Private placement product data storage method and device, equipment and storage medium

Abstract

The invention relates to the field of data duplicate checking, and discloses a private placement product data storage method and device, equipment and a storage medium. The method comprises the following steps: acquiring a private placement product feature set to be analyzed, wherein the private placement product feature set comprises a product name, a product manager name and a product company name; according to a preset splitting extraction algorithm, allowing the product names to be subjected to splitting processing to obtain a splitting keyword set; reading split keywords in the split keyword set, and performing connection and combination processing on the product manager name, the product company name and the split keywords according to a preset combination framework to obtain a search word; according to a preset vector conversion algorithm, carrying out vector conversion processing on the retrieval word to obtain a retrieval vector, and according to a preset weight assignment algorithm, carrying out weight control processing on the retrieval vector to obtain a detection weight vector; according to a preset similarity algorithm, calculating the similarity between the detection weight vector and a feature target vector corresponding to a private placement feature set in a private placement feature set database to obtain a similarity set; judging whether the similarities in the similarity set are all smaller than a preset similarity threshold value or not; and if not, adding the private placement product feature set to the private placement feature set database.

Description

technical field [0001] The present invention relates to the field of data plagiarism checking, in particular to a data storage method, device, equipment and storage medium for private equity products. Background technique [0002] Under the existing technology, judging whether a new private equity product is an existing private equity product can only be judged based on some unique characteristics of the private equity product, such as the private equity registration number, the full name of the private equity product, and the abbreviation of the private equity product. By comparing these unique characteristics to determine whether the product already exists. However, when some private equity products lack registration numbers, or the full names or abbreviations of private equity products are not exactly the same, it is difficult to judge, and manual intervention is necessary. In the case of a particularly large amount of data, manual intervention is used. The workload is h...

AI Technical Summary

Problems solved by technology

[0008] The main purpose of the present invention is to solve the technical problem that it is impossible to determine whether there is substantially the same private equity product data in the database due to irregular private equity product names and missing registration codes during the current private equity data processing process

Images