Application method and device of semantic comprehension recall model, equipment and storage medium

A technology of semantic understanding and application method, applied in the field of artificial intelligence and digital medicine, can solve the problem of single, high matching error rate, and achieve the effect of improving accuracy, precise semantic recognition, and improving accuracy

Pending Publication Date: 2022-07-12
KANG JIAN INFORMATION TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to the simple and single sample training process of the existing recall model, it is easy to have a high matching error rate when using the recall model to perform search tasks and obtain matching semantic content.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Application method and device of semantic comprehension recall model, equipment and storage medium
  • Application method and device of semantic comprehension recall model, equipment and storage medium
  • Application method and device of semantic comprehension recall model, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0056]Example 1, the input information is "diarrhea", and the M corpus information is "Dr. Li A" and "Dr. Wang B", then after obtaining the first semantic information and the second semantic information corresponding to "diarrhea", combined with "diarrhea" The corresponding first semantic information and the second semantic information are used to obtain the presentation layer information corresponding to "diarrhea". Similarly, obtain the first semantic information and the second semantic information corresponding to "Dr. Li A", and combine the first semantic information and the second semantic information corresponding to "Dr. Li A" to obtain the presentation layer information corresponding to "Dr. Li A" After the first semantic information and the second semantic information corresponding to "Doctor Wang B" are combined with the first semantic information and the second semantic information corresponding to "Doctor Wang B", the presentation layer information corresponding to ...

example 2

[0058] Example 2: Combined with the above example 1, after obtaining the corresponding representation layer information of "diarrhea", "Dr. Li A" and "Dr. Wang B", the preset algorithm is used to obtain "diarrhea" and "Dr. Li A" respectively. The matching threshold for ", diarrhea" and the matching threshold for "Dr. Wang B".

[0059] Exemplarily, the above-mentioned preset algorithm may be preset in advance, or may be preset by a user, which is not limited in the present invention.

[0060] In the application method of the semantic understanding recall model provided by the embodiment of the present invention, M pieces of corpus information having a first relationship with the input information are first extracted from the semantic sample database corresponding to the target semantic understanding recall model, and then, the M pieces of corpus information are extracted. Perform pre-training with input information, convert the above M corpus information and input information i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an application method and device of a semantic comprehension recall model, equipment and a storage medium. The application method comprises the following steps: extracting M pieces of corpus information having a first relationship with input information from a semantic sample library corresponding to a target semantic comprehension recall model; executing pre-training on the M pieces of corpus information and the input information, and converting the M pieces of corpus information and the input information into X word vectors; inputting each word vector in the X word vectors into a first presentation layer, and executing semantic recognition to obtain X pieces of first semantic information; inputting each word vector into a second presentation layer, executing semantic recognition, and obtaining X pieces of second semantic information; and determining M matching thresholds between the M pieces of corpus information and the input information by utilizing a preset algorithm according to the X pieces of first semantic information and the X pieces of second semantic information. In this way, the accuracy of determining the correlation between the corpus information and the input information is improved, and the accuracy of follow-up content search by a user is further improved.

Description

technical field [0001] The present invention relates to the field of artificial intelligence and digital medicine, in particular to an application method, device, device and storage medium of a semantic understanding recall model. Background technique [0002] At present, with the continuous development of information technology, it is more and more convenient to find and search for information through the network, and the efficiency of finding and searching for information is constantly improving. [0003] In the related art, for different industries, different recall models can be set in advance, and when a user searches, the recall model can match the user with appropriate content according to the specific search content. Among them, the recall model is a learning and training model, specifically, a model trained through massive samples. For example, for a recall model that is used to search for doctors, the recall model can be trained by setting a large amount of doctor...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/33G06F40/284G06F40/30G06K9/62G16H40/20
CPCG06F16/3344G06F40/30G06F40/284G16H40/20G06F18/22
Inventor 薛忠源
Owner KANG JIAN INFORMATION TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products