Question and answering method and apparatus, computer device, and readable storage medium
By compressing and modularizing the large language model, and combining slot parameters and vector models, the problem of high computational and storage requirements of traditional question-answering systems is solved, achieving high efficiency, accuracy and fast response of the question-answering system.
WO2026114046A1PCT designated stage Publication Date: 2026-06-04CHINA TELECOM CLOUD TECH CO LTD
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- CHINA TELECOM CLOUD TECH CO LTD
- Filing Date
- 2025-11-19
- Publication Date
- 2026-06-04
AI Technical Summary
Technical Problem
Traditional question-answering systems use large language models, which require a lot of computing resources and storage space, resulting in slow reasoning speed.
Method used
By compressing the model parameters of a large language model, a quantized language model is obtained. Combined with slot parameters and a vector model, the standardization of user questions and document retrieval are achieved, generating answer text.
Benefits of technology
It significantly reduces the requirements for computing resources and storage space, improves the reasoning speed and accuracy of the question-answering system, and enhances the efficiency of user intent recognition and document matching.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN2025136011_04062026_PF_FP_ABST
Abstract
The present application relates to the field of artificial intelligence, and in particular to a question and answering method, comprising: inputting initial question text of a user into a quantized language model to obtain a slot parameter corresponding to the initial question text, wherein the slot parameter comprises description information related to a target question and answer scenario, and the quantized language model is a language model obtained by compressing a model parameter of a large language model; inputting the slot parameter and the initial question text into a quantized language model to obtain standardized question text, wherein the standardized question text is text that conforms to a predefined text structure and clearly reflects a user intention; inputting the standardized question text into a vector model to obtain a plurality of documents having a highest degree of correlation with the standardized question text; and inputting the standardized question text and the plurality of documents into the quantized language model to obtain response text generated for answering the initial question text. In addition, the present application also relates to the field of natural language processing.
Need to check novelty before this filing date? Find Prior Art