# US 2023/0411022 A1 · Intelligent question-answering system for prostate cancer and implementation method thereof

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

- Number: US 2023/0411022 A1
- Document ID: US20230411022A1
- Status: Published application
- Kind: A1
- Application number: 18/315,412
- Filed: 2023-05-10
- Published: 2023-12-21
- Earliest claimed: 2022-05-19
- Assignees: West China Hospital, Sichuan University
- Applicants: West China Hospital, Sichuan University
- Inventors: Bairong Shen; Tong Tang; Jiao Wang; Xingyun Liu; Rongrong Wu; Mengqiao He; Fei Ye; Yingbo Zhang
- Web page: https://patentgrep.com/patent/US20230411022A1

## CPC

- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 70/60: relating to pathologies
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

An implementation method of an intelligent question-answering system for prostate cancer includes: acquiring lifestyle data for prostate cancer based on a preset first data source; using the lifestyle data for prostate cancer as metadata to construct a lifestyle knowledge base; constructing a lifestyle knowledge graph based on a preset second data source and the lifestyle knowledge base; and fusing the lifestyle knowledge base and the lifestyle knowledge graph to obtain the intelligent question-answering system for prostate cancer. The intelligent question-answering system for prostate cancer can help clinicians, medical staff, scientific researchers, and patients, as well as the general public, to acquire objective lifestyle data conveniently and efficiently, and accurately assess the impact on prostate cancer.

## Claims

### Claim 1

An implementation method of an intelligent question-answering system for prostate cancer, comprising:
acquiring lifestyle data for prostate cancer based on a first data source;
constructing a lifestyle knowledge base by taking the lifestyle data for prostate cancer as metadata;
constructing a lifestyle knowledge graph based on a second data source and the lifestyle knowledge base; and
fusing the lifestyle knowledge base and the lifestyle knowledge graph to obtain the intelligent question-answering system for prostate cancer.

### Claim 2 (depends on 1)

The implementation method of the intelligent question-answering system for prostate cancer according to claim 1, wherein acquiring the lifestyle data for prostate cancer based on the first data source, comprises:
training a keyword model related to the lifestyle data for prostate cancer;
modularizing data of the first data source to obtain a plurality of datasets; and
extracting the lifestyle data for prostate cancer from the plurality of datasets by using the keyword model.

### Claim 3 (depends on 2)

The implementation method of the intelligent question-answering system for prostate cancer according to claim 2, wherein constructing the lifestyle knowledge base by taking the lifestyle data for prostate cancer as the metadata, comprises:
standardizing the lifestyle data for prostate cancer to obtain standard data; and
structuring the standard data to obtain the lifestyle knowledge base with index relationships.

### Claim 4 (depends on 3)

The implementation method of the intelligent question-answering system for prostate cancer according to claim 3, wherein constructing the lifestyle knowledge graph based on the second data source and the lifestyle knowledge base, comprises:
filtering data of the second data source to obtain prostate science popularization data related to the lifestyle data for prostate cancer by using the keyword model; and
allocating the prostate science popularization data to obtain the lifestyle knowledge graph according to a graph rule.

### Claim 5 (depends on 4)

The implementation method of the intelligent question-answering system for prostate cancer according to claim 4, wherein fusing the lifestyle knowledge base and the lifestyle knowledge graph to obtain the intelligent question-answering system for prostate cancer, comprises:
taking the prostate science popularization data in the lifestyle knowledge graph and the lifestyle data for prostate cancer in the lifestyle knowledge base as a corpus dataset, wherein the corpus dataset at least comprises prostate cancer question texts and prostate cancer answer texts;
performing semantic parsing on each of the prostate cancer question texts in the corpus dataset to obtain a user intention of each prostate cancer question text, determining a coverage of the prostate cancer question texts in the corpus dataset based on the user intention of each prostate cancer question text, and classifying each prostate cancer question text in the corpus dataset based on the user intention of each prostate cancer question text to obtain a category attribute corresponding to each prostate cancer question text; and
constructing a question-answering knowledge base based on the coverage of the prostate cancer question texts in the corpus dataset and the corresponding category attribute of each prostate cancer question text.

### Claim 6

An intelligent question-answering system for prostate cancer, comprising:
an acquisition module, configured to acquire lifestyle data for prostate cancer based on a first data source;
a lifestyle knowledge base, constructed by taking the lifestyle data for prostate cancer as metadata; and
a lifestyle knowledge graph, constructed based on a second data source and the lifestyle knowledge base; and
wherein the intelligent question-answering system for prostate cancer is implemented by fusing the lifestyle knowledge base and the lifestyle knowledge graph.

### Claim 7 (depends on 6)

The intelligent question-answering system for prostate cancer according to claim 6, wherein the acquisition module comprises: a keyword model trained to be related to the lifestyle data for prostate cancer; and
wherein the acquisition module is configured to modularize data of the first data source to obtain a plurality of datasets, and extract the lifestyle data for prostate cancer from the plurality of datasets by using the keyword model.

### Claim 8 (depends on 7)

The intelligent question-answering system for prostate cancer according to claim 7, wherein the lifestyle knowledge base is implemented by:
standardizing the lifestyle data for prostate cancer to obtain standard data; and
structuring the standard data to obtain the lifestyle knowledge base with index relationships.

### Claim 9 (depends on 8)

The intelligent question-answering system for prostate cancer according to claim 8, wherein the lifestyle knowledge graph is implemented by:
filtering data of the second data source to obtain prostate science popularization data related to lifestyle data for prostate cancer by using the keyword model; and
allocating the prostate science popularization data to obtain the lifestyle knowledge graph according to a graph rule.

### Claim 10 (depends on 9)

The intelligent question-answering system for prostate cancer according to claim 9, wherein the intelligent question-answering system for prostate cancer is implemented by fusing the lifestyle knowledge base and the lifestyle knowledge graph, comprises:
taking the prostate science popularization data in the lifestyle knowledge graph and the lifestyle data for prostate cancer in the lifestyle knowledge base as a corpus dataset, wherein the corpus dataset at least comprises prostate cancer question texts and prostate cancer answer texts;
performing semantic parsing on each of the prostate cancer question texts in the corpus dataset to obtain a user intention of each prostate cancer question text, determining a coverage of the prostate cancer question texts in the corpus dataset based on the user intention of each prostate cancer question text, and classifying each prostate cancer question text in the corpus dataset based on the user intention of each prostate cancer question text to obtain a category attribute corresponding to each prostate cancer question text; and
constructing the question-answering knowledge base based on the coverage of the prostate cancer question texts in the corpus dataset and the corresponding category attribute of each prostate cancer question text.
