Search

CN-122022985-A - Enterprise credit processing method, device, equipment, medium and product

CN122022985ACN 122022985 ACN122022985 ACN 122022985ACN-122022985-A

Abstract

The application discloses an enterprise credit processing method, device, equipment, medium and product, and relates to the field of financial science and technology. The method comprises the steps of obtaining public financial data, public production data and industry technical information of a target enterprise, determining at least one enterprise technical point of the target enterprise according to the public production data and the industry technical information, determining attention weights of the enterprise technical points relative to technical hotspots in the industry technical information based on the public production data and the enterprise technical points, and determining trust results of the target enterprise according to the public financial data, the enterprise technical points and the attention weights. The technical scheme of the embodiment of the application can effectively improve the efficiency of multidimensional heterogeneous data processing and the accuracy of trust in the trust process, and has good universality and adaptability.

Inventors

  • QIAN CHENGXIANG

Assignees

  • 中国工商银行股份有限公司

Dates

Publication Date
20260512
Application Date
20260123

Claims (10)

  1. 1. The enterprise trust processing method is characterized by comprising the following steps: acquiring public financial data, public yield data and industry technical information of a target industry of a target enterprise; determining at least one enterprise technology point of the target enterprise according to the public yield data and the industry technology information; determining the attention weight of each enterprise technical point relative to each technical hot spot in the industry technical information based on the public production data and each enterprise technical point; And determining a trust result of the target enterprise according to the public financial data, each enterprise technical point and the attention weight.
  2. 2. The method of claim 1, wherein determining the attention weight of each of the business technology points relative to each of the technical hotspots in the industry technology information based on the publicly known production data and each of the business technology points comprises: respectively determining enterprise technical point feature vectors corresponding to the enterprise technical points and technical hot point feature vectors corresponding to the technical hot points; determining an external weight of attention of each of the enterprise technology points relative to each of the technology hotspots based on the publicly known production data and each of the enterprise technology points; and determining the attention weight according to the enterprise technical point feature vector, the technical hot point feature vector and the external weight.
  3. 3. The method of claim 2, wherein the determining the attention weight from the enterprise technical point feature vector, the technical hotspot feature vector, and the external weight comprises: determining an original attention score according to the technical point feature vector of the enterprise and the technical hot point feature vector; the attention weight is determined from the original attention score and the external weight.
  4. 4. The method of claim 2, wherein the determining an external weight for the attention of each of the business technology points relative to each of the technology hotspots based on the publicly known production data and each of the business technology points comprises: Acquiring research and development investment ratio data of each enterprise technical point in a target enterprise; Determining known production authorization amounts corresponding to the enterprise technical points in the disclosed known production data respectively; For any enterprise technical point, determining a supporting strength value of the enterprise technical point according to the research and development investment ratio data and the known production authorization quantity; And taking a vector formed by the support intensity values of all enterprise technical points as the external weight.
  5. 5. The method of claim 1, wherein said determining the trust outcome of the target enterprise based on the public financial data, each of the enterprise technical points, and the attention weight comprises: Extracting business line financial data corresponding to each enterprise technical point from the public financial data; Converting each business line financial data and each enterprise technical point into a business line financial vector and an enterprise technical point vector based on a pre-trained semantic embedding model, and determining cosine similarity between the business line financial vector and the enterprise technical point vector; and determining the trust result of the target enterprise according to the cosine similarity and the attention weight.
  6. 6. The method of any of claims 1-5, wherein said determining at least one business technology point of the target business from the publicly known production data and the industry technology information comprises: Converting the public known production data and the industry technical information into a known production text vector and an industry information vector respectively based on a text vector model which is trained; calculating semantic similarity between the known text vector and the industry information vector; And determining the enterprise technical points of the target enterprise in response to the semantic similarity exceeding a preset similarity threshold.
  7. 7. An enterprise trusted processing device, comprising: The data acquisition module is used for acquiring public financial data, public yield data and industry technical information of the target industry; an enterprise technical point determining module, configured to determine at least one enterprise technical point of the target enterprise according to the public production data and the industry technical information; the attention weight determining module is used for determining the attention weight of each enterprise technical point relative to each technical hot spot in the industry technical information based on the public production data and each enterprise technical point; And the trust result determining module is used for determining the trust result of the target enterprise according to the public financial data, the enterprise technical points and the attention weight.
  8. 8. An electronic device, the electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the enterprise trust processing method of any one of claims 1-6.
  9. 9. A computer readable storage medium storing computer instructions for causing a processor to perform the enterprise trust processing method of any one of claims 1-6.
  10. 10. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the enterprise trust processing method according to any one of claims 1-6.

Description

Enterprise credit processing method, device, equipment, medium and product Technical Field The application relates to the technical field of financial science and technology, in particular to an enterprise credit processing method, an enterprise credit processing device, equipment, a medium and a product. Background With the advancement of society and the development of the great deal of science and technology, more and more industries have adopted more emerging technologies in the process of data processing. In enterprise technology assessment and analysis, conventional methods often face challenges associated with data integration and quantification. The existing method usually respectively examines the technical asset information of the enterprise and the whole technical dynamics of the industry, but the two are always in a fracture state, and the inherent association of the two is difficult to systematically measure. At present, how to effectively correlate and analyze scattered, different-source, different-type and different-structure data and extract representative quantization indexes from the data is a ubiquitous technical problem. Meanwhile, the fusion calculation of the index and other dimension data also lacks flexible and self-adaptive mechanism support. Therefore, constructing an analysis framework capable of automatically processing multi-source data, accurately quantifying association relations and supporting dynamic weight adjustment has become one of the key points of researches of those skilled in the relevant fields. Disclosure of Invention The application provides an enterprise credit processing method, device, equipment, medium and product, which are used for improving the accuracy, objectivity and rationality of credit processing. According to one aspect of the application, there is provided an enterprise trust processing method, including: acquiring public financial data, public yield data and industry technical information of a target industry of a target enterprise; Determining at least one enterprise technical point of the target enterprise according to the public production data and the industry technical information; based on the public production data and each enterprise technical point, determining the attention weight of each enterprise technical point relative to each technical hot spot in the industry technical information; and determining the trust result of the target enterprise according to the public financial data, the technical points of each enterprise and the attention weight. According to another aspect of the present application, there is provided an enterprise trust processing apparatus, including: The data acquisition module is used for acquiring public financial data, public yield data and industry technical information of the target industry; The enterprise technical point determining module is used for determining at least one enterprise technical point of the target enterprise according to the publicly known production data and the industry technical information; The attention weight determining module is used for determining the attention weight of each enterprise technical point relative to each technical hot spot in the industry technical information based on the public production data and each enterprise technical point; And the trust result determining module is used for determining the trust result of the target enterprise according to the public financial data, the technical points of each enterprise and the attention weight. According to another aspect of the present application, there is provided an electronic apparatus including: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the enterprise trust processing method of any one of the embodiments of the present application. According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the enterprise trust processing method according to any one of the embodiments of the present application when executed. According to another aspect of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements an enterprise trust processing method according to any one of the embodiments of the present application. According to the technical scheme provided by the embodiment of the application, at least one key technical point of the enterprise is extracted according to the public intellectual property data and the industry technical information of the target enterprise, the technical problem of automatically identifying and structuring the technical characteristics of the enterprise from the multi-source heterogeneous data is solved, the efficie