# US 2019/0171656 A1 · Traditional chinese medicine knowledge graph and establishment method therefor, and computer system

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

- Number: US 2019/0171656 A1
- Document ID: US20190171656A1
- Status: Published application
- Kind: A1
- Application number: 16/313,837
- Filed: 2018-03-13
- Published: 2019-06-06
- Earliest claimed: 2017-05-10
- Assignees: Boe Technology Group Co., Ltd.
- Applicants: Boe Technology Group Co., Ltd.
- Inventors: Chao Zhang
- Web page: https://patentgrep.com/patent/US20190171656A1

## CPC

- G06F 16/367: {Ontology}
- G06F 16/254: {Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses}
- G06F 16/288: {Entity relationship models}
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 20/90: relating to alternative medicines, e.g. homeopathy or oriental medicines
- G16H 70/40: relating to drugs, e.g. their side effects or intended usage
- G16H 70/60: relating to pathologies
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A traditional Chinese medicine knowledge graph, a method for establishing a traditional Chinese medicine knowledge graph, and a computer system. The method for establishing the traditional Chinese medicine knowledge graph comprises collecting original data from a traditional Chinese medicine database. The method comprises processing the original data to obtain structural data. The method comprises extracting an entity and an attribute from the structural data. The method comprises constructing the traditional Chinese medicine knowledge graph by utilizing the entity and attribute.

## Claims

### Claim 1

A method for establishing a medical knowledge graph implemented in a data processing apparatus, the method comprising:
collecting raw data from a medical database;
processing the raw data to obtain structured data;
extracting entities and attributes from the structured data; and
constructing a medical knowledge graph using the entities and attributes.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the entities comprise a plurality of items of interest or respective values of the items, and the attributes comprise a relationship between the entities.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the entities comprise one or more of: a medicine name, a disease type, a processing method, a dosage form, a medicinal property, and a drug amount.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the attributes comprise one or more of an influence relationship, a correlation relationship, a dependency relationship and a value relationship.

### Claim 5 (depends on 4)

The method according to claim 4, wherein,
the influence relationship represents an influence between the entities;
the correlation relationship is determined based on a number of co-occurrences of the entities in the medical database;
the dependency relationship represents that one of the entities belongs to another one of the entities; and
the value relationship represents that one of the entities is a value of another one of the entities.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the influence relationship comprises one or more of curing, restraining, and requiring.

### Claim 7 (depends on 2)

The method according to claim 2, wherein the value of each item of the entities comprises an absolute quantity value of the item, a relative quantity value of the value and a nature of the item.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the medical database comprises one or more of a case of an illness database, a medical journal database, a medical patent database, and a medical professional dictionary.

### Claim 9 (depends on 1)

The method according to claim 1, wherein processing the raw data to obtain structured data comprises:
processing the raw data using a natural language processing technique.

### Claim 10

A non-transitory computer-readable storage medium having stored therein instructions that, when executed by a processor of a data processing apparatus, causes a data processing apparatus to present a medical knowledge graph comprising:
entities obtained from a medical database; and
attributes obtained from the medical database,
wherein the entities and the attributes are extracted respectively from structured data generated by processing data collected from the medical database.

### Claim 11

A data processing apparatus comprising:
a processor; and
a memory storing computer readable instructions,
wherein when the computer readable instructions stored in the memory are executed, the computer system is caused to perform a method for establishing a medical knowledge graph, the method comprising:
collect raw data from a medical database;
processing the raw data to obtain structured data;
extracting entities and attributes from the structured data; and
constructing the medical knowledge graph using the entities and attributes.

### Claim 12 (depends on 11)

The computer system according to claim 11, wherein the entities comprise a plurality of items of interest or respective values of the plurality of items, and the attributes comprise a relationship between the entities.

### Claim 13 (depends on 12)

The computer system according to claim 12, wherein the entities comprises one or more of: a medicine name, a disease type, a processing method, a dosage form, a medicinal property, and a drug amount.

### Claim 14 (depends on 12)

The computer system according to claim 12, wherein the attributes comprises one or more of an influence relationship, a correlation relationship, a dependency relationship and a value relationship.

### Claim 15 (depends on 14)

The computer system according to claim 14, wherein,
the influence relationship represents an influence between the entities;
the correlation relationship is determined based on a number of co-occurrences of the entities in the medical database;
the dependency relationship represents that one of the entities belongs to another one of the entities; and
the value relationship represents that one of the entities is a value of another one of the entities.

### Claim 16 (depends on 15)

The computer system according to claim 15, wherein the influence relationship comprises one or more of curing, restraining, and requiring.

### Claim 17 (depends on 12)

The computer system according to claim 12, wherein the value of each item of the entities comprises an absolute quantity value of the item, a relative quantity value of the value or a nature of the item.

### Claim 18 (depends on 11)

The computer system according to claim 11, wherein the medical database comprises one or more of a case of illness database, a medical journal database, a medical patent database, and a medical professional dictionary.

### Claim 19 (depends on 11)

The computer system according to claim 11, wherein the processing the raw data to obtain structured data comprises:
processing the raw data using a natural language processing technique.

### Claim 20 (depends on 1)

The method according to claim 1, wherein the raw data is text data.
