CN111339766A - Operation ticket compliance checking method and device - Google Patents
Operation ticket compliance checking method and device Download PDFInfo
- Publication number
- CN111339766A CN111339766A CN202010100909.XA CN202010100909A CN111339766A CN 111339766 A CN111339766 A CN 111339766A CN 202010100909 A CN202010100909 A CN 202010100909A CN 111339766 A CN111339766 A CN 111339766A
- Authority
- CN
- China
- Prior art keywords
- data set
- ticket
- training
- matching
- initial data
- 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 24
- 238000012549 training Methods 0.000 claims abstract description 59
- 230000011218 segmentation Effects 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000007689 inspection Methods 0.000 claims description 10
- 238000013519 translation Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 description 3
- 230000037430 deletion Effects 0.000 description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Landscapes
- Document Processing Apparatus (AREA)
Abstract
The application discloses a method and a device for checking compliance of operation tickets, wherein the method comprises the steps of obtaining an initial data set of filing tickets and revocation tickets; preprocessing an initial data set by using NLP data enhancement to obtain a basic corpus; performing text splitting processing on the basic corpus to obtain a Chinese character set, and performing part-of-speech tagging on the Chinese characters; converting the part-of-speech marked characters into numbers to form a training data set; training the training data set by using a BERT model; training the filing ticket data by using the trained BERT model to generate a corresponding rule base; training the operation order to be checked by using the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence; and matching the word segmentation result and the part-of-speech tagging sequence with a rule base to complete the compliance check of the operation ticket. The method and the device are used for training the filing tickets and the voiding tickets based on the BERT model, generate the rule base, can quickly check the compliance of the operation tickets to be checked, reduce the error rate of the operation tickets in invoicing, and further improve the invoicing efficiency.
Description
Technical Field
The application relates to the technical field of operation ticket checking, in particular to a method and a device for checking operation ticket compliance.
Background
And the power grid dispatching operation is issued in an operation order form. Firstly, the operation order is issued by a dispatcher according to the dispatching regulation and the operation mode and experience, and then the operation order can take effect after being checked by the dispatching, operation mode, protection and other departments. The correct filling, checking and execution of the operation ticket are important factors for determining whether misoperation occurs. With the increasing expansion of the scale of the power system, new technologies of new equipment emerge endlessly, and the structure and the operation mode of a power grid become diversified. The workload and the working strength of the transformer substation workers are increased day by day, and a large amount of daily repeated work needs to be done. The billing error is often caused by negligence of billing personnel, the operation order is wasted, and the billing efficiency is low.
At present, the issuing and the checking of the operation ticket are still carried out manually, and the manual issuing and the checking process are carried out by substation issuing personnel and checking personnel, so that the issuing and the checking errors are easily caused, the working efficiency is reduced, and the safety risk is caused, therefore, the method for checking the compliance of the operation ticket with high efficiency and high accuracy needs to be developed urgently.
Disclosure of Invention
The application aims to provide an operation ticket compliance checking method and device to solve the problem of low ticket compliance checking efficiency.
In one aspect, according to an embodiment of the present application, there is provided an operation ticket compliance checking method including:
acquiring an initial data set of an archive ticket and a revocation ticket;
preprocessing the initial data set by using NLP data enhancement to obtain a basic corpus;
performing text splitting processing on the basic corpus to obtain a Chinese character set;
performing part-of-speech tagging on the Chinese characters in the Chinese character set;
converting the part-of-speech marked characters into numbers to form a training data set;
training the training data set by using a BERT model;
training the filing ticket data by using the trained BERT model to generate a corresponding rule base;
training the operation order to be checked by using the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence;
and matching the word segmentation result and the part-of-speech tagging sequence with the rule base to complete the operation ticket compliance check.
Further, the step of obtaining the initial data set of the filing ticket and the revocation ticket comprises:
acquiring data of the filing ticket and the revocation ticket;
and extracting operation task names and operation item characteristic text information in the data of the filing tickets and the revocation tickets as an initial data set.
Further, the step of preprocessing the initial data set with NLP data enhancement comprises:
reverse translating the text information in the initial data set; and/or the presence of a gas in the gas,
selecting synonyms to replace original words and sentences in the initial data set; and/or the presence of a gas in the gas,
randomly deleting partial characters and words in the initial data set, and replacing the partial characters and words with spaces; and/or the presence of a gas in the gas,
and randomly disordering the word order in the initial data set.
Further, the step of matching the word segmentation result and the part-of-speech tagging sequence with the rule base to complete the operation ticket compliance check comprises the following steps:
matching the operation task name;
matching operation actions based on the rule base to complete the correctness check of the scheduling terms;
matching the line model, the line name, the equipment model and the equipment name based on the rule base to complete double naming standard inspection;
and matching the word segmentation result of the current operation task and the part-of-speech tagging sequence based on the rule base, and finishing the inspection of the non-standard words and the wrong words.
On the other hand, according to an embodiment of the present application, there is provided an operation ticket compliance checking device including:
the acquisition unit is used for acquiring an initial data set of the filing ticket and the revocation ticket;
the preprocessing unit is used for preprocessing the initial data set by utilizing NLP data enhancement to obtain basic corpora;
a splitting unit for splitting the text of the basic corpus to obtain a Chinese character set,
the part-of-speech tagging unit is used for performing part-of-speech tagging on the Chinese characters in the Chinese character set;
the conversion unit is used for converting the part-of-speech marked characters into numbers to form a training data set;
a first training unit for training a training data set using a BERT model;
the second training unit is used for training the filing ticket data by utilizing the trained BERT model to generate a corresponding rule base;
the third training unit is used for training the operation order to be checked by utilizing the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence;
and the matching unit is used for matching the word segmentation result and the part-of-speech tagging sequence with the rule base to finish the operation ticket compliance check.
Further, the acquisition unit includes:
the acquisition subunit is used for acquiring the data of the filing ticket and the revocation ticket;
and the extracting unit is used for extracting the operation task name and the operation item characteristic text information in the data of the filing ticket and the invalidation ticket as an initial data set.
Further, the preprocessing unit includes:
a reverse translation unit, configured to reverse translate the text information in the initial data set; and/or the presence of a gas in the gas,
the replacing unit is used for selecting synonyms to replace original words and sentences in the initial data set; and/or the presence of a gas in the gas,
a deleting unit, configured to delete part of characters and words in the initial data set at random, and replace the part of characters and words with spaces; and/or the presence of a gas in the gas,
and the scrambling unit is used for randomly scrambling the word sequence in the initial data set.
Further, the matching unit includes:
the first matching subunit is used for matching the operation task name;
the second matching subunit is used for matching operation actions based on the rule base and completing the correctness check of the scheduling terms;
the third matching subunit is used for matching the line model, the line name, the equipment model and the equipment name based on the rule base to complete double naming standard check;
and the fourth matching subunit is used for matching the word segmentation result and the part-of-speech tagging sequence of the current operation task based on the rule base to complete the inspection of the non-standard phrases and the wrong words.
As can be seen from the above technical solutions, an embodiment of the present application provides an operation ticket compliance checking method and apparatus, where the method includes: acquiring an initial data set of an archive ticket and a revocation ticket; preprocessing the initial data set by using NLP data enhancement to obtain a basic corpus; performing text splitting processing on the basic corpus to obtain a Chinese character set, and performing part-of-speech tagging on Chinese characters in the Chinese character set; converting the part-of-speech marked characters into numbers to form a training data set; training the training data set by using a BERT model; training the filing ticket data by using the trained BERT model to generate a corresponding rule base; training the operation order to be checked by using the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence; and matching the word segmentation result and the part-of-speech tagging sequence with the rule base to complete the operation ticket compliance check. The method and the device are used for training the filing tickets and the voiding tickets based on the BERT model, generate the rule base, can quickly check the compliance of the operation tickets to be checked, reduce the error rate of the operation tickets in invoicing, and further improve the invoicing efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart illustrating an operation ticket compliance checking method according to an embodiment of the present application.
Detailed Description
Referring to fig. 1, an embodiment of the present application provides an operation ticket compliance checking method, including:
step S1, acquiring an initial data set of the filing ticket and the revocation ticket;
the archiving ticket represents the correct operation ticket for making an invoice, the invalidation ticket represents the wrong operation ticket, and the two types of operation tickets are fused, so that the model can learn in the forward direction and the reverse direction, and the accuracy of prediction is improved.
Specifically, the step of obtaining the initial data set of the filing ticket and the revocation ticket includes:
acquiring data of the filing ticket and the revocation ticket;
and extracting operation task names and operation item characteristic text information in the data of the filing tickets and the revocation tickets as an initial data set.
The operation ticket contains redundant information including operation type, operation place, remark information and other prompt information. Therefore, the operation task name and the operation item are extracted from the operation ticket as the feature text to construct an initial data set.
Step S2, preprocessing the initial data set by using NLP data enhancement to obtain a basic corpus;
further, the step of preprocessing the initial data set with NLP data enhancement comprises:
reverse translating the text information in the initial data set; and/or the presence of a gas in the gas,
selecting synonyms to replace original words and sentences in the initial data set; and/or the presence of a gas in the gas,
randomly deleting partial characters and words in the initial data set, and replacing the partial characters and words with spaces; and/or the presence of a gas in the gas,
and randomly disordering the word order in the initial data set.
The used data enhancement method comprises the steps of retranslation, synonym replacement, random deletion and random word order disorder concentration. The retranslation is a process of translating a text into other languages through machine translation and then translating the text into an original language, synonym replacement refers to replacement by using words with the same expression, random deletion refers to deletion of a word and filling by using a blank space, and random word order scrambling refers to scrambling of the word order of a sentence.
The goal of data augmentation is to create more training data by generating variants of existing training samples through transformations that tend to reflect changes that may occur in the real world.
Step S3, performing text splitting processing on the basic corpus to obtain a Chinese character set;
step S4, performing part-of-speech tagging on Chinese characters in the Chinese character set;
wherein, each Chinese character is labeled with part of speech, "b" represents the beginning of a word, "m" represents the middle of a word, and "e" represents the end of a word.
For example, the text: checking that the position indication of a 1362 disconnecting switch at the ii-section bus side of the gold tension line of the 110kv microcomputer bus differential protection device is correct. The results of Chinese character splitting and part of speech tagging are as follows:
splitting a Chinese character: checking that the position indication of the 1362 isolating switch on the bus side of the segment i i of the gold wire of the 110kv microcomputer bus differential protection device is correct.
And part of speech tagging results: b _ v e _ v b _ ms _ m _ ms _ e _ ms _ nr _ m _ nr _ e _ nr _ s _ s b _ ns m _ ns _ e _ ms _ e _ ns _ s _ f b _ mrm _ mr _ m _ mr _ e _ mr _ b _ nr _ m _ nr _ e _ nr _ m _ nz m _ nz _ e _ nz _ e _ ad.
Wherein ms represents kilovoltage level (110 kv); nr represents the device name (microcomputer bus differential protection device); ns represents the line name (gold wire); mr represents a device number (1362); nz denotes a term of art (position indication).
Step S5, converting the part-of-speech marked characters into numbers to form a training data set;
for example: checking that the position indication of a 1362 isolating switch at the ii section of a gold-tension line of a 110kv microcomputer bus differential protection device is correct, and converting corresponding characters into numerical values which are expressed as: 30,1,3,4,5,5,5,6,14,15,15,15,15,15,15,15,15,16,29,7,8,9,4,6,7,9,28,10,11,11,12,14,15,15,16,17,18,18,19,21,23,31.
S6, training a training data set by using a BERT model;
s7, training the filing ticket data by using the trained BERT model to generate a corresponding rule base;
s8, training the operation order to be checked by using the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence;
and step S9, matching the word segmentation result and the part-of-speech tagging sequence with the rule base to finish the operation ticket compliance check.
The operation ticket compliance check comprises a scheduling term correctness check, a double naming standard check, a standard expression check and a wrongly written word check.
Specifically, the step of matching the word segmentation result and the part-of-speech tagging sequence with the rule base to complete the operation ticket compliance check includes:
matching the operation task name;
matching operation actions based on the rule base to complete the correctness check of the scheduling terms;
matching the line model, the line name, the equipment model and the equipment name based on the rule base to complete double naming standard inspection;
and matching the word segmentation result of the current operation task and the part-of-speech tagging sequence based on the rule base, and finishing the inspection of the non-standard words and the wrong words.
The embodiment of the application provides an operation ticket compliance inspection device, includes:
the acquisition unit is used for acquiring an initial data set of the filing ticket and the revocation ticket;
the preprocessing unit is used for preprocessing the initial data set by utilizing NLP data enhancement to obtain basic corpora;
a splitting unit for splitting the text of the basic corpus to obtain a Chinese character set,
the part-of-speech tagging unit is used for performing part-of-speech tagging on the Chinese characters in the Chinese character set;
the conversion unit is used for converting the part-of-speech marked characters into numbers to form a training data set;
a first training unit for training a training data set using a BERT model;
the second training unit is used for training the filing ticket data by utilizing the trained BERT model to generate a corresponding rule base;
the third training unit is used for training the operation order to be checked by utilizing the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence;
and the matching unit is used for matching the word segmentation result and the part-of-speech tagging sequence with the rule base to finish the operation ticket compliance check.
Further, the acquisition unit includes:
the acquisition subunit is used for acquiring the data of the filing ticket and the revocation ticket;
and the extracting unit is used for extracting the operation task name and the operation item characteristic text information in the data of the filing ticket and the invalidation ticket as an initial data set.
Further, the preprocessing unit includes:
a reverse translation unit, configured to reverse translate the text information in the initial data set; and/or the presence of a gas in the gas,
the replacing unit is used for selecting synonyms to replace original words and sentences in the initial data set; and/or the presence of a gas in the gas,
a deleting unit, configured to delete part of characters and words in the initial data set at random, and replace the part of characters and words with spaces; and/or the presence of a gas in the gas,
and the scrambling unit is used for randomly scrambling the word sequence in the initial data set.
Further, the matching unit includes:
the first matching subunit is used for matching the operation task name;
the second matching subunit is used for matching operation actions based on the rule base and completing the correctness check of the scheduling terms;
the third matching subunit is used for matching the line model, the line name, the equipment model and the equipment name based on the rule base to complete double naming standard check;
and the fourth matching subunit is used for matching the word segmentation result and the part-of-speech tagging sequence of the current operation task based on the rule base to complete the inspection of the non-standard phrases and the wrong words.
As can be seen from the above technical solutions, an embodiment of the present application provides an operation ticket compliance checking method and apparatus, where the method includes: acquiring an initial data set of an archive ticket and a revocation ticket; preprocessing the initial data set by using NLP data enhancement to obtain a basic corpus; performing text splitting processing on the basic corpus to obtain a Chinese character set, and performing part-of-speech tagging on Chinese characters in the Chinese character set; converting the part-of-speech marked characters into numbers to form a training data set; training the training data set by using a BERT model; training the filing ticket data by using the trained BERT model to generate a corresponding rule base; training the operation order to be checked by using the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence; and matching the word segmentation result and the part-of-speech tagging sequence with the rule base to complete the operation ticket compliance check. The method and the device are used for training the filing tickets and the voiding tickets based on the BERT model, generate the rule base, can quickly check the compliance of the operation tickets to be checked, reduce the error rate of the operation tickets in invoicing, and further improve the invoicing efficiency.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (8)
1. An operation ticket compliance checking method, comprising:
acquiring an initial data set of an archive ticket and a revocation ticket;
preprocessing the initial data set by using NLP data enhancement to obtain a basic corpus;
performing text splitting processing on the basic corpus to obtain a Chinese character set;
performing part-of-speech tagging on the Chinese characters in the Chinese character set;
converting the part-of-speech marked characters into numbers to form a training data set;
training the training data set by using a BERT model;
training the filing ticket data by using the trained BERT model to generate a corresponding rule base;
training the operation order to be checked by using the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence;
and matching the word segmentation result and the part-of-speech tagging sequence with the rule base to complete the operation ticket compliance check.
2. The method of claim 1, wherein the step of obtaining an initial dataset of archival and revocation tickets comprises:
acquiring data of the filing ticket and the revocation ticket;
and extracting operation task names and operation item characteristic text information in the data of the filing tickets and the revocation tickets as an initial data set.
3. The method of claim 1, wherein the step of pre-processing the initial data set with NLP data enhancement comprises:
reverse translating the text information in the initial data set; and/or the presence of a gas in the gas,
selecting synonyms to replace original words and sentences in the initial data set; and/or the presence of a gas in the gas,
randomly deleting partial characters and words in the initial data set, and replacing the partial characters and words with spaces; and/or the presence of a gas in the gas,
and randomly disordering the word order in the initial data set.
4. The method according to claim 1, wherein the step of matching the word segmentation result and the part-of-speech tagging sequence with the rule base to complete the operation ticket compliance check comprises:
matching the operation task name;
matching operation actions based on the rule base to complete the correctness check of the scheduling terms;
matching the line model, the line name, the equipment model and the equipment name based on the rule base to complete double naming standard inspection;
and matching the word segmentation result of the current operation task and the part-of-speech tagging sequence based on the rule base, and finishing the inspection of the non-standard words and the wrong words.
5. An operation ticket compliance check device, comprising:
the acquisition unit is used for acquiring an initial data set of the filing ticket and the revocation ticket;
the preprocessing unit is used for preprocessing the initial data set by utilizing NLP data enhancement to obtain basic corpora;
the splitting unit is used for carrying out text splitting processing on the basic corpus to obtain a Chinese character set;
the part-of-speech tagging unit is used for performing part-of-speech tagging on the Chinese characters in the Chinese character set;
the conversion unit is used for converting the part-of-speech marked characters into numbers to form a training data set;
a first training unit for training a training data set using a BERT model;
the second training unit is used for training the filing ticket data by utilizing the trained BERT model to generate a corresponding rule base;
the third training unit is used for training the operation order to be checked by utilizing the trained BERT model to obtain a word segmentation result and a part-of-speech tagging sequence;
and the matching unit is used for matching the word segmentation result and the part-of-speech tagging sequence with the rule base to finish the operation ticket compliance check.
6. The apparatus of claim 5, wherein the obtaining unit comprises:
the acquisition subunit is used for acquiring the data of the filing ticket and the revocation ticket;
and the extracting unit is used for extracting the operation task name and the operation item characteristic text information in the data of the filing ticket and the invalidation ticket as an initial data set.
7. The apparatus of claim 5, wherein the pre-processing unit comprises:
a reverse translation unit, configured to reverse translate the text information in the initial data set; and/or the presence of a gas in the gas,
the replacing unit is used for selecting synonyms to replace original words and sentences in the initial data set; and/or the presence of a gas in the gas,
a deleting unit, configured to delete part of characters and words in the initial data set at random, and replace the part of characters and words with spaces; and/or the presence of a gas in the gas,
and the scrambling unit is used for randomly scrambling the word sequence in the initial data set.
8. The apparatus of claim 5, wherein the matching unit comprises:
the first matching subunit is used for matching the operation task name;
the second matching subunit is used for matching operation actions based on the rule base and completing the correctness check of the scheduling terms;
the third matching subunit is used for matching the line model, the line name, the equipment model and the equipment name based on the rule base to complete double naming standard check;
and the fourth matching subunit is used for matching the word segmentation result and the part-of-speech tagging sequence of the current operation task based on the rule base to complete the inspection of the non-standard phrases and the wrong words.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010100909.XA CN111339766A (en) | 2020-02-19 | 2020-02-19 | Operation ticket compliance checking method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010100909.XA CN111339766A (en) | 2020-02-19 | 2020-02-19 | Operation ticket compliance checking method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111339766A true CN111339766A (en) | 2020-06-26 |
Family
ID=71184172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010100909.XA Pending CN111339766A (en) | 2020-02-19 | 2020-02-19 | Operation ticket compliance checking method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111339766A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232078A (en) * | 2020-10-10 | 2021-01-15 | 云南电网有限责任公司昆明供电局 | Scheduling operation ticket auditing method based on bidirectional GRU and attention mechanism |
| CN112396399A (en) * | 2020-11-23 | 2021-02-23 | 海南电网有限责任公司东方供电局 | Distribution network operation ticket simulation method based on natural language processing technology |
| CN112540086A (en) * | 2020-11-23 | 2021-03-23 | 海南电网有限责任公司东方供电局 | Ticket face compliance detection system |
| CN113991843A (en) * | 2021-10-21 | 2022-01-28 | 广东电网有限责任公司 | Anti-misoperation method, system, equipment and medium for power grid dispatching operation |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1275223A (en) * | 1998-08-31 | 2000-11-29 | 索尼株式会社 | Natural language processing device and method |
| CN107729337A (en) * | 2016-08-11 | 2018-02-23 | 北京国双科技有限公司 | The monitoring method and device of event |
| CN108021552A (en) * | 2017-11-09 | 2018-05-11 | 国网浙江省电力公司电力科学研究院 | A kind of power system operation ticket method for extracting content and system |
| CN108710647A (en) * | 2018-04-28 | 2018-10-26 | 苏宁易购集团股份有限公司 | A kind of data processing method and device for chat robots |
| CN109493166A (en) * | 2018-10-23 | 2019-03-19 | 深圳智能思创科技有限公司 | A kind of construction method for e-commerce shopping guide's scene Task conversational system |
| CN109977689A (en) * | 2017-12-28 | 2019-07-05 | ***通信集团广东有限公司 | A kind of Method of Database Secure Audit method, apparatus and electronic equipment |
| CN110097430A (en) * | 2019-05-08 | 2019-08-06 | 厦门正北科技有限公司 | A kind of auto metal halide lamp product intelligent matching system based on artificial intelligence |
| CN110222225A (en) * | 2019-06-11 | 2019-09-10 | 苏州思必驰信息科技有限公司 | The abstraction generating method and device of GRU codec training method, audio |
| CN110287494A (en) * | 2019-07-01 | 2019-09-27 | 济南浪潮高新科技投资发展有限公司 | A method of the short text Similarity matching based on deep learning BERT algorithm |
| CN110321562A (en) * | 2019-06-28 | 2019-10-11 | 广州探迹科技有限公司 | A kind of short text matching process and device based on BERT |
| CN110442718A (en) * | 2019-08-08 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Sentence processing method, device and server and storage medium |
| CN110502643A (en) * | 2019-08-28 | 2019-11-26 | 南京璇玑信息技术有限公司 | A kind of next model autocreating technology of the prediction based on BERT model |
| CN110609899A (en) * | 2019-08-29 | 2019-12-24 | 成都信息工程大学 | Specific target emotion classification method based on improved BERT model |
| CN110674772A (en) * | 2019-09-29 | 2020-01-10 | 国家电网有限公司技术学院分公司 | Intelligent safety control auxiliary system and method for electric power operation site |
-
2020
- 2020-02-19 CN CN202010100909.XA patent/CN111339766A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1275223A (en) * | 1998-08-31 | 2000-11-29 | 索尼株式会社 | Natural language processing device and method |
| CN107729337A (en) * | 2016-08-11 | 2018-02-23 | 北京国双科技有限公司 | The monitoring method and device of event |
| CN108021552A (en) * | 2017-11-09 | 2018-05-11 | 国网浙江省电力公司电力科学研究院 | A kind of power system operation ticket method for extracting content and system |
| CN109977689A (en) * | 2017-12-28 | 2019-07-05 | ***通信集团广东有限公司 | A kind of Method of Database Secure Audit method, apparatus and electronic equipment |
| CN108710647A (en) * | 2018-04-28 | 2018-10-26 | 苏宁易购集团股份有限公司 | A kind of data processing method and device for chat robots |
| CN109493166A (en) * | 2018-10-23 | 2019-03-19 | 深圳智能思创科技有限公司 | A kind of construction method for e-commerce shopping guide's scene Task conversational system |
| CN110097430A (en) * | 2019-05-08 | 2019-08-06 | 厦门正北科技有限公司 | A kind of auto metal halide lamp product intelligent matching system based on artificial intelligence |
| CN110222225A (en) * | 2019-06-11 | 2019-09-10 | 苏州思必驰信息科技有限公司 | The abstraction generating method and device of GRU codec training method, audio |
| CN110321562A (en) * | 2019-06-28 | 2019-10-11 | 广州探迹科技有限公司 | A kind of short text matching process and device based on BERT |
| CN110287494A (en) * | 2019-07-01 | 2019-09-27 | 济南浪潮高新科技投资发展有限公司 | A method of the short text Similarity matching based on deep learning BERT algorithm |
| CN110442718A (en) * | 2019-08-08 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Sentence processing method, device and server and storage medium |
| CN110502643A (en) * | 2019-08-28 | 2019-11-26 | 南京璇玑信息技术有限公司 | A kind of next model autocreating technology of the prediction based on BERT model |
| CN110609899A (en) * | 2019-08-29 | 2019-12-24 | 成都信息工程大学 | Specific target emotion classification method based on improved BERT model |
| CN110674772A (en) * | 2019-09-29 | 2020-01-10 | 国家电网有限公司技术学院分公司 | Intelligent safety control auxiliary system and method for electric power operation site |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232078A (en) * | 2020-10-10 | 2021-01-15 | 云南电网有限责任公司昆明供电局 | Scheduling operation ticket auditing method based on bidirectional GRU and attention mechanism |
| CN112396399A (en) * | 2020-11-23 | 2021-02-23 | 海南电网有限责任公司东方供电局 | Distribution network operation ticket simulation method based on natural language processing technology |
| CN112540086A (en) * | 2020-11-23 | 2021-03-23 | 海南电网有限责任公司东方供电局 | Ticket face compliance detection system |
| CN112540086B (en) * | 2020-11-23 | 2024-04-05 | 海南电网有限责任公司东方供电局 | Ticket face compliance detecting system |
| CN113991843A (en) * | 2021-10-21 | 2022-01-28 | 广东电网有限责任公司 | Anti-misoperation method, system, equipment and medium for power grid dispatching operation |
| CN113991843B (en) * | 2021-10-21 | 2024-06-07 | 广东电网有限责任公司 | Error prevention method, system, equipment and medium for power grid dispatching operation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111339766A (en) | Operation ticket compliance checking method and device | |
| Shaalan | Rule-based approach in Arabic natural language processing | |
| CN111260338B (en) | Intelligent generation method, device and platform for substation operation ticket | |
| CN101908042A (en) | Tagging method of bilingual combination semantic role | |
| ITUD20000228A1 (en) | SYSTEM AND METHOD OF AUTOMATIC OR SEMI-AUTOMATIC TRANSLATION WITH POSTEDITATION FOR THE CORRECTION OF ERRORS | |
| CN110188345B (en) | Intelligent identification method and device for electric operation ticket | |
| CN112528041B (en) | Scheduling term specification verification method based on knowledge graph | |
| CN112883693A (en) | Method and terminal for automatically generating electric power work ticket | |
| Dipper et al. | Simple annotation tools for complex annotation tasks: an evaluation | |
| Chang | A new approach for automatic Chinese spelling correction | |
| CN111581965B (en) | Operation ticket generation method and device | |
| CN112966529A (en) | Neural network machine translation training method, system, medium, equipment and application | |
| CN114996470A (en) | Intelligent scheduling maintenance identification library construction method | |
| Huang et al. | Zero resource code-switched speech benchmark using speech utterance pairs for multiple spoken languages | |
| CN112036179B (en) | Electric power plan information extraction method based on text classification and semantic frame | |
| CN113868422A (en) | Multi-label inspection work order problem traceability identification method and device | |
| CN115099232A (en) | Power grid operation knowledge model construction method for scheduling regulations and historical data | |
| Garside | The large-scale production of syntactically analysed corpora | |
| CN113010682A (en) | Command ticket system checking method, device and storage medium | |
| Volk et al. | XML-based phrase alignment in parallel treebanks | |
| CN111553158A (en) | Method and system for identifying named entities in power scheduling field based on BilSTM-CRF model | |
| Bosch et al. | Towards Zulu corpus clean-up, lexicon development and corpus annotation by means of computational morphological analysis | |
| Furuta et al. | A Fact-checking Assistant System for Textual Documents | |
| Tolegen et al. | A finite state transducer based morphological analyzer for the kazakh language | |
| CN113515950B (en) | Natural language processing semantic analysis method suitable for intelligent power dispatching |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200626 |