Model processing method, device, equipment and storage medium

Abstract

The disclosed embodiments relate to a model processing method, device, equipment and storage medium, the method comprising: obtaining the industrial chain of the target industry, wherein the industrial chain includes at least one industrial node; obtaining the scientific and technological resources of the target industry, and determining the scientific and technological resources associated with the industrial node; obtaining the scientific and technological needs of the target industry, and determining the scientific and technological needs associated with the industrial node; using the industrial node and its associated scientific and technological resources and scientific and technological needs, training the supply and demand matching model to obtain a trained supply and demand matching model. The disclosed embodiments can improve the accuracy of the trained supply and demand matching model for supply and demand matching of scientific and technological resources.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a model processing method, apparatus, device, and storage medium. Background Art

[0002] In the new economic environment, faced with objective environments such as the global flow of innovation factors, the spatial dispersion of innovation entities, and the rapidly changing information resources, scientific and technological services (such as matching the supply and demand of scientific and technological resources) play an important role in the national innovation system, carrying core functions such as optimizing R&D resource allocation services, providing professional value-added services, promoting the transfer and transformation of technological achievements, and strengthening information consulting services.

[0003] At present, the existing technology resource supply and demand matching methods are based on technology resources and technology needs to establish and train matching models, so that the technology needs are input into the trained matching model to obtain the matching technology resources output by the matching model, or the technology needs are input into the trained matching model to obtain the matching technology resources output by the matching model. However, the existing technology resource supply and demand matching methods have the problem of inaccurate matching results. Therefore, how to obtain a matching model with high matching result accuracy has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a model processing method, device, equipment and storage medium.

[0005] A first aspect of an embodiment of the present disclosure provides a model processing method, the method comprising:

[0006] Acquire the industrial chain of the target industry, wherein the industrial chain includes at least one industrial node;

[0007] Obtain the scientific and technological resources of the target industry and determine the scientific and technological resources associated with the industrial node;

[0008] Obtain the technological needs of the target industry and determine the technological needs associated with the industrial nodes;

[0009] The supply and demand matching model is trained by utilizing the industrial nodes and their associated scientific and technological resources and scientific and technological needs to obtain a trained supply and demand matching model.

[0010] A second aspect of an embodiment of the present disclosure provides a model processing device, the device comprising:

[0011] A first acquisition module is used to acquire the industrial chain of a target industry, wherein the industrial chain includes at least one industrial node;

[0012] The second acquisition module is used to acquire the scientific and technological resources of the target industry and determine the scientific and technological resources associated with the industrial node;

[0013] The third acquisition module is used to acquire the technological needs of the target industry and determine the technological needs associated with the industrial node;

[0014] The training module is used to train the supply and demand matching model by using the industrial node and its associated scientific and technological resources and scientific and technological needs to obtain a trained supply and demand matching model.

[0015] A third aspect of an embodiment of the present disclosure provides an electronic device, the server comprising: a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the method of the first aspect above.

[0016] A fourth aspect of an embodiment of the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method of the first aspect described above can be implemented.

[0017] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0018] The disclosed embodiment can obtain the industrial chain of the target industry, wherein the industrial chain includes at least one industrial node; obtain the scientific and technological resources of the target industry, and determine the scientific and technological resources associated with the industrial node; obtain the scientific and technological needs of the target industry, and determine the scientific and technological needs associated with the industrial node; use the industrial node and its associated scientific and technological resources and scientific and technological needs to train the supply and demand matching model to obtain a trained supply and demand matching model. It can be seen that the industrial chain is introduced in the above technical solution. When the trained supply and demand matching model is used to match the supply and demand of scientific and technological resources, the industrial chain is taken into consideration, which can provide a more macro and comprehensive perspective, better understand the relationship between scientific and technological resources and scientific and technological needs, thereby improving the accuracy of the matching results. In addition, taking the industrial chain into consideration can provide a richer and more diverse data source, helping the supply and demand matching model to better learn the laws between scientific and technological resources and scientific and technological needs, thereby improving the training accuracy of the supply and demand matching model. In addition, taking the industrial chain into consideration can provide a more flexible and general framework to help the supply and demand matching model better adapt to the characteristics and changes of different industries, thereby improving the generalization ability of the matching model. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 is a flow chart of a model processing method provided by an embodiment of the present disclosure;

[0022] Figure 2 is a schematic diagram of the industrial chain of the photoresist industry provided by the embodiments of the present disclosure;

[0023] Figure 3 It is a logic schematic diagram for obtaining the industrial chain of a target industry provided by an embodiment of the present disclosure;

[0024] Figure 4 is a structural schematic diagram of a model processing device provided by an embodiment of the present disclosure;

[0025] Figure 5 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0028] Existing methods for matching supply and demand of scientific and technological resources are all based on establishing and training matching models based on scientific and technological resources and scientific and technological needs. The applicant has conducted research on this and found that when the portrait of scientific and technological resources or scientific and technological needs is inaccurate, the matching results output by the matching model will be inaccurate. In addition, due to the small number of training samples, the training accuracy of the matching model is usually not high, which will also lead to inaccurate matching results. In addition, the supply and demand conversion methods of scientific and technological resources are usually different in different industries (or scientific and technological fields), which makes it difficult for the matching model to accurately match supply and demand in all industries, and thus leads to inaccurate matching results. In view of this, the applicant believes that the industrial chain of the industry can be introduced in the process of training the matching model, so that the scientific and technological needs matched by the matching model for scientific and technological resources, or the scientific and technological resources matched by the matching model for scientific and technological needs, meet the requirements of the industry to which they belong, thereby improving the matching accuracy of the matching model. Based on the inventive concept, the embodiments of the present application provide a model processing method, device, equipment and storage medium. Below, the model processing method is first described in detail.

[0029] Figure 1 is a flow chart of a model processing method provided by an embodiment of the present disclosure, and the method can be executed by an electronic device. The electronic device can be exemplarily understood as a device such as a mobile phone, a tablet computer, a laptop computer, a desktop computer, a smart TV, etc. Figure 1 As shown, the method provided in this embodiment includes the following steps:

[0030] S110. Acquire the industrial chain of the target industry, wherein the industrial chain includes at least one industrial node.

[0031] Specifically, the target industry can be any industry, and the number of target industries can be set by those skilled in the art according to actual conditions, and is not limited here. For example, the target industry can include agriculture, automobile industry, banking industry, etc., but is not limited thereto. Preferably, the target industry includes all industries currently on the market.

[0032] Specifically, each target industry has an industrial chain, wherein the industrial chain is in a tree structure, usually including at least one of the three industrial links of the upstream link, the midstream link and the downstream link, and an industrial link usually includes at least one industrial node.

[0033] For example, Figure 2 Schematic diagram of the industrial chain of the photoresist industry provided by the embodiment of the present disclosure. Figure 2As shown, the industrial chain of the photoresist industry has a tree-like structure, including upstream, midstream and downstream links. Among them, the upstream link mainly involves the production of photoresist raw materials, including resins, solvents, photoinitiators, monomers and other industrial nodes; the midstream link mainly involves the research and development, manufacturing and sales of photoresists, including PCB photoresists, LCD photoresists, semiconductor photoresists and other industrial nodes; the downstream link mainly involves the application of photoresists and the manufacture of related equipment, including printed circuit boards, display panels, electronic chips, electronic terminals, consumer electronics, aerospace, military industry and other industrial nodes.

[0034] It should be noted that there are many specific implementation methods for obtaining the industrial chain of the target industry. Typical examples are described below, but are not limited to these.

[0035] In some embodiments, S110 may include: S111, obtaining original corpus of the target industry.

[0036] Specifically, the original corpus of the target industry can be obtained from any public channel, for example, from Internet search engines, industry blogs and forums of the target industry, industry associations of the target industry, and other channels.

[0037] Specifically, the original forecast may include structured data and / or unstructured data, which is not limited in this application.

[0038] S112. Extract knowledge from the original corpus to obtain multiple elements.

[0039] Specifically, for the structured data in the original corpus, knowledge extraction can be performed directly to obtain the corresponding elements.

[0040] Specifically, for the unstructured data in the original corpus, the information contained in the audio, video, and pictures can be converted into text information, and then the text information can be processed by natural language processing (i.e., NLP), such as word segmentation, introduction of stop words, etc. Then, the information processed by NLP can be processed by feature processing, such as vectorization and Hash Trick processing, etc. Finally, knowledge extraction is performed to obtain the corresponding elements.

[0041] Specifically, knowledge extraction may include extracting entities, attributes of entities, and relationships between entities to obtain elements.

[0042] S113. Determine the industry and industrial link to which the factor belongs.

[0043] Specifically, the multiple elements obtained are classified, and for the elements under each category, the industry and upstream, midstream and downstream links are identified and processed to obtain the industry and industrial link to which the elements under each category belong.

[0044] S114. For each industrial link, cluster the elements under the industrial link to obtain corresponding multiple element sets.

[0045] Specifically, any clustering algorithm known to those skilled in the art may be used for clustering processing, and this application does not limit this.

[0046] Specifically, through clustering processing, the factors under the same industrial link can be divided into several factor sets according to the intrinsic properties of the factors. The factors in each factor set have the same characteristics as much as possible, and the differences in characteristics between different factor sets are as large as possible.

[0047] S115. Determine the industrial node to which the element set belongs, thereby obtaining the industrial chain.

[0048] Specifically, for each element set, element structuring processing (i.e., processing unstructured and semi-structured data into structured data), industry node identification processing, and multi-entity fusion processing are performed in turn to obtain the industry node corresponding to the element set.

[0049] Of course, the industrial chain obtained through S111-S115 can also be manually reviewed to improve its accuracy.

[0050] For example, Figure 3 This is a logical schematic diagram of obtaining the industrial chain of a target industry provided by an embodiment of the present disclosure. Figure 3 As shown in the figure, according to the combined method and technical route of "industry dictionary + industry corpus + business rules + model construction", the industry dictionary step includes unstructured data analysis, the industry corpus includes a detailed description of the key nodes of the industry, the business rules include the association between nodes, etc., and the model construction includes model design, parameter expression, model training and model verification. An industry dictionary is established according to industry needs, the industry corpus is annotated according to the industry dictionary, and a statistical learning model and a deep learning model are established; when the sample size is small (<10 million sentences), rules and statistical operations are mainly used, and when the sample size is large (more than 10 million sentences), a deep learning model is used; for the processing of large granularity such as chapters, a layered method is adopted, and different processing methods are used for titles, abstracts, texts, etc., to obtain the final processing results with different accuracy requirements.

[0051] Of course, in other embodiments, if the industrial chain of the target industry has been disclosed by a public channel, the industrial chain of the target industry can be directly obtained from the public channel.

[0052] S120. Obtain the scientific and technological resources of the target industry and determine the scientific and technological resources associated with the industrial nodes.

[0053] Specifically, scientific and technological resources can be relevant data of any form of scientific and technological achievements. For example, scientific and technological resources include relevant data of basic theoretical achievements (such as papers, monographs, patents), applied technological achievements (such as products) and soft science achievements (such as basic software, application software), but are not limited to these.

[0054] Specifically, scientific and technological resources of the target industry can be obtained from public channels, such as Internet search engines, patent databases, paper databases, product introduction websites, etc., but not limited thereto.

[0055] Specifically, for each target industry, the scientific and technological resources of the target industry are associated with the industrial nodes of the target industry.

[0056] It should be noted that there are many specific implementation methods for determining the scientific and technological resources associated with industrial nodes. Typical examples are described below, but are not limited to these.

[0057] In some implementations, determining the scientific and technological resources associated with the industrial node may include: S121, summarizing and labeling the scientific and technological resources to obtain a brief introduction and label of the scientific and technological resources.

[0058] Specifically, any summarization algorithm and labeling algorithm known to those skilled in the art may be used to summarize and label scientific and technological resources, and this application does not limit this.

[0059] Specifically, the introduction of scientific and technological resources is a text that briefly introduces the scientific and technological resources. For example, the introduction of scientific and technological resources is a text that describes the characteristics and value of scientific and technological resources.

[0060] Specifically, the labels of scientific and technological resources are words that stereotype scientific and technological resources or classify them into a certain category, so as to realize the portrait of scientific and technological resources. For example, the labels of scientific and technological resources are texts and a set of labels (such as resource name, resource type, resource description, etc.) that describe the characteristics and value of scientific and technological resources. Accordingly, keywords can be extracted from information such as resource name, resource type, resource description, etc., and combined with other information to generate labels for scientific and technological resources. The introduction and labels of scientific and technological resources can help users find the scientific and technological resources they need more quickly and improve the quality of scientific and technological resource search and recommendation.

[0061] S122. Summarize and label the industrial nodes to obtain a brief introduction and labels of the industrial nodes.

[0062] Specifically, any summarization algorithm and labeling algorithm known to those skilled in the art may be used to summarize and label the industry nodes, and this application does not limit this.

[0063] Specifically, the introduction of the industry node is a text that briefly introduces the industry node. For example, the introduction of the industry node is a text that describes the characteristics and requirements of the industry node.

[0064] Specifically, the label of an industry node is a word that stereotypes or classifies the industry node into a certain category to achieve a portrait of the industry node. For example, the label of an industry node is a set of labels that describe the characteristics and requirements of the industry node (such as industry category, product type, technology level, etc.).

[0065] The introduction and labels of industry nodes can help users more clearly understand the structure and development trend of the industrial chain, as well as the problems and opportunities in the industrial chain.

[0066] S123. Input the brief introduction and label of scientific and technological resources, and the brief introduction and label of industrial nodes into the trained first matching model to obtain the first matching degree of scientific and technological resources and industrial nodes.

[0067] Specifically, the construction and specific training process of the first matching model can be configured by those skilled in the art according to actual conditions and are not limited here.

[0068] Exemplarily, first, a large amount of data on scientific and technological resources and industrial chains are collected. The data on scientific and technological resources include, for example, the name, type, description, and keywords of scientific and technological resources. The data on the industrial chain may include information such as the characteristics of each industrial node and demand. The data on scientific and technological resources and industrial chains are cleaned and preprocessed to extract effective introductions and labels of scientific and technological resources and industrial nodes. The matching degree between scientific and technological resources and industrial nodes is calculated. For example, for an industrial node and multiple scientific and technological resources, a high-dimensional spatial distribution of the multiple scientific and technological resources and the industrial node is performed using a K-nearest neighbor classification algorithm. The multiple scientific and technological resources are fully classified by a feature selection method based on various high-document frequencies and a supervised K-NN classification method. The distance between each scientific and technological resource in each category and the industrial node is calculated based on the classification. The larger the distance, the smaller the matching degree. At the same time, the average distance between all scientific and technological resources in each category and the industrial node is calculated to determine the class with the smallest average distance. Among all the distances corresponding to the class with the smallest average distance, the scientific and technological resource with the smallest distance is found, which means that the scientific and technological resource is most matched with the industrial node. In this way, a large number of training samples are obtained, including industrial nodes, scientific and technological resources associated with industrial nodes, and the real matching degree between industrial nodes and their associated scientific and technological resources. It can be understood that the more the number of training samples, the higher the training accuracy of the first matching model, and the more accurate the matching result.

[0069] Then, a suitable matching algorithm is selected for the first matching model, and the structure and parameters of the first matching model are designed according to the characteristics of scientific and technological resources and industrial chains. For example, a matching algorithm based on deep learning, such as a twin-tower neural network, can be used to improve the expressiveness and accuracy of the first matching model by using technologies such as autoencoders or attention mechanisms. Among them, the twin-tower neural network is a commonly used deep matching algorithm, which uses two neural networks of the same structure to encode two inputs respectively and calculate the similarity between them. The autoencoder is an unsupervised learning algorithm that can learn a low-dimensional representation of the input data and reconstruct the original data. The attention mechanism is a technology that enhances the expressiveness of neural networks. It can assign different weights according to the importance of the input data and aggregate them into a high-level representation.

[0070] Finally, training samples are needed to train and optimize the first matching model so that the first matching model can learn the intrinsic connection and similarity between scientific and technological resources and industrial nodes. Among them, the performance of the first matching model can be evaluated by using methods such as cross entropy loss function or contrast loss function, and the parameters of the matching algorithm in the first matching model can be updated by using methods such as gradient descent or stochastic gradient descent.

[0071] Specifically, the first matching degree is used to characterize the matching degree or correlation degree between scientific and technological resources and industrial nodes.

[0072] It can be understood that using the trained first matching model to determine the first matching degree of the target industry's scientific and technological resources and industrial nodes can eliminate the need for manual labeling of the first matching degrees of the two, which is more efficient and saves labor costs.

[0073] Of course, in other embodiments, determining the scientific and technological resources associated with the industry nodes may include: determining the scientific and technological resources associated with each industry node in response to a first association operation input by a user.

[0074] S124. Determine the association between scientific and technological resources and industrial nodes whose first matching degree is greater than a preset first threshold.

[0075] Specifically, the specific value of the preset first threshold can be set by those skilled in the art according to actual conditions and is not limited here.

[0076] S130. Obtain the technological needs of the target industry and determine the technological needs associated with the industrial nodes.

[0077] Specifically, the scientific and technological demand may be any form of relevant data on the demand for scientific and technological achievements. For example, the scientific and technological demand may include demands expressed orally or in writing by users, demands obtained through data or information analysis, etc., but is not limited thereto.

[0078] Specifically, the specific method of obtaining the scientific and technological needs of the target industry can be set by technical personnel in this field according to actual conditions and is not limited here.

[0079] For example, the technological needs can be collected verbally or in writing in a demand-guided manner. Specifically, the technological needs are classified according to different industries, and then demand collection templates for different types of technological needs are established. The demand collection templates are used to guide the demand proposers to provide their technological needs verbally or in writing.

[0080] Specifically, for each target industry, the technological needs of the target industry are associated with the industrial nodes of the target industry.

[0081] It should be noted that there are many specific implementation methods for determining the technological needs associated with industrial nodes. Typical examples are described below, but are not limited to these.

[0082] In some implementations, determining the technological needs associated with the industrial node may include: S131, summarizing and labeling the technological needs to obtain a brief introduction and labels of the technological needs.

[0083] Specifically, any summarization algorithm and labeling algorithm known to those skilled in the art may be used to summarize and label scientific and technological needs, and this application does not limit this.

[0084] Specifically, the introduction of the technological demand is a text that briefly introduces the technological demand. For example, the introduction of the technological demand is a text that describes the characteristics and conditions of the user's demand.

[0085] Specifically, the labels of scientific and technological needs are words that stereotype or classify scientific and technological needs into a certain category to achieve a profile of scientific and technological needs. For example, the labels of scientific and technological needs are a set of labels that describe the characteristics and conditions of user needs (such as demand subject, demand type, demand deadline, etc.). Exemplarily, natural language processing technologies such as word segmentation, part-of-speech tagging, named entity recognition, keyword extraction, etc. can be used to perform semantic analysis on the description of scientific and technological needs, and combined with other information to generate labels for scientific and technological needs.

[0086] The introduction and labeling of technological needs can help users express their needs more accurately and improve the efficiency of demand information collection and processing.

[0087] S132. Input the brief introduction and labels of the technological needs, and the brief introduction and labels of the industrial nodes into the trained second matching model to obtain the second matching degree between the technological needs and the industrial nodes.

[0088] Specifically, the construction and specific training process of the second matching model can be configured by those skilled in the art according to actual conditions and are not limited here.

[0089] For example, first, collect a large amount of data on scientific and technological needs, such as designing a demand information collection form, including basic information such as demand subject, demand description, demand type, demand deadline, demand budget, and some specific information for different types of needs, such as technical difficulties, results form, cooperation mode, etc. Based on the demand information collection form, dynamically generate a guided question-and-answer process to guide users to fill in the demand information collection form. For example, a rule-based or machine learning-based dialogue system can be used to ask appropriate questions or give corresponding feedback and prompts based on the user's answer. Then, analyze and process the demand data filled in by the user to extract effective introductions and tags. Calculate the matching degree between technology demand and industrial node. For example, for an industrial node and multiple technology demand, use the K-nearest classification algorithm to distribute the multiple technology demand and the industrial node in high-dimensional space. Through the feature selection method based on various high document frequencies and the supervised K-NN classification method, classify the multiple technology demand in full dimensions. Calculate the distance between each technology demand and the industrial node in each category of technology demand based on classification. The larger the distance, the smaller the matching degree. At the same time, calculate the average value of the distance of each category, determine the category with the smallest average distance, and find the technology demand with the smallest distance among all distances of the category with the smallest average distance, which means that the technology demand is the most matched with the industrial node. In this way, a large number of training samples are obtained, and the training samples include industrial nodes, technology demand associated with industrial nodes, and the real matching degree between industrial nodes and their associated technology demand. It can be understood that the more training samples there are, the higher the training accuracy of the second matching model and the more accurate the matching result.

[0090] Then, select a suitable matching algorithm for the second matching model, and design the structure and parameters of the second matching model according to the technological needs and the characteristics of the industrial chain. For example, a matching algorithm based on deep learning, such as a twin-tower neural network, can be used, and technologies such as autoencoders or attention mechanisms can be used to improve the expressiveness and accuracy of the second matching model.

[0091] Finally, the training samples are needed to train and optimize the second matching model so that the second matching model can learn the intrinsic connection and similarity between scientific and technological needs and industrial nodes. The performance of the second matching model can be evaluated by using methods such as cross entropy loss function or contrast loss function, and the parameters of the matching algorithm in the second matching model, such as learning rate, batch size, hidden layer size, etc., can be updated by using methods such as gradient descent or stochastic gradient descent. The cross entropy loss function is a commonly used loss function for classification problems, which measures the difference between two probability distributions. The contrast loss function is a commonly used loss function for metric learning problems, which makes the distance between similar inputs smaller and the distance between dissimilar inputs larger. Gradient descent is a commonly used optimization algorithm that updates the parameters according to the gradient direction of the loss function to the parameters so that the loss function reaches the minimum value. Stochastic gradient descent is an improved gradient descent algorithm that uses only one or a small batch of training samples to update the parameters each time, making the optimization process faster and more stable.

[0092] Specifically, the first matching degree is used to characterize the matching degree or correlation degree between scientific and technological needs and industrial nodes.

[0093] It can be understood that using the trained second matching model to determine the first matching degree of the target industry's technological needs and industrial nodes can eliminate the need for manual labeling of the first matching degrees of the two, which is more efficient and saves labor costs.

[0094] Of course, in other embodiments, determining the technological requirements associated with the industry nodes may include: determining the technological requirements associated with each industry node in response to an association operation input by a user.

[0095] S133, determining the association between the technological demand and the industrial node whose second matching degree is greater than a preset second threshold.

[0096] Specifically, the specific value of the preset second threshold can be set by those skilled in the art according to actual conditions and is not limited here.

[0097] It can be understood that using the trained second matching model to determine the first matching degree of the target industry's technological needs and industrial nodes can eliminate the need for manual labeling of the first matching degrees of the two, which is more efficient and saves labor costs.

[0098] Of course, in other embodiments, determining the technological resources associated with the industry nodes may include: determining the technological requirements associated with each industry node in response to a second association operation input by the user.

[0099] S140. Utilize the industrial nodes and their associated scientific and technological resources and scientific and technological needs to train the supply and demand matching model to obtain a trained supply and demand matching model.

[0100] In some embodiments, S140 may include: S141, using the introduction and labels of the industry node, the introduction and labels of the scientific and technological resources associated with the industry node, and the introduction and labels of the scientific and technological needs associated with the industry node to train the supply and demand matching model to obtain a trained supply and demand matching model.

[0101] In some examples, S141 may include: S1411, inputting the introduction and labels of the technological requirements and the introduction and labels of the associated industrial nodes into the supply and demand matching model, obtaining the introduction and labels of the training technological resources output by the supply and demand matching model, and determining the first difference between the introduction and labels of the technological resources associated with the technological requirements and the introduction and labels of the training technological resources; and / or; S1412, inputting the introduction and labels of the technological resources and the introduction and labels of the associated industrial nodes into the supply and demand matching model, obtaining the introduction and labels of the training technological requirements output by the supply and demand matching model, and determining the second difference between the introduction and labels of the technological requirements associated with the technological resources and the introduction and labels of the training technological requirements.

[0102] Specifically, the industrial nodes and their associated scientific and technological resources and scientific and technological needs obtained through S110-S130 are used as training samples to train the supply and demand matching model.

[0103] Specifically, the supply and demand matching model is a matching model established based on a rule base that can comprehensively consider the profile and labels of industrial nodes, the profile and labels of scientific and technological needs, and the profile and labels of scientific and technological resources.

[0104] Among them, the rule base includes a series of rules formulated according to the characteristics of the industrial chain, scientific and technological needs and scientific and technological resources, which are used to judge the degree of matching and correlation between the three. The process of establishing the rule base is as follows: First, collect a large amount of data on the industrial chain, scientific and technological needs and scientific and technological resources, perform data cleaning and preprocessing, and extract effective profiles and labels. Then, analyze the similarities, differences, dependencies and other relationships between industrial nodes, scientific and technological needs and scientific and technological resources, and summarize some general or specific matching rules, such as label-based matching rules, content-based matching rules, context-based matching rules, etc. Organize these matching rules into a rule base, and assign a weight or priority to each rule to indicate the importance of the rule in the matching process.

[0105] The establishment process of the supply and demand matching model is as follows: First, the rule base is converted into a computable form, such as a logical expression, a mathematical formula, a decision tree, etc. Then, a matching function is defined to calculate the matching score between the introduction and label of the industry node, the introduction and label of the technology demand, and the introduction and label of the technology resource. The matching function can give different matching scores according to different rules (such as cosine similarity, Pearson correlation coefficient, etc.), such as complete match, partial match, mismatch, etc. The matching score can characterize the closeness between the introduction and label of the industry node, the introduction and label of the technology demand, and the introduction and label of the technology resource, that is, the degree of similarity or correlation between them in semantics or logic. The higher the closeness, the more likely they are to match; the lower the closeness, the more likely they are to mismatch. It is also necessary to set a threshold to determine whether the matching result meets the user's needs. The higher the threshold, the stricter the matching result. Only the introduction and label of the industry node, the introduction and label of the technology demand, and the introduction and label of the technology resource whose closeness exceeds the threshold can be considered as a match; the lower the threshold, the looser the matching result. As long as the introduction and label of the industry node, the introduction and label of the technology demand, and the introduction and label of the technology resource whose closeness is not less than the threshold can be considered as a match. The threshold can be adjusted according to the user's preference or the system's performance, such as high precision and low recall or low precision and high recall.

[0106] S1413. Adjust the model parameters of the supply-demand matching model according to the first difference and / or the second difference until a training end condition is met to obtain a trained supply-demand matching model.

[0107] Specifically, when S141 includes S1411 but does not include S1412, the model parameters of the supply and demand matching model are adjusted according to the first difference until the training end condition is met, so as to obtain a trained supply and demand matching model; when S141 includes S1411 but does not include S1412, the model parameters of the supply and demand matching model are adjusted according to the second difference until the training end condition is met, so as to obtain a trained supply and demand matching model; when S141 includes S1411 and S1412, the model parameters of the supply and demand matching model are adjusted according to the first difference and the second difference until the training end condition is met, so as to obtain a trained supply and demand matching model.

[0108] In some examples, S1413 may include: adjusting the model parameters of the supply and demand matching model according to the first difference and / or the second difference until the first difference is less than a preset third threshold and / or the second difference is less than a preset third threshold, to obtain an intermediate supply and demand matching model; and verifying the validity of the intermediate supply and demand matching model to obtain a trained supply and demand matching model. It should be noted that the understanding of "and / or" refers to the understanding in the previous paragraph and will not be repeated here.

[0109] Specifically, the specific value of the preset third threshold can be set by those skilled in the art according to actual conditions and is not limited here.

[0110] It should be noted that any possible validity verification method can be used to verify the validity of the intermediate supply and demand matching model, and this application does not limit this.

[0111] It can be understood that by verifying the validity of the intermediate supply and demand matching model to obtain a trained supply and demand matching model, the matching results of the trained supply and demand matching model can be made more accurate.

[0112] Of course, in other examples, the model parameters of the supply and demand matching model may also be adjusted according to the first difference and / or the second difference until the first difference is less than a preset third threshold and / or the second difference is less than a preset third threshold, and the training is completed.

[0113] Specifically, after the supply and demand matching model is trained, when it is used to match the supply and demand of scientific and technological resources, the input is the introduction and labels of the user's scientific and technological needs, as well as the introduction and labels of the industry nodes selected by the user, and the output is the introduction and labels of the scientific and technological resources with the highest matching score; and / or; the input is the introduction and labels of the user's scientific and technological resources, as well as the introduction and labels of the industry nodes selected by the user, and the output is the introduction and labels of the scientific and technological needs with the highest matching score.

[0114] Optionally, the method further includes: obtaining the labels and introduction of the technological needs and the labels and introduction of the industrial nodes input by the user; inputting the labels and introduction of the technological needs and the labels and introduction of the industrial nodes input by the user into the trained supply-demand matching model, and obtaining the introduction and labels of the technological resources output by the trained supply-demand matching model; and / or;

[0115] Obtain the labels and introductions of the scientific and technological resources and the labels and introductions of the industrial nodes input by the user; input the labels and introductions of the scientific and technological resources and the labels and introductions of the industrial nodes input by the user into the trained supply and demand matching model, and obtain the introductions and labels of the scientific and technological resources output by the trained supply and demand matching model.

[0116] The disclosed embodiment can obtain the industrial chain of the target industry, wherein the industrial chain includes at least one industrial node; obtain the scientific and technological resources of the target industry, and determine the scientific and technological resources associated with the industrial node; obtain the scientific and technological needs of the target industry, and determine the scientific and technological needs associated with the industrial node; use the industrial node and its associated scientific and technological resources and scientific and technological needs to train the supply and demand matching model to obtain a trained supply and demand matching model. It can be seen that the industrial chain is introduced in the above technical solution. When the trained supply and demand matching model is used to match the supply and demand of scientific and technological resources, the industrial chain is taken into consideration, which can provide a more macro and comprehensive perspective, better understand the relationship between scientific and technological resources and scientific and technological needs, thereby improving the accuracy of the matching results. In addition, taking the industrial chain into consideration can provide a richer and more diverse data source, helping the supply and demand matching model to better learn the laws between scientific and technological resources and scientific and technological needs, thereby improving the training accuracy of the supply and demand matching model. In addition, taking the industrial chain into consideration can provide a more flexible and general framework to help the supply and demand matching model better adapt to the characteristics and changes of different industries, thereby improving the generalization ability of the matching model.

[0117] Figure 4 is a schematic diagram of the structure of a model processing device provided by an embodiment of the present disclosure, and the model processing device can be understood as the above-mentioned electronic device or a part of the functional modules in the above-mentioned electronic device. Figure 4 As shown, the model processing device 400 includes:

[0118] A first acquisition module 410 is used to acquire the industrial chain of a target industry, wherein the industrial chain includes at least one industrial node;

[0119] The second acquisition module 420 is used to acquire the scientific and technological resources of the target industry and determine the scientific and technological resources associated with the industrial node;

[0120] The third acquisition module 430 is used to acquire the technology demand of the target industry and determine the technology demand associated with the industry node;

[0121] The training module 440 is used to train the supply-demand matching model by using the industrial node and its associated scientific and technological resources and scientific and technological needs to obtain a trained supply-demand matching model.

[0122] In another embodiment of the present disclosure, the first acquisition module 410 is specifically used to acquire the original corpus of the target industry;

[0123] Extracting knowledge from the original corpus to obtain multiple elements;

[0124] Determine the industry and industrial link to which the said factor belongs;

[0125] For each of the industrial links, clustering the elements under the industrial link to obtain a corresponding plurality of element sets;

[0126] Determine the industrial node to which the element set belongs, thereby obtaining the industrial chain.

[0127] In another embodiment of the present disclosure, the second acquisition module 420 includes a first determination submodule for determining the scientific and technological resources associated with the industrial node, and the first determination submodule is specifically used to summarize and label the scientific and technological resources to obtain the introduction and label of the scientific and technological resources;

[0128] Summarize and label the industrial nodes to obtain a brief introduction and labels of the industrial nodes;

[0129] Inputting the brief introduction and label of the scientific and technological resources and the brief introduction and label of the industrial nodes into the trained first matching model to obtain a first matching degree between the two;

[0130] Determine the association between scientific and technological resources and industrial nodes whose first matching degree is greater than a preset first threshold.

[0131] In another embodiment of the present disclosure, the third acquisition module 430 includes a second determination submodule for determining the technological demand associated with the industrial node, and the second determination submodule is specifically used to summarize and label the technological demand to obtain the introduction and label of the technological demand;

[0132] Inputting the brief introduction and label of the technology demand and the brief introduction and label of the industry node into the trained second matching model to obtain a second matching degree between the two;

[0133] Determine the association between the technology demand and the industrial node whose second matching degree is greater than a preset second threshold.

[0134] In yet another embodiment of the present disclosure, the training module 440 may include:

[0135] The third determination submodule is used to input the introduction and label of the technological demand and the introduction and label of the industrial node associated with the technological demand into the supply and demand matching model, obtain the introduction and label of the training technological resource output by the supply and demand matching model, and determine the first difference between the introduction and label of the technological resource associated with the technological demand and the introduction and label of the training technological resource; and / or; input the introduction and label of the technological resource and the introduction and label of the industrial node associated with the technological demand into the supply and demand matching model, obtain the introduction and label of the training technological demand output by the supply and demand matching model, and determine the second difference between the introduction and label of the technological demand associated with the technological resource and the introduction and label of the training technological demand;

[0136] The fourth determination submodule is used to adjust the model parameters of the supply-demand matching model according to the first difference and / or the second difference until the training end condition is met to obtain a trained supply-demand matching model.

[0137] In another embodiment of the present disclosure, the fourth determination submodule is specifically used to adjust the model parameters of the supply and demand matching model according to the first difference and / or the second difference until the first difference is less than a preset third threshold and / or the second difference is less than a preset third threshold, so as to obtain an intermediate supply and demand matching model;

[0138] The validity of the intermediate supply and demand matching model is verified to obtain the trained supply and demand matching model.

[0139] In another embodiment of the present disclosure, the device further comprises:

[0140] The fourth acquisition module is used to obtain the labels and introductions of the technology requirements and the labels and introductions of the industry nodes input by the user;

[0141] A fifth acquisition module, used to input the labels and introduction of the technological needs and the labels and introduction of the industry nodes input by the user into the trained supply-demand matching model, and obtain the introduction and labels of the technological resources output by the trained supply-demand matching model;

[0142] and / or;

[0143] The sixth acquisition module is used to acquire the labels and introductions of scientific and technological resources and the labels and introductions of industrial nodes input by the user;

[0144] The seventh acquisition module is used to input the labels and introductions of the scientific and technological resources and the labels and introductions of the industrial nodes input by the user into the trained supply and demand matching model, and obtain the introductions and labels of the scientific and technological resources output by the trained supply and demand matching model.

[0145] The device provided in this embodiment can execute the method of any of the above embodiments, and its execution method and beneficial effects are similar, which will not be repeated here.

[0146] An embodiment of the present disclosure further provides an electronic device, which includes: a memory, in which a computer program is stored; and a processor, for executing the computer program. When the computer program is executed by the processor, the method of any of the above embodiments can be implemented.

[0147] For example, Figure 5 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 5, which shows a schematic diagram of the structure of an electronic device 500 suitable for implementing the embodiment of the present disclosure. The electronic device 500 in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0148] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0149] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0150] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0151] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0152] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0153] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0154] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the industrial chain of the target industry, wherein the industrial chain includes at least one industrial node; obtains the scientific and technological resources of the target industry, and determines the scientific and technological resources associated with the industrial node; obtains the scientific and technological needs of the target industry, and determines the scientific and technological needs associated with the industrial node; uses the industrial nodes and their associated scientific and technological resources and scientific and technological needs to train the supply and demand matching model to obtain a trained supply and demand matching model.

[0155] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0156] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0157] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0158] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0159] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0160] The embodiments of the present disclosure further provide a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method of any of the above embodiments can be implemented. The execution method and beneficial effects are similar and will not be repeated here.

[0161] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0162] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A model processing method, characterized in that: include: Acquire the industrial chain of the target industry, wherein the industrial chain includes at least one industrial node; Obtain the scientific and technological resources of the target industry and determine the scientific and technological resources associated with the industrial node; Obtain the technological needs of the target industry and determine the technological needs associated with the industrial nodes; Using the industrial nodes and their associated scientific and technological resources and scientific and technological needs, the supply and demand matching model is trained to obtain a trained supply and demand matching model; The step of determining the scientific and technological resources associated with the industrial node includes: Summarizing and labeling the scientific and technological resources to obtain a brief introduction and labels of the scientific and technological resources; Summarize and label the industrial nodes to obtain a brief introduction and labels of the industrial nodes; Inputting the brief introduction and label of the scientific and technological resources and the brief introduction and label of the industrial nodes into the trained first matching model to obtain a first matching degree between the two; Determine the association between scientific and technological resources and industrial nodes whose first matching degree is greater than a preset first threshold; Determining the technological needs associated with the industrial node includes: Summarize and label the technological needs to obtain a brief introduction and labels of the technological needs; Inputting the brief introduction and label of the technology demand and the brief introduction and label of the industry node into the trained second matching model to obtain a second matching degree between the two; Determine the association between the technology demand and the industrial node whose second matching degree is greater than a preset second threshold.

2. The method according to claim 1, characterized in that The industrial chain of the target industry is obtained, including: Obtaining original corpus of the target industry; Extracting knowledge from the original corpus to obtain multiple elements; Determine the industry and industrial link to which the said factor belongs; For each of the industrial links, clustering the elements under the industrial link to obtain a corresponding plurality of element sets; Determine the industrial node to which the element set belongs, thereby obtaining the industrial chain.

3. The method according to claim 1, characterized in that The use of the industrial nodes and their associated scientific and technological resources and scientific and technological needs to train the supply and demand matching model includes: Inputting the introduction and label of the technological demand and the introduction and label of the industrial node associated therewith into the supply and demand matching model, obtaining the introduction and label of the training technological resource output by the supply and demand matching model, and determining the first difference between the introduction and label of the technological resource associated with the technological demand and the introduction and label of the training technological resource; and / or; inputting the introduction and label of the technological resource and the introduction and label of the industrial node associated therewith into the supply and demand matching model, obtaining the introduction and label of the training technological demand output by the supply and demand matching model, and determining the second difference between the introduction and label of the technological demand associated with the technological resource and the introduction and label of the training technological demand; The model parameters of the supply-demand matching model are adjusted according to the first difference and / or the second difference until a training end condition is met, thereby obtaining a trained supply-demand matching model.

4. The method according to claim 3, characterized in that The step of adjusting the model parameters of the supply-demand matching model according to the first difference and / or the second difference until a training end condition is met to obtain a trained supply-demand matching model includes: Adjusting the model parameters of the supply-demand matching model according to the first difference and / or the second difference until the first difference is less than a preset third threshold and / or the second difference is less than a preset third threshold, to obtain an intermediate supply-demand matching model; The validity of the intermediate supply and demand matching model is verified to obtain the trained supply and demand matching model.

5. The method according to claim 3, characterized in that: Also includes: Obtain the labels and introductions of the technological needs and the labels and introductions of the industrial nodes input by the user; Input the labels and introduction of the technological needs and the labels and introduction of the industrial nodes input by the user into the trained supply-demand matching model, and obtain the introduction and labels of the technological resources output by the trained supply-demand matching model; and / or; Obtain the labels and introductions of scientific and technological resources and the labels and introductions of industrial nodes input by users; The labels and introductions of the scientific and technological resources and the labels and introductions of the industrial nodes input by the user are input into the trained supply-demand matching model, and the introductions and labels of the scientific and technological resources output by the trained supply-demand matching model are obtained.

6. A model processing device, characterized in that: include: A first acquisition module is used to acquire the industrial chain of a target industry, wherein the industrial chain includes at least one industrial node; The second acquisition module is used to acquire the scientific and technological resources of the target industry and determine the scientific and technological resources associated with the industrial node; The third acquisition module is used to acquire the technological needs of the target industry and determine the technological needs associated with the industrial node; A training module, used to train the supply-demand matching model using the industrial node and its associated scientific and technological resources and scientific and technological needs, to obtain a trained supply-demand matching model; The second acquisition module is specifically used to acquire the scientific and technological resources of the target industry, and summarize and label the scientific and technological resources to obtain the introduction and label of the scientific and technological resources; Summarize and label the industrial nodes to obtain a brief introduction and labels of the industrial nodes; Inputting the brief introduction and label of the scientific and technological resources and the brief introduction and label of the industrial nodes into the trained first matching model to obtain a first matching degree between the two; Determine the association between scientific and technological resources and industrial nodes whose first matching degree is greater than a preset first threshold; The third acquisition module is specifically used to acquire the technology needs of the target industry, and summarize and label the technology needs to obtain the introduction and label of the technology needs; Inputting the brief introduction and label of the technology demand and the brief introduction and label of the industry node into the trained second matching model to obtain a second matching degree between the two; Determine the association between the technology demand and the industrial node whose second matching degree is greater than a preset second threshold.

7. An electronic device, characterized in that: include: A processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images