CN111950840A - Intelligent operation and maintenance knowledge retrieval method and system for metrological verification device - Google Patents
Intelligent operation and maintenance knowledge retrieval method and system for metrological verification device Download PDFInfo
- Publication number
- CN111950840A CN111950840A CN202010564518.3A CN202010564518A CN111950840A CN 111950840 A CN111950840 A CN 111950840A CN 202010564518 A CN202010564518 A CN 202010564518A CN 111950840 A CN111950840 A CN 111950840A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- intelligent operation
- verification device
- metrological verification
- maintenance knowledge
- 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.)
- Pending
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 96
- 238000012795 verification Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000009826 distribution Methods 0.000 claims abstract description 52
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 239000013598 vector Substances 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 238000012163 sequencing technique Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 22
- 238000012952 Resampling Methods 0.000 claims description 12
- 230000000737 periodic effect Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000003672 processing method Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims 1
- 238000007418 data mining Methods 0.000 abstract description 4
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000031968 Cadaver Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06F16/332—Query formulation
-
- 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
- G06Q—INFORMATION 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent operation and maintenance knowledge retrieval method and system for a metrological verification device, which are used for acquiring intelligent operation and maintenance knowledge query data; calculating the intelligent operation and maintenance knowledge query data to obtain a query data topic distribution vector; similarity calculation is carried out on the query data topic distribution vector and a topic distribution matrix in a pre-constructed semantic analysis model to obtain similarity sequencing, and the higher the sequencing is, the better the retrieval result is represented; and acquiring user feedback information aiming at the retrieval result, carrying out self-learning by the semantic analysis model, and updating the learning result to an intelligent operation and maintenance knowledge base of the semantic analysis model. The advantages are that: the method improves the accuracy of similarity calculation between the documents, and further improves the precision level of the intelligent operation and maintenance knowledge retrieval result; the invention utilizes the subject model principle of Bayesian learning, is not only suitable for text data mining of knowledge retrieval, but also can be expanded to multiple fields of image processing, biological information processing and the like.
Description
Technical Field
The invention relates to an intelligent operation and maintenance knowledge retrieval method and system for a metrological verification device, and belongs to the technical field of data mining and intelligent analysis.
Background
According to the requirements of the national power grid company, a metering center undertakes the centralized verification work of metering devices such as an intelligent electric energy meter, a collection terminal and the like, a metering verification device is used as a physical carrier of the verification work, the metering verification device runs for a certain time under overload, corresponding accessories enter an aging stage, and faults are in a high-incidence trend.
The current operation and maintenance status of the current metrological verification device is as follows:
(1) the metering and calibrating device is increasingly complex, the requirement on maintenance personnel is increasingly improved, the operation and maintenance work of a metering center mainly takes manufacturer personnel as main personnel, the situation of fault treatment passive response is caused by a mechanism of finding faults through passive patrol, and the running state data, the production and calibration data, the field operation and maintenance data and the like of equipment are not communicated with each other, so that the operation and maintenance work cannot be supported through data mining analysis, and the stable production and calibration of a metering device cannot be ensured;
(2) the equipment operation and maintenance lacks a uniform knowledge system, and the personnel flow to cause the obvious decline trend of the operation and maintenance work quality mainly depending on the experience of the operation and maintenance personnel, thereby seriously influencing the normal work. And as time goes on, new faults of the metrological verification device continuously occur, and corresponding processing methods are continuously updated. Due to the lack of an effective knowledge system, an operation and maintenance knowledge sharing mechanism is not mature, and faults cannot be eliminated accurately and timely.
At present, the operation and maintenance knowledge combing means for the metrological verification device is as follows:
(1) combing under an operation and maintenance knowledge line: the method adopts a statistical induction means, compiles, sorts and analyzes the classical fault cases of the metrological verification device, and establishes the operation and maintenance knowledge of 'fault phenomenon-fault reason-fault solution' which is the main mode adopted at present, and the operation and maintenance knowledge mainly depends on the carding of operation and maintenance personnel and has the defects of insufficient hysteresis, reliability and the like.
(2) Intelligent operation and maintenance knowledge retrieval: the currently adopted knowledge retrieval matching mode is mainly to determine the keywords of an article by calculating the word frequency (TF) and the inverse text frequency Index (IDF) based on text analysis, and the larger the TF-IDF value is, the higher the importance degree of a word in the article is, the more possible the word is the keyword. Considering the situation that a search sentence often contains "ambiguous word" and "ambiguous word", the text analysis method without semantics may cause the retrieval result to be inaccurate.
From the application modes, the conventional metrological verification device knowledge combing mainly depends on offline summary arrangement of operation and maintenance personnel, the retrieval mode mainly depends on text analysis-based methods to determine keywords, and further a semantic-based text analysis method is not adopted to construct a metrological verification device knowledge system according to text matching.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an intelligent operation and maintenance knowledge retrieval method and system for a metrological verification device.
In order to solve the technical problems, the invention provides an intelligent operation and maintenance knowledge retrieval method for a metrological verification device, which is used for acquiring intelligent operation and maintenance knowledge query data;
calculating intelligent operation and maintenance knowledge query data to obtain a query data topic distribution vector;
similarity calculation is carried out on the query data topic distribution vector and a topic distribution matrix in a pre-constructed semantic analysis model to obtain similarity sequencing, and the higher the sequencing is, the better the retrieval result is represented;
and acquiring user feedback information aiming at the retrieval result, carrying out self-learning by the semantic analysis model, and updating the learning result to an intelligent operation and maintenance knowledge base of the semantic analysis model.
Further, the intelligent operation and maintenance knowledge query data is preprocessed as follows:
and removing non-characteristic words and noise words according to the existing fault processing system of the metrological verification device and the basic periodic operation and maintenance rules of the metrological verification device.
Further, the semantic analysis model is constructed by:
acquiring sample basic data of intelligent operation and maintenance knowledge, removing non-characteristic vocabularies and noise vocabularies according to a fault processing system of a metrological verification device and basic periodic operation and maintenance rules of the metrological verification device, and determining a sample library of the intelligent operation and maintenance knowledge;
setting a user professional dictionary, bringing the special nouns of the metrological verification device in the sample library into the dictionary, and realizing text word segmentation by adopting a JIEBA tool through a large amount of corpus training to form a document word bag set; coding the vocabulary of the word bag, calculating the word frequency of each sample document in the sample library and vectorizing the text to obtain a word frequency matrix of a document set consisting of all documents;
random initialization, wherein a theme is randomly given to each word of a sample document in a sample library; rescanning the sample document, resampling the topic for each word according to the expected maximum algorithm, updating in the sample library, repeating the resampling process of the sample library, and adjusting the number of topics until the likelihood function is maximized.
Further, the similarity calculation uses a cosine similarity function:
θ1: inquiring a data topic distribution vector;
θ2: topic distribution vectors in the knowledge base.
Further, the user feedback information comes from the arrangement sequence selected by the client after the similarity sorting and the accuracy of the method content;
if the position of the intelligent operation and maintenance knowledge retrieval result selected by the user in the ordered list indicates that the accuracy is poor for the matching, adding the user input into the topic description of the corresponding knowledge document, and improving the model by adjusting the distribution mode of the topic words in the model; and if the operation and maintenance personnel find that the accuracy of the recommendation method is insufficient after the operation and maintenance personnel check, adding the actual processing method into the document sample set and calculating the theme matrix.
By feeding back the information of actual operation to the sample set, the method is more service-instructive for learning and perfecting the model, and is more accurate for recommending the subsequent operation and maintenance knowledge.
An intelligent operation and maintenance knowledge retrieval system for a metrological verification device, comprising:
the acquisition module is used for acquiring intelligent operation and maintenance knowledge query data;
the first calculation module is used for calculating the intelligent operation and maintenance knowledge query data to obtain a query data topic distribution vector;
the second calculation module is used for carrying out similarity calculation on the topic distribution vector of the query data and a topic distribution matrix in a pre-constructed semantic analysis model to obtain similarity sequencing, wherein the higher the sequencing is, the better the representation retrieval result is;
and the feedback processing module is used for acquiring user feedback information aiming at the retrieval result, the semantic analysis model performs self-learning, and the learning result is updated to the intelligent operation and maintenance knowledge base of the semantic analysis model.
Further, the acquisition module further comprises a preprocessing module for removing non-characteristic words and noise words according to the existing fault processing system of the metrological verification device and the basic periodic operation and maintenance rules of the metrological verification device.
Further, the second calculation module further includes:
the first determination module is used for acquiring sample basic data of the intelligent operation and maintenance knowledge, removing non-characteristic vocabularies and noise vocabularies according to a fault processing system of the metrological verification device and basic periodic operation and maintenance rules of the metrological verification device, and determining a sample library of the intelligent operation and maintenance knowledge;
the second determination module is used for setting a user professional dictionary, bringing the proper nouns of the metrological verification device in the sample library into the dictionary, and realizing text word segmentation by adopting a JIEBA tool through a large amount of corpus training to form a document word bag set; coding the vocabulary of the word bag, calculating the word frequency of each sample document in the sample library and vectorizing the text to obtain a word frequency matrix of a document set consisting of all documents;
the circulation module is used for carrying out random initialization and randomly endowing a theme to each word of the sample document in the sample library; rescanning the sample document, resampling the topic for each word according to the expected maximum algorithm, updating in the sample library, repeating the resampling process of the sample library, and adjusting the number of topics until the likelihood function is maximized.
Further, the second calculating module further includes a similarity calculating module, configured to calculate a similarity through a cosine similarity function, where the cosine similarity function is expressed as:
θ1: inquiring a data topic distribution vector;
θ2: topic distribution vectors in the knowledge base.
Further, the feedback processing module further includes:
the feedback information acquisition module is used for acquiring user feedback information, wherein the user feedback information is derived from the arrangement sequence and the accuracy of the method content selected by the client after the similarity sorting;
the feedback information acquisition module includes:
the judging module is used for judging that if the later position of the intelligent operation and maintenance knowledge retrieval result selected by the user in the ordered list indicates that the accuracy is poor for the matching, adding the user input into the topic description of the corresponding knowledge document, and improving the model by adjusting the distribution mode of the topic words in the model; and if the operation and maintenance personnel find that the accuracy of the recommendation method is insufficient after the operation and maintenance personnel check, adding the actual processing method into the document sample set and calculating the theme matrix.
The invention achieves the following beneficial effects:
the invention can solve the problems of 'ambiguous word' and the like by utilizing the thought of Bayesian learning and performing text analysis based on semantics, improves the accuracy of similarity calculation between documents and further improves the accuracy level of intelligent operation and maintenance knowledge retrieval results.
The technology used by the invention is the expansion of algorithms such as a word vector space model, latent semantic analysis, probability latent semantic analysis and the like, and the Bayesian learning topic model principle is utilized, so that the method not only can be suitable for text data mining of knowledge retrieval, but also can be expanded to multiple fields such as image processing, biological information processing and the like.
Drawings
Fig. 1 is a flowchart illustrating steps of an intelligent operation and maintenance knowledge retrieval method for a metrological verification apparatus according to an embodiment of the present invention.
FIG. 2 is a flowchart of the steps of the document theme determination model in the embodiment shown in FIG. 1.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The invention discloses a semantic analysis technology-based intelligent operation and maintenance knowledge method for a metrological verification device, which is shown in figure 1 and has the following specific implementation modes:
1) preprocessing basic data:
constructing and coding a five-level fault processing system of 'fault part-fault phenomenon-fault reason-processing method-verification after repair', formulating a periodic operation and maintenance rule comprising operation and maintenance working type, period, content, safe working condition and matched spare parts and tools, removing punctuation marks and non-characteristic words with low reverse text frequency in the rule, and improving the data accuracy and the accuracy of a text matching algorithm.
2) Building semantic analysis model
(1) Calculating word frequency matrix
As shown in fig. 2, a user professional dictionary is set, proper nouns (such as AGV, RFID, PLC, master control, etc.) of the metrological verification device are brought into the dictionary, text word segmentation is realized through a large amount of corpus training by using a JIEBA tool, and a document "word bag" set is formed. And coding the vocabulary of the word bag, calculating the word frequency of each document, vectorizing the text, and obtaining a word frequency matrix of the document set as the input of the model.
(2) Document topic computation
Random initialization, wherein a theme is randomly given to each word of a sample document in a sample library; rescanning the sample document, resampling the topic for each word according to the expected maximum algorithm, updating in the sample library, repeating the resampling process of the sample library, and adjusting the number of topics until the likelihood function is maximized.
The likelihood function is the following equation:
description of the parameters:
d: a set of documents (corps);
m: the number of documents;
Nd: the number of words contained in the d-th document;
k: number of topics (model parameters set by user);
wd,n: the nth vocabulary of document d;
zd,n: the topic to which the nth word of document d belongs;
θd: the text topic distribution vector value obeys the hyper-parameter of polynomial distribution;
parameter estimation (z)d,n，wd,n) Maximizing the likelihood function to finally obtain the theme distribution of each document;
3) calculating text matching degree
Using the cosine similarity function:
θ1: inquiring a data topic distribution vector;
θ2: topic distribution vectors in the knowledge base.
And carrying out similarity calculation on the topic distribution matrix of the knowledge document and the topic distribution vector of the query information input by the user to obtain similarity sequencing, and selecting the knowledge document with the top rank to provide for the user.
4) Model iterative tuning
And the intelligent retrieval and recommendation functions of the method are perfected according to the use feedback of the user, and the deep self-learning is carried out. The user feedback is derived from the ranking order of the selected knowledge methods and the accuracy of the method content. If the later position of the knowledge method selected by the user in the sorted list indicates that the accuracy is poor for the matching, adding the user input into the topic description of the corresponding knowledge document, and adjusting the mode of topic word distribution in the model to improve the model; and if the user finds that the accuracy of the recommendation method is not enough after the reason is checked, adding the actual processing method into the document sample set and calculating the theme matrix.
Correspondingly, the invention also provides an intelligent operation and maintenance knowledge retrieval system of the metrological verification device, which comprises:
the acquisition module is used for acquiring intelligent operation and maintenance knowledge query data;
the first calculation module is used for calculating the intelligent operation and maintenance knowledge query data to obtain a query data topic distribution vector;
the second calculation module is used for carrying out similarity calculation on the topic distribution vector of the query data and a topic distribution matrix in a pre-constructed semantic analysis model to obtain similarity sequencing, wherein the higher the sequencing is, the better the representation retrieval result is;
and the feedback processing module is used for acquiring user feedback information aiming at the retrieval result, the semantic analysis model performs self-learning, and the learning result is updated to the intelligent operation and maintenance knowledge base of the semantic analysis model.
Further, the acquisition module further comprises a preprocessing module for removing non-characteristic words and noise words according to the existing fault processing system of the metrological verification device and the basic periodic operation and maintenance rules of the metrological verification device.
The second computing module further comprises:
the first determination module is used for acquiring sample basic data of the intelligent operation and maintenance knowledge, removing non-characteristic vocabularies and noise vocabularies according to a fault processing system of the metrological verification device and basic periodic operation and maintenance rules of the metrological verification device, and determining a sample library of the intelligent operation and maintenance knowledge;
the second determination module is used for setting a user professional dictionary, bringing the proper nouns of the metrological verification device in the sample library into the dictionary, and realizing text word segmentation by adopting a JIEBA tool through a large amount of corpus training to form a document word bag set; coding the vocabulary of the word bag, calculating the word frequency of each sample document in the sample library and vectorizing the text to obtain a word frequency matrix of a document set consisting of all documents;
the circulation module is used for carrying out random initialization and randomly endowing a theme to each word of the sample document in the sample library; rescanning the sample document, resampling the topic for each word according to the expected maximum algorithm, updating in the sample library, repeating the resampling process of the sample library, and adjusting the number of topics until the likelihood function is maximized.
The second calculation module further includes a similarity calculation module for calculating a similarity by a cosine similarity function, where the cosine similarity function is expressed as:
θ1: inquiring a data topic distribution vector;
θ2: topic distribution vectors in the knowledge base.
The feedback processing module further comprises:
the feedback information acquisition module is used for acquiring user feedback information, wherein the user feedback information is derived from the arrangement sequence and the accuracy of the method content selected by the client after the similarity sorting;
the feedback information acquisition module includes:
the judging module is used for judging that if the later position of the intelligent operation and maintenance knowledge retrieval result selected by the user in the ordered list indicates that the accuracy is poor for the matching, adding the user input into the topic description of the corresponding knowledge document, and improving the model by adjusting the distribution mode of the topic words in the model; and if the operation and maintenance personnel find that the accuracy of the recommendation method is insufficient after the operation and maintenance personnel check, adding the actual processing method into the document sample set and calculating the theme matrix.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. An intelligent operation and maintenance knowledge retrieval method for a metrological verification device is characterized in that,
acquiring intelligent operation and maintenance knowledge query data;
calculating intelligent operation and maintenance knowledge query data to obtain a query data topic distribution vector;
similarity calculation is carried out on the query data topic distribution vector and a topic distribution matrix in a pre-constructed semantic analysis model to obtain similarity sequencing, and the higher the sequencing is, the better the retrieval result is represented;
and acquiring user feedback information aiming at the retrieval result, carrying out self-learning by the semantic analysis model, and updating the learning result to an intelligent operation and maintenance knowledge base of the semantic analysis model.
2. The intelligent operation and maintenance knowledge retrieval method of the metrological verification device as claimed in claim 1, wherein the intelligent operation and maintenance knowledge query data is preprocessed as follows:
and removing non-characteristic words and noise words according to the existing fault processing system of the metrological verification device and the basic periodic operation and maintenance rules of the metrological verification device.
3. The intelligent operation and maintenance knowledge retrieval method for the metrological verification device as claimed in claim 1, wherein the construction of the semantic analysis model comprises:
acquiring sample basic data of intelligent operation and maintenance knowledge, removing non-characteristic vocabularies and noise vocabularies according to a fault processing system of a metrological verification device and basic periodic operation and maintenance rules of the metrological verification device, and determining a sample library of the intelligent operation and maintenance knowledge;
setting a user professional dictionary, bringing the special nouns of the metrological verification device in the sample library into the dictionary, and realizing text word segmentation by adopting a JIEBA tool through a large amount of corpus training to form a document word bag set; coding the vocabulary of the word bag, calculating the word frequency of each sample document in the sample library and vectorizing the text to obtain a word frequency matrix of a document set consisting of all documents;
random initialization, wherein a theme is randomly given to each word of a sample document in a sample library; rescanning the sample document, resampling the topic for each word according to the expected maximum algorithm, updating in the sample library, repeating the resampling process of the sample library, and adjusting the number of topics until the likelihood function is maximized.
4. The intelligent operation and maintenance knowledge retrieval method for the metrological verification device as claimed in claim 1, wherein the similarity calculation uses a cosine similarity function:
θ1: inquiring a data topic distribution vector;
θ2: topic distribution vectors in the knowledge base.
5. The intelligent operation and maintenance knowledge retrieval method of the metrological verification device as claimed in claim 1, wherein the user feedback information is derived from the accuracy of the method content and the arrangement sequence selected by the customer after the similarity ranking;
if the position of the intelligent operation and maintenance knowledge retrieval result selected by the user in the ordered list indicates that the accuracy is poor for the matching, adding the user input into the topic description of the corresponding knowledge document, and improving the model by adjusting the distribution mode of the topic words in the model; and if the operation and maintenance personnel find that the accuracy of the recommendation method is insufficient after the operation and maintenance personnel check, adding the actual processing method into the document sample set and calculating the theme matrix.
6. The utility model provides a metrological verification device intelligence operation and maintenance knowledge retrieval system which characterized in that includes:
the acquisition module is used for acquiring intelligent operation and maintenance knowledge query data;
the first calculation module is used for calculating the intelligent operation and maintenance knowledge query data to obtain a query data topic distribution vector;
the second calculation module is used for carrying out similarity calculation on the topic distribution vector of the query data and a topic distribution matrix in a pre-constructed semantic analysis model to obtain similarity sequencing, wherein the higher the sequencing is, the better the representation retrieval result is;
and the feedback processing module is used for acquiring user feedback information aiming at the retrieval result, the semantic analysis model performs self-learning, and the learning result is updated to the intelligent operation and maintenance knowledge base of the semantic analysis model.
7. The intelligent operation and maintenance knowledge retrieval system for the metrological verification device as claimed in claim 6, wherein the obtaining module further comprises a preprocessing module for removing non-characteristic words and noise words according to the existing fault handling system of the metrological verification device and the basic periodic operation and maintenance rules of the metrological verification device.
8. The intelligent operation and maintenance knowledge retrieval system of metrological verification device as claimed in claim 6, wherein said second computing module further comprises:
the first determination module is used for acquiring sample basic data of the intelligent operation and maintenance knowledge, removing non-characteristic vocabularies and noise vocabularies according to a fault processing system of the metrological verification device and basic periodic operation and maintenance rules of the metrological verification device, and determining a sample library of the intelligent operation and maintenance knowledge;
the second determination module is used for setting a user professional dictionary, bringing the proper nouns of the metrological verification device in the sample library into the dictionary, and realizing text word segmentation by adopting a JIEBA tool through a large amount of corpus training to form a document word bag set; coding the vocabulary of the word bag, calculating the word frequency of each sample document in the sample library and vectorizing the text to obtain a word frequency matrix of a document set consisting of all documents;
the circulation module is used for carrying out random initialization and randomly endowing a theme to each word of the sample document in the sample library; rescanning the sample document, resampling the topic for each word according to the expected maximum algorithm, updating in the sample library, repeating the resampling process of the sample library, and adjusting the number of topics until the likelihood function is maximized.
9. The intelligent operation and maintenance knowledge retrieval system of a metrological verification device as claimed in claim 6, wherein the second calculation module further comprises a similarity calculation module for calculating the similarity by a cosine similarity function expressed as:
θ1: querying dataA topic distribution vector;
θ2: topic distribution vectors in the knowledge base.
10. The intelligent operation and maintenance knowledge retrieval system of a metrological verification device as claimed in claim 6, wherein the feedback processing module further comprises:
the feedback information acquisition module is used for acquiring user feedback information, wherein the user feedback information is derived from the arrangement sequence and the accuracy of the method content selected by the client after the similarity sorting;
the feedback information acquisition module includes:
the judging module is used for judging that if the later position of the intelligent operation and maintenance knowledge retrieval result selected by the user in the ordered list indicates that the accuracy is poor for the matching, adding the user input into the topic description of the corresponding knowledge document, and improving the model by adjusting the distribution mode of the topic words in the model; and if the operation and maintenance personnel find that the accuracy of the recommendation method is insufficient after the operation and maintenance personnel check, adding the actual processing method into the document sample set and calculating the theme matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010564518.3A CN111950840A (en) | 2020-06-19 | 2020-06-19 | Intelligent operation and maintenance knowledge retrieval method and system for metrological verification device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010564518.3A CN111950840A (en) | 2020-06-19 | 2020-06-19 | Intelligent operation and maintenance knowledge retrieval method and system for metrological verification device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111950840A true CN111950840A (en) | 2020-11-17 |
Family
ID=73337881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010564518.3A Pending CN111950840A (en) | 2020-06-19 | 2020-06-19 | Intelligent operation and maintenance knowledge retrieval method and system for metrological verification device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111950840A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580831A (en) * | 2020-11-19 | 2021-03-30 | 国网江苏省电力有限公司信息通信分公司 | Intelligent auxiliary operation and maintenance method and system for power communication network based on knowledge graph |
| CN112599120A (en) * | 2020-12-11 | 2021-04-02 | 上海中通吉网络技术有限公司 | Semantic determination method and device based on user-defined weighted WMD algorithm |
| CN113626594A (en) * | 2021-07-16 | 2021-11-09 | 上海齐网网络科技有限公司 | Operation and maintenance knowledge base establishing method and system based on multiple intelligent agents |
| CN116522011A (en) * | 2023-05-16 | 2023-08-01 | 深圳九星互动科技有限公司 | Big data-based pushing method and pushing system |
| WO2024169171A1 (en) * | 2023-02-13 | 2024-08-22 | 合肥工业大学 | Green knowledge recommendation method based on feature similarity and user requirements |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156272A (en) * | 2016-06-21 | 2016-11-23 | 北京工业大学 | A kind of information retrieval method based on multi-source semantic analysis |
| CN110147798A (en) * | 2019-04-18 | 2019-08-20 | 北京彼维网络技术有限公司 | A kind of semantic similarity learning method can be used for network information detection |
| CN110457442A (en) * | 2019-08-09 | 2019-11-15 | 国家电网有限公司 | The knowledge mapping construction method of smart grid-oriented customer service question and answer |
| CN110955782A (en) * | 2019-11-15 | 2020-04-03 | 国网甘肃省电力公司 | Scheduling control knowledge representation method based on knowledge graph |
| CN111159343A (en) * | 2019-12-26 | 2020-05-15 | 上海科技发展有限公司 | Text similarity searching method, device, equipment and medium based on text embedding |
-
2020
- 2020-06-19 CN CN202010564518.3A patent/CN111950840A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156272A (en) * | 2016-06-21 | 2016-11-23 | 北京工业大学 | A kind of information retrieval method based on multi-source semantic analysis |
| CN110147798A (en) * | 2019-04-18 | 2019-08-20 | 北京彼维网络技术有限公司 | A kind of semantic similarity learning method can be used for network information detection |
| CN110457442A (en) * | 2019-08-09 | 2019-11-15 | 国家电网有限公司 | The knowledge mapping construction method of smart grid-oriented customer service question and answer |
| CN110955782A (en) * | 2019-11-15 | 2020-04-03 | 国网甘肃省电力公司 | Scheduling control knowledge representation method based on knowledge graph |
| CN111159343A (en) * | 2019-12-26 | 2020-05-15 | 上海科技发展有限公司 | Text similarity searching method, device, equipment and medium based on text embedding |
Non-Patent Citations (4)
| Title |
|---|
| DAVID M.BLEI等: "Latent Dirichlet Allocation", JOURNAL OF MACHINE LEARNING RESEARCH, vol. 3, 31 January 2003 (2003-01-31), pages 993 - 1022 * |
| 何旭峰等: "基于LDA主题模型的分布式信息检索集合选择方法", 中文信息学报, vol. 31, no. 3, pages 125 - 133 * |
| 图书情报工作杂志社: "知识服务的现在与未来", 31 October 2013, 海洋出版社, pages: 245 - 249 * |
| 来骥等: "基于语义分析的运维数据关联知识库构建方法", 科学技术与工程, vol. 18, no. 19, pages 218 - 223 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580831A (en) * | 2020-11-19 | 2021-03-30 | 国网江苏省电力有限公司信息通信分公司 | Intelligent auxiliary operation and maintenance method and system for power communication network based on knowledge graph |
| CN112580831B (en) * | 2020-11-19 | 2024-03-29 | 国网江苏省电力有限公司信息通信分公司 | Intelligent auxiliary operation and maintenance method and system for power communication network based on knowledge graph |
| CN112599120A (en) * | 2020-12-11 | 2021-04-02 | 上海中通吉网络技术有限公司 | Semantic determination method and device based on user-defined weighted WMD algorithm |
| CN113626594A (en) * | 2021-07-16 | 2021-11-09 | 上海齐网网络科技有限公司 | Operation and maintenance knowledge base establishing method and system based on multiple intelligent agents |
| CN113626594B (en) * | 2021-07-16 | 2023-09-01 | 上海齐网网络科技有限公司 | Operation and maintenance knowledge base establishing method and system based on multiple intelligent agents |
| WO2024169171A1 (en) * | 2023-02-13 | 2024-08-22 | 合肥工业大学 | Green knowledge recommendation method based on feature similarity and user requirements |
| CN116522011A (en) * | 2023-05-16 | 2023-08-01 | 深圳九星互动科技有限公司 | Big data-based pushing method and pushing system |
| CN116522011B (en) * | 2023-05-16 | 2024-02-13 | 深圳九星互动科技有限公司 | Big data-based pushing method and pushing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111950840A (en) | Intelligent operation and maintenance knowledge retrieval method and system for metrological verification device | |
| CN111581545A (en) | Method for sorting recalled documents and related equipment | |
| CN108986907A (en) | A kind of tele-medicine based on KNN algorithm divides the method for examining automatically | |
| CN117217277A (en) | Pre-training method, device, equipment, storage medium and product of language model | |
| CN116910599A (en) | Data clustering method, system, electronic equipment and storage medium | |
| CN117290404A (en) | Method and system for rapidly searching and practical main distribution network fault processing method | |
| CN113032573B (en) | Large-scale text classification method and system combining topic semantics and TF-IDF algorithm | |
| CN113010643B (en) | Method, device, equipment and storage medium for processing vocabulary in Buddha field | |
| Wang et al. | Neighborhood Intervention Consistency: Measuring Confidence for Knowledge Graph Link Prediction. | |
| CN112926340B (en) | Semantic matching model for knowledge point positioning | |
| CN111382265B (en) | Searching method, device, equipment and medium | |
| CN116738214A (en) | Data dimension reduction preprocessing method based on high-order tensor | |
| CN115757464B (en) | Intelligent materialized view query method based on deep reinforcement learning | |
| CN114372145B (en) | Scheduling method for dynamic allocation of operation and maintenance resources based on knowledge graph platform | |
| CN111104422A (en) | Training method, device, equipment and storage medium of data recommendation model | |
| CN111444414A (en) | Information retrieval model for modeling various relevant characteristics in ad-hoc retrieval task | |
| Yang et al. | Court similar case recommendation model based on word embedding and word frequency | |
| CN114610882A (en) | Abnormal equipment code detection method and system based on electric power short text classification | |
| Purnomo et al. | Synthesis ensemble oversampling and ensemble tree-based machine learning for class imbalance problem in breast cancer diagnosis | |
| CN113590755A (en) | Word weight generation method and device, electronic equipment and storage medium | |
| CN111737469A (en) | Data mining method and device, terminal equipment and readable storage medium | |
| CN115859968B (en) | Policy granulation analysis system based on natural language analysis and machine learning | |
| CN114118085B (en) | Text information processing method, device and equipment | |
| Xie et al. | Data-dependent locality sensitive hashing | |
| CN118550908A (en) | Standardized method and system for manufacturing process text 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 |