Enterprise attribute data prediction method and device, electronic equipment and storage medium
A technology of attribute data and prediction method, applied in the field of data processing, can solve problems such as poor model application effect, information loss, unfavorable agile development model, etc., and achieve the effect of improving integrity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0027] figure 1 A schematic flowchart of a method for predicting enterprise attribute data according to the first embodiment of the present application is shown. As shown in the figure, this embodiment mainly includes the following steps:
[0028] Step S102, obtaining a given attribute of an enterprise object.
[0029] Optionally, relevant attribute data of enterprise objects can be collected from one or more open source databases, including but not limited to enterprise annual report information, enterprise shareholders and capital contribution information, enterprise involvement information (such as the relevant cause of action of the enterprise as the defendant, the amount involved, etc. Information), enterprise credit information (such as whether the enterprise is listed as a dishonest person subject to enforcement), enterprise property information (such as whether the enterprise has property disposal), etc.
[0030] Optionally, the given attribute of the enterprise obje...
no. 2 example
[0038] figure 2 A schematic flowchart of a method for predicting enterprise attribute data according to the second embodiment of the present application is shown. This embodiment mainly shows an exemplary training scheme of an attribute data prediction model. As shown in the figure, this embodiment mainly includes the following steps:
[0039] Step S202, perform feature extraction on each structured attribute data and each unstructured attribute data of the sample enterprise, and obtain a feature vector set including each structured feature vector and each unstructured feature vector.
[0040] In this embodiment, relevant attribute data of enterprise objects can be collected from one or more open source databases, including but not limited to enterprise annual report information, enterprise shareholders and capital contribution information, enterprise involvement information (such as the relevant cause of action of the enterprise as the defendant, the case involved Amount a...
no. 3 example
[0053] image 3 A schematic flowchart of a method for predicting enterprise attribute data according to the third embodiment of the present application is shown. This embodiment mainly shows the specific implementation of the above step S202. As shown in the figure, this embodiment mainly includes the following steps:
[0054] Step S302, based on preset structured feature extraction rules, perform feature extraction for each structured attribute data, and obtain each structured feature vector.
[0055] Optionally, according to each candidate binning code corresponding to the structured attribute data, perform binning processing on the structured attribute data, determine the real binning code of the structured attribute data from each candidate binning code, and then according to the preset Feature mapping rules that map ground-truth binning encodings to structured feature vectors.
[0056] In this embodiment, the binning processing method adopted may include but not limite...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


