CN115422991A - Fault record classification method - Google Patents
Fault record classification method Download PDFInfo
- Publication number
- CN115422991A CN115422991A CN202210904343.5A CN202210904343A CN115422991A CN 115422991 A CN115422991 A CN 115422991A CN 202210904343 A CN202210904343 A CN 202210904343A CN 115422991 A CN115422991 A CN 115422991A
- Authority
- CN
- China
- Prior art keywords
- classification
- fault
- record
- name
- distance
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000012423 maintenance Methods 0.000 claims abstract description 11
- 230000002708 enhancing effect Effects 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 11
- 238000007635 classification algorithm Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000014509 gene expression Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000005728 strengthening Methods 0.000 claims 2
- 238000006467 substitution reaction Methods 0.000 claims 1
- 241000208125 Nicotiana Species 0.000 abstract description 3
- 235000002637 Nicotiana tabacum Nutrition 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 2
- 230000009286 beneficial effect 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06Q50/04—Manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a fault record classification method, and belongs to the technical field of tobacco MES (manufacturing execution system) automatic equipment management. The fault record classification method comprises a text enhancement method for performing keyword replacement and enhancing equipment part classification on fault records by using common languages and a weighted text editing distance algorithm to achieve automatic classification of fuzzy record fault information similar to spoken language. The method can classify the MES fault maintenance records by fewer samples on the basis of experience, has stable algorithm, automatically classifies the faults, classifies information under different management systems, takes the calculated total edit distance as a classification basis, and takes the middle position name of the target classification system corresponding to the sequenced maximum value as a classification result, thereby improving the accuracy of fault record identification.
Description
Technical Field
The invention belongs to the technical field of tobacco MES (manufacturing execution system) automatic equipment management, and particularly relates to a fault record classification method.
Background
The tobacco MES system management relates to related records in the equipment maintenance process, including equipment fault parts, fault description and the like, in order to use the information in the life cycle management of accessories, the point position control of key functions of equipment and the like, fuzzy MES maintenance records recorded manually need to correspond to the corresponding key function management positions of the equipment, but the MES records have ambiguity, and the number of samples is not large, so that the algorithm of more complex automatic classification is not enough, otherwise, the problems of data overfitting and the like are easily caused.
Therefore, there is a need to provide a fault record classification method, which has stable algorithm, can automatically classify faults and classify information under different management systems.
Disclosure of Invention
In order to overcome the problems that the MES records in the background technology have ambiguity, a relatively complex automatic classification algorithm is not enough due to the small number of samples, and data overfitting is easily caused otherwise, the invention provides a fault record classification method which is stable in algorithm, automatically classifies faults and classifies information under different management systems.
In order to realize the purpose, the invention is realized by the following technical scheme:
the invention provides a fault record classification method, which comprises a text enhancement method for performing keyword replacement and device part classification enhancement on fault records by using common languages and a weighted text editing distance algorithm to achieve automatic classification of fuzzy record fault information similar to spoken language.
The fault record classification method determines the corresponding positions of the MES maintenance record and the key function point position control by substituting the weighted Jaro-Winkler distance with empirical keywords, and the algorithm flow is as follows: fault recording general abnormal character processing; common names of semi-empirical equipment and materials are unified into unified key words in key function point positions; replacing the device name with some keywords with Jaro-Winkler distance of 0; respectively recording the Jaro-Winkler distance between the maintenance record content and the original classification name; adding the distance terms according to the weight; and sequencing according to the weight merging value to determine the final classification.
Preferably, the method for replacing the fault records by the keywords in the common language comprises the following steps: many common expressions commonly used in spoken language related to materials used by the device, names of bits on the device are all replaced by a uniform name in the device critical function location management system or the accessory lifecycle management system. Or uniformly removing the information such as the device name and the like in each record.
Preferably, the text enhancement method for enhancing the device location classification includes: similar part names used on different devices are replaced with name phrases that differ very much for the following classification algorithm.
Preferably, the weighted text editing distance algorithm achieves automatic classification of fuzzy record fault information similar to spoken language as follows: based on the original general Jaro-Winkler edit distance algorithm, the original system part name in the fault record, the fault description and the part names in the target classification system are used for respectively calculating the Jaro-Winkler edit distance, and the edit distance sum is calculated according to the weight coefficients of 2.5/4 and 1.5/4.
Preferably, the weighted Jaro-Winkler distance algorithm comprises the steps of quantifying and sorting the target classification name and a plurality of information items in the fault record system according to a certain weight, determining the most matched classification item, taking the calculated total edit distance as a classification basis, and taking the middle position name of the target classification system corresponding to the sorted maximum value as a classification result, so that the accuracy of fault record identification is improved.
The invention has the beneficial effects that:
the invention can classify MES fault maintenance records by less samples on the basis of experience, has stable algorithm, automatically classifies faults and classifies information under different management systems.
Drawings
FIG. 1 is a flow chart of the algorithm of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings to facilitate understanding of the skilled person.
As shown in fig. 1, the fault record classification method includes a text enhancement method for performing keyword replacement and enhancing device part classification on fault records by using a common language, and a weighted text editing distance algorithm to achieve automatic classification of fuzzy record fault information similar to spoken language.
The fault record classification method determines the corresponding positions of the MES maintenance record and the key function point position control by substituting the weighted Jaro-Winkler distance with empirical keywords, and the algorithm flow is as follows: fault recording general abnormal character processing; common names of semi-empirical equipment and materials are unified keywords in key function points; replacing the device name with some keywords with Jaro-Winkler distance of 0; respectively recording the Jaro-Winkler distance between the maintenance record content and the original classification name; adding the distance terms according to the weight; and sorting according to the weight merging value to determine the final classification.
The method for replacing the fault records by the keywords in the common language comprises the following steps: many common expressions commonly used in spoken language related to materials used by the device, names of bits on the device are all replaced by a uniform name in the device critical function location management system or the accessory lifecycle management system. Or uniformly removing the information such as the device name and the like in each record.
The text enhancement method for enhancing the device part classification comprises the following steps: similar part names used on different devices are replaced with name phrases that differ very much for the following classification algorithm.
The weighted text editing distance algorithm achieves the automatic classification of fuzzy recording fault information similar to spoken language as follows: based on the original general Jaro-Winkler edit distance algorithm, the original system part name in the fault record, the fault description and the part names in the target classification system are used for respectively calculating the Jaro-Winkler edit distance, and the edit distance sum is calculated according to the weight coefficients of 2.5/4 and 1.5/4.
The weighted Jaro-Winkler distance algorithm comprises the steps of quantifying and sorting the target classification name and a plurality of information items in the fault recording system according to a certain weight, determining the most matched classification item, taking the calculated total edit distance as a classification basis, and taking the middle position name of the target classification system corresponding to the sorted maximum value as a classification result, so that the accuracy of fault recording identification is improved.
Table 1 shows the results of partial fault classification:
table 1 partial fault classification result display
The method can classify the MES fault maintenance records by fewer samples on the basis of experience, has stable algorithm, automatically classifies the faults, classifies information under different management systems, takes the calculated total edit distance as a classification basis, and takes the middle position name of the target classification system corresponding to the sequenced maximum value as a classification result, thereby improving the accuracy of fault record identification.
Finally, it is noted that the above-mentioned preferred embodiments illustrate rather than limit the invention, and that, although the invention has been described in detail with reference to the above-mentioned preferred embodiments, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the invention as defined by the appended claims.
Claims (6)
1. A fault record classification method is characterized in that: the fault record classification method comprises a text strengthening method and a weighted text editing distance algorithm, wherein the common language is used for carrying out keyword substitution on fault records and strengthening equipment part classification, so that the automatic classification of fuzzy record fault information similar to spoken language is achieved;
the fault record classification method determines the corresponding positions of the MES maintenance record and the key function point position control by substituting the weighted Jaro-Winkler distance with empirical keywords, and the algorithm flow is as follows:
fault recording general abnormal character processing;
common names of semi-empirical equipment and materials are unified into unified key words in key function point positions;
replacing the device name with some keywords with Jaro-Winkler distance of 0;
respectively recording the Jaro-Winkler distance between the maintenance record content and the original classification name;
adding the distance terms according to the weight;
and sequencing according to the weight merging value to determine the final classification.
2. The fault record classification method according to claim 1, characterized in that: the method for replacing the fault records by the keywords in the common language comprises the following steps: the common general expressions in the spoken language related to the materials used by the equipment and the names of the upper parts of the equipment are all replaced by the unified names in the key function position management system or the accessory life cycle management system of the equipment, or the information such as the equipment names in all records is removed in a unified way.
3. A fault record classification method according to claim 1 or 2, characterized in that: the text enhancement method for enhancing the device part classification comprises the following steps: similar part names used on different devices are replaced with name phrases that are very different for the following classification algorithm.
4. A fault record classification method according to claim 1 or 2, characterized in that: the weighted text editing distance algorithm achieves automatic classification of fuzzy recording fault information similar to spoken language as follows: based on the original general Jaro-Winkler edit distance algorithm, the original system part name in the fault record, the fault description and the part names in the target classification system are used for respectively calculating the Jaro-Winkler edit distance, and the edit distance sum is calculated according to the weight coefficients of 2.5/4 and 1.5/4.
5. A fault record classification method according to claim 1 or 2, characterized in that: the weighted Jaro-Winkler distance algorithm comprises the steps of quantifying and sorting the target classification name and a plurality of information items in the fault recording system according to a certain weight, determining the most matched classification item, taking the calculated total edit distance as a classification basis, and taking the middle position name of the target classification system corresponding to the sorted maximum value as a classification result, so that the accuracy of fault recording identification is improved.
6. The fault record classification method according to claim 4, characterized in that: the weighted Jaro-Winkler distance algorithm comprises the steps of quantifying and sorting the target classification name and a plurality of information items in the fault recording system according to a certain weight, determining the most matched classification item, taking the calculated total edit distance as a classification basis, and taking the middle position name of the target classification system corresponding to the sorted maximum value as a classification result, so that the accuracy of fault recording identification is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210904343.5A CN115422991A (en) | 2022-07-29 | 2022-07-29 | Fault record classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210904343.5A CN115422991A (en) | 2022-07-29 | 2022-07-29 | Fault record classification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115422991A true CN115422991A (en) | 2022-12-02 |
Family
ID=84196329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210904343.5A Pending CN115422991A (en) | 2022-07-29 | 2022-07-29 | Fault record classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115422991A (en) |
-
2022
- 2022-07-29 CN CN202210904343.5A patent/CN115422991A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109165294B (en) | Short text classification method based on Bayesian classification | |
| CN111414479A (en) | Label extraction method based on short text clustering technology | |
| CN112632980A (en) | Enterprise classification method and system based on big data deep learning and electronic equipment | |
| CN111860981A (en) | Enterprise national industry category prediction method and system based on LSTM deep learning | |
| CN113468317B (en) | Resume screening method, system, equipment and storage medium | |
| CN111026870A (en) | ICT system fault analysis method integrating text classification and image recognition | |
| CN111462752A (en) | Client intention identification method based on attention mechanism, feature embedding and BI-L STM | |
| CN108363691A (en) | A kind of field term identifying system and method for 95598 work order of electric power | |
| CN111078979A (en) | Method and system for identifying network credit website based on OCR and text processing technology | |
| CN115794798A (en) | Market supervision informationized standard management and dynamic maintenance system and method | |
| CN114491034B (en) | Text classification method and intelligent device | |
| CN109543038B (en) | Emotion analysis method applied to text data | |
| CN116841779A (en) | Abnormality log detection method, abnormality log detection device, electronic device and readable storage medium | |
| CN107480126B (en) | Intelligent identification method for engineering material category | |
| CN111104422B (en) | Training method, device, equipment and storage medium of data recommendation model | |
| CN117454220A (en) | Data hierarchical classification method, device, equipment and storage medium | |
| CN117436440A (en) | Log identification method, system, terminal equipment and storage medium | |
| CN102103604B (en) | Method and device for determining core weight of term | |
| CN108615124B (en) | Enterprise evaluation method and system based on word frequency analysis | |
| CN110688445B (en) | Digital archive construction method | |
| CN115422991A (en) | Fault record classification method | |
| CN115936748A (en) | Business big data analysis method and system | |
| CN115952282A (en) | Intelligent bank customer complaint diversion handling method and system based on NLP technology | |
| CN114638219A (en) | Intelligent wrong word recognition method based on machine learning algorithm | |
| CN114490937A (en) | Comment analysis method and device based on semantic perception |
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 |