WO2018201772A1 - Système et procédé destinés à inférer une maladie éventuelle à partir d'un texte médical, et support d'informations lisible - Google Patents

Système et procédé destinés à inférer une maladie éventuelle à partir d'un texte médical, et support d'informations lisible Download PDF

Info

Publication number
WO2018201772A1
WO2018201772A1 PCT/CN2018/076149 CN2018076149W WO2018201772A1 WO 2018201772 A1 WO2018201772 A1 WO 2018201772A1 CN 2018076149 W CN2018076149 W CN 2018076149W WO 2018201772 A1 WO2018201772 A1 WO 2018201772A1
Authority
WO
WIPO (PCT)
Prior art keywords
medical
disease
text
vocabulary
medical text
Prior art date
Application number
PCT/CN2018/076149
Other languages
English (en)
Chinese (zh)
Inventor
赵清源
韦邕
吕梓燊
徐亮
肖京
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2018201772A1 publication Critical patent/WO2018201772A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the present application relates to the field of computer technology, and in particular, to a potential disease inference method, system, and readable storage medium for medical text.
  • the first step in dealing with medical texts is to infer potential diseases in order to make the next diagnostic recommendations.
  • the underlying disease inference for the medical text can only artificially infer the underlying disease in the medical text according to the doctor's personal experience, and the efficiency is low, and the existing medical data resources cannot be utilized to effectively infer the underlying disease.
  • the main purpose of the present application is to provide a potential disease inference method, system and readable storage medium for medical texts, which aim to accurately and efficiently infer potential diseases of medical texts.
  • a first aspect of the present application provides a method for inferring a potential disease of a medical text, the method comprising the following steps:
  • the second aspect of the present application further provides a potential disease inference system for a medical text, where the potential disease inference system of the medical text includes:
  • a word segmentation module configured to segment the received medical text, and match each word segment corresponding to the medical text with a predetermined medical field-specific vocabulary to extract a medical vocabulary in each word segment corresponding to the medical text;
  • a determining module configured to determine a disease corresponding to the medical vocabulary in the medical text based on a pre-built medical professional database; wherein the medical professional database includes a mapping relationship between different types of diseases and medical vocabulary;
  • An output module for outputting the determined disease as an inferred potential disease of the medical text.
  • a third aspect of the present application further provides a computer readable storage medium storing a potential disease inference system of medical text
  • the potential disease inference system of the medical text may be Executing by at least one processor to cause the at least one processor to perform the steps of the potential disease inference method of the medical text as described above.
  • the potential disease inferring method, system and readable storage medium of the medical text proposed by the present application extracts the medical vocabulary in each participle corresponding to the medical text by segmenting the received medical text; and based on the pre-built inclusion
  • a medical professional database that maps the relationship between disease and medical vocabulary to determine the disease corresponding to the medical vocabulary in the medical text as a delineated underlying disease of the medical text. Because it can construct the mapping relationship between different diseases and medical vocabulary according to various medical data resources, and find the disease mapped according to the medical vocabulary in the medical text, it is more efficient and accurate than manual estimation based on the doctor's personal experience. high.
  • FIG. 1 is a schematic flow chart of a first embodiment of a method for inferring a potential disease of a medical text according to the present application
  • FIG. 2 is a schematic flow chart of a second embodiment of a method for inferring a potential disease of a medical text according to the present application;
  • FIG. 3 is a schematic diagram of an operating environment of a preferred embodiment of the underlying disease inference system 10 of the medical text of the present application;
  • FIG. 4 is a schematic diagram of functional modules of a first embodiment of a potential disease inference system for medical text of the present application
  • FIG. 5 is a schematic diagram of functional modules of a second embodiment of a potential disease inference system for medical text of the present application.
  • the present application provides a method for inferring a potential disease of a medical text.
  • FIG. 1 is a schematic flow chart of an embodiment of a method for estimating a potential disease of a medical text according to the present application.
  • the potential disease inference method of the medical text includes:
  • Step S10 segmenting the received medical text, and matching each word segment corresponding to the medical text with a predetermined medical field-specific vocabulary, and extracting the medical vocabulary in each participle corresponding to the medical text.
  • Receiving medical text to be diagnosed such as receiving medical text to be diagnosed sent by the user through a browser, a client APP, or the like.
  • the received medical text is first subjected to word segmentation processing.
  • the medical text can be divided into a complete statement according to the punctuation marks, and then the word segmentation processing is performed on each segmented sentence, for example, the word segmentation method can be used to perform segmentation processing on each segmented sentence, such as positive direction.
  • the maximum matching method which divides the string in a segmented statement from left to right; or, the inverse maximum matching method, divides the string in a segmented statement from right to left; or, the shortest path
  • Word segmentation the string in a segmented statement requires the number of words to be cut out to be the least; or, the two-way maximum matching method, and the word segmentation is performed in both forward and reverse directions.
  • Word segmentation can also be used to classify each segmented sentence.
  • Word segmentation is a segmentation method for machine speech judgment. It uses syntactic information and semantic information to deal with ambiguity phenomena to segment words. Statistical segmentation can also be used to process word segmentation of each segmented sentence.
  • the respective word segments corresponding to the medical text are matched with the predetermined medical field-specific vocabulary, and the predetermined medical field-specific vocabulary may include the medical lexicon in the general medical dictionary, according to a large number.
  • the medical field-specific vocabulary can be fixed, or it can be based on the latest open source medical data on the Internet to regularly update the medical vocabulary in the medical field-specific vocabulary.
  • the medical vocabulary matching the predetermined medical field-specific vocabulary among the respective word segments corresponding to the medical text is extracted, and the medical vocabulary that is related to the potential disease in the medical text, that is, the extracted medical vocabulary can be obtained.
  • Step S20 Determine a disease corresponding to the medical vocabulary in the medical text based on the pre-built medical professional database; wherein the medical professional database includes a mapping relationship between different types of diseases and medical vocabulary.
  • the medical vocabulary corresponding to the medical vocabulary in the medical text is determined based on the pre-built medical professional database.
  • the medical professional database contains mapping relationships between different types of diseases and medical vocabulary (such as symptoms, drugs, examinations, departments and other information vocabulary extracted from a large number of medical texts), such as building medical professional materials based on open source data and texts.
  • the database contains professional information such as diseases and their corresponding profiles, symptoms, complications, treatments, and common tests. Based on the constructed mapping relationship between different diseases and medical vocabulary, the disease mapped with the medical vocabulary in the medical text can be found.
  • step S30 the determined disease is output as the inferred potential disease of the medical text.
  • the determined disease After determining the corresponding disease according to the extracted medical vocabulary in the medical text, the determined disease can be output as the inferred potential disease of the medical text, based on the inferred potential disease of the medical text. Subsequent diagnostic recommendations.
  • the disease label accuracy rate obtained by the potential disease inference method in this embodiment can reach about 85%, which can effectively improve the potential disease inference for the medical text. The accuracy rate.
  • the medical vocabulary in each participle corresponding to the medical text is extracted by segmenting the received medical text; and the medical text is determined based on a pre-built medical professional database containing mapping relationships between different diseases and medical vocabulary.
  • the medical vocabulary corresponds to the disease as a potential disease inferred from the medical text. Because it can construct the mapping relationship between different diseases and medical vocabulary according to various medical data resources, and find the disease mapped according to the medical vocabulary in the medical text, it is more efficient and accurate than manual estimation based on the doctor's personal experience. high.
  • the second embodiment of the present application provides a method for inferring a potential disease of a medical text.
  • the method before the step S10, the method further includes:
  • Step S40 Obtain medical data from a predetermined data source, find one or more medical vocabularies corresponding to each disease from the medical data, and establish a medical professional database according to a mapping relationship between different types of diseases and medical vocabulary.
  • the medical data is first acquired from the predetermined data source to establish a medical professional database according to the mapping relationship between the different types of diseases and the medical vocabulary in the medical data.
  • the medical data may be an authoritative interpretation of various diseases obtained from an existing medical database, including corresponding information such as profiles, symptoms, complications, therapeutic drugs, common examinations, etc., or medical treatments corresponding to various drugs.
  • Information such as the type of disease in which the drug is administered, the medical data can also be an open source medical data source on the Internet in real time or regularly through tools such as web crawlers (for example, questions and answers about different diseases in various forums, etc., or Specific types of information obtained by various latest medical cases, medical question and answer texts, etc.
  • the medical professional database further includes the weight of each medical vocabulary corresponding to the disease
  • the step S20 may include:
  • the medical vocabulary corresponding to one disease may be one or more, and one medical vocabulary may have one or more diseases.
  • the same symptom may map multiple diseases, the same type.
  • Medicines can also treat a variety of diseases. Therefore, in the medical professional database constructed, different medical vocabularies are given different weights, so that when there are multiple medical vocabularies in the medical texts found based on the constructed medical professional database, the medical vocabulary corresponding to each disease can be calculated. The sum of the weights is selected, and the weight of the corresponding medical vocabulary is added to add the highest disease as the disease corresponding to the medical text determined. For example, the weight of a disease map can be summed as the degree of self-confidence of the disease, and the disease with the highest degree of confidence is selected as the final result, thereby further improving the accuracy of the underestimation of the medical text.
  • the step of performing word segmentation processing on the received medical text in the above step S10 includes:
  • the string to be processed in the medical text and the predetermined medical field-specific vocabulary (for example, the medical field-specific vocabulary may be a general medical professional vocabulary, or may be a scalable learning medical
  • the lexicon is matched to obtain the first matching result
  • the character string to be processed in the medical text and the predetermined medical field-specific vocabulary (for example, the medical field-specific vocabulary can be a general medical professional vocabulary, or can be a scalable learning medical word.
  • the library is matched to obtain the second matching result.
  • the first matching result includes a first number of first phrases
  • the second matching result includes a second number of second phrases
  • the first matching result includes a third number of words
  • the second matching result includes a fourth number of words.
  • the first quantity is equal to the second quantity, and the third quantity is less than or equal to the fourth quantity, outputting the first matching result (including a phrase and a single word) corresponding to the medical text;
  • the first quantity is equal to the second quantity, and the third quantity is greater than the fourth quantity, outputting the second matching result (including a phrase and a single word) corresponding to the medical text;
  • the first quantity is not equal to the second quantity, and the first quantity is greater than the second quantity, outputting the second matching result (including a phrase and a single word) corresponding to the medical text;
  • the first quantity is not equal to the second quantity, and the first quantity is less than the second quantity, outputting the first matching result (including a phrase and a single word) corresponding to the medical text.
  • the two-way matching method is used to perform word segmentation processing on medical texts, and the word segmentation matching is performed by forward and reverse simultaneous segmentation to analyze the stickiness of the combined content in the character string to be processed of the medical text, since the phrase can represent the core viewpoint information under normal circumstances.
  • the probability is greater, that is, the phrase is more likely to be the medical vocabulary in the medical text. Therefore, through the simultaneous and reverse word segmentation matching, the word segment matching result with fewer words and more phrases is found to be used as the word segmentation result of the medical text, thereby improving the accuracy of the word segmentation, so as to extract the medical text more accurately.
  • Medical vocabulary is used to perform word segmentation processing on medical texts, and the word segmentation matching is performed by forward and reverse simultaneous segmentation to analyze the stickiness of the combined content in the character string to be processed of the medical text, since the phrase can represent the core viewpoint information under normal circumstances.
  • the probability is greater, that is, the phrase is more likely to be the medical vocabulary in the medical text. Therefore, through the simultaneous and reverse word segmentation matching
  • the application further provides a potential disease inference system for medical text.
  • FIG. 3 is a schematic diagram of an operating environment of a preferred embodiment of the underlying disease inference system 10 of the medical text of the present application.
  • the medical text potential disease inference system 10 is installed and operated in the electronic device 1.
  • the electronic device 1 may include, but is not limited to, a memory 11, a processor 12, and a display 13.
  • Figure 3 shows only the electronic device 1 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a hard disk or memory of the electronic device 1.
  • the memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC), and a secure digital device. (Secure Digital, SD) card, flash card, etc.
  • SMC smart memory card
  • secure digital device Secure Digital, SD
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 is used to store application software installed on the electronic device 1 and various types of data, such as program codes of the underlying disease inference system 10 of the medical text.
  • the memory 11 can also be used to temporarily store data that has been output or is about to be output.
  • the processor 12 may be a central processing unit (CPU), a microprocessor or other data processing chip for running program code or processing data stored in the memory 11, for example A potential disease inference system 10 or the like that executes the medical text.
  • CPU central processing unit
  • microprocessor or other data processing chip for running program code or processing data stored in the memory 11, for example A potential disease inference system 10 or the like that executes the medical text.
  • the display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor or the like in some embodiments.
  • the display 13 is used to display information processed in the electronic device 1 and a user interface for displaying visualizations, such as displaying medical vocabulary in the extracted medical text, inferred potential disease of the medical text, and the like.
  • the components 11-13 of the electronic device 1 communicate with one another via a system bus.
  • FIG. 4 is a functional block diagram of a first embodiment of the underlying disease inference system 10 of the medical text of the present application.
  • the potential disease inference system 10 of the medical text may be segmented into one or more modules, the one or more modules being stored in the memory 11 and processed by one or more
  • the present invention (this embodiment is the processor 12) is executed to complete the application.
  • the potential disease inference system 10 of the medical text may be divided into a component word extraction module 01, a determination module 02, and an output module 03.
  • a module referred to in this application refers to a series of computer program instructions that are capable of performing a particular function, and are more suitable than the program to describe the execution of the speech recognition system 10 in the electronic device 1.
  • the following description will specifically describe the functions of the word segmentation module 01, the determination module 02, and the output module 03.
  • the word segmentation module 01 is configured to segment the received medical text, and match each word segment corresponding to the medical text with a predetermined medical field-specific vocabulary to extract the medical vocabulary in each participle corresponding to the medical text. ;
  • Receiving medical text to be diagnosed such as receiving medical text to be diagnosed sent by the user through a browser, a client APP, or the like.
  • the received medical text is first subjected to word segmentation processing.
  • the medical text can be divided into a complete statement according to the punctuation marks, and then the word segmentation processing is performed on each segmented sentence, for example, the word segmentation method can be used to perform segmentation processing on each segmented sentence, such as positive direction.
  • the maximum matching method which divides the string in a segmented statement from left to right; or, the inverse maximum matching method, divides the string in a segmented statement from right to left; or, the shortest path
  • Word segmentation the string in a segmented statement requires the number of words to be cut out to be the least; or, the two-way maximum matching method, and the word segmentation is performed in both forward and reverse directions.
  • Word segmentation can also be used to classify each segmented sentence.
  • Word segmentation is a segmentation method for machine speech judgment. It uses syntactic information and semantic information to deal with ambiguity phenomena to segment words. Statistical segmentation can also be used to process word segmentation of each segmented sentence.
  • the respective word segments corresponding to the medical text are matched with the predetermined medical field-specific vocabulary, and the predetermined medical field-specific vocabulary may include the medical lexicon in the general medical dictionary, according to a large number.
  • the medical field-specific vocabulary can be fixed, or it can be based on the latest open source medical data on the Internet to regularly update medical vocabulary in the medical field-specific vocabulary.
  • the medical vocabulary matching the predetermined medical field-specific vocabulary among the respective word segments corresponding to the medical text is extracted, and the medical vocabulary that is related to the potential disease in the medical text, that is, the extracted medical vocabulary can be obtained.
  • a determining module 02 configured to determine, according to a pre-built medical professional database, a disease corresponding to the medical vocabulary in the medical text; wherein the medical professional database includes a mapping relationship between different types of diseases and medical vocabulary;
  • the medical vocabulary corresponding to the medical vocabulary in the medical text is determined based on the pre-built medical professional database.
  • the medical professional database contains mapping relationships between different types of diseases and medical vocabulary (such as symptoms, drugs, examinations, departments and other information vocabulary extracted from a large number of medical texts), such as building medical professional materials based on open source data and texts.
  • the database contains professional information such as diseases and their corresponding profiles, symptoms, complications, treatments, and common tests. Based on the constructed mapping relationship between different diseases and medical vocabulary, the disease mapped with the medical vocabulary in the medical text can be found.
  • the output module 03 is configured to output the determined disease as the inferred potential disease of the medical text.
  • the determined disease After determining the corresponding disease according to the extracted medical vocabulary in the medical text, the determined disease can be output as the inferred potential disease of the medical text, based on the inferred potential disease of the medical text. Subsequent diagnostic recommendations.
  • the disease label accuracy rate obtained by the potential disease inference method in this embodiment can reach about 85%, which can effectively improve the potential disease inference for the medical text. The accuracy rate.
  • the medical vocabulary in each participle corresponding to the medical text is extracted by segmenting the received medical text; and the medical text is determined based on a pre-built medical professional database containing mapping relationships between different diseases and medical vocabulary.
  • the medical vocabulary corresponds to the disease as a potential disease inferred from the medical text. Because it can construct the mapping relationship between different diseases and medical vocabulary according to various medical data resources, and find the disease mapped according to the medical vocabulary in the medical text, it is more efficient and accurate than manual estimation based on the doctor's personal experience. high.
  • the second embodiment of the present application provides a potential disease inference system for a medical text. Based on the foregoing embodiments, the method further includes:
  • the establishing module 04 is configured to obtain medical data from a predetermined data source, find one or more medical vocabularies corresponding to each disease from the medical data, and establish a medical relationship according to a mapping relationship between different types of diseases and medical vocabulary Professional database.
  • the medical data is first acquired from a predetermined data source to establish a medical professional database according to the mapping relationship between different types of diseases and medical vocabulary in the medical data.
  • the medical data may be an authoritative interpretation of various diseases obtained from an existing medical database, including corresponding information such as profiles, symptoms, complications, therapeutic drugs, common examinations, etc., or medical treatments corresponding to various drugs.
  • Information such as the type of disease in which the drug is administered, the medical data can also be an open source medical data source on the Internet in real time or regularly through tools such as web crawlers (for example, questions and answers about different diseases in various forums, etc., or Specific types of information obtained by various latest medical cases, medical question and answer texts, etc.
  • the medical professional database further includes the weight of each medical vocabulary corresponding to the disease
  • the determining module 02 may further be used to:
  • the medical vocabulary corresponding to one disease may be one or more, and one medical vocabulary may have one or more diseases.
  • the same symptom may map multiple diseases, the same type.
  • Medicines can also treat a variety of diseases. Therefore, in the medical professional database constructed, different medical vocabularies are given different weights, so that when there are multiple medical vocabularies in the medical texts found based on the constructed medical professional database, the medical vocabulary corresponding to each disease can be calculated. The sum of the weights is selected, and the weight of the corresponding medical vocabulary is added to add the highest disease as the disease corresponding to the medical text determined. For example, the weight of a disease map can be summed as the degree of self-confidence of the disease, and the disease with the highest degree of confidence is selected as the final result, thereby further improving the accuracy of the underestimation of the medical text.
  • the word segmentation module 01 is further configured to:
  • the string to be processed in the medical text and the predetermined medical field-specific vocabulary (for example, the medical field-specific vocabulary may be a general medical professional vocabulary, or may be a scalable learning medical
  • the lexicon is matched to obtain the first matching result
  • the character string to be processed in the medical text and the predetermined medical field-specific vocabulary (for example, the medical field-specific vocabulary can be a general medical professional vocabulary, or can be a scalable learning medical word.
  • the library is matched to obtain the second matching result.
  • the first matching result includes a first number of first phrases
  • the second matching result includes a second number of second phrases
  • the first matching result includes a third number of words
  • the second matching result includes a fourth number of words.
  • the first quantity is equal to the second quantity, and the third quantity is less than or equal to the fourth quantity, outputting the first matching result (including a phrase and a single word) corresponding to the medical text;
  • the first quantity is equal to the second quantity, and the third quantity is greater than the fourth quantity, outputting the second matching result (including a phrase and a single word) corresponding to the medical text;
  • the first quantity is not equal to the second quantity, and the first quantity is greater than the second quantity, outputting the second matching result (including a phrase and a single word) corresponding to the medical text;
  • the first quantity is not equal to the second quantity, and the first quantity is less than the second quantity, outputting the first matching result (including a phrase and a single word) corresponding to the medical text.
  • the two-way matching method is used to perform word segmentation processing on medical texts, and the word segmentation matching is performed by forward and reverse simultaneous segmentation to analyze the stickiness of the combined content in the character string to be processed of the medical text, since the phrase can represent the core viewpoint information under normal circumstances.
  • the probability is greater, that is, the phrase is more likely to be the medical vocabulary in the medical text. Therefore, through the simultaneous and reverse word segmentation matching, the word segment matching result with fewer words and more phrases is found to be used as the word segmentation result of the medical text, thereby improving the accuracy of the word segmentation, so as to extract the medical text more accurately.
  • Medical vocabulary is used to perform word segmentation processing on medical texts, and the word segmentation matching is performed by forward and reverse simultaneous segmentation to analyze the stickiness of the combined content in the character string to be processed of the medical text, since the phrase can represent the core viewpoint information under normal circumstances.
  • the probability is greater, that is, the phrase is more likely to be the medical vocabulary in the medical text. Therefore, through the simultaneous and reverse word segmentation matching
  • the present application also provides a computer readable storage medium storing a potential disease inference system of medical text, the potential disease inference system of the medical text being executable by at least one processor such that The at least one processor performs the steps of the potential disease inference method of the medical text in the above embodiment, and the specific implementation processes of the steps S10, S20, S30, etc. of the potential disease inference method of the medical text are as described above, and are not Let me repeat.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and can also be implemented by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

La présente invention concerne un système et un procédé destinés à inférer une maladie éventuelle à partir d'un texte médical, et un support d'informations lisible. Le procédé consiste : à réaliser une segmentation sur un texte médical reçu, à réaliser une mise en correspondance entre des mots respectifs correspondant au texte médical et une base de terminologie spécifique au domaine médical prédéterminée, et à extraire une terminologie médicale à partir des mots respectifs correspondant au texte médical (S10) ; à déterminer, sur la base d'une base de données de spécialité médicale préétablie, une maladie correspondant à la terminologie médicale dans le texte médical (S20) ; et à délivrer la maladie déterminée en tant que maladie éventuelle inférée à partir du texte médical (S30). Le procédé permet une inférence précise et hautement efficace d'une maladie éventuelle à partir d'un texte médical.
PCT/CN2018/076149 2017-05-05 2018-02-10 Système et procédé destinés à inférer une maladie éventuelle à partir d'un texte médical, et support d'informations lisible WO2018201772A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710313520.1 2017-05-05
CN201710313520.1A CN107680689A (zh) 2017-05-05 2017-05-05 医疗文本的潜在疾病推断方法、系统及可读存储介质

Publications (1)

Publication Number Publication Date
WO2018201772A1 true WO2018201772A1 (fr) 2018-11-08

Family

ID=61134116

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/076149 WO2018201772A1 (fr) 2017-05-05 2018-02-10 Système et procédé destinés à inférer une maladie éventuelle à partir d'un texte médical, et support d'informations lisible

Country Status (2)

Country Link
CN (1) CN107680689A (fr)
WO (1) WO2018201772A1 (fr)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107680689A (zh) * 2017-05-05 2018-02-09 平安科技（深圳）有限公司 医疗文本的潜在疾病推断方法、系统及可读存储介质
CN109215771B (zh) * 2018-05-29 2024-07-12 深圳平安医疗健康科技服务有限公司 医疗映射关系库建立方法、装置、计算机设备和存储介质
CN109036506B (zh) * 2018-07-25 2023-04-18 平安科技（深圳）有限公司 互联网医疗问诊的监管方法、电子装置及可读存储介质
CN109215796B (zh) * 2018-08-14 2023-04-25 深圳平安医疗健康科技服务有限公司 搜索方法、装置、计算机设备和存储介质
CN109192300A (zh) * 2018-08-17 2019-01-11 百度在线网络技术（北京）有限公司 智能问诊方法、系统、计算机设备和存储介质
CN109215754A (zh) * 2018-09-10 2019-01-15 平安科技（深圳）有限公司 病历数据处理方法、装置、计算机设备和存储介质
CN109192321A (zh) * 2018-09-26 2019-01-11 北京理工大学 药品知识图谱的构建方法及计算存储装置
CN109616165A (zh) * 2018-11-07 2019-04-12 平安科技（深圳）有限公司 医疗信息展示方法及装置
CN109698018A (zh) * 2018-12-24 2019-04-30 广州天鹏计算机科技有限公司 医疗文本处理方法、装置、计算机设备和存储介质
CN110021439B (zh) * 2019-03-07 2023-01-24 平安科技（深圳）有限公司 基于机器学习的医疗数据分类方法、装置和计算机设备
CN112002416A (zh) * 2020-08-23 2020-11-27 吾征智能技术(北京)有限公司 一种基于尿液性状自学习的疾病征兆预测系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100042436A1 (en) * 2008-08-15 2010-02-18 Sultan Haider Disease oriented user interfaces
CN105095665A (zh) * 2015-08-13 2015-11-25 易保互联医疗信息科技（北京）有限公司 一种中文疾病诊断信息的自然语言处理方法及系统
CN105138829A (zh) * 2015-08-13 2015-12-09 易保互联医疗信息科技（北京）有限公司 一种中文诊疗信息的自然语言处理方法及系统
CN106095913A (zh) * 2016-06-08 2016-11-09 广州同构医疗科技有限公司 一种电子病历文本结构化方法
CN106557653A (zh) * 2016-11-15 2017-04-05 合肥工业大学 一种移动医疗智能导医系统及其方法
CN107680689A (zh) * 2017-05-05 2018-02-09 平安科技（深圳）有限公司 医疗文本的潜在疾病推断方法、系统及可读存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102915299B (zh) * 2012-10-23 2015-04-08 海信集团有限公司 一种分词方法及装置
CN104102816B (zh) * 2014-06-20 2017-07-25 周晋 基于症状匹配和机器学习的自动诊断系统和方法
CN104484845B (zh) * 2014-12-30 2019-03-05 天津迈沃医药技术股份有限公司 基于医学信息本体数据库的疾病自我分析平台
CN104915413B (zh) * 2015-06-05 2018-09-07 广东顺德中山大学卡内基梅隆大学国际联合研究院 一种健康检测方法及系统
CN105139237A (zh) * 2015-09-25 2015-12-09 百度在线网络技术（北京）有限公司 信息推送的方法和装置
CN106372439A (zh) * 2016-09-21 2017-02-01 北京大学 基于病例库的疾病症状及其权重知识的获取和处理方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100042436A1 (en) * 2008-08-15 2010-02-18 Sultan Haider Disease oriented user interfaces
CN105095665A (zh) * 2015-08-13 2015-11-25 易保互联医疗信息科技（北京）有限公司 一种中文疾病诊断信息的自然语言处理方法及系统
CN105138829A (zh) * 2015-08-13 2015-12-09 易保互联医疗信息科技（北京）有限公司 一种中文诊疗信息的自然语言处理方法及系统
CN106095913A (zh) * 2016-06-08 2016-11-09 广州同构医疗科技有限公司 一种电子病历文本结构化方法
CN106557653A (zh) * 2016-11-15 2017-04-05 合肥工业大学 一种移动医疗智能导医系统及其方法
CN107680689A (zh) * 2017-05-05 2018-02-09 平安科技（深圳）有限公司 医疗文本的潜在疾病推断方法、系统及可读存储介质

Also Published As

Publication number Publication date
CN107680689A (zh) 2018-02-09

Similar Documents

Publication Publication Date Title
WO2018201772A1 (fr) Système et procédé destinés à inférer une maladie éventuelle à partir d'un texte médical, et support d'informations lisible
WO2021000676A1 (fr) Procédé de q&r, dispositif de q&r, équipement informatique et support de stockage
US10162886B2 (en) Embedding-based parsing of search queries on online social networks
WO2019214149A1 (fr) Procédé d'identification d'informations clés de texte, dispositif électronique, et support de stockage lisible
US9633006B2 (en) Question answering system and method for structured knowledgebase using deep natural language question analysis
Matci et al. Address standardization using the natural language process for improving geocoding results
WO2021012878A1 (fr) Procédé de traitement de questions et de réponses de graphe de connaissance du domaine médical, appareil, dispositif, et support de stockage
US11720611B2 (en) Entailment knowledge base in natural language processing systems
CN110442840B (zh) 序列标注网络更新方法、电子病历处理方法及相关装置
WO2023029513A1 (fr) Procédé et appareil de reconnaissance d'intention de recherche basée sur l'intelligence artificielle, dispositif et support
CN105210055B (zh) 根据跨语种短语表的断词器
WO2022160614A1 (fr) Procédé et appareil pour construire un diagramme de relations d'entités médicales, procédé et appareil pour un contrôle de qualité d'ordonnance médicale, dispositif et support
US11080615B2 (en) Generating chains of entity mentions
CN112599213B (zh) 一种分类编码确定方法、装置、设备及存储介质
CN113488157B (zh) 智能导诊处理方法、装置、电子设备及存储介质
CN111985241A (zh) 医学信息查询方法、装置、电子设备及介质
CN113724830B (zh) 基于人工智能的用药风险检测方法及相关设备
CA3164921A1 (fr) Extraction de taxinomie non supervisee pour essais cliniques medicaux
CN112149409A (zh) 医疗词云生成方法、装置、计算机设备及存储介质
WO2023178978A1 (fr) Procédé et appareil de révision d'ordonnance basés sur l'intelligence artificielle, dispositif et support
WO2023178979A1 (fr) Procédé et appareil d'étiquetage de question, dispositif électronique et support de stockage
WO2023116572A1 (fr) Procédé de génération de mots ou de phrases et dispositif associé
WO2022227171A1 (fr) Procédé et appareil d'extraction d'informations clés, dispositif électronique et support
CN118051598A (zh) 药品知识问答方法、装置、电子设备及存储介质
CN107688594B (zh) 基于社交信息的风险事件的识别系统及方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18795172

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27/02/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18795172

Country of ref document: EP

Kind code of ref document: A1