CN114579712A - Text attribute extraction and matching method based on dynamic model - Google Patents

Text attribute extraction and matching method based on dynamic model Download PDF

Info

Publication number
CN114579712A
CN114579712A CN202210478783.9A CN202210478783A CN114579712A CN 114579712 A CN114579712 A CN 114579712A CN 202210478783 A CN202210478783 A CN 202210478783A CN 114579712 A CN114579712 A CN 114579712A
Authority
CN
China
Prior art keywords
null
extraction
attribute
attribute name
text
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
CN202210478783.9A
Other languages
Chinese (zh)
Other versions
CN114579712B (en
Inventor
杨波
王小莉
秦克良
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.)
Zhongke Yuchen Technology Co Ltd
Original Assignee
Zhongke Yuchen Technology 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 Zhongke Yuchen Technology Co Ltd filed Critical Zhongke Yuchen Technology Co Ltd
Priority to CN202210478783.9A priority Critical patent/CN114579712B/en
Publication of CN114579712A publication Critical patent/CN114579712A/en
Application granted granted Critical
Publication of CN114579712B publication Critical patent/CN114579712B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a text attribute extraction and matching system based on a dynamic model, which can automatically extract and match attribute names in text data and improve the extraction and matching speed and accuracy.

Description

Text attribute extraction and matching method based on dynamic model
Technical Field
The application relates to the field of text recognition, in particular to a text attribute extraction and matching method based on a dynamic model.
Background
Generally, corresponding specifications are provided for materials in life so as to know the characteristics and functions of the materials. At present, the attributes of the materials are manually obtained from the specification, so as to obtain the attribute information of the corresponding materials, for example, the material name, the material components and other attribute information. However, for mass specifications, the manual acquisition mode has the defects of low efficiency, high labor intensity and the like.
Disclosure of Invention
In view of the above technical problems, an embodiment of the present invention provides a text attribute extraction and matching system based on a dynamic model, which is used to solve at least one of the above technical problems.
The embodiment of the invention adopts the technical scheme that:
the embodiment of the invention provides a text attribute extraction and matching system based on a dynamic model, which comprises: communication connectionThe system comprises a processor, a memory and a database, wherein the memory is stored with text data of N types of target objects, and the ith line of the database comprises (C)i，A0 i，Di，R0 i），CiIs ID of the i-th class target object, A0 iIs CiCorresponding text data TiCurrent attribute name set of A0 iIs Null; di=（Di1，Di2，…，Dimi），DijIs TiCorresponding set of data elements DiThe jth data element in (1); r0 iIs a and A0 iCorresponding set of matching results, R0 i∈Di，R0 iIs Null;
text data T for any target object iiSaid processor being adapted to execute a computer program to perform the steps of:
s10, based on TiObtaining the corresponding current attribute name set A from the database0 i(ii) a If A is0 iNot Null, perform S20, otherwise, perform S30;
s20, based on A0 iExtraction of TiAttribute name in (1) to obtain TiProperty name set A ofi；
S30, extracting T based on the set extraction ruleiGet TiProperty name set A ofi；
S40, based on TiTo A, aiCorrecting to obtain a corrected attribute name set Ac i=（Ac i1，Ac i2，…，Ac ini），Ac irIs Ac iR is 1 to ni, and ni is Ac iThe number of attribute names in (1); using Ac iUpdate A0 i；
S50, if Ac ir∈A0 iThen A will be0 iNeutral with Ac irThe data elements corresponding to the same attribute name are used as Ac irThe matching result of (1); otherwise, go to S60;
s60, obtaining Dc ir=max（Dc ir1，Dc ir2，…，Dc irmi），Dc irsIs Ac irAnd text data TiCorresponding set of data elements DiData element D in (1)isS is 1 to mi;
s70, if Dc irIf > D, then D isc irCorresponding data element as Ac irThe matching result of (1); d is a set threshold;
s80, obtaining A based on S60-S70c iIs matched with the result set Ri(ii) a To RiCorrecting to obtain a corrected matching result set Rc iAnd use of Rc iUpdating R0 i。
The embodiment of the invention provides a text attribute extraction matching system based on a dynamic model, which optimizes an attribute name set extracted last time by using a currently extracted attribute name set to serve as a basis for extracting an attribute name next time. Because the attribute name sets stored in the database are all the attribute name sets manually corrected last time, the subsequent automatic extraction of the attribute names can be more accurate, and all the attribute names in the text data can be automatically extracted as accurately as possible. In addition, the matching result of each time is corrected, and the corrected matching result is used as the matching basis of the attribute name of the next time, so that the automatic matching result can be continuously optimized, the automatic matching result is more accurate, and the matching result of the extracted attribute name can be automatically found from the set attribute name set as accurate as possible.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a method implemented when a computer program is executed by the system for extracting and matching text attributes based on dynamic models according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the invention provides a text attribute extraction and matching system based on a dynamic model, which comprises: a processor, a memory, and a database communicatively coupled.
Wherein the memory stores text data of N types of target objects, and the ith row of the database comprises (C)i，A0 i，Di，R0 i），CiIs ID of the i-th class target object, A0 iIs CiCorresponding text data TiCurrent property name set of Ai=（Ai1，Ai2，…，Aini），A0 ipIs AiP-th attribute name in (1), p is 1 to ni, and ni is AiThe number of attribute names in (1); a. the0 iIs Null. Di=（Di1，Di2，…，Dimi），DijIs TiCorresponding set of data elements DiThe jth data element in (1); r is0 iIs a and A0 iCorresponding set of matching results, R0 i∈Di，R0 iIs Null.
In an embodiment of the present invention, the target object may be a material, for example, a product such as a medicine, a food, an equipment, and the like. The text data may be text identified from a description file, such as a specification, corresponding to the target object. Those skilled in the art will appreciate that the text identified from the description file corresponding to the target object may be identified by any conventional means, such as ocr text recognition software.
Further, in the embodiment of the present invention, the description file of the target object for recognition may be obtained by photographing with the image pickup device.
In the embodiment of the present invention, the attribute name may be a name describing characteristics of the material, such as specification, content, composition, and the like.
In the embodiment of the present invention, the data element may be a primary attribute name for the target object, that is, primary information of the target object can be known through the data element.
Further, in the embodiment of the present invention, the text data T for any one target object iiThe processor is configured to execute a computer program to implement the following steps (as shown in fig. 1):
s10, based on TiObtaining the corresponding current attribute name set A from the database0 i(ii) a If A is0 iNot Null, S20 is performed, otherwise S30 is performed.
Otherwise, the description is that the text data T is processed for the first timeiT is not stored in the databaseiHistory data of (i.e. A)0 iIs Null.
S20, based on A0 iExtraction of TiAttribute name in (1) to obtain TiProperty name set A ofi。
If A is0 iNot Null, meaning that the text data T is not processed for the first timeiT is stored in the databaseiHistory data of (A)0 iIs the last extracted attribute name set, therefore, utilizes A0 iExtraction of TiAttribute name in (1) to obtain TiProperty name set A ofiThe attribute extraction accuracy can be improved.
S30, extracting T based on the set extraction ruleiTo obtain TiProperty name set A ofi。
In an embodiment of the present invention, the ith row of the database further comprises TiCorresponding first identifier set M1iAnd a second set of identifiers M2i. First set of identifiers M1iIs TiThe inherent identifier set in the method can comprise at least one identifier, and the identifiers can be ":< >"," [ sic ], and the like. Second set of identifiers M2iCan be a customized set of identifiers and can include at least one identifier.
Further, in S30, if M1iNot Null, then M1iExtraction of TiProperty name in (2). Specifically, if M1iIncluding ui identifiers, i.e. M1i=（M1i1，M1i2，…，M1iui) Then T can be extracted as followsiProperty name in (2):
s301, go through M1iUsing either M1ivFrom TiExtracting corresponding attribute names; v is from 1 to ui;
s302, based on S301, generating basis M1iExtracted TiThe attribute name of (2).
The information extracted based on each identifier may be a key-value pair, i.e., including a key and a corresponding value, in the present invention, the key is an attribute name. Those skilled in the art know that extracting attribute names in text data based on identifiers may be an existing method.
Further, in S30, if M1iIs Null and M2iNot Null, then M2iExtraction of TiProperty name in (2). Based on M2iExtraction of TiThe attribute name in (1) can be based on M1iExtraction of TiIn a similar manner.
Further, in an embodiment of the present invention, in S30, if M1iIs Null and M2iIs Null, then T can be extracted based on NulliThe obtained attribute name is also Null.
Further, in one embodiment of the present invention, in S30, if M1 is satisfiediIs Null and M2iBeing Null, T can then be extracted based on the randomly generated identifieriThe obtained corresponding attribute name.
S40, based on TiTo A, aiCorrecting to obtain a corrected attribute name set Ac i=（Ac i1，Ac i2，…，Ac ini），Ac irIs Ac iR is 1 to ni, and ni is Ac iThe number of attribute names in (1); using Ac iUpdate A0 i。
In the embodiment of the invention, A can be manually pairediAnd (6) correcting. Specifically, the operator may manually seek from TiFinding out all attribute names to form a contrast attribute name set, and then adding AiComparing with the formed comparison attribute name set to find out the missing, error or redundant attribute names to AiCorrecting to obtain a corrected attribute name set Ac i。
In the present embodiment, use is made of Ac iUpdate A0 iCan be a0 iIs replaced by Ac iThat is, the attribute name set extracted last time is optimized by using the attribute name set extracted currently, so as to be used as the basis for extracting the attribute name next time. Because the attribute name sets stored in the database are all the attribute name sets manually corrected last time, the subsequent automatic extraction of the attribute names can be more accurate, and all the attribute names in the text data can be automatically extracted as accurately as possible.
S50, if Ac ir∈A0 iThen A is added0 iNeutral with Ac irThe data elements corresponding to the same attribute name are used as Ac irThe matching result of (1); otherwise, S60 is executed.
In an embodiment of the invention, the data element corresponding to each text data is fixed, i.e. DiIs stationary.
In another embodiment of the present invention, the data element corresponding to each text data may be dynamically changed, for example, updated with each type of material, in this case, due to DiReason for update, there will be Ac ir∈A0 i，A0 iNeutral with Ac irThe data elements corresponding to the same attribute name are not in DiThus, in S50, if a0 iNeutral with Ac irData elements corresponding to the same attribute name do not belong to DiThen S60 is executed.
The technical effect of S50 is that if Ac ir∈A0 iAnd A is0 iNeutral with Ac irData elements corresponding to the same attribute name are in DiIn (1), then A is0 iNeutral with Ac irThe data elements corresponding to the same attribute name are used as Ac irThe matching result of the time can be directly obtained based on the last matching result, and the matching speed and the matching accuracy can be improved.
S60, obtaining Dc ir=max（Dc ir1，Dc ir2，…，Dc irmi），Dc irsIs Ac irAnd text data TiCorresponding set of data elements DiData element D in (1)isS is 1 to mi.
Specifically, in this step, for Ac iAny attribute name A in (1)c irFirst, the D and D can be obtained respectivelyiIs obtained by obtaining the similarity between each data element in (1), i.e. D is obtained separatelyc ir1，Dc ir2，…，Dc irmi(ii) a Then, from Dc ir1，Dc ir2，…，Dc irmiSelecting the largest one as Dc ir. As known to those skilled in the art, the similarity can be obtained by using an existing similarity calculation method such as hanlp,such as euclidean distance, cosine distance, mahalanobis distance, etc.
S70, if Dc irIf > D, then D isc irCorresponding data element as Ac irThe matching result of (1); d is a set threshold.
In embodiments of the present invention, D can be an empirical value, such as 90% to 99%, preferably, can be 95% to 99%, and more preferably, can be 99%.
S80, obtaining A based on S60-S70c iIs matched with the result set Ri(ii) a To RiCorrecting to obtain a corrected matching result set Rc iAnd use of Rc iUpdating R0 i。
In embodiments of the present invention, R may be empirically pairediAnd (6) correcting.
In the present embodiment, R is usedc iUpdating R0 iCan be prepared by reacting R0 iIs replaced by Rc i。
In the embodiment of the invention, because the matching result of each time is corrected and the corrected matching result is used as the matching basis of the attribute name of the next time, the automatic matching result can be continuously optimized, so that the automatic matching result is more accurate, and the matching result of the extracted attribute name can be automatically found from the set attribute name set as accurate as possible.
Further, in the embodiment of the present invention, before S40, the data element further includes:
s32, for Ac iAnd performing visual presentation.
In visual presentation, A may be presented sequentially, e.g., from top to bottomc iFor example, the content displayed in each line may be: a name; XX, and the like.
Further, in the embodiment of the present invention, the method further includes:
s90, to Rc iAnd performing visual presentation.
In the pair Rc iWhen performing visual presentation, R can be presented sequentially, e.g., from top to bottomc iAnd the corresponding attribute name.
Although some specific embodiments of the present application have been described in detail by way of illustration, it should be understood by those skilled in the art that the above illustration is only for purposes of illustration and is not intended to limit the scope of the present application. Those skilled in the art will also appreciate that various modifications might be made to the embodiments without departing from the scope and spirit of the present application. The scope of the disclosure of the present application is defined by the appended claims.

Claims (9)

1. A text attribute extraction matching system based on a dynamic model is characterized by comprising: a processor, a memory and a database connected in communication, wherein the memory stores text data of N types of target objects, and the ith line of the database comprises (C)i，A0 i，Di，R0 i），CiIs ID of the i-th class target object, A0 iIs CiCorresponding text data TiCurrent property name set of A0 iIs Null; di=（Di1，Di2，…，Dimi），DijIs TiCorresponding set of data elements DiThe jth data element in (1); r0 iIs a and A0 iCorresponding set of matching results, R0 i∈Di，R0 iIs Null;
text data T for any target object iiSaid processor being adapted to execute a computer program to perform the steps of:
s10, based on TiObtaining the corresponding current attribute name set A from the database0 i(ii) a If A is0 iNot Null, perform S20, otherwise, perform S30;
s20, based on A0 iExtraction of TiAttribute name in (1) to obtain TiProperty name set A ofi；
S30, extracting T based on the set extraction ruleiGet TiProperty name set A ofi；
S40, based on TiTo A, aiCorrecting to obtain a corrected attribute name set Ac i=（Ac i1，Ac i2，…，Ac ini），Ac irIs Ac iR is 1 to ni, and ni is Ac iThe number of attribute names in (1); using Ac iUpdate A0 i；
S50, if Ac ir∈A0 iThen A will be0 iNeutral with Ac irThe data elements corresponding to the same attribute name are used as Ac irThe matching result of (1); otherwise, go to S60;
s60, obtaining Dc ir=max（Dc ir1，Dc ir2，…，Dc irmi），Dc irsIs Ac irAnd text data TiCorresponding set of data elements DiData element D in (1)isS is 1 to mi;
s70, if Dc irIf > D, then D isc irCorresponding data element as Ac irThe matching result of (1); d is a set threshold;
s80, obtaining A based on S60-S70c iIs matched with the result set Ri(ii) a To RiCorrecting to obtain a corrected matching result set Rc iAnd use of Rc iUpdating R0 i。
2. The system of claim 1, wherein the text data is text identified from a description file corresponding to the target object.
3. The system of claim 1, wherein row i of the database further comprises TiCorresponding first identifier set M1iAnd a second set of identifiers M2i。
4. The system of claim 3, wherein in S30, if M1iNot Null, then M1iExtraction of TiProperty name in (2).
5. The system of claim 3, wherein in S30, if M1iIs Null and M2iNot Null, based on M2iExtraction of TiProperty name in (2).
6. The system of claim 1, wherein in S50, if a is0 iNeutral with Ac irData elements corresponding to the same attribute name do not belong to DiThen S60 is executed.
7. The system of claim 1, further comprising, prior to S40:
s32, for Ac iAnd performing visual presentation.
8. The system of claim 1, further comprising:
s90, to Rc iAnd performing visual presentation.
9. The system of any one of claims 1 to 8, wherein the target object is a material.
CN202210478783.9A 2022-05-05 2022-05-05 Text attribute extraction and matching method based on dynamic model Active CN114579712B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210478783.9A CN114579712B (en) 2022-05-05 2022-05-05 Text attribute extraction and matching method based on dynamic model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210478783.9A CN114579712B (en) 2022-05-05 2022-05-05 Text attribute extraction and matching method based on dynamic model

Publications (2)

Publication Number Publication Date
CN114579712A true CN114579712A (en) 2022-06-03
CN114579712B CN114579712B (en) 2022-07-15

Family

ID=81784688

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210478783.9A Active CN114579712B (en) 2022-05-05 2022-05-05 Text attribute extraction and matching method based on dynamic model

Country Status (1)

Country Link
CN (1) CN114579712B (en)

Citations (39)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100250598A1 (en) * 2009-03-30 2010-09-30 Falk Brauer Graph based re-composition of document fragments for name entity recognition under exploitation of enterprise databases
US20120323576A1 (en) * 2011-06-17 2012-12-20 Microsoft Corporation Automated adverse drug event alerts
CN102999623A (en) * 2012-12-04 2013-03-27 方蝶软件（上海）有限公司 Method for topologically constructing digital dynamic fluid model by using contour tree
US20140188867A1 (en) * 2004-08-31 2014-07-03 Semantic Search Technologies Llc Computer-aided extraction of semantics from keywords to confirm match of buyer offers to seller bids
CN104268241A (en) * 2014-09-29 2015-01-07 北京合力思腾科技股份有限公司 Attribute display method in configuration database
US20160246779A1 (en) * 2015-02-23 2016-08-25 International Business Machines Corporation Facilitating information extraction via semantic abstraction
CN105912666A (en) * 2016-04-12 2016-08-31 中国科学院软件研究所 Method for high-performance storage and inquiry of hybrid structure data aiming at cloud platform
CN106997509A (en) * 2017-03-28 2017-08-01 南京航空航天大学 A kind of emergency materials distributed needs Forecasting Methodology of uncertain information fusion
CN107784397A (en) * 2017-11-09 2018-03-09 贵州电网有限责任公司 A kind of power network material requirements forecasting system and its Forecasting Methodology
CN107798435A (en) * 2017-11-09 2018-03-13 贵州电网有限责任公司 A kind of Power Material needing forecasting method based on Text Information Extraction
US20180075323A1 (en) * 2016-09-13 2018-03-15 Sophistio, Inc. Automatic wearable item classification systems and methods based upon normalized depictions
CN108228158A (en) * 2018-01-18 2018-06-29 东南大学 A kind of framework behavior pattern recognition method based on ontology
CN109033135A (en) * 2018-06-06 2018-12-18 北京大学 A kind of natural language querying method and system of software-oriented project knowledge map
CN109062921A (en) * 2018-05-31 2018-12-21 武昌船舶重工集团有限公司 A kind of method and system for extracting ship pallet control information
CN109064294A (en) * 2018-08-21 2018-12-21 重庆大学 A kind of time of fusion factor, the drug recommended method of text feature and correlation
CN109147010A (en) * 2018-08-22 2019-01-04 广东工业大学 Band attribute Face image synthesis method, apparatus, system and readable storage medium storing program for executing
CN109429260A (en) * 2017-08-23 2019-03-05 中兴通讯股份有限公司 A kind of method of calibration and device of northbound data
CN109598063A (en) * 2018-12-04 2019-04-09 中国航空无线电电子研究所 A kind of data-link networking dynamic model driving method based on AADL
CN109598794A (en) * 2018-11-30 2019-04-09 苏州维众数据技术有限公司 The construction method of three-dimension GIS dynamic model
CN109783614A (en) * 2019-01-25 2019-05-21 北京信息科技大学 A kind of the difference privacy leakage detection method and system of social networks text to be released
CN109885688A (en) * 2019-03-05 2019-06-14 湖北亿咖通科技有限公司 File classification method, device, computer readable storage medium and electronic equipment
CN109902144A (en) * 2019-01-11 2019-06-18 杭州电子科技大学 A kind of entity alignment schemes based on improvement WMD algorithm
CN110069631A (en) * 2019-04-08 2019-07-30 腾讯科技（深圳）有限公司 A kind of text handling method, device and relevant device
US10438264B1 (en) * 2016-08-31 2019-10-08 Amazon Technologies, Inc. Artificial intelligence feature extraction service for products
CN110334814A (en) * 2019-07-01 2019-10-15 阿里巴巴集团控股有限公司 For constructing the method and system of risk control model
CN110471367A (en) * 2019-08-14 2019-11-19 上海明材教育科技有限公司 A kind of construction method of dynamic 3 D model that capableing of cooperative motion
CN110609998A (en) * 2019-08-07 2019-12-24 中通服建设有限公司 Data extraction method of electronic document information, electronic equipment and storage medium
CN110674272A (en) * 2019-09-05 2020-01-10 科大讯飞股份有限公司 Question answer determining method and related device
CN110795482A (en) * 2019-10-16 2020-02-14 浙江大华技术股份有限公司 Data benchmarking method, device and storage device
CN110796390A (en) * 2019-11-08 2020-02-14 云南电网有限责任公司昆明供电局 Distribution network maintenance, production and live working application fusion system based on dynamic model
CN110889036A (en) * 2019-10-31 2020-03-17 深圳市微立德科技有限公司 Multi-dimensional information processing method and device and terminal equipment
CN111078833A (en) * 2019-12-03 2020-04-28 哈尔滨工程大学 Text classification method based on neural network
CN111241793A (en) * 2020-02-17 2020-06-05 湖南快乐阳光互动娱乐传媒有限公司 Method, system, and medium for parsing rich text editor content for native client rendering
CN111274783A (en) * 2020-01-14 2020-06-12 广州供电局有限公司 Intelligent surrounding string label identification method based on semantic similarity analysis
CN111404960A (en) * 2020-03-26 2020-07-10 军事科学院系统工程研究院网络信息研究所 Attribute extraction method applied to heaven-earth integrated network access control system
CN111639815A (en) * 2020-06-02 2020-09-08 贵州电网有限责任公司 Method and system for predicting power grid defect materials through multi-model fusion
CN111723371A (en) * 2020-06-22 2020-09-29 上海斗象信息科技有限公司 Method for constructing detection model of malicious file and method for detecting malicious file
CN112434691A (en) * 2020-12-02 2021-03-02 上海三稻智能科技有限公司 HS code matching and displaying method and system based on intelligent analysis and identification and storage medium
CN114153962A (en) * 2021-11-26 2022-03-08 浙江大华技术股份有限公司 Data matching method and device and electronic equipment

Patent Citations (40)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140188867A1 (en) * 2004-08-31 2014-07-03 Semantic Search Technologies Llc Computer-aided extraction of semantics from keywords to confirm match of buyer offers to seller bids
US20170199933A1 (en) * 2004-08-31 2017-07-13 Semantic Search Technologies Llc, A Texas Limited Liability Company Computer-aided extraction of semantics from keywords to confirm match of buyer offers to seller bids
US20100250598A1 (en) * 2009-03-30 2010-09-30 Falk Brauer Graph based re-composition of document fragments for name entity recognition under exploitation of enterprise databases
US20120323576A1 (en) * 2011-06-17 2012-12-20 Microsoft Corporation Automated adverse drug event alerts
CN102999623A (en) * 2012-12-04 2013-03-27 方蝶软件（上海）有限公司 Method for topologically constructing digital dynamic fluid model by using contour tree
CN104268241A (en) * 2014-09-29 2015-01-07 北京合力思腾科技股份有限公司 Attribute display method in configuration database
US20160246779A1 (en) * 2015-02-23 2016-08-25 International Business Machines Corporation Facilitating information extraction via semantic abstraction
CN105912666A (en) * 2016-04-12 2016-08-31 中国科学院软件研究所 Method for high-performance storage and inquiry of hybrid structure data aiming at cloud platform
US10438264B1 (en) * 2016-08-31 2019-10-08 Amazon Technologies, Inc. Artificial intelligence feature extraction service for products
US20180075323A1 (en) * 2016-09-13 2018-03-15 Sophistio, Inc. Automatic wearable item classification systems and methods based upon normalized depictions
CN106997509A (en) * 2017-03-28 2017-08-01 南京航空航天大学 A kind of emergency materials distributed needs Forecasting Methodology of uncertain information fusion
CN109429260A (en) * 2017-08-23 2019-03-05 中兴通讯股份有限公司 A kind of method of calibration and device of northbound data
CN107798435A (en) * 2017-11-09 2018-03-13 贵州电网有限责任公司 A kind of Power Material needing forecasting method based on Text Information Extraction
CN107784397A (en) * 2017-11-09 2018-03-09 贵州电网有限责任公司 A kind of power network material requirements forecasting system and its Forecasting Methodology
CN108228158A (en) * 2018-01-18 2018-06-29 东南大学 A kind of framework behavior pattern recognition method based on ontology
CN109062921A (en) * 2018-05-31 2018-12-21 武昌船舶重工集团有限公司 A kind of method and system for extracting ship pallet control information
CN109033135A (en) * 2018-06-06 2018-12-18 北京大学 A kind of natural language querying method and system of software-oriented project knowledge map
CN109064294A (en) * 2018-08-21 2018-12-21 重庆大学 A kind of time of fusion factor, the drug recommended method of text feature and correlation
CN109147010A (en) * 2018-08-22 2019-01-04 广东工业大学 Band attribute Face image synthesis method, apparatus, system and readable storage medium storing program for executing
CN109598794A (en) * 2018-11-30 2019-04-09 苏州维众数据技术有限公司 The construction method of three-dimension GIS dynamic model
CN109598063A (en) * 2018-12-04 2019-04-09 中国航空无线电电子研究所 A kind of data-link networking dynamic model driving method based on AADL
CN109902144A (en) * 2019-01-11 2019-06-18 杭州电子科技大学 A kind of entity alignment schemes based on improvement WMD algorithm
CN109783614A (en) * 2019-01-25 2019-05-21 北京信息科技大学 A kind of the difference privacy leakage detection method and system of social networks text to be released
CN109885688A (en) * 2019-03-05 2019-06-14 湖北亿咖通科技有限公司 File classification method, device, computer readable storage medium and electronic equipment
CN110069631A (en) * 2019-04-08 2019-07-30 腾讯科技（深圳）有限公司 A kind of text handling method, device and relevant device
CN110334814A (en) * 2019-07-01 2019-10-15 阿里巴巴集团控股有限公司 For constructing the method and system of risk control model
CN110609998A (en) * 2019-08-07 2019-12-24 中通服建设有限公司 Data extraction method of electronic document information, electronic equipment and storage medium
CN110471367A (en) * 2019-08-14 2019-11-19 上海明材教育科技有限公司 A kind of construction method of dynamic 3 D model that capableing of cooperative motion
CN110674272A (en) * 2019-09-05 2020-01-10 科大讯飞股份有限公司 Question answer determining method and related device
CN110795482A (en) * 2019-10-16 2020-02-14 浙江大华技术股份有限公司 Data benchmarking method, device and storage device
CN110889036A (en) * 2019-10-31 2020-03-17 深圳市微立德科技有限公司 Multi-dimensional information processing method and device and terminal equipment
CN110796390A (en) * 2019-11-08 2020-02-14 云南电网有限责任公司昆明供电局 Distribution network maintenance, production and live working application fusion system based on dynamic model
CN111078833A (en) * 2019-12-03 2020-04-28 哈尔滨工程大学 Text classification method based on neural network
CN111274783A (en) * 2020-01-14 2020-06-12 广州供电局有限公司 Intelligent surrounding string label identification method based on semantic similarity analysis
CN111241793A (en) * 2020-02-17 2020-06-05 湖南快乐阳光互动娱乐传媒有限公司 Method, system, and medium for parsing rich text editor content for native client rendering
CN111404960A (en) * 2020-03-26 2020-07-10 军事科学院系统工程研究院网络信息研究所 Attribute extraction method applied to heaven-earth integrated network access control system
CN111639815A (en) * 2020-06-02 2020-09-08 贵州电网有限责任公司 Method and system for predicting power grid defect materials through multi-model fusion
CN111723371A (en) * 2020-06-22 2020-09-29 上海斗象信息科技有限公司 Method for constructing detection model of malicious file and method for detecting malicious file
CN112434691A (en) * 2020-12-02 2021-03-02 上海三稻智能科技有限公司 HS code matching and displaying method and system based on intelligent analysis and identification and storage medium
CN114153962A (en) * 2021-11-26 2022-03-08 浙江大华技术股份有限公司 Data matching method and device and electronic equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
贾丽梅 等: ""基于动态权值的关联数据语义相似度算法研究"", 《计算机科学》 *

Also Published As

Publication number Publication date
CN114579712B (en) 2022-07-15

Similar Documents

Publication Publication Date Title
US20210192202A1 (en) Recognizing text in image data
CN109783617B (en) Model training method, device, equipment and storage medium for replying to questions
US10740372B2 (en) System and method for extracting data from a non-structured document
US8971641B2 (en) Spatial image index and associated updating functionality
CN109992601B (en) To-do information pushing method and device and computer equipment
CN111582169B (en) Image recognition data error correction method, device, computer equipment and storage medium
WO2020155740A1 (en) Information query method and apparatus, and computer device and storage medium
CN107784057B (en) Medical data matching method and device
CN110999264B (en) System and method for integrating message content into a target data processing device
CN110990546A (en) Intelligent question and answer corpus updating method and device
CN110046155B (en) Method, device and equipment for updating feature database and determining data features
WO2021036547A1 (en) Express query method, server, and terminal
CN112036362A (en) Image processing method, image processing device, computer equipment and readable storage medium
CN112528882B (en) Method, device, equipment and medium for determining property certificate information based on OCR (optical character recognition)
CN114579712B (en) Text attribute extraction and matching method based on dynamic model
US11442982B2 (en) Method and system for acquiring data files of blocks of land and of building plans and for making matches thereof
KR20160116789A (en) A method for learning record management and a system using the same
CN112417195A (en) Trademark inquiry system and method based on mobile terminal and storage medium
CN112148819A (en) Address recognition method and device combining RPA and AI
JP2017111500A (en) Character recognizing apparatus, and program
CN110147791A (en) Character recognition method, device, equipment and storage medium
CN112333182B (en) File processing method, device, server and storage medium
US11593417B2 (en) Assigning documents to entities of a database
EP4163803A1 (en) Sample data annotation system, method, and related device
EP4278315A1 (en) Ticket troubleshooting support system

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