Data information processing method and device, storage medium and electronic equipment

By optimizing a general neural network model for financial business scenarios, the problem of low prediction accuracy for missing text in financial business consultation statements has been solved, achieving more accurate semantic supplementation and response content.

CN116737904BActive Publication Date: 2026-06-19INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
INDUSTRIAL AND COMMERCIAL BANK OF CHINA
Filing Date
2023-06-21
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

In existing technologies, general neural network models have low prediction accuracy for missing words in financial business consultation statements, and cannot accurately answer users' business inquiries.

Method used

By obtaining training samples from the target financial business scenario, the general neural network model is optimized to obtain the target neural network model. The consultation statement is then input into the model to supplement the predicted text information, and the complete consultation statement is output to return the response content.

Benefits of technology

It improves the accuracy of predicting missing words in consultation statements in financial business scenarios, and enhances the accuracy of semantic supplementation of consultation statements and response content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116737904B_ABST
    Figure CN116737904B_ABST
Patent Text Reader

Abstract

This application discloses a data information processing method, apparatus, storage medium, and electronic device, relating to the field of artificial intelligence technology. The method includes: acquiring a consultation statement, wherein the consultation statement is a statement with semantically missing elements collected during the consultation process; when the domain of the consultation statement is financial business, determining the target financial business scenario of the consultation statement; acquiring a target neural network model, inputting the consultation statement into the target neural network model, and outputting predicted text information, wherein the target neural network model is obtained by optimizing a general neural network model using a first training sample; semantically supplementing the consultation statement based on the predicted text information, and returning a response to the consultation statement based on the supplemented consultation statement. This application solves the problem in related technologies where using a general neural network model to predict missing text in financial business consultation statements results in relatively low accuracy in text prediction.
Need to check novelty before this filing date? Find Prior Art