CN-121996757-A - Data query method, device, computer equipment and storage medium

CN121996757ACN 121996757 ACN121996757 ACN 121996757ACN-121996757-A

Abstract

The application belongs to the technical field of artificial intelligence, and relates to a data query method, a device, computer equipment and a storage medium, wherein the method comprises the steps of judging whether a query request sent by a user is received or not; the query request carries query content, if yes, acquiring identity information of a user, calling a target assistant instance corresponding to the identity information, retrieving resource data corresponding to the query content from an independent resource pool based on the target assistant instance, finding knowledge data corresponding to the query content from a personal knowledge base, comprehensively reasoning the resource data and the knowledge data based on a reasoning strategy to generate a corresponding reasoning result, generating target answer data based on the reasoning result, and returning the target answer data to the user. In addition, the application also relates to a blockchain technology, and target answer data can be stored in the blockchain. The application can be applied to the data query scene in the fields of finance and science and digital medical treatment, and effectively improves the accuracy and individuation of query processing.

Inventors

WANG JIANZONG
QU XIAOYANG
ZHANG NAN

Assignees

平安科技（深圳）有限公司

Dates

Publication Date: 20260508
Application Date: 20260106

Claims (10)

1. A data query method, comprising the steps of: Judging whether a query request sent by a user is received or not, wherein the query request carries query content; if yes, acquiring the identity information of the user, and calling a target assistant instance corresponding to the identity information; retrieving resource data corresponding to the query content from a preset independent resource pool based on the target assistant instance; searching knowledge data corresponding to the query content from a preset personal knowledge base; carrying out comprehensive reasoning processing on the resource data and the knowledge data based on a preset reasoning strategy to generate a corresponding reasoning result; Generating corresponding target answer data based on the reasoning result; And returning the target answer data to the user.
2. The data query method according to claim 1, wherein the step of retrieving resource data corresponding to the query content from a preset independent resource pool based on the target helper instance specifically includes: carrying out semantic analysis on the query content based on the target assistant instance to obtain a corresponding semantic analysis result; Inquiring the domain knowledge index in the independent resource pool based on the semantic analysis result to obtain corresponding target domain knowledge; performing data acquisition processing on the target domain knowledge based on a preset data acquisition strategy to obtain corresponding related data; And taking the related data as the resource data.
3. The data query method according to claim 1, wherein the step of finding knowledge data corresponding to the query content from a preset personal knowledge base specifically includes: Searching target personal terms related to the query content from the personal knowledge base; searching a target analysis template related to the query content from the personal knowledge base; integrating the target personal term and the target analysis template to obtain corresponding integrated data; and taking the integrated data as the knowledge data.
4. The data query method according to claim 1, wherein the step of performing comprehensive inference processing on the resource data and the knowledge data based on a preset inference policy to generate a corresponding inference result specifically includes: carrying out fusion processing on the resource data and the knowledge data to obtain corresponding fusion data; Carrying out causal relation analysis processing on the fusion data to obtain a corresponding analysis result; carrying out trend prediction evaluation processing on the fusion data to obtain a corresponding trend evaluation result; integrating the analysis result and the trend evaluation result to obtain a corresponding integration result; And taking the integrated result as the reasoning result.
5. The data query method of claim 1, wherein the step of generating corresponding target answer data based on the inference result specifically comprises: extracting information from the reasoning result to obtain corresponding key information; carrying out logic combing and content organization processing on the key information to obtain corresponding initial answer data; performing language optimization processing on the initial answer data to obtain corresponding first answer data; performing format optimization processing on the first answer data to obtain corresponding second answer data; And taking the second answer data as the target answer data.
6. The data query method of claim 1, wherein the step of returning the target answer data to the user specifically comprises: acquiring a preset target display mode; optimizing the target display mode to obtain an optimized target display mode; Calling a preset target interface; And based on the optimized target display mode, displaying and processing the target answer data in the target interface.
7. The method for querying data according to claim 6, wherein the step of obtaining a preset target display mode specifically comprises: performing evaluation processing on the dimension and complexity of the data on the target answer data to obtain a corresponding evaluation result; acquiring the requirement information of the user; acquiring available display modes; Based on the evaluation result and the demand information, determining a corresponding appointed display mode from the available display modes; And taking the appointed display mode as the target display mode.
8. A data query device, comprising: the judging module is used for judging whether a query request sent by a user is received or not, wherein the query request carries query content; the processing module is used for acquiring the identity information of the user if yes, and calling a target assistant instance corresponding to the identity information; The retrieval module is used for retrieving resource data corresponding to the query content from a preset independent resource pool based on the target assistant instance; the searching module is used for searching knowledge data corresponding to the query content from a preset personal knowledge base; the reasoning module is used for carrying out comprehensive reasoning processing on the resource data and the knowledge data based on a preset reasoning strategy to generate a corresponding reasoning result; the generation module is used for generating corresponding target answer data based on the reasoning result; and the return module is used for returning the target answer data to the user.
9. A computer device comprising a memory and a processor, the memory having stored therein computer readable instructions which when executed by the processor implement the steps of the data querying method according to any of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the data querying method according to any of claims 1 to 7.

Description

Data query method, device, computer equipment and storage medium Technical Field The application relates to the technical field of artificial intelligence, which can be applied to the fields of financial science and technology, digital medical treatment and the like, in particular to a data query method, a data query device, computer equipment and a storage medium. Background In the application scenes of various business systems, the problem that the system is difficult to provide deep and professional services in the specific business field exists generally. The existing system mostly adopts a stiff general mode, and cannot effectively learn and adapt to personalized characteristics such as analysis thinking, common terms, analysis paths and the like of different business roles and even different users under the same role. This results in a system that easily gives wrong or confusing answers, and the accuracy of generating answer data is low, severely affecting the user experience. In the financial field, taking the credit risk assessment scenario as an example, traditional credit risk assessment systems often only assess based on limited financial metrics (e.g., income, liabilities) and underlying credit records. However, the risk characteristics of customers in different industries and different business models are significantly different. For example, for an emerging scientific enterprise, the traditional method may underestimate its development potential and repayment capability by neglecting key factors such as the research and development investment ratio, the number of technical patents, the market prospect, etc., give out wrong risk assessment results, influence loan decisions of financial institutions, and even lead to loss of good customers. In the medical field, taking a medicine efficacy prediction scene as an example, a traditional medicine efficacy prediction system is mainly used for predicting based on the general pharmacological actions of medicines and clinical test data of part of common people. However, the physical condition, genetic characteristics, basic diseases and other conditions of different patients are quite different, and all factors have important influence on the curative effect of the medicine. For example, for patients with certain genetically modified cancers, traditional systems may predict based solely on the therapeutic effect data of the drug on the general cancer type, ignoring the specific effects of the genetic mutation on drug metabolism and mechanism of action, giving inaccurate drug efficacy predictions, leading to physicians prescribing inappropriate treatment regimens, affecting the patient's therapeutic effect and rehabilitation progress. Therefore, a system capable of deeply adapting to a specific service area and accurately adapting to individual needs of different users so as to improve service professionals and accuracy is needed. Disclosure of Invention The embodiment of the application aims to provide a data query method, a data query device, computer equipment and a storage medium, so as to solve the technical problems that the existing service providing system mostly adopts a stiff general mode, cannot effectively learn and adapt to different service roles, so that the system is easy to give wrong or confusing answers, and the accuracy of generating answer data is low. In a first aspect, a data query method is provided, including: Judging whether a query request sent by a user is received or not, wherein the query request carries query content; if yes, acquiring the identity information of the user, and calling a target assistant instance corresponding to the identity information; retrieving resource data corresponding to the query content from a preset independent resource pool based on the target assistant instance; searching knowledge data corresponding to the query content from a preset personal knowledge base; carrying out comprehensive reasoning processing on the resource data and the knowledge data based on a preset reasoning strategy to generate a corresponding reasoning result; Generating corresponding target answer data based on the reasoning result; And returning the target answer data to the user. In a second aspect, there is provided a data query apparatus comprising: the judging module is used for judging whether a query request sent by a user is received or not, wherein the query request carries query content; the processing module is used for acquiring the identity information of the user if yes, and calling a target assistant instance corresponding to the identity information; The retrieval module is used for retrieving resource data corresponding to the query content from a preset independent resource pool based on the target assistant instance; the searching module is used for searching knowledge data corresponding to the query content from a preset personal knowledge base; the reasoning module is used for carrying out comprehensiv