Academic Information Recommendation Method and Device Based on Data Flow Management

Abstract

The present invention relates to an academic information recommendation method and device based on data stream management. An academic information recommendation request is sent to a data relay end to instruct the data relay end to capture academic information from the cloud or a database. The academic information is segmented into multiple sub-data streams. Based on the number of the data relay end and the data recommendation end, the academic information is segmented into multiple sub-data streams to determine an original effective sub-data stream set. The effective sub-data streams in the original effective sub-data stream set are divided into recommended data streams and to-be-recommended data streams, and the data recommendation end is controlled to recommend the recommended data streams based on the academic information recommendation request. The update of the recommendation quantity is monitored in real time, and the recommended data streams and the to-be-recommended data streams are converted according to the update. Based on this, while accurately identifying the recommended data streams, the data processing volume is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of information data management, and particularly to an academic information recommendation method and device based on data stream management. Background Art

[0002] Academic information recommendation refers to the service of providing researchers with the latest academic research results, conference information, journal dynamics, etc. This service is usually carried out through specific platforms or websites, helping researchers keep abreast of the latest developments in their fields in a timely manner, thereby promoting academic exchanges and research progress.

[0003] With the development of recommendation data platforms, recommendation algorithms, and AI algorithms, the data means for academic information recommendation emerge in an endless stream. In current academic information management, academic information recommendation mainly relies on data means to capture academic resources from the Internet or specific databases for corresponding recommendations. However, due to the large number of data sources and types of current academic information, and the large amount of academic information data, the data calculation for directly capturing and recommending academic information is large, and the accuracy is often not high enough. Summary of the Invention

[0004] In view of the above analysis, the embodiments of the present invention aim to provide an academic information recommendation method and device based on data stream management to solve the problems in the implementation results of the prior art that there are a large number of data sources and types of current academic information, and the large amount of academic information data, resulting in a large amount of data calculation for directly capturing and recommending academic information, and the accuracy is often not high enough.

[0005] An academic information recommendation method based on data stream management, which is applied to a data platform including a data relay end and a data recommendation end, includes the steps of:

[0006] Sending an academic information recommendation request to the data relay end to instruct the data relay end to capture academic information from the cloud or a database;

[0007] Dividing the academic information into a plurality of sub-data streams, dividing the academic information into a plurality of sub-data streams based on the number of the data relay end and the data recommendation end, and determining an original effective sub-data stream set;

[0008] Dividing the effective sub-data streams of the original effective sub-data stream set into recommended data streams and to-be-recommended data streams, and controlling the data recommendation end to recommend the recommended data streams based on the academic information recommendation request;

[0009] Real-time monitoring the update of the recommended quantity, and converting the recommended data streams and the to-be-recommended data streams according to the update.

[0010] The academic information recommendation method based on data stream management in the embodiments of this application sends the academic information recommendation request to the data relay end to instruct the data relay end to capture academic information from the cloud or the database. The academic information is segmented into multiple sub-data streams. Based on the number of data relay ends and data recommendation ends, the academic information is segmented into multiple sub-data streams to determine the original effective sub-data stream set. The effective sub-data streams in the original effective sub-data stream set are divided into recommended data streams and to-be-recommended data streams, and the data recommendation end is controlled to recommend the recommended data streams based on the academic information recommendation request. The update of the recommendation volume is monitored in real time, and the recommended data stream and the to-be-recommended data stream are converted according to the update. Based on this, the recommended data stream is accurately identified while reducing the data processing volume.

[0011] As an optional embodiment, the process of segmenting the academic information into multiple sub-data streams and allocating the sub-data streams based on the number of data relay ends and data recommendation ends to determine the original effective sub-data stream set includes the steps of:

[0012] Segment the academic information into a set number of sub-data streams; wherein, the number of the sub-data streams is the product of the number of data relay ends and data recommendation ends.

[0013] As an optional embodiment, the process of dividing the effective sub-data streams in the original effective sub-data stream set into recommended data streams and to-be-recommended data streams includes the steps of:

[0014] Calculate the data volume according to the academic information recommendation request;

[0015] Determine the number of effective sub-data streams in the original effective sub-data stream set according to the data volume;

[0016] Divide the recommended data stream and the to-be-recommended data stream according to the number.

[0017] As an optional embodiment, the process of monitoring the update of the recommendation volume in real time and converting the recommended data stream and the to-be-recommended data stream according to the update includes the steps of:

[0018] Perform a weight ranking on the recommended data stream according to the capture time-consuming of the academic information;

[0019] Recommend the recommended data stream in real time according to the weight ranking;

[0020] Calculate the data proportion of the recommended data stream according to the update of the recommendation volume after the recommended data stream is recommended;

[0021] Convert the recommended data stream with a data proportion less than the set proportion into the to-be-recommended data stream.

[0022] As one of the optional embodiments, the process of calculating the data proportion of the recommended data stream according to the update of the recommended quantity after the recommended data stream is recommended is as follows: Wherein, represents the data proportion; represents the recommended quantity after the recommended data stream is recommended, represents the recommended quantity before the recommended data stream is recommended.

[0023] As one of the optional embodiments, it further includes the steps of: recommending the recommended data stream again, obtaining the updated vector data of the recommended quantities before and after; performing dimensionality reduction processing on the vector data to update the data proportion.

[0024] As one of the optional embodiments, as follows: Wherein, represents the updated data proportion, represents the data proportion for the first time, represents the data proportion for the second time, represents the Euclidean norm of the recommended quantity for the first recommendation, represents the Euclidean norm of the recommended quantity for the second recommendation.

[0025] An academic information recommendation device based on data stream management, which is applied to a data platform including a data relay end and a data recommendation end, includes:

[0026] An information capture module, configured to send an academic information recommendation request to the data relay end to instruct the data relay end to capture academic information from the cloud or a database;

[0027] An information segmentation module, configured to segment the academic information into multiple sub-data streams, segment the academic information into multiple sub-data streams based on the number of the data relay end and the data recommendation end, and determine an original effective sub-data stream set;

[0028] A data stream recommendation module, configured to divide the effective sub-data streams of the original effective sub-data stream set into a recommended data stream and a to-be-recommended data stream, and control the data recommendation end to recommend the recommended data stream based on the academic information recommendation request;

[0029] A data stream update module, configured to monitor the update of the recommended quantity in real time, and convert the recommended data stream and the to-be-recommended data stream according to the update.

[0030] The academic information recommendation device based on data stream management according to the embodiments of the present application sends an academic information recommendation request to a data relay end to instruct the data relay end to capture academic information from the cloud or a database. The academic information is segmented into multiple sub-data streams, and the academic information is segmented into multiple sub-data streams based on the number of data relay ends and data recommendation ends to determine an original effective sub-data stream set; the effective sub-data streams in the original effective sub-data stream set are divided into recommended data streams and to-be-recommended data streams, and the data recommendation end is controlled to recommend the recommended data streams based on the academic information recommendation request; the update of the recommendation volume is monitored in real time, and the recommended data streams and the to-be-recommended data streams are converted according to the update. Based on this, the recommended data streams can be accurately identified while reducing the data processing volume.

[0031] At least one embodiment of the present application further provides a data control device, including:

[0032] One or more memories that non-transiently store computer-executable instructions;

[0033] One or more processors configured to run the computer-executable instructions, wherein when the computer-executable instructions are run by the one or more processors, the academic information recommendation method based on data stream management according to any embodiment of the present application is implemented.

[0034] The above data control device sends an academic information recommendation request to a data relay end to instruct the data relay end to capture academic information from the cloud or a database. The academic information is segmented into multiple sub-data streams, and the academic information is segmented into multiple sub-data streams based on the number of data relay ends and data recommendation ends to determine an original effective sub-data stream set; the effective sub-data streams in the original effective sub-data stream set are divided into recommended data streams and to-be-recommended data streams, and the data recommendation end is controlled to recommend the recommended data streams based on the academic information recommendation request; the update of the recommendation volume is monitored in real time, and the recommended data streams and the to-be-recommended data streams are converted according to the update. Based on this, the recommended data streams can be accurately identified while reducing the data processing volume.

[0035] At least one embodiment of the present application further provides a non-transient computer-readable storage medium, wherein the non-transient computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the academic information recommendation method based on data stream management according to any embodiment of the present application is implemented.

[0036] The above non-transitory computer-readable storage medium sends an academic information recommendation request to a data relay end to instruct the data relay end to capture academic information from the cloud or a database. The academic information is segmented into multiple sub-data streams. The academic information is segmented into multiple sub-data streams based on the number of the data relay end and the data recommendation end, and an original effective sub-data stream set is determined; the effective sub-data streams in the original effective sub-data stream set are divided into a recommended data stream and a to-be-recommended data stream, and the data recommendation end is controlled to recommend the recommended data stream based on the academic information recommendation request; the update of the recommended quantity is monitored in real time, and the recommended data stream and the to-be-recommended data stream are converted according to the update. Based on this, while accurately identifying the recommended data stream, the data processing volume is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flowchart of an academic information recommendation method based on data stream management according to an embodiment of the application;

[0038] Figure 2 is a module structure diagram of an academic information recommendation device based on data stream management according to an embodiment of the application;

[0039] Figure 3 is a schematic block diagram of a data control device provided by the present invention;

[0040] Figure 4 is a schematic diagram of a non-transitory computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] In order to better understand the purpose, technical solution and technical effect of the present invention, the present invention will be further described and explained below with reference to the drawings and embodiments. At the same time, it is stated that the embodiments described below are only used to explain the present invention and are not used to limit the present invention.

[0042] An embodiment of the present invention provides an academic information recommendation method based on data stream management.

[0043] Figure 1 is a flowchart of an academic information recommendation method based on data stream management according to an embodiment of the application. As Figure 1 shown, an academic information recommendation method based on data stream management according to an embodiment of the application is applied to a data platform including a data relay end and a data recommendation end, and includes steps S100 to S103:

[0044] S100, sending an academic information recommendation request to the data relay end to instruct the data relay end to capture academic information from the cloud or a database;

[0045] S101. Split the academic information into multiple sub-data streams. Based on the number of data relay terminals and data recommendation terminals, split the academic information into multiple sub-data streams, and determine the set of original effective sub-data streams.

[0046] S102. Divide the effective sub-data streams in the set of original effective sub-data streams into recommended data streams and data streams to be recommended, and control the data recommendation terminals to recommend the recommended data streams based on the academic information recommendation request.

[0047] S103. Monitor the update of the recommended quantity in real time, and convert the recommended data stream and the data stream to be recommended according to the update.

[0048] Among them, during the deployment of the data platform, the data relay terminal is a centralized processing center, which is distributedly connected to each data recommendation terminal. The data relay terminal captures academic information from the cloud or database and synchronizes the academic information to each data recommendation terminal.

[0049] As one embodiment, the process of splitting the academic information into multiple sub-data streams in step S101 and allocating the sub-data streams based on the number of data relay terminals and data recommendation terminals to determine the set of original effective sub-data streams includes the steps of:

[0050] Split the academic information into a set number of sub-data streams; wherein, the number of sub-data streams is the product of the number of data relay terminals and data recommendation terminals.

[0051] The academic information exists in the form of data packets in the data relay terminal. Parse the data packets and allocate data according to the set number, and re-encapsulate to form sub-data streams.

[0052] Preferably, adjust the content of the data stream according to the independent header in the parsed data packet to ensure that each sub-data stream stores one or more complete data with independent headers. Among them, the data with independent headers is used to express an independent and complete fragment of academic information.

[0053] Preferably, the process of dividing the effective sub-data streams in the set of original effective sub-data streams into recommended data streams and data streams to be recommended in step S102 includes the steps of:

[0054] Calculate the data volume according to the academic information recommendation request;

[0055] Determine the number of effective sub-data streams in the set of original effective sub-data streams according to the data volume;

[0056] Divide the recommended data stream and the data stream to be recommended according to the number.

[0057] Among them, the data relay end is also used to capture the user's academic information request, calculate the amount of data of the academic information to be pushed according to the academic information request, determine the number of effective sub-data streams in the original effective sub-data stream set, so as to divide the recommended data stream and the data stream to be recommended.

[0058] Preferably, the number of recommended data streams is the same as the number of effective sub-data streams.

[0059] Preferably, in step S103, the process of real-time monitoring the update of the recommended quantity and converting the recommended data stream and the data stream to be recommended according to the update includes the steps of:

[0060] Perform weight sorting on the recommended data stream according to the time-consuming for capturing the academic information;

[0061] Recommend the recommended data stream in real time according to the weight sorting;

[0062] Calculate the data proportion of the recommended data stream according to the update of the recommended quantity after the recommended data stream is recommended;

[0063] Convert the recommended data stream with a data proportion less than the set proportion into the data stream to be recommended.

[0064] Preferably, the binary exponential backoff algorithm is used for the conversion between the recommended data stream and the data stream to be recommended, and the backoff time of the binary exponential backoff algorithm is determined according to the data proportion, that is, backoff time = set time * data proportion. The data stream to be recommended needs to wait for the backoff time to be converted into the recommended data stream. The initial conversion is relatively short to test whether the conversion is normal, and the backoff time is reduced subsequently to ensure the conversion efficiency.

[0065] Preferably, the process of calculating the data proportion of the recommended data stream according to the update of the recommended quantity after the recommended data stream is recommended is as follows: Among them, represents the data proportion; represents the recommended quantity after the recommended data stream is recommended, represents the recommended quantity before the recommended data stream is recommended.

[0066] Preferably, it further includes the steps of:

[0067] Recommend the recommended data stream again, obtain the vector data of the update of the recommended quantity before and after; perform dimensionality reduction processing on the vector data to update the data proportion.

[0068] Preferably, as follows: Among them, represents the updated data proportion, represents the data proportion for the first time, Represents the data proportion of the second time, Represents the Euclidean norm of the recommended quantity of the first recommendation, Represents the Euclidean norm of the recommended quantity of the second recommendation.

[0069] Through dimensionality reduction processing, improve the similarity between the updated data proportion and the true proportion.

[0070] For the academic information recommendation method based on data flow management in any of the above embodiments, send the academic information recommendation request to the data relay end to instruct the data relay end to capture academic information from the cloud or database. Divide the academic information into multiple sub-data flows, divide the academic information into multiple sub-data flows based on the number of data relay ends and data recommendation ends, and determine the set of original effective sub-data flows; divide the effective sub-data flows in the set of original effective sub-data flows into recommended data flows and to-be-recommended data flows, and control the data recommendation end to recommend the recommended data flow based on the academic information recommendation request; monitor the update of the recommended quantity in real time, and convert the recommended data flow and the to-be-recommended data flow according to the update. Based on this, accurately identify the recommended data flow while reducing the data processing volume.

[0071] An embodiment of the present invention also provides an academic information recommendation device based on data flow management.

[0072] Figure 2 For the module structure diagram of the academic information recommendation device based on data flow management in an application embodiment, as Figure 2 shown, the academic information recommendation device based on data flow management in an application embodiment includes:

[0073] An information capture module 100, configured to send an academic information recommendation request to a data relay end to instruct the data relay end to capture academic information from the cloud or database;

[0074] An information segmentation module 101, configured to divide the academic information into multiple sub-data flows, divide the academic information into multiple sub-data flows based on the number of data relay ends and data recommendation ends, and determine a set of original effective sub-data flows;

[0075] A data flow recommendation module 102, configured to divide the effective sub-data flows in the set of original effective sub-data flows into recommended data flows and to-be-recommended data flows, and control the data recommendation end to recommend the recommended data flow based on the academic information recommendation request;

[0076] A data flow update module 103, configured to monitor the update of the recommended quantity in real time, and convert the recommended data flow and the to-be-recommended data flow according to the update.

[0077] The above-mentioned academic information recommendation device based on data stream management sends an academic information recommendation request to a data relay end to instruct the data relay end to capture academic information from the cloud or a database. The academic information is segmented into multiple sub-data streams, and the academic information is segmented into multiple sub-data streams based on the number of the data relay end and the data recommendation end, and an original effective sub-data stream set is determined; the effective sub-data streams in the original effective sub-data stream set are divided into a recommended data stream and a to-be-recommended data stream, and the data recommendation end is controlled to recommend the recommended data stream based on the academic information recommendation request; the update of the recommended quantity is monitored in real time, and the recommended data stream and the to-be-recommended data stream are converted according to the update. Based on this, the recommended data stream is accurately identified while reducing the data processing volume.

[0078] At least one embodiment of the present application further provides a data control device. Figure 3 It is a schematic block diagram of a data control device provided by at least one embodiment of the present application. For example, as Figure 3 shown, the data control device 20 may include one or more memories 200 and one or more processors 201. The memory 200 is used for non-transiently storing computer-executable instructions; the processor 201 is used for running the computer-executable instructions, and when the computer-executable instructions are run by the processor 201, the processor 201 can be made to execute one or more steps in the academic information recommendation method based on data stream management according to any embodiment of the present application.

[0079] For the specific implementation of each step of the academic information recommendation method based on data stream management and the relevant explanatory content, reference may be made to the relevant content in the embodiments of the academic information recommendation method based on data stream management described above, and details are not repeated here. It should be noted that Figure 3 the components of the data control device 20 shown are only exemplary and not restrictive. According to actual application requirements, the data control device 20 may further have other components.

[0080] In one embodiment, the processor 201 and the memory 200 can communicate with each other directly or indirectly. For example, the processor 201 and the memory 200 can communicate through a network connection. The network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The type and function of the network are not limited herein. For another example, the processor 201 and the memory 200 can also communicate through a bus connection. The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. For example, the processor 201 and the memory 200 can be disposed at a remote data server side (cloud) or a distributed energy system side (local side), or can be disposed at a client side (e.g., a mobile device such as a mobile phone). For example, the processor 201 can be a Central Processing Unit (CPU), a Tensor Processing Unit (TPU), or a Graphics Processing Unit (GPU), etc., which has data processing capabilities and / or instruction execution capabilities, and can control other components in the data control device 20 to perform desired functions. The Central Processing Unit (CPU) can be of an X86 or ARM architecture, etc.

[0081] In one embodiment, the memory 200 can include any combination of one or more computer program products. The computer program products can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory can include, for example, Random Access Memory (RAM) and / or a cache, etc. Non-volatile memory can include, for example, Read-Only Memory (ROM), a hard disk, Erasable Programmable Read-Only Memory (EPROM), a Portable Compact Disc Read-Only Memory (CD-ROM), a USB memory, a flash memory, etc. One or more computer-executable instructions can be stored on the computer-readable storage media. The processor 201 can run the computer-executable instructions to implement various functions of the data control device 20. Various application programs and various data can also be stored in the memory 200, as well as various data used and / or generated by the application programs, etc.

[0082] It should be noted that the data control device 20 can achieve technical effects similar to those of the foregoing academic information recommendation method based on data stream management. The repeated parts will not be elaborated herein.

[0083] At least one embodiment of the present application further provides a non-transitory computer-readable storage medium. Figure 4 It is a schematic diagram of a non-transitory computer-readable storage medium provided by at least one embodiment of the present application. For example, as Figure 4As shown, one or more computer-executable instructions 301 can be non-transiently stored on a non-transitory computer-readable storage medium 30. For example, when the computer-executable instructions 301 are executed by a computer, the computer can be caused to execute one or more steps in the academic information recommendation method based on data stream management according to any embodiment of the present application.

[0084] In one embodiment, the non-transitory computer-readable storage medium 30 can be applied to the above data control device 20. For example, it can be the memory 200 in the data control device 20.

[0085] In one embodiment, the description of the non-transitory computer-readable storage medium 30 can refer to the description of the memory 200 in the embodiment of the data control device 20, and the repeated parts will not be elaborated.

[0086] It should be noted that when different non-transitory computer-executable instructions are stored in the memory 200, the data control device 20 correspondingly serves as a firmware upgrade device. When the computer-executable instructions are run by the processor 201, the processor 201 can be caused to execute one or more steps in the academic information recommendation method based on data stream management according to any embodiment of the present application.

[0087] For the present application, there are also the following points to note:

[0088] (1) The accompanying drawings of the embodiments of the present application only relate to the structures involved in the embodiments of the present application, and other structures can refer to the general design.

[0089] (2) For the sake of clarity, in the accompanying drawings used to describe the embodiments of the present invention, the thickness and dimensions of layers or structures are enlarged. It can be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element, or there can be intermediate elements.

[0090] (3) Without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other to obtain new embodiments. The above are only the specific implementation manners of the present application, but the protection scope of the present application is not limited thereto. The protection scope of the present application shall be subject to the protection scope of the claims.

[0091] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combinations of these technical features do not conflict, they should all be considered as the scope described in this specification.

[0092] The above embodiments only represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patented application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. An academic information recommendation method based on data stream management, characterized in that, Applied to a data platform including a data relay end and a data recommendation end, comprising the steps: Sending an academic information recommendation request to the data relay end to instruct the data relay end to capture academic information from the cloud or a database; Dividing the academic information into multiple sub-data streams, dividing the academic information into multiple sub-data streams based on the number of the data relay end and the data recommendation end, and determining an original effective sub-data stream set; Dividing the effective sub-data streams of the original effective sub-data stream set into recommended data streams and to-be-recommended data streams, and controlling the data recommendation end to recommend the recommended data streams based on the academic information recommendation request; Performing weight sorting on the recommended data streams according to the capture time of the academic information; Recommending the recommended data streams in real time according to the weight sorting; Calculate the data proportion of the recommended data stream according to the update of the recommended quantity after the recommended data stream is recommended, as shown in the following formula: Where represents the data proportion; represents the recommended quantity after the recommended data stream is recommended, represents the recommended quantity before the recommended data stream is recommended; Converting the recommended data streams with a data proportion less than a set proportion into the to-be-recommended data streams; Recommending the recommended data streams again to obtain updated vector data of the recommendation amounts before and after; Perform dimensionality reduction processing on the vector data to update the data proportion, as shown in the following formula: Wherein, represents the updated data proportion, represents the data proportion of the first time, represents the data proportion of the second time, represents the Euclidean norm of the recommended quantity of the first recommendation, represents the Euclidean norm of the recommended quantity of the second recommendation.

2. The academic information recommendation method based on data stream management according to claim 1, characterized in that The process of dividing the academic information into multiple sub-data streams and allocating the sub-data streams based on the number of the data relay end and the data recommendation end to determine the original effective sub-data stream set includes the steps: Dividing the academic information into a set number of sub-data streams; wherein, the number of sub-data streams is the product of the data relay end and the data recommendation end.

3. The academic information recommendation method based on data stream management according to claim 1, wherein The process of dividing the effective sub-data streams of the original effective sub-data stream set into recommended data streams and to-be-recommended data streams includes the steps: Calculating the data volume according to the academic information recommendation request; Determining the number of the effective sub-data streams of the original effective sub-data stream set according to the data volume; Dividing the recommended data streams and the to-be-recommended data streams according to the number.

4. An academic information recommendation device based on data stream management, characterized in that, Applied to a data platform including a data relay end and a data recommendation end, including: An information capture module for sending an academic information recommendation request to the data relay end to instruct the data relay end to capture academic information from the cloud or a database; An information division module for dividing the academic information into multiple sub-data streams, dividing the academic information into multiple sub-data streams based on the number of the data relay end and the data recommendation end, and determining an original effective sub-data stream set; A data stream recommendation module for dividing the effective sub-data streams of the original effective sub-data stream set into recommended data streams and to-be-recommended data streams, and controlling the data recommendation end to recommend the recommended data streams based on the academic information recommendation request; A data stream update module for performing weight sorting on the recommended data streams according to the capture time of the academic information; Recommending the recommended data streams in real time according to the weight sorting; Calculate the data proportion of the recommended data stream according to the update of the recommended quantity after the recommended data stream is recommended, as shown in the following formula: Wherein, represents the data proportion; represents the recommended quantity after the recommended data stream is recommended, represents the recommended quantity before the recommended data stream is recommended; Converting the recommended data streams with a data proportion less than a set proportion into the to-be-recommended data streams; Recommending the recommended data streams again to obtain updated vector data of the recommendation amounts before and after; Perform dimensionality reduction on the vector data to update the data proportion as follows: Wherein, represents the updated data proportion, represents the data proportion of the first time, represents the data proportion of the second time, represents the Euclidean norm of the recommended quantity of the first recommendation, represents the Euclidean norm of the recommended quantity of the second recommendation.

5. A non-transitory computer-readable storage medium, characterized in that, A non-transitory computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the academic information recommendation method based on data stream management as described in any one of claims 1 to 3 is implemented.

6. A data control device, characterized in that, Including: One or more memories that non-transitorily store computer-executable instructions; One or more processors configured to run computer-executable instructions, wherein when the computer-executable instructions are run by the one or more processors, the academic information recommendation method based on data stream management as described in any one of claims 1 to 3 is implemented.

Images