# US 2026/0065095 A1 · Knowledge question-answering method, apparatus, readable medium, electronic device, and program product

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0065095 A1
- Document ID: US20260065095A1
- Status: Published application
- Kind: A1
- Application number: 19/299,961
- Filed: 2025-08-14
- Published: 2026-03-05
- Earliest claimed: 2024-08-29
- Assignees: Beijing Youzhuju Network Technology Co., Ltd.
- Applicants: Beijing Youzhuju Network Technology Co., Ltd.
- Inventors: Yongfu MA; Shaoyu ZHANG; Xuefeng LIU
- Web page: https://patentgrep.com/patent/US20260065095A1

## CPC

- G06N 5/04: Inference or reasoning models
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present disclosure relates to a knowledge question-answering method, an apparatus, a readable medium, an electronic device, and a program product. The method includes: acquiring a target question input by a user in a natural language; retrieving, through a machine learning model, in a knowledge base according to the target question to obtain a target knowledge document for answering the target question, and determining, based on the target knowledge document, a target answer for the target question, wherein the knowledge base is used to store a business knowledge document; and displaying the target answer to the user.

## Claims

### Claim 1

A knowledge question-answering method, comprising:
acquiring a target question input by a user in a natural language;
retrieving, through a machine learning model, in a knowledge base according to the target question to obtain a target knowledge document for answering the target question, and determining, based on the target knowledge document, a target answer for the target question, wherein the knowledge base is used to store a business knowledge document; and
displaying the target answer to the user.

### Claim 2 (depends on 1)

The knowledge question-answering method according to claim 1, wherein a plurality of target knowledge documents are provided, and the determining, based on the target knowledge document, a target answer for the target question, comprises:
determining content relevance between the target question and each of the plurality of target knowledge documents;
determining a preset number of knowledge documents from the plurality of target knowledge documents according to the content relevance, wherein content relevance corresponding to each of the preset number of knowledge documents is greater than content relevance corresponding to each of knowledge documents other than the preset number of knowledge documents in the plurality of target knowledge documents; and
determining the target answer for the target question according to the preset number of knowledge documents.

### Claim 3 (depends on 2)

The knowledge question-answering method according to claim 2, wherein the determining content relevance between the target question and each of the plurality of target knowledge documents, comprises:
inputting the target question and the plurality of target knowledge documents into a relevance model to obtain the content relevance between the target question and each of the target knowledge documents, wherein the relevance model is configured to output, according to an input question and an input knowledge document, content relevance between the input question and the input knowledge document.

### Claim 4 (depends on 1)

The knowledge question-answering method according to claim 1, wherein the determining, based on the target knowledge document, a target answer for the target question, comprises:
generating a target prompt based on the target knowledge document, the target question, and a preset prompt template, wherein the target prompt is used to instruct the machine learning model to determine, based on the target knowledge document, the target answer for the target question; and
inputting the target prompt into the machine learning model to obtain the target answer for the target question.

### Claim 5 (depends on 1)

The knowledge question-answering method according to claim 1, wherein the retrieving, through a machine learning model, in a knowledge base according to the target question to obtain a target knowledge document for answering the target question, comprises:
extracting a key field in the target question through the machine learning model;
performing, at least according to the key field, a semantic recall in the knowledge base to obtain a first knowledge document, wherein the semantic recall is used to query a knowledge document comprising a first similar field in the knowledge base, and a semantic similarity between the first similar field and the key field is greater than a preset threshold; and
performing, at least according to the key field, a matching retrieval in the knowledge base to obtain a second knowledge document, wherein the matching retrieval is used to query a knowledge document comprising the key field in the knowledge base;
wherein the target knowledge document comprises the first knowledge document and the second knowledge document.

### Claim 6 (depends on 5)

The knowledge question-answering method according to claim 5, further comprising:
determining an expansion word with a same semantics as the key field;
wherein the performing, at least according to the key field, a semantic recall in the knowledge base, comprises:
performing, according to the key field and the expansion word, the semantic recall in the knowledge base, wherein the semantic recall is used to query a knowledge document comprising a second similar field in the knowledge base, and a semantic similarity between the second similar field and the key field or a semantic similarity between the second similar field and the expansion word is greater than the preset threshold;
wherein the performing, at least according to the key field, a matching retrieval in the knowledge base, comprises:
performing, according to the key field and the expansion word, the matching retrieval in the knowledge base, wherein the matching retrieval is used to retrieve a knowledge document comprising the key field or the expansion word in the knowledge base.

### Claim 7 (depends on 1)

The knowledge question-answering method according to claim 1, wherein the business knowledge document in the knowledge base is stored in a following manner:
acquiring a plurality of business knowledge documents through different channels;
performing a splitting processing on each of the plurality of business knowledge documents to obtain a business knowledge fragment;
performing a vectorization processing on the business knowledge fragment to obtain a knowledge fragment vector; and
storing the knowledge fragment vector into the knowledge base.

### Claim 8

A non-transitory computer-readable medium having a computer program stored thereon, wherein the non-transitory computer program, when executed by a processing apparatus, implements a knowledge question-answering method;
wherein the knowledge question-answering method comprises:
acquiring a target question input by a user in a natural language;
retrieving, through a machine learning model, in a knowledge base according to the target question to obtain a target knowledge document for answering the target question, and determining, based on the target knowledge document, a target answer for the target question, wherein the knowledge base is used to store a business knowledge document; and
displaying the target answer to the user.

### Claim 9 (depends on 8)

The non-transitory computer-readable medium according to claim 8, wherein a plurality of target knowledge documents are provided, and the determining, based on the target knowledge document, a target answer for the target question, comprises:
determining content relevance between the target question and each of the plurality of target knowledge documents;
determining a preset number of knowledge documents from the plurality of target knowledge documents according to the content relevance, wherein content relevance corresponding to each of the preset number of knowledge documents is greater than content relevance corresponding to each of knowledge documents other than the preset number of knowledge documents in the plurality of target knowledge documents; and
determining the target answer for the target question according to the preset number of knowledge documents.

### Claim 10 (depends on 9)

The non-transitory computer-readable medium according to claim 9, wherein the determining content relevance between the target question and each of the plurality of target knowledge documents, comprises:
inputting the target question and the plurality of target knowledge documents into a relevance model to obtain the content relevance between the target question and each of the target knowledge documents, wherein the relevance model is configured to output, according to an input question and an input knowledge document, content relevance between the input question and the input knowledge document.

### Claim 11 (depends on 8)

The non-transitory computer-readable medium according to claim 8, wherein the determining, based on the target knowledge document, a target answer for the target question, comprises:
generating a target prompt based on the target knowledge document, the target question, and a preset prompt template, wherein the target prompt is used to instruct the machine learning model to determine, based on the target knowledge document, the target answer for the target question; and
inputting the target prompt into the machine learning model to obtain the target answer for the target question.

### Claim 12 (depends on 8)

The non-transitory computer-readable medium according to claim 8, wherein the retrieving, through a machine learning model, in a knowledge base according to the target question to obtain a target knowledge document for answering the target question, comprises:
extracting a key field in the target question through the machine learning model;
performing, at least according to the key field, a semantic recall in the knowledge base to obtain a first knowledge document, wherein the semantic recall is used to query a knowledge document comprising a first similar field in the knowledge base, and a semantic similarity between the first similar field and the key field is greater than a preset threshold; and
performing, at least according to the key field, a matching retrieval in the knowledge base to obtain a second knowledge document, wherein the matching retrieval is used to query a knowledge document comprising the key field in the knowledge base;
wherein the target knowledge document comprises the first knowledge document and the second knowledge document.

### Claim 13 (depends on 12)

The non-transitory computer-readable medium according to claim 12, wherein the knowledge question-answering method further comprises:
determining an expansion word with a same semantics as the key field;
wherein the performing, at least according to the key field, a semantic recall in the knowledge base, comprises:
performing, according to the key field and the expansion word, the semantic recall in the knowledge base, wherein the semantic recall is used to query a knowledge document comprising a second similar field in the knowledge base, and a semantic similarity between the second similar field and the key field or a semantic similarity between the second similar field and the expansion word is greater than the preset threshold;
wherein the performing, at least according to the key field, a matching retrieval in the knowledge base, comprises:
performing, according to the key field and the expansion word, the matching retrieval in the knowledge base, wherein the matching retrieval is used to retrieve a knowledge document comprising the key field or the expansion word in the knowledge base.

### Claim 14 (depends on 8)

The non-transitory computer-readable medium according to claim 8, wherein the business knowledge document in the knowledge base is stored in a following manner:
acquiring a plurality of business knowledge documents through different channels;
performing a splitting processing on each of the plurality of business knowledge documents to obtain a business knowledge fragment;
performing a vectorization processing on the business knowledge fragment to obtain a knowledge fragment vector; and
storing the knowledge fragment vector into the knowledge base.

### Claim 15

An electronic device, characterized by comprising:
a storage apparatus having a computer program stored thereon; and
a processing apparatus, configured to execute the computer program in the storage apparatus to implement a knowledge question-answering method;
wherein the knowledge question-answering method comprises:
acquiring a target question input by a user in a natural language;
retrieving, through a machine learning model, in a knowledge base according to the target question to obtain a target knowledge document for answering the target question, and determining, based on the target knowledge document, a target answer for the target question, wherein the knowledge base is used to store a business knowledge document; and
displaying the target answer to the user.

### Claim 16 (depends on 15)

The electronic device according to claim 15, wherein a plurality of target knowledge documents are provided, and the determining, based on the target knowledge document, a target answer for the target question, comprises:
determining content relevance between the target question and each of the plurality of target knowledge documents;
determining a preset number of knowledge documents from the plurality of target knowledge documents according to the content relevance, wherein content relevance corresponding to each of the preset number of knowledge documents is greater than content relevance corresponding to each of knowledge documents other than the preset number of knowledge documents in the plurality of target knowledge documents; and
determining the target answer for the target question according to the preset number of knowledge documents.

### Claim 17 (depends on 16)

The electronic device according to claim 16, wherein the determining content relevance between the target question and each of the plurality of target knowledge documents, comprises:
inputting the target question and the plurality of target knowledge documents into a relevance model to obtain the content relevance between the target question and each of the target knowledge documents, wherein the relevance model is configured to output, according to an input question and an input knowledge document, content relevance between the input question and the input knowledge document.

### Claim 18 (depends on 15)

The electronic device according to claim 15, wherein the determining, based on the target knowledge document, a target answer for the target question, comprises:
generating a target prompt based on the target knowledge document, the target question, and a preset prompt template, wherein the target prompt is used to instruct the machine learning model to determine, based on the target knowledge document, the target answer for the target question; and
inputting the target prompt into the machine learning model to obtain the target answer for the target question.

### Claim 19 (depends on 15)

The electronic device according to claim 15, wherein the retrieving, through a machine learning model, in a knowledge base according to the target question to obtain a target knowledge document for answering the target question, comprises:
extracting a key field in the target question through the machine learning model;
performing, at least according to the key field, a semantic recall in the knowledge base to obtain a first knowledge document, wherein the semantic recall is used to query a knowledge document comprising a first similar field in the knowledge base, and a semantic similarity between the first similar field and the key field is greater than a preset threshold; and
performing, at least according to the key field, a matching retrieval in the knowledge base to obtain a second knowledge document, wherein the matching retrieval is used to query a knowledge document comprising the key field in the knowledge base;
wherein the target knowledge document comprises the first knowledge document and the second knowledge document.

### Claim 20 (depends on 15)

The electronic device according to claim 15, wherein the knowledge question-answering method further comprises:
determining an expansion word with a same semantics as the key field;
wherein the performing, at least according to the key field, a semantic recall in the knowledge base, comprises:
performing, according to the key field and the expansion word, the semantic recall in the knowledge base, wherein the semantic recall is used to query a knowledge document comprising a second similar field in the knowledge base, and a semantic similarity between the second similar field and the key field or a semantic similarity between the second similar field and the expansion word is greater than the preset threshold;
wherein the performing, at least according to the key field, a matching retrieval in the knowledge base, comprises:
performing, according to the key field and the expansion word, the matching retrieval in the knowledge base, wherein the matching retrieval is used to retrieve a knowledge document comprising the key field or the expansion word in the knowledge base.
