Domain knowledge base construction method and device, equipment and storage medium
A technology of domain knowledge and construction method, applied in the field of domain knowledge base construction method, equipment and storage media, and devices, which can solve the problems of lack of labeled corpus
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0077] see figure 1 , which shows a schematic flowchart of a method for constructing a domain knowledge base provided by an embodiment of the present application, and the method may include:
[0078] Step S101: Obtain the seed knowledge base corresponding to the specified field.
[0079] It should be noted that the "field" mentioned in this application refers to industries, including but not limited to banking, insurance, government affairs, operators, electric power, etc.
[0080] In this embodiment, the seed knowledge base corresponding to the specified field contains the seed sentence pattern marked under the knowledge point of the specified field. It should be noted that a clause type x marked under the knowledge point y refers to the seed sentence The label information of formula x is knowledge point y.
[0081] Wherein, the knowledge points in the specified field are obtained by sorting out the services in the specified field, and optionally, the knowledge points in th...
no. 2 example
[0092] In this embodiment, in step S102 in the above embodiment, "based on the seed sentence patterns in the seed knowledge base, excavate the field sentence patterns that can be marked under the knowledge points of the specified field from the field sentence pattern database corresponding to the specified field" Implementation process is introduced.
[0093] see image 3 , shows a schematic flow diagram of mining the domain sentence patterns that can be marked under the knowledge points of the specified field from the field sentence pattern database corresponding to the specified field based on the seed sentence patterns in the seed knowledge base, which may include:
[0094] Step S301: Use the sentence patterns in each field in the field sentence pattern library as the target field sentence patterns, and execute:
[0095] Step S3011: According to the sentence patterns in the target domain and the seed sentence patterns in the seed knowledge base, determine the knowledge poi...
no. 3 example
[0145] In order to obtain a domain knowledge base with better quality and a semantic understanding model with better performance, this embodiment provides another method for constructing a domain knowledge base. Please refer to Figure 4 , which shows a schematic flowchart of the method for building the domain knowledge base, which may include:
[0146] Step S401: Obtain the seed knowledge base corresponding to the specified field.
[0147] Wherein, the seed knowledge base contains the seed sentence patterns marked under the knowledge points in the specified field.
[0148] Step S402: Based on the seed sentence patterns in the seed knowledge base, excavate domain sentence patterns that can be marked under the knowledge points of the specified field from the domain sentence pattern database corresponding to the specified field, and mark the excavated domain sentence patterns, To obtain the excavated sentence patterns marked under the knowledge points in the specified field.
...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


