Scientific research task recommendation method and device based on distributed AI kernel density

Abstract

The invention relates to a distributed AI kernel density-based scientific research task recommendation method and device, and the method comprises the steps: deploying a sub-AI language model at each scientific research management platform, and capturing the scientific research data of the corresponding scientific research management platform according to the sub-AI language model. And identifying POI data of the scientific research data based on the main AI language model, quantifying various POI distribution density of the scientific research management platform corresponding to the scientific research category according to the kernel density of the POI data, and determining density quantification data. And quantifying the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantization data. Inputting the density quantization data and the frequency quantization data into a main AI language model, and strengthening the main AI language model; the enhanced main AI language model is used for inputting and outputting a scientific research task recommendation result according to the user information. On the basis, scientific research data of all scientific research management platforms are integrated, the model capability of the main AI language model is enhanced through POI data, and the accuracy and reference of inputting and outputting scientific research task recommendation results according to user information are improved.

Description

Technical Field

[0001] The present application relates to the field of task data processing technology, and in particular to a method and device for recommending scientific research tasks based on distributed AI kernel density. Background Art

[0002] Scientific research task recommendation refers to recommending relevant scientific research tasks or projects to researchers in the field of scientific research through certain algorithms and technical means. Recommendations are usually based on researchers' historical behavior information, research interests, domain knowledge and other factors, aiming to help researchers find research topics that suit them more efficiently and improve scientific research efficiency and the quality of results.

[0003] Therefore, scientific research task recommendation needs to rely on a large amount of data. With the development of the big data era, data management tools for scientific research tasks have become an important auxiliary tool for data-intensive scientific research environments. At present, the data management tools for scientific research task recommendation are mainly scientific research management platforms of various scientific research institutions. The data of such scientific research management platforms mainly come from the records of the scientific research institutions and the public data of the Internet / third-party databases. However, the data within a single scientific research institution is relatively limited, and the scientific research task recommendations formed by data access are not comprehensive enough; while the public data of the Internet / third-party databases has a lot of interference information, and the reference value of scientific research task recommendations formed by data access is not high.

[0004] In summary, the current scientific research task recommendation based on big data still has the above shortcomings. Summary of the invention

[0005] In view of the above analysis, the embodiments of the present invention aim to provide a method and device for recommending scientific research tasks based on distributed AI kernel density, so as to solve the problems in the existing technology implementation results that the data within a single scientific research institution is relatively limited, and the scientific research task recommendations formed by data access are not comprehensive; and the public data on the Internet / third-party databases has a lot of interference information, and the reference value of the scientific research task recommendations formed by data access is not high.

[0006] The present application embodiment provides a scientific research task recommendation method based on distributed AI kernel density, comprising the steps of: Deploy a sub-AI language model on each scientific research management platform, and capture the scientific research data of the corresponding scientific research management platform according to the sub-AI language model; wherein the scientific research management platform is classified into a corresponding scientific research category; Identify the POI data of the scientific research data based on the main AI language model, and determine the density quantification data by quantifying the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category according to the kernel density of the POI data; wherein there is a corresponding relationship between the POI data, the scientific research data, the scientific research category and the scientific research management platform; Quantifying the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data; The density quantization data and the frequency quantization data are input into the main AI language model to strengthen the main AI language model; wherein the strengthened main AI language model is used to output scientific research task recommendation results according to user information input.

[0007] The scientific research task recommendation method based on distributed AI kernel density in the embodiment of the present application deploys a sub-AI language model on each scientific research management platform, and captures the scientific research data of the corresponding scientific research management platform according to the sub-AI language model. The POI data of the scientific research data is identified based on the main AI language model, and the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category is quantified according to the kernel density of the POI data to determine the density quantification data. The distribution frequency of each POI type of each scientific research category in the scientific research data is quantified to obtain frequency quantification data. The density quantification data and the frequency quantification data are input into the main AI language model to strengthen the main AI language model; the strengthened main AI language model is used to input and output scientific research task recommendation results according to user information. Based on this, the scientific research data of each scientific research management platform are integrated, and the model capability of the main AI language model is strengthened through POI data to improve the accuracy and reference of the scientific research task recommendation results input and output according to user information.

[0008] As one of the optional embodiments, the process of determining density quantification data according to the kernel density quantification of the POI data corresponding to the distribution density of various POIs on the scientific research management platform comprises the steps of: The POI position and the POI bandwidth are smoothed using a POI kernel function, and the result of the POI kernel function is used as the density quantization data.

[0009] As an optional embodiment, the POI kernel density is calculated as follows: ; in, Core(x) represents the POI kernel density, x represents the location of the evaluation point, n Indicates the total number of POIs, m represents the kernel density bandwidth, H represents the POI kernel density, X i No. i The location of a POI.

[0010] As an optional embodiment, the POI kernel density is calculated as follows: ; in, R c,mIndicates research category c The kernel density bandwidth is m The sum of the weights of the POIs (normalized), U c,m Indicates research category c and kernel density bandwidth m The POI index collection, M c Indicates research category c The collection of all impact areas under X i,y express i POI y The location of a point.

[0011] As one of the optional embodiments, the process of quantifying the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data is as follows: ; in, represents frequency quantitative data, r The identifier of the POI type. o Represents scientific research data, Indicates r The weight of the POI type, Representing scientific research data o Corresponding scientific research category c No. r The number of POI types; Indicates all the first r The number of POI types.

[0012] As one of the optional embodiments, the scientific research categories include basic research, applied research, development research, engineering research and interdisciplinary research.

[0013] As one of the optional embodiments, the sub-AI language model is deployed locally on the scientific research management platform; and the main AI language model is deployed in the cloud.

[0014] The embodiment of the present application also provides a scientific research task recommendation device based on distributed AI kernel density, including: A data acquisition module, used to deploy a sub-AI language model on each scientific research management platform, and to capture the scientific research data of the corresponding scientific research management platform according to the sub-AI language model; wherein the scientific research management platform is classified into a corresponding scientific research category; A density calculation module, for identifying the POI data of the scientific research data based on the main AI language model, and determining the density quantification data according to the kernel density quantification of the scientific research category of the POI data corresponding to the various POI distribution densities of the scientific research management platform; wherein there is a corresponding relationship between the POI data, the scientific research data, the scientific research category and the scientific research management platform; A frequency calculation module, used to quantify the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data; A model strengthening module is used to input the density quantization data and the frequency quantization data into the main AI language model to strengthen the main AI language model; wherein the strengthened main AI language model is used to output scientific research task recommendation results based on user information input.

[0015] The scientific research task recommendation device based on distributed AI kernel density in the embodiment of the present application deploys a sub-AI language model on each scientific research management platform, and captures the scientific research data of the corresponding scientific research management platform according to the sub-AI language model. The POI data of the scientific research data is identified based on the main AI language model, and the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category is quantified according to the kernel density of the POI data to determine the density quantification data. The distribution frequency of each POI type of each scientific research category in the scientific research data is quantified to obtain frequency quantification data. The density quantification data and the frequency quantification data are input into the main AI language model to strengthen the main AI language model; the strengthened main AI language model is used to input and output scientific research task recommendation results according to user information. Based on this, the scientific research data of each scientific research management platform are integrated, and the model capability of the main AI language model is strengthened through POI data to improve the accuracy and reference of the scientific research task recommendation results input and output according to user information.

[0016] At least one embodiment of the present application further provides a data control device, including: one or more memories non-transitorily storing computer-executable instructions; One or more processors are configured to run computer executable instructions, wherein the computer executable instructions, when executed by one or more processors, implement a scientific research task recommendation method based on distributed AI kernel density according to any embodiment of the present application.

[0017] The above-mentioned data control device deploys a sub-AI language model on each scientific research management platform, and captures the scientific research data of the corresponding scientific research management platform according to the sub-AI language model. The POI data of the scientific research data is identified based on the main AI language model, and the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category is quantified according to the kernel density of the POI data to determine the density quantification data. The distribution frequency of each POI type of each scientific research category in the scientific research data is quantified to obtain frequency quantification data. The density quantification data and the frequency quantification data are input into the main AI language model to strengthen the main AI language model; the strengthened main AI language model is used to input and output scientific research task recommendation results according to user information. Based on this, the scientific research data of each scientific research management platform are integrated, and the model capability of the main AI language model is strengthened through POI data to improve the accuracy and reference of the scientific research task recommendation results input and output according to user information.

[0018] At least one embodiment of the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, a scientific research task recommendation method based on distributed AI kernel density according to any embodiment of the present application is implemented.

[0019] The above-mentioned non-transitory computer-readable storage medium deploys a sub-AI language model on each scientific research management platform, and captures the scientific research data of the corresponding scientific research management platform according to the sub-AI language model. Based on the main AI language model, the POI data of the scientific research data is identified, and the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category is quantified according to the kernel density of the POI data to determine the density quantification data. The distribution frequency of each POI type of each scientific research category in the scientific research data is quantified to obtain frequency quantification data. The density quantification data and the frequency quantification data are input into the main AI language model to strengthen the main AI language model; the strengthened main AI language model is used to input and output scientific research task recommendation results according to user information. Based on this, the scientific research data of each scientific research management platform are integrated, and the model capability of the main AI language model is strengthened through POI data to improve the accuracy and reference of the scientific research task recommendation results input and output according to user information. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of a method for recommending scientific research tasks based on distributed AI kernel density according to an embodiment of an application; Figure 2 This is a diagram of the AI ​​deployment framework of an embodiment of the present application; Figure 3 This is a module structure diagram of a scientific research task recommendation device based on distributed AI core density according to an embodiment; Figure 4 A schematic block diagram of a data control device provided by the present invention; Figure 5 A schematic diagram of a non-transitory computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be clearly and completely described below in conjunction with the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the described embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0022] Unless otherwise defined, the technical terms or scientific terms used in this application should be understood by people with ordinary skills in the field to which this application belongs. "First", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0023] In order to keep the following description of the embodiments of the present application clear and concise, the present application omits detailed descriptions of some known functions and known components.

[0024] An embodiment of the present application provides a scientific research task recommendation method based on distributed AI kernel density.

[0025] Figure 1 Flowchart of a method for recommending scientific research tasks based on distributed AI kernel density according to an embodiment of an application, such as Figure 1 As shown, a scientific research task recommendation method based on distributed AI kernel density in an application embodiment includes steps S100 to S101: S100, deploying a sub-AI language model on each scientific research management platform, and capturing scientific research data of the corresponding scientific research management platform according to the sub-AI language model; wherein the scientific research management platform is classified into a corresponding scientific research category; S101, identifying POI data of the scientific research data based on the main AI language model, and determining density quantification data according to the kernel density quantification of the scientific research categories of the POI data corresponding to the distribution density of various POIs of the scientific research management platform; wherein there is a corresponding relationship between the POI data, the scientific research data, the scientific research categories and the scientific research management platform; S102, quantifying the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data; S103, inputting the density quantization data and the frequency quantization data into the main AI language model to strengthen the main AI language model; wherein the strengthened main AI language model is used to output scientific research task recommendation results according to user information input.

[0026] Figure 2 This is a diagram of the AI ​​deployment framework of an embodiment of the present application, such as Figure 2 As shown in the figure, the cloud platform manages various scientific research management platforms in a distributed manner and communicates with each scientific research management platform. The sub-AI language model is deployed on each scientific research management platform, and the main AI language model is deployed on the cloud. The sub-AI language model is used to capture the scientific research data of the corresponding scientific research management platform, and the main AI language model identifies the POI (point of interest) data of the scientific research data. At the same time, the main AI language model has an open iteration capability and can be iterated based on third-party data. The main AI language model gradually improves the user information input and scientific research task recommendation results based on iteration.

[0027] As one of the optional embodiments, the sub-AI language model is deployed locally on the scientific research management platform; and the main AI language model is deployed in the cloud.

[0028] As one of the optional embodiments, the process of determining density quantification data according to the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category of the kernel density quantification of the POI data includes the steps of: The POI position and the POI bandwidth are smoothed using a POI kernel function, and the result of the POI kernel function is used as the density quantization data.

[0029] Among them, the calculation method of POI kernel density is as follows: ; in, Core(x) represents the POI kernel density, x represents the location of the evaluation point, n Indicates the total number of POIs, m represents the kernel density bandwidth, H represents the POI kernel density, X i No. i The location of a POI.

[0030] The calculation method of POI kernel density is as follows: ; in, R c,m Indicates research category c The kernel density bandwidth is m The sum of the weights of the POIs, U c,m Indicates research category c and kernel density bandwidth m The POI index collection, M c Indicates research category c The collection of all impact areas under X i,y express i POI y The location of a point.

[0031] As one of the embodiments, the process of quantifying the distribution frequency of each POI type of each scientific research category in the scientific research data and obtaining the frequency quantification data is as follows: ; in, represents frequency quantitative data, r The identifier of the POI type. o Represents scientific research data, Indicates r The weight of the POI type, Representing scientific research data o Corresponding scientific research category c No. r The number of POI types; Indicates all the first r The number of POI types.

[0032] Preferably, scientific research categories include basic research, applied research, development research, engineering research and interdisciplinary research.

[0033] Among them, the main AI language model before enhancement recommends scientific research tasks based on points of interest (POI), predicts the user's next POI visit based on user information input, and organizes the next scientific research task. In the embodiment of the present application, the enhanced main AI language model uses density quantization data and frequency quantization data to replace the POI point of interest part in the original model to iterate the model.

[0034] Preferably, the POI points of interest in the original AI language model are replaced according to the step-by-step weighted results of the density quantization data and the frequency quantization data. Specifically, corresponding weights are configured for the density quantization data and the frequency quantization data, and normalization processing is performed after weighted summation, and the POI points of interest in the original AI language model are adjusted according to the normalization processing result.

[0035] It should be noted that, based on the rapid development of AI language models, for example, the output of scientific research tasks can be modified by repeatedly inputting information into the AI ​​language model. Therefore, the use of density quantization data and frequency quantization data in the embodiments of the present application is not limited to the only way, and the above method is only an example. The calculation of density quantization data and frequency quantization data is mainly to highlight the characteristics of POI data and improve the recognition and iteration accuracy of the AI ​​language model. The scientific research task recommendation method based on distributed AI kernel density in the embodiment of the present application deploys a sub-AI language model on each scientific research management platform, and captures the scientific research data of the corresponding scientific research management platform according to the sub-AI language model. The POI data of the scientific research data is identified based on the main AI language model, and the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category is quantified according to the kernel density of the POI data to determine the density quantification data. The distribution frequency of each POI type of each scientific research category in the scientific research data is quantified to obtain frequency quantification data. The density quantification data and the frequency quantification data are input into the main AI language model to strengthen the main AI language model; the strengthened main AI language model is used to input and output scientific research task recommendation results according to user information. Based on this, the scientific research data of each scientific research management platform are integrated, and the model capability of the main AI language model is strengthened through POI data to improve the accuracy and reference of the scientific research task recommendation results input and output according to user information.

[0036] The embodiment of the present application also provides a scientific research task recommendation device based on distributed AI kernel density.

[0037] Figure 3 : is a module structure diagram of a scientific research task recommendation device based on distributed AI core density according to an embodiment of the present invention, such as Figure 3 As shown, a scientific research task recommendation device based on distributed AI kernel density according to one embodiment includes: The data acquisition module 100 is used to deploy the sub-AI language model on each scientific research management platform, and to capture the scientific research data of the corresponding scientific research management platform according to the sub-AI language model; wherein the scientific research management platform is classified into a corresponding scientific research category; The density calculation module 101 is used to identify the POI data of the scientific research data based on the main AI language model, and quantify the distribution density of various POIs of the scientific research category corresponding to the scientific research management platform according to the kernel density of the POI data, and determine the density quantification data; wherein there is a corresponding relationship between the POI data, the scientific research data, the scientific research category and the scientific research management platform; A frequency calculation module 102, for quantifying the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data; The model strengthening module 103 is used to input the density quantization data and the frequency quantization data into the main AI language model to strengthen the main AI language model; wherein the strengthened main AI language model is used to output scientific research task recommendation results based on user information input.

[0038] The scientific research task recommendation device based on distributed AI kernel density in the embodiment of the present application deploys a sub-AI language model on each scientific research management platform, and captures the scientific research data of the corresponding scientific research management platform according to the sub-AI language model. The POI data of the scientific research data is identified based on the main AI language model, and the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category is quantified according to the kernel density of the POI data to determine the density quantification data. The distribution frequency of each POI type of each scientific research category in the scientific research data is quantified to obtain frequency quantification data. The density quantification data and the frequency quantification data are input into the main AI language model to strengthen the main AI language model; the strengthened main AI language model is used to input and output scientific research task recommendation results according to user information. Based on this, the scientific research data of each scientific research management platform are integrated, and the model capability of the main AI language model is strengthened through POI data to improve the accuracy and reference of the scientific research task recommendation results input and output according to user information.

[0039] At least one embodiment of the present application also provides a data control device. Figure 4 A schematic block diagram of a data control device provided in at least one embodiment of the present application. Figure 4 As shown, the data control device 20 may include one or more memories 200 and one or more processors 201. The memory 200 is used to store computer executable instructions non-transiently; the processor 201 is used to run the computer executable instructions, and when the computer executable instructions are run by the processor 201, the processor 201 can execute one or more steps in the scientific research task recommendation method based on distributed AI kernel density according to any embodiment of the present application.

[0040] The specific implementation and related explanation of each step of the method for recommending scientific research tasks based on distributed AI kernel density can be found in the above-mentioned embodiment of the method for recommending scientific research tasks based on distributed AI kernel density, which will not be elaborated here. Figure 4 The components of the data control device 20 shown are merely exemplary and non-limiting. The data control device 20 may also have other components according to actual application requirements.

[0041] 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 via a network connection. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network, and the present application does not limit the type and function of the network. For another example, the processor 201 and the memory 200 can also communicate via a bus connection. The bus may be a peripheral component interconnect standard (PCI) bus or an extended industrial standard architecture (EISA) bus, etc. For example, the processor 201 and the memory 200 may be arranged at a remote data server end (cloud) or a distributed energy system end (local end), or may be arranged at a client end (for example, a mobile device such as a mobile phone). For example, the processor 201 may be a device having data processing capability and / or instruction execution capability such as a central processing unit (CPU), a tensor processor (TPU) or a graphics processor GPU, and may control other components in the data prediction device 20 to perform the desired functions. The central processing unit (CPU) may be an X86 or ARM architecture, etc.

[0042] In one embodiment, the memory 200 may include any combination of one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), portable compact disk read-only memory (CD-ROM), USB memory, flash memory, etc. One or more computer-executable instructions may be stored on the computer-readable storage medium, and the processor 201 may execute the computer-executable instructions to implement various functions of the data prediction device 20. Various applications and various data, as well as various data used and / or generated by the application, etc. may also be stored in the memory 200.

[0043] It should be noted that the data control device 20 can achieve technical effects similar to the aforementioned scientific research task recommendation method based on distributed AI kernel density, and the repeated parts will not be repeated.

[0044] At least one embodiment of the present application also provides a non-transitory computer-readable storage medium. Figure 5 A schematic diagram of a non-transitory computer-readable storage medium provided for at least one embodiment of the present application. Figure 5 As shown, one or more computer executable instructions 301 may be non-transiently stored on a non-transient computer readable storage medium 30. For example, when the computer executable instructions 301 are executed by a computer, the computer may execute one or more steps in the method for recommending scientific research tasks based on distributed AI kernel density according to any embodiment of the present application.

[0045] In one embodiment, the non-transitory computer-readable storage medium 30 may be applied to the above-mentioned data control device 20 , for example, it may be the memory 200 in the data control device 20 .

[0046] In one embodiment, the description of the non-transitory computer-readable storage medium 30 may refer to the description of the memory 200 in the embodiment of the data control device 20, and the repeated parts will not be repeated.

[0047] It should be noted that the memory 200 stores different non-transiently stored computer executable instructions, and the data control device 20 corresponds to a firmware upgrade device. When the computer executable instructions are executed by the processor 201, the processor 201 can execute one or more steps in the scientific research task recommendation method based on distributed AI kernel density according to any embodiment of the present application.

[0048] There are a few points to note about this application:

[0049] (1) The drawings of the embodiments of the present application only relate to the structures related to the embodiments of the present application, and other structures may refer to the general design.

[0050] (2) For the sake of clarity, the thickness and size of layers or structures are exaggerated in the drawings used to describe the embodiments of the present invention. It is 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 may be "directly" "on" or "under" the other element, or there may be intervening elements.

[0051] (3) In the absence of conflict, the embodiments of the present application and the features in the embodiments may be combined with each other to obtain new embodiments. The above are only specific implementation methods 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 based on the protection scope of the claims.

[0052] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0053] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A scientific research task recommendation method based on distributed AI kernel density, characterized in that: Includes steps: Deploy a sub-AI language model on each scientific research management platform, and capture the scientific research data of the corresponding scientific research management platform according to the sub-AI language model; wherein the scientific research management platform is classified into a corresponding scientific research category; Identify the POI data of the scientific research data based on the main AI language model, and determine the density quantification data by quantifying the distribution density of various POIs of the scientific research management platform corresponding to the scientific research category according to the kernel density of the POI data; wherein there is a corresponding relationship between the POI data, the scientific research data, the scientific research category and the scientific research management platform; Quantifying the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data; The density quantization data and the frequency quantization data are input into the main AI language model to strengthen the main AI language model; wherein the strengthened main AI language model is used to output scientific research task recommendation results according to user information input.

2. The scientific research task recommendation method based on distributed AI kernel density according to claim 1 is characterized in that: The process of determining density quantification data according to the kernel density quantification of the POI data corresponding to the distribution density of various POIs on the scientific research management platform comprises the steps of: The POI position and the POI bandwidth are smoothed using a POI kernel function, and the result of the POI kernel function is used as the density quantization data.

3. The scientific research task recommendation method based on distributed AI kernel density according to claim 2 is characterized in that: The calculation method of POI kernel density is as follows: ； in, Core(x) represents the POI kernel density, x represents the location of the evaluation point, n Indicates the total number of POIs, m represents the kernel density bandwidth, H represents the POI kernel density, X i No. i The location of a POI.

4. The method for recommending scientific research tasks based on distributed AI kernel density according to claim 3 is characterized in that: The POI kernel density is calculated as follows: ； in, R c,m Indicates research category c The kernel density bandwidth is m The sum of the weights of the POIs, U c,m Indicates research category c and kernel density bandwidth m The POI index collection, M c Indicates research category c The collection of all impact areas under X i,y express i POI y The location of a point.

5. The method for recommending scientific research tasks based on distributed AI kernel density according to claim 1, characterized in that: The process of quantifying the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data is as follows: ； in, represents frequency quantitative data, r The identifier of the POI type. o Represents scientific research data, r The weight of the POI type, Representing scientific research data o Corresponding scientific research category c No. r The number of POI types; Indicates all the first r The number of POI types.

6. The method for recommending scientific research tasks based on distributed AI kernel density according to claim 1, characterized in that: The scientific research categories include basic research, applied research, development research, engineering research and interdisciplinary research.

7. The method for recommending scientific research tasks based on distributed AI kernel density according to claim 1, characterized in that: The sub-AI language model is deployed locally on the scientific research management platform; the main AI language model is deployed in the cloud.

8. A scientific research task recommendation device based on distributed AI kernel density, characterized in that: include: A data acquisition module, used to deploy a sub-AI language model on each scientific research management platform, and to capture the scientific research data of the corresponding scientific research management platform according to the sub-AI language model; wherein the scientific research management platform is classified into a corresponding scientific research category; A density calculation module, for identifying the POI data of the scientific research data based on the main AI language model, and determining the density quantification data according to the kernel density quantification of the scientific research category of the POI data corresponding to the various POI distribution densities of the scientific research management platform; wherein there is a corresponding relationship between the POI data, the scientific research data, the scientific research category and the scientific research management platform; A frequency calculation module, used to quantify the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data; A model strengthening module is used to input the density quantization data and the frequency quantization data into the main AI language model to strengthen the main AI language model; wherein the strengthened main AI language model is used to output scientific research task recommendation results based on user information input.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the scientific research task recommendation method based on distributed AI kernel density as described in any one of claims 1 to 7.

10. A data control device, characterized in that: include: one or more memories non-transitorily storing computer-executable instructions; One or more processors are configured to run computer executable instructions, wherein the computer executable instructions, when executed by one or more processors, implement the scientific research task recommendation method based on distributed AI kernel density as described in any one of claims 1 to 7.

Images