store the computer programs and / or modules. The processor 21 implements various functions of the educational application recommendation device 20 by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one educational application required for a function, etc.; the data storage area may store relevant data, etc. In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0063] The modules / units integrated into the educational application recommendation device 20, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 21, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0064] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided in this application, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0065] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications are also considered to be within the scope of protection of this application.

Claims

1. A method for recommending educational applications, characterized in that, include: Based on the region where the enterprise is located and the enterprise's historical behavior data on its accessed educational applications, the enterprise's first level of interest in its accessed educational applications is calculated; wherein, the historical behavior data includes at least one of the following: historical usage behavior data and historical browsing behavior data; Calculate the interest similarity between enterprises based on the first interest score; Based on the interest similarity, predict the target company's second interest in its unaccessed educational applications; Recommendations are made for the target companies based on the second level of interest.

2. The educational application recommendation method as described in claim 1, characterized in that, The calculation of the enterprise's primary interest in its accessed educational applications, based on the enterprise's geographical location and historical behavioral data, includes: Based on the company's location, the degree of interest in the company's accessed educational applications can be obtained from the region where the company is located. Based on the historical usage data of the educational applications accessed by the enterprise, the usage volume of the educational applications accessed by the enterprise is statistically analyzed, and the usage volume is normalized. Based on the historical browsing behavior data of enterprises in their accessed educational applications, the number of views of enterprises in their accessed educational applications is counted, and the number of views is normalized. The first interest level is obtained based on the stated level of interest, the normalized usage, and the normalized pageviews.

3. The educational application recommendation method as described in claim 1, characterized in that, The step of calculating the interest similarity between enterprises based on the first interest level includes: Construct an interest matrix using the first interest score as matrix elements; Based on the interest matrix, the interest similarity between enterprises is calculated using the cosine similarity algorithm.

4. The educational application recommendation method as described in claim 1, characterized in that, The step of predicting the target enterprise's second level of interest in its unaccessed educational applications based on the interest similarity includes: Based on the interest similarity, one or more companies that are most similar to the target company are selected to form a candidate company set. The second interest level is predicted based on the interest level of each enterprise in the candidate enterprise set in the unaccessed educational applications of the target enterprise.

5. The educational application recommendation method as described in claim 4, characterized in that, The step of predicting the second interest level based on the interest level of each enterprise in the candidate enterprise set for the unaccessed educational applications of the target enterprise includes: Calculate the average interest level based on the interest level of each enterprise in the candidate enterprise set towards the unaccessed educational applications of the target enterprise; The average interest level is used as the second interest level.

6. The educational application recommendation method as described in claim 1, characterized in that, The step of recommending the target company based on the second interest level includes: Based on the second level of interest, one or more unaccessed educational applications with the highest level of interest are selected and recommended to the target enterprise.

7. An educational application recommendation device, characterized in that, include: The first calculation module is used to calculate the enterprise's first level of interest in its accessed educational applications based on the enterprise's location and the enterprise's historical behavior data in its accessed educational applications; wherein, the historical behavior data includes at least one of the following: historical usage behavior data and historical browsing behavior data; The second calculation module is used to calculate the interest similarity between enterprises based on the first interest degree; The prediction module is used to predict the target enterprise's second level of interest in its unaccessed educational applications based on the interest similarity. The recommendation module is used to make recommendations for the target company based on the second degree of interest.

8. An educational application recommendation device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the educational application recommendation method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program; wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the educational application recommendation method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program / instruction that, when executed by a processor, implements the educational application recommendation method as described in any one of claims 1 to 6.

Images