CN111695339A - Automatic matching method and device for hidden danger-oriented rule standard provisions - Google Patents

Automatic matching method and device for hidden danger-oriented rule standard provisions Download PDF

Info

Publication number
CN111695339A
CN111695339A CN202010534869.XA CN202010534869A CN111695339A CN 111695339 A CN111695339 A CN 111695339A CN 202010534869 A CN202010534869 A CN 202010534869A CN 111695339 A CN111695339 A CN 111695339A
Authority
CN
China
Prior art keywords
matching
information
hidden danger
keyword
regulation
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
CN202010534869.XA
Other languages
Chinese (zh)
Other versions
CN111695339B (en
Inventor
胡万宏
高亮
段州君
唐君
李强
程洪
谢筱依
董志勇
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.)
China Tobacco Hubei Industrial LLC
Hubei Xinye Tobacco Sheet Development Co Ltd
Original Assignee
China Tobacco Hubei Industrial LLC
Hubei Xinye Tobacco Sheet Development 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 China Tobacco Hubei Industrial LLC, Hubei Xinye Tobacco Sheet Development Co Ltd filed Critical China Tobacco Hubei Industrial LLC
Priority to CN202010534869.XA priority Critical patent/CN111695339B/en
Publication of CN111695339A publication Critical patent/CN111695339A/en
Application granted granted Critical
Publication of CN111695339B publication Critical patent/CN111695339B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing
    • G06F40/216Parsing using statistical methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/3332Query translation
    • G06F16/3334Selection or weighting of terms from queries, including natural language queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/335Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/237Lexical tools
    • G06F40/247Thesauruses; Synonyms
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/18Legal services
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Technology Law (AREA)
  • Probability & Statistics with Applications (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention belongs to the technical field of fire-fighting hidden danger laws and regulations, and discloses a hidden danger-oriented automatic matching method for standard provisions of laws and regulations, which comprises the steps of extracting keyword information from a law library; acquiring detected hidden danger information and keywords thereof, matching the keywords with keyword information of a rule base according to a preset matching rule, and outputting matched rules and rule provisions; obtaining feedback information of the matched laws and regulations provisions, and adjusting and optimizing the matching rules by combining the feedback information; an automatic matching device is also disclosed; the accuracy of the result is ensured by extracting the keyword information of the rule base, accurately matching the detected hidden danger information and the detected keywords of the hidden danger information, and performing synonym matching, and meanwhile, the matching rule is continuously optimized through the matching result fed back by the user, so that the accuracy of hidden danger troubleshooting is improved, the time for manually inquiring rule provisions is reduced, and the working efficiency of the hidden danger troubleshooting is improved.

Description

Automatic matching method and device for hidden danger-oriented rule standard provisions
Technical Field
The invention belongs to the technical field of fire-fighting hidden danger regulations, and particularly relates to a hidden danger-oriented automatic regulation standard clause matching method and device.
Background
The hidden danger investigation refers to the investigation of people, mechanical equipment, working environment and production management of production and management units one by utilizing a related method of safe production management according to national safe production laws and regulations, and aims to find hidden dangers of safe production accidents; after the hidden trouble is found, the hidden trouble is eliminated according to various treatment means, so that the production safety accident is eliminated in a sprouting state, and the aim of safe production is fulfilled.
Referring to a method and a device for matching and processing vulnerability information with Chinese patent number CN110808957A, the method comprises the following steps: acquiring vulnerability related information in a network, and performing part-of-speech tagging and block extraction on vulnerability related beliefs to obtain preprocessed vulnerability information; combining a plurality of blocks which accord with a preset syntactic structure in the preprocessed vulnerability information into new noun blocks to obtain the vulnerability information of the blocks; matching verbs in the block vulnerability information according to preset sensitive verbs, and determining target names connected with the matched target verbs as vulnerability information.
By combining the mentioned loophole information processing mode, it can be found that security personnel cannot accurately judge whether hidden dangers exist when carrying out hidden danger investigation, and when judging that the hidden dangers exist, accurate and convincing regulation and rule basis cannot be provided; meanwhile, the optimization cannot be carried out by combining the collected feedback information when a processing mode is adopted, so that the result is lack of rationality.
Disclosure of Invention
The invention aims to provide a hidden danger-oriented automatic matching method and device for a standard rule and a standard sentence, which are used for solving the problems that safety personnel cannot accurately judge whether hidden dangers exist when carrying out hidden danger investigation, and cannot provide accurate and convincing rule and rule basis when judging that the hidden dangers exist; meanwhile, the optimization cannot be carried out by combining the collected feedback information when a processing mode is adopted, so that the result is lack of rationality.
The invention provides a hidden danger-oriented automatic matching method of a regulation standard clause, which adopts the technical scheme for solving the technical problem and comprises the following steps:
extracting keyword information from a regulation library;
acquiring detected hidden danger information and keywords thereof, matching the keywords with keyword information of a rule base according to a preset matching rule, and outputting matched rules and rule provisions;
and obtaining feedback information of the matched laws and regulations provisions, and adjusting and optimizing the matching rules by combining the feedback information.
Further preferably, the "extracting keyword information from a regulation library" specifically includes: calling a rule base text, filtering the full text of the rule base text, and screening out a candidate word base according to a preset word frequency; calculating the word frequency of candidate words and the reverse frequency of the candidate words in the candidate word library; and calculating the statistical characteristic weight of the candidate words by combining the word frequency of the candidate words and the reverse frequency of the candidate words, and listing the previous topK words as keyword information according to a preset keyword threshold.
Further preferably, the matching the keyword with the keyword information of the rule base according to the preset matching rule and outputting the matched rule and rule provisions specifically comprises: carrying out full-text accurate matching on the keyword information according to the hidden danger information keywords; carrying out preset synonym library matching on the hidden danger information keywords which are not accurately matched, and obtaining corresponding keyword information; and corresponding the matched keyword information to a regulation library to obtain the regulation and regulation provisions containing the keyword information.
Further preferably, the feedback information includes one of poor matching accuracy, good matching accuracy, low matching efficiency, and high matching efficiency.
Further preferably, the "adjusting and optimizing matching rules in combination with feedback information" specifically includes: when the feedback information is detected to be 'poor matching precision', increasing the selection range of the keyword threshold value of the rule base; and when the feedback information is detected to be 'low matching efficiency', reducing the selection range of the keyword threshold value of the rule base.
Another technical solution adopted to solve the technical problem of the present invention is to provide an automatic matching device for hidden danger-oriented regulatory standard provisions, comprising:
the calling module is used for extracting keyword information from a regulation library;
the matching output module is used for acquiring the detected hidden danger information and the keywords thereof, matching the keywords with the keyword information of the rule base according to a preset matching rule, and outputting the matched rules and rules provisions;
and the feedback processing module is used for acquiring feedback information of the matched laws and regulations provisions and adjusting and optimizing the matching rules by combining the feedback information.
Further preferably, the "extracting keyword information from a regulation library" specifically includes: calling a rule base text, filtering the full text of the rule base text, and screening out a candidate word base according to a preset word frequency; calculating the word frequency of candidate words and the reverse frequency of the candidate words in the candidate word library; and calculating the statistical characteristic weight of the candidate words by combining the word frequency of the candidate words and the reverse frequency of the candidate words, and listing the previous topK words as keyword information according to a preset keyword threshold.
Further preferably, the matching the keyword with the keyword information of the rule base according to the preset matching rule and outputting the matched rule and rule provisions specifically comprises: carrying out full-text accurate matching on the keyword information according to the hidden danger information keywords; carrying out preset synonym library matching on the hidden danger information keywords which are not accurately matched, and obtaining corresponding keyword information; and corresponding the matched keyword information to a regulation library to obtain the regulation and regulation provisions containing the keyword information.
Further preferably, the feedback information includes one of poor matching accuracy, good matching accuracy, low matching efficiency, and high matching efficiency.
Further preferably, the "adjusting and optimizing matching rules in combination with feedback information" specifically includes: when the feedback information is detected to be 'poor matching precision', increasing the selection range of the keyword threshold value of the rule base; and when the feedback information is detected to be 'low matching efficiency', reducing the selection range of the keyword threshold value of the rule base.
The invention has the beneficial effects that:
the accuracy of the result is ensured by extracting the keyword information of the rule base, accurately matching the detected hidden danger information and the detected keywords of the hidden danger information, and performing synonym matching, and meanwhile, the matching rule is continuously optimized through the matching result fed back by the user, so that the accuracy of hidden danger troubleshooting is improved, the time for manually inquiring rule provisions is reduced, and the working efficiency of the hidden danger troubleshooting is improved.
Drawings
Fig. 1 is a schematic flow chart of an automatic matching method for hidden danger-oriented regulatory standard provisions according to an embodiment of the present invention;
fig. 2 is another schematic flow chart of an automatic matching method for hidden danger-oriented regulatory standard provisions according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of an automatic matching method for hidden danger-oriented regulatory standard provisions according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an automatic matching device for hidden-risk-oriented regulatory standard provisions according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention and/or the technical solutions in the prior art, the following description will explain specific embodiments of the present invention with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort. In addition, the term "orientation" merely indicates a relative positional relationship between the respective members, not an absolute positional relationship.
Referring to fig. 1, an automatic matching method for hidden danger-oriented regulatory standard provisions of the present embodiment is shown, which includes the following steps:
s1 extracting keyword information from the rule base;
s2, acquiring the detected hidden danger information and the keywords thereof, matching the keywords with the keyword information of the rule base according to a preset matching rule, and outputting the matched rules and rules;
s3, obtaining feedback information of the matched laws and regulations and statutory provisions, and adjusting and optimizing the matching rules by combining the feedback information.
As shown in fig. 2, the step S1 of extracting the keyword information from the rule base specifically includes:
s101, calling a rule library text, filtering the full text of the rule library text, and screening out a candidate word library according to a preset word frequency;
s102, calculating a candidate word frequency and a candidate word reverse frequency of candidate words in the candidate word library;
s103, calculating a candidate word statistical characteristic weight by combining the candidate word frequency and the candidate word reverse frequency, and listing the previous topK word as keyword information according to a preset keyword threshold.
The required fire control field rule base can be called through the Internet, the preset keyword word frequency is substituted into the rule base to search and screen out the candidate word base (the preset word frequency can be obtained by searching the keyword history record or network search), and the candidate word base is obtained
Figure DEST_PATH_IMAGE002
For in aAny one of the laws and regulations
Figure DEST_PATH_IMAGE004
In the case of a composite material, for example,
Figure DEST_PATH_IMAGE006
the word frequency of (c) may be expressed as:
Figure DEST_PATH_IMAGE008
wherein
Figure DEST_PATH_IMAGE010
Is a word
Figure 650204DEST_PATH_IMAGE006
In the law and regulations
Figure 832924DEST_PATH_IMAGE004
The denominator is in the regulation
Figure 878240DEST_PATH_IMAGE004
The sum of the occurrence times of all candidate words in the Chinese character;
Figure DEST_PATH_IMAGE012
the higher the candidate word
Figure 430706DEST_PATH_IMAGE006
To the law and regulations
Figure 510658DEST_PATH_IMAGE004
The more important it is that the more important,
Figure 598699DEST_PATH_IMAGE012
the lower the candidate word
Figure 6678DEST_PATH_IMAGE006
To the law and regulations
Figure 736737DEST_PATH_IMAGE004
The less important.
At the same time, need to pay attention toThat is, words or phrases such as "in", "out" or the like among words or phrases meaningless in the laws and regulations are frequently appeared in the laws and regulations but do not belong to the category of keywords, so that a specific word or phrase is not included in the category of keywords
Figure DEST_PATH_IMAGE014
The total number of rules can be divided by the number of rules containing the word, and the obtained quotient is logarithmized to obtain the reverse frequency of the candidate word, as shown in the following:
Figure DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE018
is the total number of all the laws and regulations in the laws and regulations library, and the denominator is the contained word
Figure 592566DEST_PATH_IMAGE006
All of the legislation numbers of (a).
In summary, for a high candidate word frequency within a specific rule and a low document frequency of the candidate word in the whole rule base, the statistical feature weight of the candidate word can be generated as shown in the following formula:
Figure DEST_PATH_IMAGE020
the keyword extraction algorithm of the rule base can obtain the statistical characteristic weight of a series of candidate words after calculation, and because more words are obtained, the previous topK words can be listed as keywords according to the actual situation (the threshold value of the keywords can be selected as the previous 10).
As shown in fig. 3, the step S2 of "matching the keyword with the keyword information in the rule base according to the preset matching rule, and outputting the matched rule and rule provision" specifically includes:
s201, carrying out full-text accurate matching on the keyword information according to the hidden danger information keywords;
s202, carrying out preset synonym library matching on the hidden danger information keywords which are not accurately matched, and obtaining corresponding keyword information;
s203, the matched keyword information corresponds to a regulation library to obtain the regulation and regulation clauses containing the keyword information.
Aiming at the detected hidden danger information, on one hand, keywords in the hidden danger information can be manually called, and the selected words or phrases are bound when the keywords are selected; on the other hand, the keyword information may also be extracted in the manner of step S1, and the embodiment employs the manner of step S1 to call the keyword; the extracted keywords are matched with the keyword information extracted from the rule base one by one, wherein the keywords are completely consistent with the keyword information in the rule base and have similar meanings to the keyword information in the rule base, and therefore the phenomenon of missing information is avoided, and accuracy is further improved; it should be noted that the preset synonym library mentioned in step S202 may be based on the manner of extracting the keyword information from the rule library in step S1, wherein the keyword threshold may be set to 20-30, so as to expand the keyword range and the synonym range thereof, and ensure the authenticity and reliability of the data; and (4) the matched keyword information is called corresponding to relevant laws and regulations provisions, and is sent to an operator or a terminal.
The feedback information in step S3 may include one of poor matching accuracy, good matching accuracy, low matching efficiency, and high matching efficiency; the step of adjusting and optimizing the matching rule by combining the feedback information specifically comprises the step of increasing the selection range of the keyword threshold value of the rule base when the feedback information is detected to be poor in matching precision; and when the feedback information is detected to be 'low matching efficiency', reducing the selection range of the keyword threshold value of the rule base.
After receiving corresponding laws and regulations provisions, an operator can feed back according to actual conditions; if the operator selects one of good matching precision or high matching efficiency on the interface or the terminal, the matching method is indicated to have accurate result; if the operator selects 'poor matching precision' on the interface or the terminal, the value of topK can be increased, the selection range of the keywords in the rule base is expanded (each keyword is changed from 10 to 15-20), so that the keyword description of the rule base is more accurate, and the matching with the hidden danger information is more accurate; if the operator selects 'low matching efficiency' on the interface or the terminal, the time is longer, the value of topK can be properly reduced, the calculation amount is reduced, and the matching speed is accelerated.
As shown in fig. 4, this embodiment may further disclose an automatic matching device for hidden-risk-oriented regulation standard provisions, comprising:
the calling module is used for extracting keyword information from a regulation library;
the matching output module is used for acquiring the detected hidden danger information and the keywords thereof, matching the keywords with the keyword information of the rule base according to a preset matching rule, and outputting the matched rules and rules provisions;
and the feedback processing module is used for acquiring feedback information of the matched laws and regulations provisions and adjusting and optimizing the matching rules by combining the feedback information.
Further, "extracting keyword information from a regulation library" specifically includes: calling a rule base text, filtering the full text of the rule base text, and screening out a candidate word base according to a preset word frequency; calculating the word frequency of candidate words and the reverse frequency of the candidate words in the candidate word library; and calculating the statistical characteristic weight of the candidate words by combining the word frequency of the candidate words and the reverse frequency of the candidate words, and listing the previous topK words as keyword information according to a preset keyword threshold.
Further, "matching the keyword with keyword information of a rule base according to a preset matching rule, and outputting the matched rule and rule provisions" specifically includes: carrying out full-text accurate matching on the keyword information according to the hidden danger information keywords; carrying out preset synonym library matching on the hidden danger information keywords which are not accurately matched, and obtaining corresponding keyword information; and corresponding the matched keyword information to a regulation library to obtain the regulation and regulation provisions containing the keyword information.
Further, the "feedback information" may include one of poor matching accuracy, good matching accuracy, low matching efficiency, and high matching efficiency.
The "adjusting and optimizing matching rules in combination with feedback information" specifically includes: when the feedback information is detected to be 'poor matching precision', increasing the selection range of the keyword threshold value of the rule base; and when the feedback information is detected to be 'low matching efficiency', reducing the selection range of the keyword threshold value of the rule base.
The present embodiments may also disclose a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the methods provided by the above-described method embodiments.
The present embodiments may also be a non-transitory computer readable storage medium storing computer instructions that cause the computer to perform the methods provided by the method embodiments described above.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
It should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A hidden danger-oriented automatic matching method for a regulation standard provision is characterized by comprising the following steps:
s1 extracting keyword information from the rule base;
s2, acquiring the detected hidden danger information and the keywords thereof, matching the keywords with the keyword information of the rule base according to a preset matching rule, and outputting the matched rules and rules;
s3, obtaining feedback information of the matched laws and regulations and statutory provisions, and adjusting and optimizing the matching rules by combining the feedback information.
2. The method for automatically matching hidden danger-oriented regulation standard provisions according to claim 1, wherein the step of "S1 extracting keyword information from a regulation library" specifically comprises: s101, calling a rule library text, filtering the full text of the rule library text, and screening out a candidate word library according to a preset word frequency; s102, calculating a candidate word frequency and a candidate word reverse frequency of candidate words in the candidate word library; s103, calculating a candidate word statistical characteristic weight by combining the candidate word frequency and the candidate word reverse frequency, and listing the previous topK word as keyword information according to a preset keyword threshold.
3. The method for automatically matching hidden danger-oriented regulation standard provisions according to claim 1, wherein "matching keywords with keyword information of a regulation library according to a preset matching rule and outputting matched regulations and regulation provisions" in S2 specifically comprises: s201, carrying out full-text accurate matching on the keyword information according to the hidden danger information keywords; s202, carrying out preset synonym library matching on the hidden danger information keywords which are not accurately matched, and obtaining corresponding keyword information; s203, the matched keyword information corresponds to a regulation library to obtain the regulation and regulation clauses containing the keyword information.
4. The automatic matching method for the hidden danger-oriented regulation standard provisions according to claim 2, characterized in that the feedback information comprises one of poor matching precision, good matching precision, low matching efficiency and high matching efficiency.
5. The method for automatically matching hidden danger-oriented regulation standard provisions according to claim 4, wherein the step of adjusting and optimizing the matching rules in combination with the feedback information in the step S3 specifically comprises the steps of: when the feedback information is detected to be 'poor matching precision', increasing the selection range of the keyword threshold value of the rule base; and when the feedback information is detected to be 'low matching efficiency', reducing the selection range of the keyword threshold value of the rule base.
6. The utility model provides a hidden danger oriented automatic matching device of regulation standard provisions, characterized by includes following:
the calling module is used for extracting keyword information from a regulation library;
the matching output module is used for acquiring the detected hidden danger information and the keywords thereof, matching the keywords with the keyword information of the rule base according to a preset matching rule, and outputting the matched rules and rules provisions;
and the feedback processing module is used for acquiring feedback information of the matched laws and regulations provisions and adjusting and optimizing the matching rules by combining the feedback information.
7. The device for automatically matching hidden danger-oriented regulation standard provisions according to claim 1, wherein the step of extracting keyword information from a regulation library specifically comprises the steps of: calling a rule base text, filtering the full text of the rule base text, and screening out a candidate word base according to a preset word frequency; calculating the word frequency of candidate words and the reverse frequency of the candidate words in the candidate word library; and calculating the statistical characteristic weight of the candidate words by combining the word frequency of the candidate words and the reverse frequency of the candidate words, and listing the previous topK words as keyword information according to a preset keyword threshold.
8. The automatic matching device for hidden danger-oriented regulation standard provisions according to claim 1, characterized in that the step of matching keywords with keyword information of a regulation library according to a preset matching rule and outputting matched regulations and regulation provisions specifically comprises the steps of: carrying out full-text accurate matching on the keyword information according to the hidden danger information keywords; carrying out preset synonym library matching on the hidden danger information keywords which are not accurately matched, and obtaining corresponding keyword information; and corresponding the matched keyword information to a regulation library to obtain the regulation and regulation provisions containing the keyword information.
9. The automatic matching device for hidden danger-oriented regulation standard provisions according to claim 7, characterized in that the feedback information comprises one of poor matching precision, good matching precision, low matching efficiency and high matching efficiency.
10. The automatic matching device for hidden danger-oriented regulation standard provisions according to claim 9, wherein the "adjusting and optimizing matching rules in combination with feedback information" specifically comprises: when the feedback information is detected to be 'poor matching precision', increasing the selection range of the keyword threshold value of the rule base; and when the feedback information is detected to be 'low matching efficiency', reducing the selection range of the keyword threshold value of the rule base.
CN202010534869.XA 2020-06-12 2020-06-12 Hidden danger-oriented automatic rule standard treaty matching method and device Active CN111695339B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010534869.XA CN111695339B (en) 2020-06-12 2020-06-12 Hidden danger-oriented automatic rule standard treaty matching method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010534869.XA CN111695339B (en) 2020-06-12 2020-06-12 Hidden danger-oriented automatic rule standard treaty matching method and device

Publications (2)

Publication Number Publication Date
CN111695339A true CN111695339A (en) 2020-09-22
CN111695339B CN111695339B (en) 2023-06-30

Family

ID=72480667

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010534869.XA Active CN111695339B (en) 2020-06-12 2020-06-12 Hidden danger-oriented automatic rule standard treaty matching method and device

Country Status (1)

Country Link
CN (1) CN111695339B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115481862A (en) * 2022-08-12 2022-12-16 华能山东发电有限公司 Safety production management platform for realizing dual management and control

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130091471A (en) * 2012-02-08 2013-08-19 주식회사 아이디어포트 Batch matching method and system for online date service
CN105630813A (en) * 2014-10-30 2016-06-01 苏宁云商集团股份有限公司 Keyword recommendation method and system based on user-defined template
CN108549697A (en) * 2018-04-16 2018-09-18 北京百度网讯科技有限公司 Information-pushing method, device, equipment based on semantic association and storage medium
CN109543044A (en) * 2018-10-22 2019-03-29 杭州叙简科技股份有限公司 A kind of event and legal provision automatic patching system and matching process
CN109614477A (en) * 2018-12-14 2019-04-12 浪潮软件股份有限公司 A kind of inspection result intelligent Matching method and system based on natural language
KR102009649B1 (en) * 2018-08-21 2019-08-13 한국건설기술연구원 Construction regulation legal information search system according to each classification plan of construction regulation, and method for the same
CN110874532A (en) * 2018-08-30 2020-03-10 北京京东尚科信息技术有限公司 Method and device for extracting keywords of feedback information

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130091471A (en) * 2012-02-08 2013-08-19 주식회사 아이디어포트 Batch matching method and system for online date service
CN105630813A (en) * 2014-10-30 2016-06-01 苏宁云商集团股份有限公司 Keyword recommendation method and system based on user-defined template
CN108549697A (en) * 2018-04-16 2018-09-18 北京百度网讯科技有限公司 Information-pushing method, device, equipment based on semantic association and storage medium
KR102009649B1 (en) * 2018-08-21 2019-08-13 한국건설기술연구원 Construction regulation legal information search system according to each classification plan of construction regulation, and method for the same
CN110874532A (en) * 2018-08-30 2020-03-10 北京京东尚科信息技术有限公司 Method and device for extracting keywords of feedback information
CN109543044A (en) * 2018-10-22 2019-03-29 杭州叙简科技股份有限公司 A kind of event and legal provision automatic patching system and matching process
CN109614477A (en) * 2018-12-14 2019-04-12 浪潮软件股份有限公司 A kind of inspection result intelligent Matching method and system based on natural language

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王万良;潘蒙;: "基于多特征的视频关联文本关键词提取方法", 浙江工业大学学报, no. 01, pages 18 - 22 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115481862A (en) * 2022-08-12 2022-12-16 华能山东发电有限公司 Safety production management platform for realizing dual management and control

Also Published As

Publication number Publication date
CN111695339B (en) 2023-06-30

Similar Documents

Publication Publication Date Title
US8402036B2 (en) Phrase based snippet generation
CN106445998A (en) Text content auditing method and system based on sensitive word
US20130238316A1 (en) System and Method for Identifying Text in Legal documents for Preparation of Headnotes
CN106598944A (en) Civil aviation security public opinion emotion analysis method
JP5711674B2 (en) Question answering program, server and method using a large amount of comment text
CN111611356B (en) Information searching method, device, electronic equipment and readable storage medium
US20140013221A1 (en) Method and device for filtering harmful information
CA2823178A1 (en) Method and system for enhanced data searching
CN111831804B (en) Method and device for extracting key phrase, terminal equipment and storage medium
WO2012174637A1 (en) System and method for matching comment data to text data
KR20150010740A (en) On-line product search method and system
CN110795628B (en) Search term processing method and device based on correlation and computing equipment
CN111767716A (en) Method and device for determining enterprise multilevel industry information and computer equipment
CN112001170B (en) Method and system for identifying deformed sensitive words
US20180246880A1 (en) System for generating synthetic sentiment using multiple points of reference within a hierarchical head noun structure
CN110032622A (en) Keyword determines method, apparatus, equipment and computer readable storage medium
US20150242493A1 (en) User-guided search query expansion
US20140101259A1 (en) System and Method for Threat Assessment
CN111695339A (en) Automatic matching method and device for hidden danger-oriented rule standard provisions
CN111444713B (en) Method and device for extracting entity relationship in news event
CN112487159B (en) Search method, search device, and computer-readable storage medium
US10474700B2 (en) Robust stream filtering based on reference document
CN112492606A (en) Classification and identification method and device for spam messages, computer equipment and storage medium
KR101291076B1 (en) Method and apparatus for determining spam document
CN116070620A (en) Information processing method and system based on big data

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