WO2021137359A1 - 임상시험 데이터 매칭 방법 및 장치 - Google Patents
임상시험 데이터 매칭 방법 및 장치 Download PDFInfo
- Publication number
- WO2021137359A1 WO2021137359A1 PCT/KR2020/005672 KR2020005672W WO2021137359A1 WO 2021137359 A1 WO2021137359 A1 WO 2021137359A1 KR 2020005672 W KR2020005672 W KR 2020005672W WO 2021137359 A1 WO2021137359 A1 WO 2021137359A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- clinical trial
- data
- trial data
- matching
- similarity
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000009193 crawling Effects 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims description 20
- 239000003814 drug Substances 0.000 claims description 14
- 229940079593 drug Drugs 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 11
- 238000013075 data extraction Methods 0.000 claims description 8
- 238000010998 test method Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 3
- 230000002787 reinforcement Effects 0.000 description 8
- 230000009471 action Effects 0.000 description 6
- 238000011160 research Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007012 clinical effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000144 pharmacologic effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/14—Details of searching files based on file metadata
- G06F16/156—Query results presentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- 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
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
-
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Definitions
- the present invention relates to a clinical trial data matching method and apparatus, and more particularly, to a clinical trial data matching method and apparatus for matching data similar to clinical trial data in a database and providing it to a user.
- Clinical trials are tests conducted on humans to confirm the safety, pharmacokinetics, pharmacological effects, and clinical effects of a drug before developing and marketing a drug. Management of data obtained through clinical trials is an important factor in increasing the reliability and quality of clinical trial data.
- the present invention is intended to solve the above-described problems, and one object is to provide a user with other clinical trial data that matches one clinical trial data.
- Another object of the present invention is to establish a database for clinical trial data by collecting clinical trial data scattered on a plurality of platforms.
- Another object of the present invention is to more accurately measure the similarity between clinical trial data by adding weights to each index in matching clinical trial data.
- the present invention for achieving this object is a method for a server to match clinical trial data according to a degree of similarity, in at least one website including the clinical trial data, the step a of receiving the first clinical trial data, the first 1 Step b of crawling clinical trial data, extracting first valid data and storing it in a database, step c of calculating a similarity between the first valid data and second valid data stored in the database, the similarity is a preset threshold If it is greater than or equal to the value, the first clinical trial data and the second clinical trial data corresponding to the second valid data are determined to be similar, and the d step of matching the first clinical trial data and the second clinical trial data; It is characterized in that it includes an e step of correcting the matching status of the first and second clinical trial data to the completed status.
- the present invention provides an apparatus for matching clinical trial data according to similarity, a data receiving unit for receiving first clinical trial data from at least one website including clinical trial data, and crawling the first clinical trial data, A data extraction unit for extracting and storing the first valid data in a database, calculating the similarity between the first valid data and the second valid data stored in the database, and if the similarity is greater than or equal to a preset threshold, the first clinical trial An operation unit that determines that the test data and the second clinical trial data corresponding to the second valid data are similar, and the second clinical trial data similar to the first clinical trial data are matched, and the first and second clinical trial data It is characterized in that it comprises a data matching unit for changing the matching state of the completed state.
- the user by providing other clinical trial data that matches one clinical trial data, the user can be provided with more various clinical trial data.
- the present invention can collect clinical trial data scattered on a plurality of platforms to build a database for clinical trial data.
- the present invention can more accurately measure the similarity between clinical trial data by adding weights to each index in matching clinical trial data, thereby improving the matching accuracy of clinical trial results.
- FIG. 1 is a configuration diagram showing the configuration of a clinical trial data matching device according to an embodiment of the present invention
- FIG. 2 is a flowchart of a clinical trial data matching method according to an embodiment of the present invention.
- FIG. 3 is a flowchart of a similarity calculation method according to an embodiment of the present invention.
- FIG. 4 is a flowchart of a method for calculating a weight for each field according to an embodiment of the present invention
- 5 to 7 are diagrams illustrating clinical trial data displayed on a display unit according to an embodiment of the present invention.
- each component may be implemented as a hardware processor, respectively, the above components may be integrated into one hardware processor, or the above components may be combined with each other and implemented as a plurality of hardware processors.
- the clinical trial data matching apparatus will include a data receiving unit 110 , a data extracting unit 130 , a calculating unit 150 , a data matching unit 170 , and a display unit 190 .
- the data receiving unit 110 may receive the first clinical trial data from at least one website including the clinical trial data. More specifically, the data receiving unit 110 receives the Ministry of Food and Drug Safety clinical trial approval information from the Ministry of Food and Drug Safety, clinical research registration information from CRIS (Clinical Research Information Service), Clinical Trials.gov (A Service of the US National Institutes of Health). ) to receive global clinical research registration information.
- CRIS Cosmetic Research Information Service
- Clinical Trials.gov A Service of the US National Institutes of Health.
- the data receiving unit 110 may receive the first clinical trial data uploaded to the site regularly or irregularly.
- the data extraction unit 130 may crawl the first clinical trial data to extract the first valid data, and store it in the database.
- the data extraction unit 130 may crawl the first clinical trial data and extract first valid data including title, test stage, medicine, subject's gender, age, test method, test tool, or biological tissue information from the data. .
- the data extraction unit 130 extracts valid data for the test phase, if the value of the test phase does not exist, the live
- the data extraction unit 130 may standardize the first valid data in order to efficiently manage clinical trial data.
- the data extractor 130 may standardize the first valid data using the pre-generated clinical trial terminology database.
- the clinical trial terminology database can improve the unity of clinical trial data by uniformizing other terms with the same meaning, including Korean/English conversion information, synonyms, abbreviations, and key keywords for clinical trial terms.
- the data extraction unit 130 uses a database in which the currently open institution name and researcher information are stored. , researchers, affiliations, and contacts can be standardized.
- the data extraction unit 130 creates an index table using the title, test stage, drug, subject's gender, age, test method, test tool, and biological tissue information as fields, and updates the index table by indexing the first valid data, , will store it in the database.
- the index table is basically stored in the database for efficient management of data stored in the database.
- the data extractor 130 may further store a matching state when updating the index table for the first valid data.
- the matching status may include a matching required status, a matching completed status, and a no matching status.
- the calculator 150 may calculate a first similarity between the first valid data and other second valid data previously stored in the database.
- the calculator 150 may first perform natural language processing on valid data in order to calculate the similarity.
- Natural language processing is a technology that interprets and simulates human language by analyzing human language by a computer such as a computer. It expresses words numerically using methods such as DTM and Word2Vec, and calculates the difference between words using Euclidean distance and cosine similarity to calculate similarity. can be calculated.
- the calculator 150 may calculate a first similarity between field values of the first valid data and the second valid data.
- the calculating unit 150 calculates the first similarity with respect to the field values for the title, test stage, drug, subject's gender, age, test method, test tool, and biological tissue information, respectively.
- the calculating unit 150 follows a conventional method in calculating the first similarity.
- the calculator 150 may calculate the second similarity by applying a weight for each field to the first similarity calculated for each field value in the first and second valid data.
- the weight will be set high in the field values that are important in determining the similarity of clinical trial data. For example, the title of clinical trial data is written based on a specific format, so the type of information included in the title is clear. Since the information is an abbreviation of clinical trial information, the weight for the title can be set the most. have.
- the calculator 150 may use a value preset by the administrator as the weight, or may set the weight through reinforcement learning.
- Reinforcement learning is a method in which an agent defined within a specific environment recognizes the current state and selects an action or action sequence that maximizes a reward among selectable actions.
- the operation unit 150 generates a weight setting environment by using the user's verification information in the matching process of the first similarity to the field value of the valid data corresponding to the clinical trial data that is already matched in the database and the corresponding clinical trial data.
- the operation unit 150 sets the first similarity of the field value of the valid data corresponding to the first clinical trial data as the current state and the weight for each field value as the action, so that the agent responds to the field value. At least one second clinical trial corresponding to the highest similarity or similarity having a value greater than or equal to a preset threshold as a result of calculating the second similarity by applying the weight to the first similarity when a weight that maximizes the reward is selected A reward can be provided to the agent by using the user's verification result for the data.
- the calculating unit 150 may include a model generating unit 151 that generates a reinforcement learning model to perform the above process, a behavior selecting unit 153 , and a reward providing unit 155 .
- the model generator 151 may generate a reinforcement learning model by using a first degree of similarity to a field value of at least one valid data corresponding to the clinical trial data stored in the database.
- the model generator 151 may have the highest similarity with the reference first clinical trial data or a preset threshold according to a second degree of similarity generated by applying a weight for each field to a first degree of similarity with respect to a field value of valid data.
- a reinforcement learning model may be generated through compensation according to the user's verification result for the second clinical trial data having a similarity greater than or equal to the value.
- the model generation unit 151 may reinforce the reinforcement learning model by repeatedly learning so that the action selection unit 153 can set a weight that maximizes the reward.
- the action selector 153 may set a weight for each field that maximizes the reward.
- the reward providing unit 155 calculates the second similarity by reflecting the weight for each field set in the first similarity of the field value of the first valid data of the first clinical trial data in the behavior selection unit 153, and the second similarity Compensation may be calculated using the user's verification result for at least one second clinical trial data extracted through . Accordingly, the reward providing unit 155 will calculate a reward based on the user's feedback.
- the data matching unit 170 may match the second clinical trial data determined to be similar to the first clinical trial data.
- the data matching unit 170 will change the matching state of the first and second clinical trial data to the completed state.
- the display unit 190 will display the first clinical trial data and at least one second clinical trial data matched with the first clinical trial data on the screen.
- the display unit 190 may display the first and second clinical trial data as shown in FIGS. 5 to 7 .
- FIGS. 2 to 4 a clinical trial data matching method will be described using FIGS. 2 to 4 .
- the detailed embodiment overlapping with the aforementioned clinical trial data matching apparatus may be omitted.
- the clinical trial data matching device which is the subject of the clinical trial data matching method, may be implemented as a server, and hereinafter, it will be referred to as a server for convenience of description.
- the server may receive the first clinical trial data from at least one website including the clinical trial data. More specifically, the data receiving unit 110 receives the Ministry of Food and Drug Safety clinical trial approval information from the Ministry of Food and Drug Safety, clinical research registration information from CRIS (Clinical Research Information Service), Clinical Trials.gov (A Service of the US National Institutes of Health). ) to receive global clinical research registration information.
- CRIS Cosmetic Research Information Service
- Clinical Trials.gov A Service of the US National Institutes of Health.
- the server may crawl the first clinical trial data to extract the first valid data, and store it in the database.
- the server may crawl the first clinical trial data to extract first valid data including title, test phase, drug, subject's gender, age, test method, test tool, or biological tissue information from the data.
- the server may standardize the first valid data in order to efficiently perform clinical trial data management.
- the server may standardize the first valid data using the pre-generated clinical trial terminology database.
- the clinical trial terminology database can improve the unity of clinical trial data by uniformizing other terms with the same meaning, including Korean/English conversion information, synonyms, abbreviations, and key keywords for clinical trial terms.
- the server uses the database that stores the currently open institution name and researcher information to determine the institution, researcher, affiliation, Contacts can be standardized.
- the server creates an index table using title, test phase, drug, subject gender, age, test method, test tool, and biological tissue information as fields, updates the index table by indexing the first valid data, and stores it in the database.
- the index table is basically stored in the database for efficient management of data stored in the database.
- the server may further store the matching state when updating the index table for the first valid data.
- the matching status may include a matching required status, a matching completed status, and a no matching status.
- the server may calculate a first similarity between the first valid data and other second valid data pre-stored in the database.
- the server may first perform natural language processing ( S310 ) on valid data in order to calculate the first similarity.
- the server may calculate a first similarity between field values of the first valid data and the second valid data.
- the server will calculate the similarity for field values for title, test phase, drug, subject's gender, age, test method, test tool, and biological tissue information, respectively.
- the server may follow a conventional method in calculating the similarity.
- the server may calculate the second similarity by applying a weight for each field to the first similarity calculated for each field value in the first and second valid data.
- the weight will be set high in the field values that are important in determining the similarity of clinical trial data.
- step 331 the server creates a weight setting environment using the first similarity to the field value of the valid data corresponding to the already matched clinical trial data stored in the database and the user's verification information in the matching process of the clinical trial data. can do.
- the server may generate the reinforcement learning model using the first similarity to the field value of at least one valid data corresponding to the clinical trial data stored in the database.
- the server uses the second degree of similarity calculated when a weight for each field is applied to the first degree of similarity to the field value of the valid data, has the highest degree of similarity with the first clinical trial data, which is the standard, or the degree of similarity above a preset threshold
- a reinforcement learning model can be created through compensation according to the user's verification result for the second clinical trial data having .
- the server may set a weight for each field that maximizes the reward.
- step 337 the server calculates a second degree of similarity by reflecting the set weight for each field in the first degree of similarity of the field value of the first valid data of the first clinical trial data, and at least one second degree of similarity extracted through the second degree of similarity is calculated.
- 2 Compensation can be calculated using the user's verification results for clinical trial data.
- the server may calculate the second similarity by setting a weight for each field that can receive the highest reward.
- the server will match the second clinical trial data determined to be similar to the first clinical trial data, and change the matching state of the first and second clinical trial data to a complete state (S500). If the second clinical trial data matching the first clinical trial data exists, the server changes the matching state of the first and second clinical trial data to the matching complete state, and if the second clinical trial data does not exist, the first clinical trial data It will change the matching status of the test data to no matching status.
- the server transmits a verification request signal for the first and second clinical trial data in the matching completion state to at least one manager terminal, and sends a button such as confirming/cancel matching with the first and second clinical test data to the manager terminal display so that the user can more easily select the verification result.
- the server may add it to the first and second clinical trial data.
- step 600 the server will display the first clinical trial data, and at least one second clinical trial data matched with the first clinical trial data on the screen.
Abstract
Description
Claims (6)
- 서버가 임상시험 데이터를 유사도에 따라 매칭하는 방법에 있어서,임상시험 데이터가 포함된 적어도 하나의 웹 사이트에서, 제1 임상시험 데이터를 수신하는 a 단계;상기 제1 임상시험 데이터를 크롤링하여 제1 유효 데이터를 추출하여 데이터베이스에 저장하는 b 단계;상기 제1 유효 데이터와 상기 데이터베이스에 저장된 제2 유효 데이터 사이의 유사도를 연산하는 c 단계;상기 유사도가 기 설정된 임계 값 이상이면, 상기 제1 임상시험 데이터와 상기 제2 유효 데이터에 대응하는 제2 임상시험 데이터가 유사하다고 판단하여 상기 제1 임상시험 데이터와 상기 제2 임상시험 데이터를 매칭하는 d 단계; 및상기 제1 및 제2 임상시험 데이터의 매칭 상태를 완료 상태로 수정하는 e 단계를 포함하는 임상시험 데이터 매칭 방법.
- 제1항에 있어서,상기 b 단계는,상기 제1 임상시험 데이터에서 타이틀, 시험 단계, 의약품, 피험자 성별, 나이, 시험 방식, 시험 도구 또는 생체조직 중 적어도 하나를 크롤링하여 제1 유효 데이터를 추출하는 단계;상기 크롤링 된 데이터를 인덱싱하여 인덱스 테이블을 업데이트하고, 데이터베이스에 저장하는 단계를 포함하는 임상시험 데이터 매칭 방법.
- 제2항에 있어서,상기 c 단계는,상기 제1 및 제2 유효 데이터 간의 제1 유사도와, 상기 인덱스 테이블의 필드 각각에 기 부여된 가중치를 적용하여 상기 제1 및 제2 유효 데이터의 제2 유사도를 연산하는 임상시험 데이터 매칭 방법.
- 제1항에 있어서,상기 제1 유효 데이터는 상기 매칭 상태를 더 포함하여,상기 e 단계에서, 상기 매칭 상태를 완료 상태로 변경하되,상기 매칭 상태는 매칭 필요 상태, 매칭 완료 상태, 매칭 없음 상태를 포함하는 임상시험 데이터 매칭 방법.
- 제1항에 있어서,상기 매칭 완료 상태의 제1 및 제2 임상시험 데이터와 검증 요청 신호를 적어도 하나의 관리자 단말에 전송하는 단계;상기 관리자 단말로부터 제1 및 제2 임상시험 데이터의 검증 결과를 수신하는 단계를 더 포함하는 임상시험 데이터 매칭 방법.
- 임상시험 데이터를 유사도에 따라 매칭하는 장치에 있어서,임상시험 데이터가 포함된 적어도 하나의 웹 사이트에서, 제1 임상시험 데이터를 수신하는 데이터 수신부;상기 제1 임상시험 데이터를 크롤링하여 제1 유효 데이터를 추출하여 데이터베이스에 저장하는 데이터 추출부;상기 제1 유효 데이터와 상기 데이터베이스에 저장된 제2 유효 데이터 사이의 유사도를 연산하고, 상기 유사도가 기 설정된 임계 값 이상이면, 상기 제1 임상시험 데이터와 상기 제2 유효 데이터에 대응하는 제2 임상시험 데이터가 유사하다고 판단하는 연산부; 및상기 제1 임상시험 데이터와 유사한 상기 제2 임상시험 데이터를 매칭하며, 상기 제1 및 제2 임상시험 데이터의 매칭 상태를 완료 상태로 변경하는 데이터 매칭부를 포함하는 임상시험 데이터 매칭 장치.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020190177425A KR20210084909A (ko) | 2019-12-30 | 2019-12-30 | 임상시험 데이터 매칭 방법 및 장치 |
KR10-2019-0177425 | 2019-12-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021137359A1 true WO2021137359A1 (ko) | 2021-07-08 |
Family
ID=76686601
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2020/005672 WO2021137359A1 (ko) | 2019-12-30 | 2020-04-29 | 임상시험 데이터 매칭 방법 및 장치 |
Country Status (2)
Country | Link |
---|---|
KR (2) | KR20210084909A (ko) |
WO (1) | WO2021137359A1 (ko) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20230100462A (ko) * | 2021-12-28 | 2023-07-05 | (주)메디아이플러스 | 다국가 임상데이터 표준화 방법 및 장치 |
KR102464893B1 (ko) * | 2022-06-03 | 2022-11-09 | 주식회사 클래스액트 | 임상 참여 조건의 정형화를 위한 데이터 파이프라인 처리 방법 |
KR102625111B1 (ko) * | 2023-04-18 | 2024-01-15 | 주식회사 티지 | 다단계 개체분리식 애완동물 의약품 임상시험 온라인 자동화 시스템 및 그 동작 방법 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090198676A1 (en) * | 2006-06-01 | 2009-08-06 | Microsoft Corporation | Indexing Documents for Information Retrieval |
KR101609716B1 (ko) * | 2014-11-28 | 2016-04-06 | 주식회사 씨알에스큐브 | 통합 데이터 허브 기반 의료 데이터 수집 서비스 제공 방법 및 시스템 |
KR20180013095A (ko) * | 2016-07-28 | 2018-02-07 | 건국대학교 산학협력단 | 유사 텍스트를 포함한 웹 페이지 수집을 위한 포털 사이트 기반 웹 크롤링 방법 및 장치 |
KR20190075067A (ko) * | 2016-09-22 | 2019-06-28 | 엔퍼런스, 인크. | 의미 정보의 시각화 및 생명 과학 엔티티들 사이의 현저한 연관을 나타내는 임시 신호의 추론을 위한 시스템, 방법 및 컴퓨터 판독 가능 매체 |
KR102035658B1 (ko) * | 2019-04-01 | 2019-10-23 | 한국과학기술정보연구원 | 신약 재창출 후보 추천 시스템 및 이 시스템의 각 기능을 실행시키기 위해 매체에 저장된 컴퓨터 프로그램 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20170110244A (ko) * | 2016-03-23 | 2017-10-11 | 황규민 | 다수의 의료기관간에 협업체계 구축을 위한 웹기반의 폐암환자 임상연구 데이터 관리시스템 및 그 제어방법 |
KR102070030B1 (ko) * | 2018-02-05 | 2020-03-02 | 재단법인 전통천연물기반 유전자동의보감 사업단 | 임상시험을 위한 데이터 관리 방법 및 장치 |
KR101953275B1 (ko) * | 2018-04-03 | 2019-05-22 | 사회복지법인 삼성생명공익재단 | 임상 연구 데이터 제공 방법 및 시스템 |
-
2019
- 2019-12-30 KR KR1020190177425A patent/KR20210084909A/ko not_active IP Right Cessation
-
2020
- 2020-04-29 WO PCT/KR2020/005672 patent/WO2021137359A1/ko active Application Filing
-
2022
- 2022-05-18 KR KR1020220060807A patent/KR102521961B1/ko active IP Right Grant
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090198676A1 (en) * | 2006-06-01 | 2009-08-06 | Microsoft Corporation | Indexing Documents for Information Retrieval |
KR101609716B1 (ko) * | 2014-11-28 | 2016-04-06 | 주식회사 씨알에스큐브 | 통합 데이터 허브 기반 의료 데이터 수집 서비스 제공 방법 및 시스템 |
KR20180013095A (ko) * | 2016-07-28 | 2018-02-07 | 건국대학교 산학협력단 | 유사 텍스트를 포함한 웹 페이지 수집을 위한 포털 사이트 기반 웹 크롤링 방법 및 장치 |
KR20190075067A (ko) * | 2016-09-22 | 2019-06-28 | 엔퍼런스, 인크. | 의미 정보의 시각화 및 생명 과학 엔티티들 사이의 현저한 연관을 나타내는 임시 신호의 추론을 위한 시스템, 방법 및 컴퓨터 판독 가능 매체 |
KR102035658B1 (ko) * | 2019-04-01 | 2019-10-23 | 한국과학기술정보연구원 | 신약 재창출 후보 추천 시스템 및 이 시스템의 각 기능을 실행시키기 위해 매체에 저장된 컴퓨터 프로그램 |
Also Published As
Publication number | Publication date |
---|---|
KR102521961B1 (ko) | 2023-04-14 |
KR20220070398A (ko) | 2022-05-31 |
KR20210084909A (ko) | 2021-07-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021137359A1 (ko) | 임상시험 데이터 매칭 방법 및 장치 | |
CN110837550B (zh) | 基于知识图谱的问答方法、装置、电子设备及存储介质 | |
Romney et al. | Cultural universals: Measuring the semantic structure of emotion terms in English and Japanese | |
He et al. | Combining evidence for automatic web session identification | |
Kernighan et al. | A spelling correction program based on a noisy channel model | |
Doane et al. | Expertise in a computer operating system: Conceptualization and performance | |
KR100919912B1 (ko) | 의미론적 지식의 평가, 교육, 및 습득을 위한 시스템 및방법 | |
US20080208836A1 (en) | Regression framework for learning ranking functions using relative preferences | |
Feinberg et al. | Guidelines for interpreting and reporting subscores | |
US20210406687A1 (en) | Method for predicting attribute of target object based on machine learning and related device | |
Vu et al. | Linguistically inspired roadmap for building biologically reliable protein language models | |
CN114676233A (zh) | 基于骨骼肌知识图谱的医疗自动问答方法 | |
JP6908977B2 (ja) | 医療情報処理システム、医療情報処理装置及び医療情報処理方法 | |
CN112836019B (zh) | 公共医疗卫生命名实体识别与实体链接方法、装置、电子设备及存储介质 | |
Woolley et al. | Application of artificial intelligence to systematics: SYSTEX—a prototype expert system for species identification | |
CN117407682A (zh) | 医学模型评估方法、装置、电子设备和存储介质 | |
Chen et al. | Constructing a web-based employee training expert system with data mining approach | |
WO2014021656A1 (ko) | 패스웨이 구축 시스템 및 방법 | |
WO2017122872A1 (ko) | 전자 출판물에 대한 정보를 생성하는 장치 및 방법 | |
JP7184093B2 (ja) | 熟練指数提供装置、熟練指数提供方法、及びプログラム | |
JP7230622B2 (ja) | 指標値付与装置、指標値付与方法及びプログラム | |
Mei et al. | An XML plagiarism detection model for C program | |
Korabik et al. | 11 Best Practices in Scale Translation and Establishing Measurement Equivalence | |
Wennerberg | Aligning medical domain ontologies for clinical query extraction | |
Van Oostendorp et al. | Navigating in a virtual environment with model-generated support |
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: 20909850 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20909850 Country of ref document: EP Kind code of ref document: A1 |
|
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 16/01/2023) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20909850 Country of ref document: EP Kind code of ref document: A1 |