Medical consumable reasonable use analysis method based on Simhash-BERT network

An analysis method and network technology, applied in semantic analysis, medical informatics, electronic digital data processing, etc., can solve the problems of unconsidered phrase complexity, large computational overhead, affecting matching accuracy, etc., to avoid similarity interpretation errors , improve retrieval adaptability, optimize the effect of weight distribution

Active Publication Date: 2022-04-29
THE SECOND HOSPITAL OF SHANDONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it needs to feed both sentences into the network, which leads to huge computational overhead
The BERT network uses sentences to map to a vector space. This space is not suitable for common similarity measures. Compared with the BERT network, the Sentence-BERT method optimized on this basis can find semantically similar sentences using cosine similarity. The calculation time is greatly shortened, but the method is aimed at the sentence pair, without considering the complexity of the phrase; at the same time, the cosine similarity is used to ignore the length attribute of the vector, which affects the accuracy of matching
[0007] Therefore, there is currently no effective method for evaluating the rationality of the use of medical consumables, which hinders the process of hospitals building a medical consumables management system

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
  • Medical consumable reasonable use analysis method based on Simhash-BERT network
  • Medical consumable reasonable use analysis method based on Simhash-BERT network
  • Medical consumable reasonable use analysis method based on Simhash-BERT network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as figure 1 As shown, the present embodiment provides the specific steps of the text retrieval and matching method based on the Simhash-BERT network:

[0056] Step 1: Use the search function of the data analysis platform to search text. First, set the interface call method to call the target document from the database. The text and sentences to be retrieved and matched are located in the call target document.

[0057] Step 2: Enter the string to be retrieved in the search function option of the data analysis platform to perform string retrieval.

[0058] Step 3: The search function is realized by optimizing the BERT network, which is formed by stacking multiple Transformers. The search network model first needs to determine the search string and word dictionary. For strings, the representation of sticky notes is used, and the word dictionary is constructed using the entry algorithm. For the BERT network, the transfer of characters is realized in the embedding lay...

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 belongs to the technical field of medical consumable management, and relates to a medical consumable reasonable use analysis method based on a Simhash-BERT network. According to the method, all semantic types are considered, errors caused by length attributes are avoided, statement judgment is carried out by adopting Simhash similarity on the basis of a BERT network, so that the position of a text is determined, and searching and positioning of the text are achieved. And the retrieval accuracy of the statement in the document is improved.

Description

technical field [0001] The invention belongs to the technical field of medical consumables management, and relates to a Simhash-BERT network-based rational use analysis method for medical consumables. Background technique [0002] At present, the cost of medical consumables in the process of diagnosis and treatment of patients in our country accounts for a relatively high proportion of the total medical expenses, and is showing an upward trend year by year. Due to the diversity of medical consumable products, the main problems of medical consumables in the category management of medical institutions are inconsistent product names and non-standard codes. The lack of corresponding management standards and norms also restricts the refined management of medical consumables. Medical consumables are an important material basis for medical institutions to carry out medical services, as well as an auxiliary tool and an important carrier for clinical development of new technologies f...

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): G06F16/335G06F16/35G06F40/186G06F40/194G06F40/242G06F40/279G06F40/30G16H50/70
CPCG06F16/335G06F16/35G06F40/186G06F40/194G06F40/242G06F40/279G06F40/30G16H50/70G06F2216/03
Inventor 宋尚玲刘泽
Owner THE SECOND HOSPITAL OF SHANDONG UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap