专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

AU2021106441A4 Method, System and Device for Extracting Compound Words of Pathological location in Medical Texts Based on Word-Formation 未知
公开(公告)号：AU2021106441A4
公开(公告)日：2021-11-04
申请号：AU2021106441
申请日：2021-08-22
申请人： FENG HONGHAI , FENG RUI MS
发明人： FENG HONGHAI , LI JUN , ZHOU PENGCHENG , LU XUZHOU , HOU RUIHUI , WEI YAJU
IPC分类号： G06F40/295 , G06F40/279 , G06F40/30 , G06F40/53
摘要： Abstract The present invention discloses a method for extracting compound words of pathological locations in medical texts based on the word-formation method. The possible morphemes included in the compound words of pathological locations in Chinese are summarized manually at first and they are taken as initial values of the compound word set. They may be ordinal words, numbers, directional words, directional collocation words, body location words, body location collocation words, substance words, adjectives, conjunction words and information words, and it is found that the compound words of pathological locations are composed of two or more of them. In the process of learning new morpheme words from a candidate compound words, the number of the learned morpheme words are limited to two words or less than two, and the learned morphemes should be in the minority of the whole compound words. In process of learning new compound words, the given morphemes are iteratively set to match the candidate compound words, and in this way a large number of compound location words are extracted, for example, lower left kidney. This invention completes the extraction of compound words of body locations in pathological indexes, which helps the extraction of subsequent pathological indexes, and the extracted structured pathological information is important for doctors to assist in diagnosing diseases. Drawings of Description Extracting Compound Words of Pathological location in Medical Texts Based on Word-Formation loain aen a odfrainmto W Or rQn o rD 0rD Figure1IA block diagram of asystem module of asystem for extracting compound words of pathological locations based on aword-formation method

2. 发明专利

AU2021106438A4 Method, system and device for extracting the terms for the causes of symptoms in Chinese medical texts based on relations between hyponyms and superordinates 未知
公开(公告)号：AU2021106438A4
公开(公告)日：2021-11-04
申请号：AU2021106438
申请日：2021-08-22
申请人： FENG HONGHAI , FENG RUI MS
发明人： FENG HONGHAI , ZHOU PENGCHENG , LI JUN , WEI YAJU , LU XUZHAO , HOU RUIHUI
IPC分类号： G06F40/295 , G06F40/279 , G06F40/30 , G06F40/53
摘要： Abstract The invention discloses a method, device and system for extracting the terms of symptom causes in Chinese medical texts based on relations between hyponym words and superordinate words, in particular to the technical field of natural language processing information extraction. The invention mainly comprises a reading module, an extraction module, a sentence pattern module and a display module. The reading module mainly refers to the system that reads the sentences that include hyponym words and superordinate words of the symptoms causes' terms, the sentences are taken the pattern of "a hyponymous term of symptom causes is a superordinate term of the symptom causes", and with the sentence pattern the superordinate words are extracted. The extraction module mainly includes the superordinate concept extraction unit. It mainly includes the following steps: firstly, summarize initial hyponym words and their superordinate words, and the sentence patterns manually and store them into computer disks; Secondly, crawl the search box drop-down lists, web page title lists and Baidu snapshots; Then, iteratively read and match the hyponym word lists to the sentences and extract the candidate superordinate words; Finally, the frequency of the superordinate words is counted, and the candidate superordinate words that meet the threshold are stored structurally. The sentence pattern module mainly constructs regular expressions through hyponym concepts and their superordinate concept expression. The display module mainly includes: storage unit and output unit. The invention takes the hyponym symptom cause words and their superordinate words and the their corresponding sentence pattern summarized manually as the starting point, and finally realizes the extraction of the symptom causes' terms in the medical texts. Drawings: Text input unit SExtraction superordinate Module extraction Unit a) 0 Regular xD 51ente!nce expressions f-oodl sentence 0 structure unit Storage Unit Display =j- Mod u1e Output Unit Fig1. System block diagram

3. 发明专利

AU2021106432A4 An approach, device and system for extracting relational words between two entities. 未知
公开(公告)号：AU2021106432A4
公开(公告)日：2021-11-04
申请号：AU2021106432
申请日：2021-08-22
申请人： FENG HONGHAI , FENG RUI MS
发明人： FENG HONGHAI , HOU RUIHUI , WEI YAJU , ZHOU PENGCHENG , LI JUN , LU XUZHAO
IPC分类号： G06F40/295 , G06F40/279 , G06F40/30 , G06F40/53
摘要： This invention discloses an approach, device and system for extracting relational words between two entities, specifically in the field of natural language processing information extraction. The present invention mainly includes a reading module, a compute module and a display module. The reading module mainly refers to the system reading some input Chinese medical texts. The calculation module mainly includes the following steps: step 1: Obtain the corpus and preprocess the sentences to obtain the joint morphemes to be extracted; step 2: Identify the order in which two entities appear in the sentence; step 3: The combined morphemes are segmented and labeled by natural language processing tools to obtain the vocabulary set to be extracted; step 4: Keep effective words such as verbs, conjunctions and prepositions in the vocabulary set; step 5: Save the reserved words into the effective word dictionary, calculate the word frequency of the words in the effective word dictionary according to the TF (term frequency) strategy in natural language processing, and store the high-frequency words (word frequency > 5) into the effective relational word dictionary; step 6: Classify and analyze the part-of-speech of the words in the effective relational word dictionary, and use the above extraction rules to calculate the proportion of each part-of-speech and the proportion of each word number. Drawings: pre-proces tesnnce to inpt~enenes - obtain the joint morphemre to be extracted Segmentation and part-of speech tagging of joint rrorphemes, obtain wordslist wordslist-sizeo 0 j=0 Calculate word frequency to get high frequency vocabu ary Ea wordslist.size) save highI trequenc n Significa t ReIlo a TRUE Words cic output:ignifiicant wrdslist.getj) caat iRellational Words

4. 发明专利

AU2021106425A4 Method, system and apparatus for extracting entity words of diseases and their corresponding laboratory indicators from Chinese medical texts 未知
公开(公告)号：AU2021106425A4
公开(公告)日：2021-11-04
申请号：AU2021106425
申请日：2021-08-22
申请人： FENG HONGHAI , FENG RUI MS
发明人： FENG HONGHAI , WEI YAJU , HOU RUIHUI , LI JUN , ZHOU PENGCHENG , LU XUZHAO
IPC分类号： G06F40/295 , G06F40/279 , G06F40/30 , G09B17/02 , G16H70/20
摘要： Method and system and apparatus for extracting entity words of diseases and their corresponding laboratory indicators from Chinese medical texts The present invention discloses a method and system and device for extracting disease and laboratory index entities from Chinese medical texts and extracting relationships between their entities, and relates to the field of information extraction. It includes three major parts, the first consists of the reading subsystem that mainly contains the modules read by the computer. The second consists of the computation subsystem that mainly captures four major entity components, that is, laboratory indicators, abnormal values, relational words, and disease names after decomposing the sentence components. Every entity component is a set that is composed of some words or terms. The first step is inputting three of the four initial word sets to learn the left relational word set. Once the relational word set is updated, it is taken as one of the new inputs, and taking one of the previous three word sets as the one being learned. The iteration is run until every word set cannot be updated. The third consists of an output subsystem that contains two parts: a storage unit and an output unit. The storage one is the set of relevant medical entity words, and the output one displays the relationship between the relevant entities. System for extracting entity words for diseases and their corresponding lab indicators from medical texts Reading Computing output subsystem subsystems Subsystem Module Decont Inform for Informat aminat action or Reading Input ion ion at Storage Output storing Module Unit matching verific extract Unit Unit 1mitial .oul .nt mthi ei ion Untni values g unit ation unit unit Figure 1: System Block Diagram

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式