CN113990473A - Medical equipment operation and maintenance information collecting and analyzing system and using method thereof - Google Patents

Medical equipment operation and maintenance information collecting and analyzing system and using method thereof Download PDF

Info

Publication number
CN113990473A
CN113990473A CN202111260955.7A CN202111260955A CN113990473A CN 113990473 A CN113990473 A CN 113990473A CN 202111260955 A CN202111260955 A CN 202111260955A CN 113990473 A CN113990473 A CN 113990473A
Authority
CN
China
Prior art keywords
entity
information
vector
field
maintenance
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN202111260955.7A
Other languages
Chinese (zh)
Other versions
CN113990473B (en
Inventor
许仁祥
张智源
阳颖
范昊
张超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Kunya Medical Equipment Co ltd
Original Assignee
Shanghai Kunya Medical Equipment Co ltd
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 Shanghai Kunya Medical Equipment Co ltd filed Critical Shanghai Kunya Medical Equipment Co ltd
Priority to CN202111260955.7A priority Critical patent/CN113990473B/en
Publication of CN113990473A publication Critical patent/CN113990473A/en
Application granted granted Critical
Publication of CN113990473B publication Critical patent/CN113990473B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/242—Query formulation
    • G06F16/2433—Query languages
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Databases & Information Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention relates to a medical equipment operation and maintenance information collecting and analyzing system and a using method thereof, belonging to the technical field of medical equipment operation and maintenance.

Description

Medical equipment operation and maintenance information collecting and analyzing system and using method thereof
Technical Field
The invention relates to the field of operation and maintenance of medical equipment, in particular to a medical equipment operation and maintenance information collecting and analyzing system and a using method thereof.
Background
In a traditional operation and maintenance mode of medical equipment, an operation and maintenance manager regularly inspects the medical equipment, records various information of the medical equipment, including operation and maintenance personnel information, equipment parameters, fault conditions and other conditions needing to be recorded in an operation and maintenance information table made of paper, and the operation and maintenance information table is edited into a book and placed in a special document management place.
In recent years, medical institutions have become larger in scale, more and more medical devices are managed by the medical institutions, the management difficulty is increased, the more difficult and more suitable the traditional way of collecting medical device data by means of paper is to meet the needs of operation and maintenance of medical devices, the medical institutions have turned to use an operation and maintenance management way based on informatization, and operation and maintenance data of medical devices can be directly stored in a database through the operation and maintenance way of the informatization medical devices for relevant personnel to perform various processing and analysis.
However, the operation and maintenance data collection and analysis of new and old medical devices are still in the handover period, although the new medical devices provide various interfaces and transmission protocols to support the operation and maintenance data collection and analysis, many old medical devices still in use lack relevant support, and the proportion of medical devices is also quite large, and for the proportion of medical devices, the traditional operation and maintenance method relying on paper records has to be adopted to collect the operation and maintenance data.
The granularity of the existing medical equipment operation and maintenance data is very small, and the existing medical equipment operation and maintenance data is stored in a database in a structured form. In addition, most data are stored in the paper document, the data in the paper document often exist in a natural language form and are unstructured, and in order to fully mine the value of the operation and maintenance data of the medical equipment and improve the operation and maintenance efficiency of the medical equipment, the operation and maintenance data of the medical equipment stored in the paper document needs to be structured so as to be fused in an existing operation and maintenance database.
Disclosure of Invention
In view of the problems in the management of the operation and maintenance data of the medical equipment, there is a need to design a new operation and maintenance method and system for the medical equipment, which provides an algorithm for collecting and structuring the operation and maintenance data of the medical equipment recorded in paper so as to be merged into the existing operation and maintenance database of the medical equipment, and uses a BI tool to automatically process and analyze the data, thereby realizing the uniform analysis and management of the operation and maintenance data of the medical equipment.
The application provides a medical equipment operation and maintenance information collection analysis system, the system includes:
the data extraction unit extracts the operation and maintenance data of the medical equipment according to the following steps:
acquiring fields in an existing medical equipment operation and maintenance database, vectorizing the fields, and acquiring field vectors k representing the fieldsj；
Collecting paper document picture information, and extracting character information in the picture;
processing the extracted character information to obtain the processed character information, wherein the processing comprises punctuation removal and stop words;
extracting the entity of the processed text information, vectorizing the entity to obtain the vector w representing the entityi；
The data processing unit is used for processing the operation and maintenance data of the medical equipment according to the following steps: inputting the entity vector into a trained LSTM network to obtain the front and back hidden state vectors of the entity
Figure BDA0003325726760000021
And
Figure BDA0003325726760000022
acquiring a first information vector upsilon of an entity according to front and back hidden state vectors of the entityi；
The first information vector is calculated according to the following formula:
Figure BDA0003325726760000023
obtaining second information of the entity according to the first information vectorVector Vi；
The second information vector is calculated according to the following formula:
Figure BDA0003325726760000024
for the second information vector and the field vector kjFusing to obtain a third information vector of the entity;
the third information vector is obtained according to the following formula: GVi+kj；
Decoding the third information vector by using a SOFTMAX decoder to obtain field distribution probability corresponding to the third information vector;
the SOFTMAX decoding specifically comprises:
Figure BDA0003325726760000031
wherein, P, Q, omega and G are the trained weight matrix, b is the trained offset vector, I is the unit matrix, and T is the number of the field vectors;
distributing probability P according to the corresponding field of the third information vectori，jAcquiring a field corresponding to the entity, specifically: determining the field corresponding to the ith entity as pi，jThe field corresponding to the maximum time;
inserting the entity into a database according to the field corresponding to the entity;
the report generation unit generates a data report according to the following steps:
importing the data in the database into a BI engine, and automatically generating an analysis report of the operation and maintenance data of the medical equipment;
the BI engine is Tableau Desktop;
a medical equipment operation and maintenance information collection and analysis method comprises the following steps:
acquiring fields in an existing medical equipment operation and maintenance database, vectorizing the fields, and acquiring field vectors k representing the fieldsj；
Collecting paper document picture information, and extracting character information in the picture;
processing the extracted character information to obtain the processed character information, wherein the processing comprises punctuation removal and stop words;
extracting the entity of the processed text information, vectorizing the entity to obtain the vector w representing the entityi；
Inputting the entity vector into a trained LSTM network to obtain the front and back hidden state vectors of the entity
Figure BDA0003325726760000032
And
Figure BDA0003325726760000033
obtaining a first information vector v of an entity according to front and back hidden state vectors of the entityi；
The first information vector is calculated according to the following formula:
Figure BDA0003325726760000041
obtaining a second information vector V of the entity according to the first information vectori；
The second information vector is calculated according to the following formula:
Figure BDA0003325726760000042
for the second information vector and the field vector kjFusing to obtain a third information vector of the entity;
the third information vector is obtained according to the following formula: GVi+kj；
Decoding the third information vector by using a decoder to obtain the field distribution probability corresponding to the third information vector;
the decoding specifically comprises:
Figure BDA0003325726760000043
wherein, P, Q, omega are the trained weight matrix, G is the trained coefficient matrix, b is the trained offset vector, I is the unit matrix, and T is the number of the field vectors;
according to the field distribution probability p corresponding to the third information vectori，jAcquiring a field corresponding to the entity, specifically: determining the field corresponding to the ith entity as pi，jThe field corresponding to the maximum time;
inserting the entity into a database according to the field corresponding to the entity;
importing the data in the database into a BI engine, and automatically generating an analysis report of the operation and maintenance data of the medical equipment;
the BI engine is Tableau Desktop;
drawings
FIG. 1 is a block diagram of a medical equipment operation and maintenance information collecting and analyzing system according to an embodiment of the present application;
fig. 2 is a medical device operation and maintenance information database in an embodiment of the present application;
Detailed Description
In order to make the invention clearer, the invention is further explained below with reference to the drawings and examples. It is to be understood that the description herein is for purposes of illustration only and is not intended to limit the invention to the particular forms disclosed.
The operation and maintenance data of the medical equipment recorded on the paper often exist in a natural language form, and in order to manage and analyze the data in a structured form, the data needs to be extracted and analyzed. The system and the method aim at solving the problem that the existing medical equipment operation and maintenance data are recorded in a paper document in a large quantity and need to be extracted into a database.
The system provided by the application performs the following steps:
as shown in fig. 2, the following fields exist in the operation and maintenance database of the medical device in the present application: maintence _ date, maintence _ person, maintence _ device _ id, maintence _ device _ name, maintence _ device _ status, maintence _ device _ error _ code, maintence _ device _ error _ info;
vectorizing the field to obtain a field vector k representing the fieldjJ denotes a few fields, e.g. k1Vector representation, k, representing the first field maintence _ date2A vector representation representing a second field maintence _ person;
for example, the operation and maintenance information in the paper document is: "3/23/2021", Li Star test omitted the NMR instrument with the equipment number 37545, and the remote transfer was good. ";
collecting paper document pictures;
the character information of 3 months and 23 days in 2021 in the picture is extracted, and the nuclear magnetic resonance spectrometer with the equipment number of 37545 is saved in Lixing detection, so that the remote transfer condition is good. ";
processing the extracted character information to obtain processed character information, wherein the processing comprises punctuation removal and stop words, and the obtained processed character information is that the long-distance rotation condition of a nuclear magnetic resonance instrument with the equipment number of 37545 is good in Lexing test at 3 months and 23 days in 2021;
and performing entity extraction on the processed text information to obtain an entity: 23/3/2021, lixing, 37545, nmr, good;
vectorizing the entity to obtain a vector w representing the entityi；
Inputting the entity vector into a trained LSTM network to obtain the front and back hidden state vectors of the entity
Figure BDA0003325726760000061
Obtaining a first information vector v of an entity according to front and back hidden state vectors of the entityi；
The first information vector is calculated according to the following formula:
Figure BDA0003325726760000062
obtaining a second information vector V of the entity according to the first information vectori；
The second information vector is calculated according to the following formula:
Figure BDA0003325726760000063
for the second information vector and the field vector kjFusing to obtain a third information vector of the entity;
the third information vector is obtained according to the following formula: GVi+kj；
Circularly decoding the third information vector by using a decoder to obtain the field distribution probability corresponding to the third information vector;
the decoding specifically comprises:
Figure BDA0003325726760000064
wherein P, Q, ω are the trained weight matrix, G is the trained coefficient matrix, b is the trained bias vector, I is the identity matrix, T is the number of field vectors, in this example 7;
according to the field distribution probability p corresponding to the third information vectori，jAcquiring a field corresponding to the entity, specifically: determining the field corresponding to the ith entity as pi，jThe field corresponding to the maximum time;
according to the steps, a field corresponding to '3/23/2021' is maintence _ date, 'a field corresponding to Lixing' is maintence _ person, 'a field corresponding to 37545' is maintence _ device _ id, 'a field corresponding to a nuclear magnetic resonance instrument' is maintence _ device _ name, 'a field corresponding to good' is maintence _ device _ status;
inserting the entity into a database according to the field corresponding to the entity, specifically using the following SQ L statement: INSERT INTO DeviceMaintance (maintence _ date, maintence _ person, maintence _ device _ id, maintence _ device _ name, maintence _ devi ce _ status) VALUES ("3/23/2021", "Lixing", "37545", "NMR", "good")
Importing data in DeviceMaintenance into a BI engine, and automatically generating an analysis report of medical equipment operation and maintenance data;
the BI engine is Tableau Desktop.

Claims (6)

1. A medical device operation and maintenance information collection and analysis system, the system comprising:
the data extraction unit extracts the operation and maintenance data of the medical equipment according to the following steps:
acquiring fields in an existing medical equipment operation and maintenance database, vectorizing the fields, and acquiring field vectors k representing the fieldsj；
Collecting paper document picture information, and extracting character information in the picture;
processing the extracted character information to obtain the processed character information, wherein the processing comprises punctuation removal and stop words;
extracting the entity of the processed text information, vectorizing the entity to obtain the vector w representing the entityi；
The data processing unit is used for processing the operation and maintenance data of the medical equipment according to the following steps: inputting the entity vector into a trained LSTM network to obtain the front and back hidden state vectors of the entity
Figure FDA0003325726750000011
And
Figure FDA0003325726750000012
obtaining a first information vector v of an entity according to front and back hidden state vectors of the entityi；
Obtaining a second information vector V of the entity according to the first information vectori；
For the second information vector and the field vector kjFusing to obtain a third information vector of the entity;
decoding the third information vector by using a decoder to obtain the field distribution probability corresponding to the third information vector;
acquiring a field corresponding to the entity according to the field distribution probability corresponding to the third information vector;
inserting the entity into a database according to the field corresponding to the entity;
the report generation unit is used for generating a data report, wherein the report field is a field in the operation and maintenance database of the existing medical equipment;
and importing the data in the database into a BI engine, and automatically generating an analysis report of the operation and maintenance data of the medical equipment.
2. The medical device operation and maintenance information collection and analysis system of claim 1, wherein: the first information vector is calculated according to the following formula:
Figure FDA0003325726750000013
the second information vector is calculated according to the following formula:
Figure FDA0003325726750000014
the pair of second information vector and field vector kjFusing to obtain the third information vector of the entity with a specific formula of GVi+kjWhere P, Q, ω are the weight matrices that have been trained, b is the bias vectors that have been trained, and I is the identity matrix.
3. The medical device operation and maintenance information collection and analysis system of claim 2, wherein: the decoder is specifically:
Figure FDA0003325726750000015
pi，jfor the field corresponding to the determined third information vectorProbabilities are assigned, where G is the coefficient matrix that has been trained and T is the number of fields.
4. The medical device operation and maintenance information collection and analysis system of claim 3, wherein: the field corresponding to the obtained entity is determined to be p according to the field distribution probability corresponding to the third information vectori，jThe field to which it corresponds when maximum.
5. The medical device operation and maintenance information collection and analysis system of claim 4, wherein: the BI engine is Tableau Desktop.
6. A medical equipment operation and maintenance information collection and analysis method comprises the following steps:
acquiring fields in an existing medical equipment operation and maintenance database, vectorizing the fields, and acquiring field vectors k representing the fieldsj；
Collecting paper document picture information, and extracting character information in the picture;
processing the extracted character information to obtain the processed character information, wherein the processing comprises punctuation removal and stop words;
extracting the entity of the processed text information, vectorizing the entity to obtain the vector w representing the entityi；
Inputting the entity vector into a trained LSTM network to obtain the front and back hidden state vectors of the entity
Figure FDA0003325726750000021
And
Figure FDA0003325726750000022
obtaining a first information vector v of an entity according to front and back hidden state vectors of the entityi；
The first information vector is calculated according to the following formula:
Figure FDA0003325726750000023
acquiring a second information vector Vi of the entity according to the first information vector;
the second information vector is calculated according to the following formula:
Figure FDA0003325726750000024
for the second information vector and the field vector kjFusing to obtain a third information vector of the entity;
the third information vector is obtained according to the following formula: GVi+kj；
Decoding the third information vector by using a decoder to obtain the field distribution probability corresponding to the third information vector;
the decoding process specifically comprises:
Figure FDA0003325726750000025
in the above formulas, P, Q, ω, and G are the trained weight matrices, b is the trained offset vector, I is the identity matrix, and T is the number of field vectors;
according to the field distribution probability p corresponding to the third information vectori，jAcquiring a field corresponding to the entity, specifically: determining that a field corresponding to an entity is pi，jThe field corresponding to the maximum time;
inserting the entity into a database according to the field corresponding to the entity;
importing the data in the database into a BI engine, and automatically generating an analysis report of the operation and maintenance data of the medical equipment;
the BI engine is Tableau Desktop.
CN202111260955.7A 2021-10-28 2021-10-28 Medical equipment operation and maintenance information collecting and analyzing system and using method thereof Active CN113990473B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111260955.7A CN113990473B (en) 2021-10-28 2021-10-28 Medical equipment operation and maintenance information collecting and analyzing system and using method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111260955.7A CN113990473B (en) 2021-10-28 2021-10-28 Medical equipment operation and maintenance information collecting and analyzing system and using method thereof

Publications (2)

Publication Number Publication Date
CN113990473A true CN113990473A (en) 2022-01-28
CN113990473B CN113990473B (en) 2022-09-30

Family

ID=79743144

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111260955.7A Active CN113990473B (en) 2021-10-28 2021-10-28 Medical equipment operation and maintenance information collecting and analyzing system and using method thereof

Country Status (1)

Country Link
CN (1) CN113990473B (en)

Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090327321A1 (en) * 2008-06-26 2009-12-31 Microsoft Corporation Document templates for schema-based data transfer into and out of a data-based application
CN205901796U (en) * 2016-05-23 2017-01-18 上海昆亚医疗器械股份有限公司 Medical equipment acquisition terminal
CN108062973A (en) * 2017-11-30 2018-05-22 江西洪都航空工业集团有限责任公司 A kind of health care data analysing method
US20180189572A1 (en) * 2016-12-30 2018-07-05 Mitsubishi Electric Research Laboratories, Inc. Method and System for Multi-Modal Fusion Model
US20190370394A1 (en) * 2018-05-31 2019-12-05 Fmr Llc Automated computer text classification and routing using artificial intelligence transfer learning
US20200042583A1 (en) * 2017-11-14 2020-02-06 Tencent Technology (Shenzhen) Company Limited Summary obtaining method, apparatus, and device, and computer-readable storage medium
US20200065374A1 (en) * 2018-08-23 2020-02-27 Shenzhen Keya Medical Technology Corporation Method and system for joint named entity recognition and relation extraction using convolutional neural network
CN111026799A (en) * 2019-12-06 2020-04-17 安翰科技(武汉)股份有限公司 Capsule endoscopy report text structuring method, apparatus and medium
CN111078825A (en) * 2019-12-20 2020-04-28 北京百度网讯科技有限公司 Structured processing method, structured processing device, computer equipment and medium
US20200218744A1 (en) * 2019-01-07 2020-07-09 International Business Machines Corporation Extracting entity relations from semi-structured information
US20200242444A1 (en) * 2019-01-30 2020-07-30 Baidu Usa Llc Knowledge-graph-embedding-based question answering
US20200250417A1 (en) * 2019-02-01 2020-08-06 Intuit Inc. System and method for information extraction with character level features
CN111522918A (en) * 2020-04-24 2020-08-11 天津易维数科信息科技有限公司 Data aggregation method and device, electronic equipment and computer readable storage medium
CN111831908A (en) * 2020-06-24 2020-10-27 平安科技（深圳）有限公司 Medical field knowledge graph construction method, device, equipment and storage medium
US20200410721A1 (en) * 2018-03-16 2020-12-31 Koninklijke Philips N.V. Method and system for generating medical image based on textual data in medical report
CN112200198A (en) * 2020-07-31 2021-01-08 厦门星宸科技有限公司 Target data feature extraction method and device and storage medium
CN112417092A (en) * 2020-11-11 2021-02-26 南京邮电大学 Intelligent text automatic generation system based on deep learning and implementation method thereof
JP2021033994A (en) * 2019-08-20 2021-03-01 株式会社Ｎｔｔドコモ Text processing method, apparatus, device and computer readable storage medium
CN112883153A (en) * 2021-01-28 2021-06-01 北京联合大学 Information-enhanced BERT-based relationship classification method and device
WO2021174774A1 (en) * 2020-07-30 2021-09-10 平安科技（深圳）有限公司 Neural network relationship extraction method, computer device, and readable storage medium

Patent Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090327321A1 (en) * 2008-06-26 2009-12-31 Microsoft Corporation Document templates for schema-based data transfer into and out of a data-based application
CN205901796U (en) * 2016-05-23 2017-01-18 上海昆亚医疗器械股份有限公司 Medical equipment acquisition terminal
US20180189572A1 (en) * 2016-12-30 2018-07-05 Mitsubishi Electric Research Laboratories, Inc. Method and System for Multi-Modal Fusion Model
US20200042583A1 (en) * 2017-11-14 2020-02-06 Tencent Technology (Shenzhen) Company Limited Summary obtaining method, apparatus, and device, and computer-readable storage medium
CN108062973A (en) * 2017-11-30 2018-05-22 江西洪都航空工业集团有限责任公司 A kind of health care data analysing method
US20200410721A1 (en) * 2018-03-16 2020-12-31 Koninklijke Philips N.V. Method and system for generating medical image based on textual data in medical report
US20190370394A1 (en) * 2018-05-31 2019-12-05 Fmr Llc Automated computer text classification and routing using artificial intelligence transfer learning
US20200065374A1 (en) * 2018-08-23 2020-02-27 Shenzhen Keya Medical Technology Corporation Method and system for joint named entity recognition and relation extraction using convolutional neural network
US20200218744A1 (en) * 2019-01-07 2020-07-09 International Business Machines Corporation Extracting entity relations from semi-structured information
US20200242444A1 (en) * 2019-01-30 2020-07-30 Baidu Usa Llc Knowledge-graph-embedding-based question answering
US20200250417A1 (en) * 2019-02-01 2020-08-06 Intuit Inc. System and method for information extraction with character level features
JP2021033994A (en) * 2019-08-20 2021-03-01 株式会社Ｎｔｔドコモ Text processing method, apparatus, device and computer readable storage medium
CN111026799A (en) * 2019-12-06 2020-04-17 安翰科技(武汉)股份有限公司 Capsule endoscopy report text structuring method, apparatus and medium
CN111078825A (en) * 2019-12-20 2020-04-28 北京百度网讯科技有限公司 Structured processing method, structured processing device, computer equipment and medium
CN111522918A (en) * 2020-04-24 2020-08-11 天津易维数科信息科技有限公司 Data aggregation method and device, electronic equipment and computer readable storage medium
CN111831908A (en) * 2020-06-24 2020-10-27 平安科技（深圳）有限公司 Medical field knowledge graph construction method, device, equipment and storage medium
WO2021174774A1 (en) * 2020-07-30 2021-09-10 平安科技（深圳）有限公司 Neural network relationship extraction method, computer device, and readable storage medium
CN112200198A (en) * 2020-07-31 2021-01-08 厦门星宸科技有限公司 Target data feature extraction method and device and storage medium
CN112417092A (en) * 2020-11-11 2021-02-26 南京邮电大学 Intelligent text automatic generation system based on deep learning and implementation method thereof
CN112883153A (en) * 2021-01-28 2021-06-01 北京联合大学 Information-enhanced BERT-based relationship classification method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
QI LI等: "LSTM-Based SQL injection detection method for intelligent transportation system", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》 *
王超: "基于神经网络的命名实体识别与实体关系联合抽取", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 *

Also Published As

Publication number Publication date
CN113990473B (en) 2022-09-30

Similar Documents

Publication Publication Date Title
CN105975980B (en) The method and apparatus of monitoring image mark quality
CN112579707B (en) Log data knowledge graph construction method
CN111581393B (en) Construction method of knowledge graph based on customer service data in power industry
US10883345B2 (en) Processing of computer log messages for visualization and retrieval
CN111708938B (en) Method, apparatus, electronic device, and storage medium for information processing
US20190213002A1 (en) Analysis software managing system and analysis software managing method
JP2011198364A (en) Method of adding label to medium document and system using the same
CN113032403B (en) Data insight method, device, electronic equipment and storage medium
CN109088793B (en) Method and apparatus for detecting network failure
CN113990473B (en) Medical equipment operation and maintenance information collecting and analyzing system and using method thereof
CN112950359B (en) User identification method and device
CN106339293B (en) A kind of log event extracting method based on signature
CN116739408A (en) Power grid dispatching safety monitoring method and system based on data tag and electronic equipment
CN110413852A (en) A kind of information-pushing method, device, equipment and medium
CN207037679U (en) A kind of system of quick scanning invoice information
CN113115107B (en) Handheld video acquisition terminal system based on 5G network
JP2022186541A (en) Source code analysis apparatus and source code analysis method
Ivanova et al. Does geographical location have an impact on data samples extracted from Twitter?
JP2010102462A (en) Apparatus, method and program for estimating trouble
CN117272170B (en) Knowledge graph-based IT operation and maintenance fault root cause analysis method
CN112231203A (en) Data warehouse test analysis method based on blood relationship
CN108986922A (en) A kind of medical treatment & health data display method and system
CN116561817B (en) Target object processing method, device and equipment
US20220327237A1 (en) System and a method for identifying private user information
CN113379004B (en) Data table classification method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant