Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Chinese natural language information matching method based on IHE PIX (Integration Healthcare Enterprise Patient Identifier Cross-referencing) standards

A natural language and information matching technology, applied in the field of information matching, can solve problems such as deviation, missing multiple pieces of information, incomplete filling of relevant information, etc., to achieve the effect of improving the matching range and matching rate, and the matching results are reliable

Active Publication Date: 2014-05-07
浙江和仁科技股份有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In China, the biggest difficulty in the integrity of personal identity information is that when the information is registered, the filling of identity information is not standardized, the relevant information is incomplete, and key information is often changed. There is a large deviation, such as "Zhang Shan (shan)" and "Zhang San (san)", which makes it difficult for the PIX manager to match personal identity information, or it will miss people belonging to the same person when performing strict matching. Multiple pieces of information for one identity

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
  • Chinese natural language information matching method based on IHE PIX (Integration Healthcare Enterprise Patient Identifier Cross-referencing) standards
  • Chinese natural language information matching method based on IHE PIX (Integration Healthcare Enterprise Patient Identifier Cross-referencing) standards
  • Chinese natural language information matching method based on IHE PIX (Integration Healthcare Enterprise Patient Identifier Cross-referencing) standards

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be further described in detail below in conjunction with examples.

[0025] like image 3 As shown, the matching method of the present invention comprises the following steps:

[0026] 1) Set the attributes of the matching item, the fuzzy sound or wildcard that can be used in the configuration file, and set the weight of the attribute of the matching item and the upper limit of the matching threshold;

[0027] 2) Enter the information that needs to be matched, if it is in Chinese, it will be converted into a pinyin list according to the configuration file;

[0028] 3) If the matching target value is in Chinese, it will be converted to standard pinyin;

[0029] 4) Input to the cross-reference manager to perform matching;

[0030] 5) Calculate the final matching value, and return the matching and non-matching results.

[0031] The preprocessing process for the input source of personal identity information is to convert the input source infor...

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 relates to a method for finishing information matching in a Chinese language environment by using master patient identifiers (MPI) or enterprise master patient identifiers (eMPI) realized by IHE PIX (Integration Healthcare Enterprise Patient Identifier Cross-referencing) standards. The method comprises the steps as follows: firstly, converting input items needed to be matched into phonetic transcriptions with certain formats; secondly, matching by using an algorithm and a matching threshold predefined by a configuration file; and lastly, computing the final matching value by using a PIX, MPI or eMPI system. According to the method, fuzzy tones and wildcard characters can be set according to the actual needs, and the attributes needed to be matched, the weight of the regulation attributes and the matching threshold upper limit are all set, so that the matching results are designed and regulated according to the requirements. Therefore, the problem of inaccurate or omitted information matching due to the reasons such as inaccurate Chinese pronunciation, input error and the like in the input process is favorably solved, and the matching success rate is increased.

Description

technical field [0001] The invention relates to an information matching method in a Chinese natural language environment, especially a Chinese natural language information matching method when constructing a cross index manager, a personal main index MPI or an organization-level personal main index eMPI under the IHE PIX specification. Background technique [0002] With the continuous change and increase of user needs, the number of institutional information systems is increasing, and the phenomenon of information islands within and between institutions is becoming more and more serious. There is no unified standard for this aspect, which makes there are many kinds of repeated information in the system, or information that needs to be combined. is completely acquired. Especially in some industries such as medical and health care, when a patient registers in different hospitals at different times, the registered personal information may be biased or even miswritten, which di...

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 Patents(China)
IPC IPC(8): G06F17/27G06F17/30
Inventor 马雄伟
Owner 浙江和仁科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products