Research Task Recommendation Method and Device Based on Distributed AI Kernel Density

Abstract

The present application relates to a scientific research task recommendation method and device based on distributed AI kernel density. Sub-AI language models are deployed on each scientific research management platform, and scientific research data of the corresponding scientific research management platform is captured according to the sub-AI language models. The POI data of the scientific research data is identified based on the main AI language model, and the distribution density of various POIs corresponding to the scientific research categories in the scientific research management platform is quantified according to the kernel density of the POI data to determine the density quantization data. The distribution frequency of each POI type in each scientific research category in the scientific research data is quantified to obtain the frequency quantization 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; 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 is integrated, and the model ability of the main AI language model is strengthened through the POI data, so as to improve the accuracy and reference of the scientific research task recommendation results input and output according to user information.

Description

Technical Field

[0001] This application relates to the technical field of task data processing, and in particular, to a scientific research task recommendation method and device based on distributed AI kernel density. Background Art

[0002] Scientific research task recommendation refers to the process of recommending relevant scientific research tasks or projects to researchers through certain algorithms and technical means in the field of scientific research. The recommendation is usually based on various factors such as the historical behavior information, research interests, and domain knowledge of the researchers, aiming to help researchers more efficiently find research topics suitable for themselves and improve the efficiency and quality of scientific research results.

[0003] Therefore, scientific research task recommendation requires relying on a large amount of data. With the development of the big data era, data management tools for scientific research tasks have become important auxiliary tools in data-intensive scientific research environments. Currently, the data management tools for scientific research task recommendation are mainly the scientific research management platforms of various scientific research institutions. The data of such scientific research management platforms mainly comes from the records of the scientific research institutions where they are located 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 interference information in the public data of the Internet / third-party databases is relatively large, and the reference value of the 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-mentioned deficiencies. Summary of the Invention

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

[0006] The embodiments of the present application provide a scientific research task recommendation method based on distributed AI kernel density, including the steps of:

[0007] Deploy sub-AI language models 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 models; wherein, the scientific research management platforms are classified into corresponding scientific research categories;

[0008] The main AI language model is used to identify the POI data of the scientific research data, and based on the kernel density of the POI data, the distribution density of various POIs corresponding to the scientific research categories in the scientific research management platform is quantified to determine the density quantization data; wherein, there is a corresponding relationship among the POI data, the scientific research data, the scientific research categories, and the scientific research management platform.

[0009] Quantify the distribution frequency of each POI type in each scientific research category in the scientific research data to obtain frequency quantization data.

[0010] 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 input and output scientific research task recommendation results according to user information.

[0011] In the scientific research task recommendation method based on distributed AI kernel density according to the embodiments of the present application, sub-AI language models are deployed on each scientific research management platform, and the scientific research data of the corresponding scientific research management platform is captured according to the sub-AI language models. The main AI language model is used to identify the POI data of the scientific research data, and based on the kernel density of the POI data, the distribution density of various POIs corresponding to the scientific research categories in the scientific research management platform is quantified to determine the density quantization data. Quantify the distribution frequency of each POI type in each scientific research category in the scientific research data to obtain frequency quantization data. Input the density quantization data and the frequency quantization data 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 is integrated, the model ability of the main AI language model is strengthened through the POI data, and the accuracy and reference of the scientific research task recommendation results input and output according to user information are improved.

[0012] As one of the optional embodiments, the process of quantifying the distribution density of various POIs corresponding to the scientific research categories in the scientific research management platform based on the kernel density of the POI data to determine the density quantization data includes the steps:

[0013] Perform data smoothing processing on the POI position and the POI bandwidth with a POI kernel function, and use the result of the POI kernel function as the density quantization data.

[0014] As one of the optional embodiments, the calculation method of the POI kernel density is as follows:

[0015] ;

[0016] Wherein, Core(x) represents the POI kernel density, x represents the evaluation point position, n represents the total number of POIs, mrepresents the kernel density bandwidth, H represents the kernel function, X i The i location of the

[0017] As one of the optional embodiments, the calculation method of the POI kernel density is as follows:

[0018] ;

[0019] wherein, R c,m represents the scientific research category of c The sum of weights (normalized) of POIs with a kernel density bandwidth of m , U c,m represents the scientific research category c and the kernel density bandwidth m of the POI index set, M c represents the scientific research category c of all influence ranges, X i,y represents i the position of the y th point in the

[0020] As one of the optional embodiments, the process of quantifying the distribution frequency of each POI type in each scientific research category in the scientific research data is as follows:

[0021] ;

[0022] wherein, represents the frequency quantization data, r represents the identifier of the POI type, o represents the scientific research data, represents the r th weight of the POI type in the represents the scientific research data o corresponding to the scientific research category c of the r th number of POI types; represents the total number of all r th POI types in the main AI language model.

[0023] As one of the optional embodiments, the scientific research categories include basic research, applied research, development research, engineering research, and interdisciplinary research.

[0024] As one of the optional embodiments, the sub-AI language model is deployed locally on the scientific research management platform; the main AI language model is deployed in the cloud.

[0025] The embodiment of the present application further provides a scientific research task recommendation device based on distributed AI kernel density, including:

[0026] A data acquisition module, configured to deploy a sub-AI language model on each scientific research management platform, and capture scientific research data of the corresponding scientific research management platform according to the sub-AI language model; wherein, the scientific research management platforms are classified into corresponding scientific research categories;

[0027] A density calculation module, configured to identify POI data of the scientific research data based on the main AI language model, and quantify the distribution density of various POIs corresponding to the scientific research category for the scientific research management platform according to the kernel density of the POI data, and determine density quantization data; wherein, there is a corresponding relationship among the POI data, the scientific research data, the scientific research category, and the scientific research management platform;

[0028] A frequency calculation module, configured to quantify the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantization data;

[0029] A model enhancement module, configured to input the density quantization data and the frequency quantization data into the main AI language model to enhance the main AI language model; wherein, the enhanced main AI language model is used to output a scientific research task recommendation result according to the input of user information.

[0030] The scientific research task recommendation device based on distributed AI kernel density according to the embodiment of the present application deploys a sub-AI language model on each scientific research management platform, and captures scientific research data of the corresponding scientific research management platform according to the sub-AI language model. Identifies POI data of the scientific research data based on the main AI language model, and quantifies the distribution density of various POIs corresponding to the scientific research category for the scientific research management platform according to the kernel density of the POI data, and determines density quantization data. Quantifies the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantization data. Inputs the density quantization data and the frequency quantization data into the main AI language model to enhance the main AI language model; the enhanced main AI language model is used to output a scientific research task recommendation result according to the input of user information. Based on this, the scientific research data of each scientific research management platform is integrated, the model ability of the main AI language model is enhanced through the POI data, and the accuracy and reference of the scientific research task recommendation result output according to the input of user information are improved.

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

[0032] One or more memories, non-transiently storing computer-executable instructions;

[0033] One or more processors, configured to run computer-executable instructions, wherein when the computer-executable instructions are run by the one or more processors, a scientific research task recommendation method based on distributed AI kernel density according to any embodiment of the present application is implemented.

[0034] The above data control device deploys sub-AI language models on each scientific research management platform and grabs scientific research data of the corresponding scientific research management platform according to the sub-AI language models. Based on the main AI language model, identify the POI data of the scientific research data, and quantify the distribution density of various POIs corresponding to the scientific research categories of the scientific research management platform according to the kernel density of the POI data to determine the density quantization data. Quantify the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantization data. Input the density quantization data and the frequency quantization data 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, integrate the scientific research data of each scientific research management platform, strengthen the model ability of the main AI language model through POI data, and improve the accuracy and reference of the scientific research task recommendation results input and output according to user information.

[0035] At least one embodiment of the present application further 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.

[0036] The above non-transitory computer-readable storage medium deploys sub-AI language models on each scientific research management platform and grabs scientific research data of the corresponding scientific research management platform according to the sub-AI language models. Based on the main AI language model, identify the POI data of the scientific research data, and quantify the distribution density of various POIs corresponding to the scientific research categories of the scientific research management platform according to the kernel density of the POI data to determine the density quantization data. Quantify the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantization data. Input the density quantization data and the frequency quantization data 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, integrate the scientific research data of each scientific research management platform, strengthen the model ability of the main AI language model through POI data, and improve the accuracy and reference of the scientific research task recommendation results input and output according to user information. Description of the Drawings

[0037] Figure 1 It is a flowchart of a scientific research task recommendation method based on distributed AI kernel density according to an embodiment of the application;

[0038] Figure 2It is a framework diagram for AI deployment in an embodiment of this application;

[0039] Figure 3 It is a module structure diagram of a scientific research task recommendation device based on distributed AI kernel density in an embodiment;

[0040] Figure 4 It is a schematic block diagram of a data control device provided by the present invention;

[0041] Figure 5 It is a schematic diagram of a non-transitory computer-readable storage medium provided by the present invention. Detailed implementation manners

[0042] In order to make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this application. Obviously, the described embodiments are some but not all of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the described embodiments of this application without creative efforts shall fall within the scope of protection of this application.

[0043] Unless otherwise defined, the technical terms or scientific terms used in this application shall have the ordinary meanings understood by those of ordinary skill in the art to which this application belongs. The "first", "second", and similar terms used in this application do not denote any order, quantity, or importance, but are only used to distinguish different components. Words such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0044] In order to keep the following description of the embodiments of this application clear and concise, some detailed descriptions of known functions and known components are omitted in this application.

[0045] The embodiments of this application provide a scientific research task recommendation method based on distributed AI kernel density.

[0046] Figure 1 It is a flowchart of a scientific research task recommendation method based on distributed AI kernel density in an embodiment of an application. As Figure 1 shown, the scientific research task recommendation method based on distributed AI kernel density in an embodiment of an application includes steps S100 to S101:

[0047] S100, Deploy sub - AI language models on each scientific research management platform, and capture scientific research data of the corresponding scientific research management platform according to the sub - AI language models; wherein, the scientific research management platforms are classified into corresponding scientific research categories;

[0048] S101, Based on the main AI language model, identify the POI data of the scientific research data, and quantify the distribution density of various POIs corresponding to the scientific research category for the scientific research management platform according to the kernel density of the POI data to determine density quantization data; wherein, there is a corresponding relationship among the POI data, the scientific research data, the scientific research category, and the scientific research management platform;

[0049] S102, Quantify the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantization data;

[0050] S103, 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 input and output scientific research task recommendation results according to user information.

[0051] Figure 2 This is the AI deployment framework diagram of the embodiment of this application, as Figure 2 shown, the cloud platform distributes and manages each scientific research management platform and communicates with each scientific research management platform. The sub - AI language models are deployed on each scientific research management platform, and the main AI language model is deployed in the cloud. The sub - AI language models are used to capture the scientific research data of the corresponding scientific research management platform, and the main AI language model is used to identify the POI (Point of Interest) data of the scientific research data. At the same time, the main AI language model has an open iterative ability and can be iterated according to third - party data. The main AI language model gradually improves the input of user information and the scientific research task recommendation results according to the iteration.

[0052] As one of the optional embodiments, the sub - AI language models are deployed locally on the scientific research management platform; the main AI language model is deployed in the cloud.

[0053] As one of the optional embodiments, the process of quantifying the distribution density of various POIs corresponding to the scientific research category for the scientific research management platform according to the kernel density of the POI data to determine density quantization data includes the steps:

[0054] Perform data smoothing processing on the POI position and POI bandwidth with a POI kernel function, and use the result of the POI kernel function as the density quantization data.

[0055] Among them, the calculation method of POI kernel density is as follows:

[0056] ;

[0057] Among them, Core(x) represents the POI kernel density, x represents the location of the evaluation point, n represents the total number of POIs, m represents the kernel density bandwidth, H represents the kernel function, X i The i location of the

[0058] The calculation method of the POI kernel density is as follows:

[0059] ;

[0060] Among them, R c,m represents the scientific research category of c The sum of the weights of the POIs with a kernel density bandwidth of m is U c,m represents the scientific research category c and the kernel density bandwidth m is the set of POI indexes, M c represents the scientific research category c is the set of all influence ranges under X i,y represents i the location of the y th point in the

[0061] As one of the embodiments, the process of quantifying the distribution frequency of each POI type in each of the scientific research categories in the scientific research data is as follows:

[0062] ;

[0063] Among them, represents the frequency quantification data, r represents the identifier of the POI type, o represents the scientific research data, represents the r th weight of the POI type in the represents the scientific research data o corresponding to the scientific research category c of the r th number of POI types; represents the total number of all r th POI types in the main AI language model.

[0064] Preferably, the scientific research categories include basic research, applied research, development research, engineering research, and interdisciplinary research.

[0065] Among them, the main AI language model before reinforcement recommends scientific research tasks based on Points of Interest (POIs), predicts the user's next POI visit according to the user information input, and organizes the next scientific research tasks. In the embodiment of the present application, for the main AI language model after reinforcement, density quantization data and frequency quantization data are used to replace the POI part in the original model for model iteration.

[0066] Preferably, the POI part in the original main AI language model is replaced according to the hierarchical weighting 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, normalized after weighted summation, and the POI part in the original main AI language model is adjusted according to the normalization result.

[0067] It should be noted that due to the rapid development of the AI language model, for example, the correction of scientific research tasks can be performed by repeatedly inputting information in the AI language model. Therefore, the usage methods of the density quantization data and the frequency quantization data in the embodiment of the present application are not uniquely limited, and the above methods are only examples. The core of the calculation of the density quantization data and the frequency quantization data is to highlight the characteristics of the POI data and improve the recognition and iteration accuracy of the AI language model.

[0068] In the scientific research task recommendation method based on distributed AI kernel density in the embodiment of the present application, sub-AI language models are deployed on each scientific research management platform, and scientific research data of the corresponding scientific research management platform is captured according to the sub-AI language models. The POI data of the scientific research data is identified based on the main AI language model, and the distribution density of various POIs corresponding to the scientific research categories of the scientific research management platform is quantified according to the kernel density of the POI data to determine the density quantization data. The distribution frequency of each POI type in each scientific research category in the scientific research data is quantified to obtain the frequency quantization 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; the strengthened main AI language model is used to output scientific research task recommendation results according to the user information input. Based on this, the scientific research data of each scientific research management platform is integrated, and the model ability of the main AI language model is strengthened through the POI data, improving the accuracy and reference of the scientific research task recommendation results output according to the user information input.

[0069] The embodiment of the present application also provides a scientific research task recommendation device based on distributed AI kernel density.

[0070] Figure 3 For the module structure diagram of the scientific research task recommendation device based on distributed AI kernel density in an embodiment, as Figure 3 shown, the scientific research task recommendation device based on distributed AI kernel density in one embodiment includes:

[0071] The data acquisition module 100 is used to deploy sub-AI language models 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 models; wherein, the scientific research management platforms are classified into corresponding scientific research categories.

[0072] 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 corresponding to the scientific research management platform of the scientific research category according to the kernel density of the POI data to determine the density quantization data; wherein, there is a corresponding relationship among the POI data, the scientific research data, the scientific research category and the scientific research management platform.

[0073] The frequency calculation module 102 is used to quantify the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain the frequency quantization data.

[0074] The model enhancement module 103 is used to input the density quantization data and the frequency quantization data into the main AI language model to enhance the main AI language model; wherein, the enhanced main AI language model is used to output scientific research task recommendation results according to the input of user information.

[0075] The scientific research task recommendation device based on distributed AI kernel density in the embodiment of the present application deploys sub-AI language models 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 models. It identifies the POI data of the scientific research data based on the main AI language model, and quantifies the distribution density of various POIs corresponding to the scientific research management platform of the scientific research category according to the kernel density of the POI data to determine the density quantization data. It quantifies the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain the frequency quantization data. It inputs the density quantization data and the frequency quantization data into the main AI language model to enhance the main AI language model; the enhanced main AI language model is used to output scientific research task recommendation results according to the input of user information. Based on this, it integrates the scientific research data of each scientific research management platform, enhances the model ability of the main AI language model through the POI data, and improves the accuracy and reference of the scientific research task recommendation results output according to the input of user information.

[0076] At least one embodiment of the present application further provides a data control device. Figure 4 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 4As 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 non-transiently store computer-executable instructions; the processor 201 is used to run the computer-executable instructions, and when the computer-executable instructions are run by the processor 201, it can cause the processor 201 to 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.

[0077] For the specific implementation and related explanatory content of each step of the scientific research task recommendation method based on distributed AI kernel density, reference can be made to the relevant content in the embodiments of the scientific research task recommendation method based on distributed AI kernel density above, and details will not be elaborated here. It should be noted that Figure 4 The components of the data control device 20 shown are merely exemplary and not restrictive. According to actual application needs, the data control device 20 may also have other components.

[0078] In one embodiment, the processor 201 and the memory 200 may communicate directly or indirectly with each other. For example, the processor 201 and the memory 200 may communicate through 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. The type and function of the network are not limited in this application. For another example, the processor 201 and the memory 200 may also communicate through a bus connection. The bus may 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 may be set at the remote data server side (cloud) or the distributed energy system side (local side), or may also be set at the client side (for example, a mobile device such as a mobile phone). For example, the processor 201 may be a Central Processing Unit (CPU), a Tensor Processing Unit (TPU), or a Graphics Processing Unit (GPU) and other devices with data processing capabilities and / or instruction execution capabilities, and may control other components in the data prediction device 20 to perform desired functions. The Central Processing Unit (CPU) may be of the X86 or ARM architecture, etc.

[0079] In one embodiment, the memory 200 may include any combination of one or more computer program products, and the computer program products 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. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), portable compact disc read-only memory (CD-ROM), USB memory, flash memory, etc. One or more computer-executable instructions may be stored on the computer-readable storage media, and the processor 201 may run the computer-executable instructions to implement various functions of the data prediction device 20. Various application programs and various data may also be stored in the memory 200, as well as various data used and / or generated by the application programs, etc.

[0080] It should be noted that the data control device 20 can achieve similar technical effects as the foregoing scientific research task recommendation method based on distributed AI kernel density, and the repeated parts will not be elaborated.

[0081] At least one embodiment of the present application also provides a non-transitory computer-readable storage medium. Figure 5 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 5 shown, one or more computer-executable instructions 301 may be non-transitorily stored on the non-transitory computer-readable storage medium 30. For example, when the computer-executable instructions 301 are executed by a computer, the computer may be caused to 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.

[0082] In one embodiment, the non-transitory computer-readable storage medium 30 may be applied to the above data control device 20. For example, it may be the memory 200 in the data control device 20.

[0083] 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 elaborated.

[0084] 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 may be caused to 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.

[0085] For this application, the following points need to be noted:

[0086] (1) The accompanying drawings of the embodiments of this application only relate to the structures involved in the embodiments of this application. Other structures can refer to the general design.

[0087] (2) For clarity, in the 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.

[0088] (3) Without conflict, the embodiments of this 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 this application, but the protection scope of this application is not limited thereto. The protection scope of this application shall be subject to the protection scope of the claims.

[0089] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope described in this specification.

[0090] The above embodiments only represent several implementation manners of this application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application patent shall be subject to the appended 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; Based on the main AI language model, the POI data of the scientific research data is identified, and the POI kernel function is used to perform data smoothing on the POI position and POI bandwidth, and the result of the POI kernel function is used as density quantization 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; Quantify the distribution frequency of each POI type of each scientific research category in the scientific research data to obtain frequency quantification data 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; 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; The calculation method of POI kernel density is as follows: ； in, Core(x) represents the POI kernel density, 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 the point, H represents the kernel function, x represents the location of the evaluation point, n Indicates the total number of POIs.

2. The scientific research task recommendation method based on distributed AI kernel density according to claim 1 is characterized in that: The scientific research categories include basic research, applied research, development research, engineering research and interdisciplinary research.

3. The scientific research task recommendation method based on distributed AI kernel density according to claim 1 is 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.

4. 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, used for identifying the POI data of the scientific research data based on the main AI language model, and performing data smoothing processing on the POI position and POI bandwidth using the POI kernel function, and using the result of the POI kernel function as 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; The frequency calculation module is 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 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; A model strengthening module, used for 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 for outputting scientific research task recommendation results according to user information input; The POI kernel density is calculated as follows: ； in, Core(x) represents the POI kernel density, 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 the point, H represents the kernel function, x represents the location of the evaluation point, n Indicates the total number of POIs.

5. 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 3.

6. 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 3.

Images