CN115455133A - Operation ticket checking method, system and equipment based on text mining - Google Patents

Abstract

The application relates to the technical field of electric power operation and management, and provides an operation order checking method, system and device based on text mining, wherein the method comprises the following steps: performing text mining on the historical operation ticket in the operation ticket database, dividing electric nouns, verbs and prepositions in the historical operation ticket, and identifying the combination relation of words with different parts of speech; constructing a dictionary by using the electric nouns as a database; obtaining sentence pattern rules to construct a knowledge base according to the combination relation of the verb or preposition and the power name word; after the operation checking is carried out by the two libraries, the correct operation ticket which is permitted to be drawn is stored in the operation ticket database as the historical operation ticket, text mining is carried out, the database and the knowledge base are supplemented, so that the two libraries can ensure the reliability of drawing the operation ticket and checking and realize the self-adaptive updating of the knowledge base and the database in the circulation of text mining and checking.

Description

Operation ticket checking method, system and equipment based on text mining

Technical Field

The invention relates to the technical field of operation order auditing, in particular to an operation order checking method, system and device based on text mining.

Background

The operation ticket is a written basis for operating the electrical equipment by an operator, and is an important means for ensuring the safe production of electric power and preventing electrical misoperation and personal injury accidents.

With the advance of the automation and intelligent work of the power grid, the operation tickets are developed to be written by machines from manual writing, the most advanced operation ticket generation system is an expert system, and a knowledge base of the operation ticket generation system needs programmers to convert the relevant operation experience and operation specification of field personnel and experts into rules; and the database is used for storing data generated in the operation process and managing the generated operation ticket.

The construction of the rule base and the database in the operation ticket generation system depends on manpower, the number of involved personnel is large, the operation is complex, and the operation is solidified during development; with the development of the power grid and the improvement of institutional regulations, word terms and regulations can also change, but the rule base and the database are difficult to update adaptively, so that the risk of missed detection and false detection exists when the operation ticket is issued.

Disclosure of Invention

The application provides an operation ticket checking method, system and device based on text mining, and solves the problems that an operation ticket checking system is difficult to construct and a rule base and a database are difficult to update along with power grid development in the prior art.

The application provides an operation order checking method based on text mining in a first aspect, which comprises the following steps:

text mining is carried out on historical operation tickets in an operation ticket database, electric nouns, verbs and prepositions in the historical operation tickets are divided through text word segmentation and part-of-speech tagging, and combination relations of words with different parts-of-speech are identified; constructing a dictionary by using the electric nouns, and taking the dictionary as a database; obtaining sentence pattern rules according to the combination relation of verbs or prepositions and power namewords, and constructing a knowledge base;

checking the operation ticket to be checked by using a database and a knowledge base; if the check result is correct, the ticket drawing is permitted;

and storing the operation ticket after the ticket drawing as a historical operation ticket into an operation ticket database, performing text mining, and supplementing the database and the knowledge base.

Optionally, the constructing a dictionary by using the electric nouns, and taking the dictionary as a database specifically includes:

key words such as station names, cabinet names, equipment numbers and equipment names are extracted from the electric nouns, and a three-layer dictionary corresponding to the station, the cabinet and the equipment is constructed to serve as a database.

Optionally, the sentence pattern rule is obtained according to the combination relationship between the verb or preposition and the power name word, and a knowledge base is constructed, specifically:

and extracting verbs and prepositions, obtaining a sentence pattern rule according to the combination relation of the verbs or prepositions and the power namewords, and constructing a regular expression corresponding to the sentence pattern rule to form a knowledge base.

Optionally, after performing text mining on the historical operation ticket, the method further includes:

after the texts of the preset number of historical operation tickets are mined, the occurrence frequency of all words in the dictionary and the occurrence frequency of all sentence pattern rules are counted, and the words and the sentence pattern rules with the occurrence frequency lower than a threshold value are eliminated from the database and the knowledge base.

Optionally, after the operation ticket to be checked is checked by using the database and the knowledge base, the method further includes:

and if the checking result is wrong, generating modification opinions, and manually checking the modification opinions one by one.

Optionally, the step of performing manual verification on the modification opinions one by one specifically comprises:

manually checking the modification opinions one by one, and judging whether the modification opinions are correct or not; and if the verification result is that the modification opinions are correct, modifying the corresponding position of the operation order according to the modification opinions, and sending the modification opinions to front-line personnel and experts for feedback and learning.

Optionally, the manually verifying the modification opinions one by one, and after determining whether the modification opinions are correct, the method further includes:

if the verification result is that the modification opinions are wrong, the contents corresponding to the modification opinions are directly reversely updated in the knowledge base or the database through reverse updating.

A second aspect of the present application provides an operation ticket checking system based on text mining, including:

the operation ticket database is respectively connected with the text mining module and the self-adaptive updating module and is used for storing historical operation tickets;

the text mining module is used for performing text mining on the historical operation tickets in the operation ticket database, dividing electric nouns, verbs and prepositions in the historical operation tickets through text word segmentation and part-of-speech tagging, and identifying the combination relation of words with different parts-of-speech; constructing a dictionary by using the electric nouns, and taking the dictionary as a database; obtaining sentence pattern rules according to the combination relation of the verb or preposition and the power name word, and constructing a knowledge base;

the operation ticket checking module is used for checking the operation tickets to be checked by using the database and the knowledge base; if the checking result is correct, the ticket drawing is permitted;

and the self-adaptive updating module is used for storing the operation ticket after the ticket is drawn as a historical operation ticket into the operation ticket database, performing text mining and supplementing the database and the knowledge base.

Optionally, in the text mining module, a sentence pattern rule is obtained according to a combined relationship between a verb or preposition and a power name word, and a knowledge base is constructed, specifically:

and extracting verbs and prepositions, obtaining a sentence pattern rule according to the combination relation of the verbs or prepositions and the power namewords, and constructing a regular expression corresponding to the sentence pattern rule to form a knowledge base.

A third aspect of the present application provides an operation ticket checking device based on text mining, the device including a processor and a memory:

the memory is used for storing program codes and transmitting the program codes to the processor;

the processor is configured to execute the operation order checking method based on text mining according to any one of the first aspect of the present application according to instructions in the program code.

According to the operation ticket checking method based on text mining, through text mining of historical operation tickets in an operation ticket database, electric nouns, verbs and prepositions in the historical operation tickets are divided, and combination relations of words with different parts of speech are identified; constructing a dictionary by using the electric nouns as a database; obtaining sentence pattern rules to construct a knowledge base according to the combination relation of the verb or preposition and the power name word; after the operation to be checked is checked by the two libraries, the correct operation ticket which is permitted to draw the ticket is stored in the operation ticket database as the historical operation ticket, text mining is carried out, the database and the knowledge base are supplemented, so that the two libraries can ensure the reliability of the operation ticket drawing checking and realize the self-adaptive updating of the knowledge base and the database in the circulation of text mining and checking.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.

FIG. 1 is a schematic flow chart of an operation ticket checking method based on text mining according to the present application;

FIG. 2 is a schematic diagram of a knowledge base and database construction flow of the operation order checking method based on text mining provided by the application;

FIG. 3 is a schematic view illustrating a procedure of checking the modification opinions of the operation ticket checking method based on text mining according to the present application;

fig. 4 is a structural diagram of an operation ticket checking system based on text mining provided by the present application.

Detailed Description

In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The application provides an operation ticket checking method based on text mining, and solves the technical problems that an operation ticket checking system is difficult to construct and a rule base and a database are difficult to develop and update along with a power grid in the prior art.

Referring to fig. 1, fig. 1 is a schematic flow chart of an operation ticket checking method based on text mining according to the present application.

A first aspect of the present embodiment provides an operation ticket checking method based on text mining, including:

s100, performing text mining on the historical operation tickets in the operation ticket database, dividing electric nouns, verbs and prepositions in the historical operation tickets through text participles and part-of-speech tagging, and identifying combination relations of words with different parts-of-speech; constructing a dictionary by using the electric nouns, and taking the dictionary as a database; obtaining sentence pattern rules according to the combination relation of the verb or preposition and the power name word, and constructing a knowledge base;

it should be noted that, the staff analyzes and finds in daily work that the operation order text has the advantages of standard words, noun library, single verb, strong regularity, fixed sentence pattern, and the like, and the text sentence is mainly the combination of the electric noun, a small number of verbs and media words used with high frequency; the word specification, the characteristic of a noun library and the use of a large number of electric noun terms in the operation ticket can quickly and accurately distinguish each word during word segmentation and mark the part of speech; and the operation order text verb is single, the regularity is strong, and the sentence pattern is fixed, for example, in an XX protection cabinet, an XX box, a XX switch and the like, the combination relationship existing among words of different parts of speech can be recognized.

A plurality of power nouns extracted from the operation ticket, such as equipment numbers, equipment names, station names and box gauge names, are used for constructing a dictionary as a database, so that the effects of strong pertinence and high identification degree on noun identification can be achieved; the combination relation among words with different parts of speech shows the line and text logic and sentence pattern rules of the operation order text, for example, verbs appearing with high frequency can be combined with electric famous words, and the constructed knowledge base can check sentences formed by combining the words without reading and understanding text contents. The database and the knowledge base respectively contain the standards of words and word combinations, and the combination of the two bases can realize the efficient and comprehensive check of the operation ticket to be checked.

The initial dictionary content in the database is less and difficult to be segmented, and an initial dictionary can be constructed according to preset electric noun information, such as other files containing electric nouns, such as a pressing plate on-off list and a pressing plate list, so as to guide the construction of the initial database.

The historical operation tickets in the operation ticket database are checked operation tickets, and the rules of the electric nouns, verbs, prepositions and sentence patterns obtained after text mining can be ensured to be correct, so that the constructed database and the knowledge base can also be used for accurately checking the operation tickets to be checked.

S200, checking the operation ticket to be checked by using a database and a knowledge base; if the checking result is correct, the ticket drawing is permitted;

it should be noted that the operation ticket to be checked is an operation ticket which is compiled but has not been executed, and the operation ticket can be issued only after the contents are checked and confirmed, so that the safety of the operator of the operation ticket is prevented from being affected by wrong contents. And checking each word of the operation ticket to be checked by using the database, checking the word combination of the operation ticket to be checked by using the knowledge base, and finishing the checking before the operation ticket is issued. It can be understood that the richer the contents of the database and the knowledge base are, the more accurate the checking of the operation ticket will be.

S300, storing the operation ticket after the ticket drawing as a historical operation ticket into an operation ticket database, performing text mining, and supplementing the database and the knowledge base.

It should be noted that, along with the development of the power grid and the improvement of the regulation system, the content of the operation ticket also changes, for example, when a transformer substation is newly built, reconstructed or expanded, the noun of electric power often changes; for some contents conforming to the checking logic of the database and the knowledge base, the contents can be identified as correct operation tickets, namely, the contents of the operation tickets can directly pass through the checking even if some changes exist on the premise of conforming to the dictionary synonym of the database or the word combination rule of the knowledge base; and then the operation tickets are stored in an operation ticket database as historical operation tickets, the contents of the operation tickets which contain the updating are supplemented into a knowledge base and a rule base through text mining, the self-adaptive feedback learning of the two bases is realized, and the contents of the two bases can be updated along with the development of a power grid and a regulation system after a period of text mining of a plurality of operation tickets.

In the embodiment, through text mining on the historical operation tickets in the operation ticket database, the electric nouns, verbs and prepositions in the historical operation tickets are divided, and the combination relation of words with different parts of speech is identified; constructing a dictionary by using the electric nouns as a database; obtaining sentence pattern rules to construct a knowledge base according to the combination relation of verbs or prepositions and power namewords; after the operation to be checked is checked by the two libraries, the correct operation ticket which is permitted to draw the ticket is stored in the operation ticket database as the historical operation ticket, text mining is carried out, the database and the knowledge base are supplemented, so that the two libraries can ensure the reliability of the operation ticket drawing checking and realize the self-adaptive updating of the knowledge base and the database in the circulation of text mining and checking.

The above is a detailed description of a first embodiment of an operation ticket checking method based on text mining provided by the present application, and the following is a detailed description of a second embodiment of an operation ticket checking method based on text mining provided by the present application.

In this embodiment, a specific embodiment of step S100 in an operation ticket checking method based on text mining is further provided, please refer to fig. 2, in the embodiment, step S100 specifically includes steps S101 to S103, and details are as follows:

s101, text mining is conducted on the historical operation tickets in the operation ticket database, the texts in the historical operation tickets are divided into words through text word segmentation and part-of-speech tagging, parts-of-speech such as nouns, verbs and prepositions are tagged to the words, and combination relations of the words with different parts-of-speech are recognized.

It should be noted that, by constructing a hidden markov model, text word segmentation extracts words from a sentence according to a certain rule, contrasts with a dictionary, realizes word segmentation after the sentence is split, performs part-of-speech tagging according to semantics and connection relations among the words, extracts words of which the part-of-speech is a noun after word segmentation, and then identifies combination relations of words of different parts-of-speech.

The operation ticket type for text mining in this embodiment is a switching operation ticket; a word segmentation method based on a dictionary is adopted, and reverse maximum matching is performed; the reverse maximum matching is to set a maximum word length, obtain a word string with the maximum word length from the right of the content to be segmented to obtain a candidate word string, then look up a dictionary, put the candidate word string into a segmentation sequence if the candidate word string is found in the dictionary, and delete the candidate word string from the content to be segmented; if the word is not found in the dictionary, the right word of the candidate word string is removed, the dictionary is searched again until the candidate word string is found in the dictionary or is a single word, and then the next candidate word string is taken from the content to be segmented until the content to be segmented is segmented.

S102, extracting key words such as station names, bin names, equipment numbers and equipment names from the electric nouns, and constructing a three-layer dictionary corresponding to the stations, the bins and the equipment to serve as a database.

It should be noted that the expression form of the database in the memory is a dictionary, and the expression form stored in the hard disk is an Excel file, that is, the two are databases in different expression forms; when the dictionary is required to be used for checking, the database reads the Excel file into the 3-layer dictionary of the memory from the hard disk, and subsequent analysis and operation are facilitated.

The database comprises data information of all the primary and secondary equipment of the transformer substation to be used for checking, and the data information corresponds to a station name, a cabinet name, an equipment number, an equipment name and the like. The three layers of dictionaries are arranged from high station to low station, cabinets and equipment, and the sequence of the layers corresponds to the actual inclusion relationship of the electric nouns; the three-layer dictionary can also be converted with the two-layer dictionary, and the two-layer dictionary is the station and the equipment.

And S103, extracting verbs and prepositions, obtaining a sentence pattern rule according to the combination relation of the verbs or the prepositions and the power name words, and constructing a regular expression corresponding to the sentence pattern rule to form a knowledge base.

It should be noted that, the method for constructing the regular expression is similar to the method for creating the mathematical expression, and small expressions are combined together by using various meta characters and operators to create a larger expression; while the components of the regular expression may be individual characters, a collection of characters, a range of characters, a selection between characters, or any combination of all of these components.

The text of the operation ticket is mainly a combination of a power noun and a few high-frequency-use nouns or prepositions, and the sentence pattern is fixed and regular, so that a regular expression can be constructed by using the verbs and prepositions and the power noun. The similar combined relation is clustered and analyzed, the rules of the operation categories and the action orientations of the semantic representation of each sentence per se are analyzed, the sequence rules of the steps among the sentences are analyzed, the sentence pattern rules are expressed in a generalization mode by utilizing the variable length regular expressions, and a knowledge base is constructed. The canonical expression form of the knowledge base is shown in table 1.

TABLE 1 regular expression of operation ticket text

The knowledge base comprises all rules to be used for checking, such as a screen cabinet double-number rule, a double-number rule of equipment such as a pressure plate and the like, a verb and checked double-line equipment double-number rule, a switch position check rule before disconnecting link action, a hot bus bar reversing rule, a fixed value changing rule, a site station name rule and the like. The more historical operation tickets are stored in the operation ticket database, the more abundant the content of the knowledge base and the database generated by the text mining program can be mined. The two libraries can be automatically generated by a text mining program, and can also be manually added, deleted and modified by experts and front-line personnel.

Furthermore, after mining the historical operation order texts with preset quantity, counting the occurrence frequency of each word in the dictionary and the occurrence frequency of each sentence pattern rule, and eliminating the word and the sentence pattern rule with the occurrence frequency lower than a threshold value from the database and the knowledge base.

It should be noted that, in the initial stage of text mining, in order to quickly construct a database and a knowledge base with sufficient contents, the adopted strategy is to store all words and sentence pattern rules obtained by text mining; in the later stage of text mining, after the text mining of the preset number of historical operation tickets is completed, the contents of the two databases are enough, in order to improve the efficiency of checking and matching, the occurrence frequency of each word and each sentence pattern rule can be counted, and the contents lower than the preset threshold value are removed from the database and the knowledge base; for example, there are words that occasionally appear in the operation ticket, and the occurrence frequency of the words is found to be very low under a large number of samples, that is, the words are not recognized any more, if the words with low word frequency exist in the dictionary, the words are not recognized any more, so that the word segmentation speed can be improved by removing the words; eliminating sentence pattern rules with low frequency can improve the efficiency of knowledge base check. The threshold value of the preset quantity and the frequency of the historical operation tickets can be set according to the space and the actual situation of the operation ticket text.

The method for building the database and the knowledge base by text mining has extremely high adaptability and customization, two bases with different targeted contents can be built by using historical operation tickets of different transformer substations, and the targeted construction simplifies the contents of the two bases, so that the method has higher accuracy for checking the operation tickets of a specific transformer substation and higher checking efficiency for the operation tickets of the specific transformer substation.

In the embodiment, the database is constructed by extracting the electric nouns of the operation ticket, and the knowledge base is constructed by the sentence pattern with strong regularity in the operation ticket and the regular expression, so that the construction of the two bases can be matched with the actual condition of the transformer substation, and the ticket drawing and checking efficiency of the operation ticket is improved.

The above is a detailed description of the second embodiment of the operation ticket checking method based on text mining provided by the present application, and the following is a detailed description of the third embodiment of the operation ticket checking method based on text mining provided by the present application.

In this embodiment, a method for checking an operation ticket based on text mining is further provided, where the step S200 is followed by a step S400, and if a checking result is an error, modification opinions are generated, and manual checking is performed on the modification opinions one by one.

Referring to fig. 3, step S400 specifically includes steps S401 to S405, which are detailed as follows:

s401, if the checking result is wrong, generating modification opinions for wrong contents according to the knowledge base and the database.

It should be noted that after the operation order is checked according to the knowledge base and the database, if there is a sentence that does not conform to the contents of the two bases, it is determined that there is an error, and a modification suggestion is generated according to the contents of the two bases in response to the error,

in this embodiment, the operation ticket to be checked is in the form of an Excel table stored row by row according to the operation steps, and after the checking is completed, a modification suggestion is annotated in the table, for example, the name of the pressing plate is wrong: XX station XX protection cabinet, or action error: not checking switch position, etc.

S402, performing manual check on the modification opinions one by one, and judging whether the modification opinions are correct or not; if the check result is that the modification opinion is correct, the method proceeds to step S403, and if the check result is that the modification opinion is incorrect, the method proceeds to step S404;

it should be noted that the modification opinions generated after the verification need to be further verified, and whether the modification opinions are caused by the fact that operation tickets are wrongly written or the knowledge base or the database needs to be updated due to power grid development and regulation change and cannot be identified is judged, so that false detection caused by old or wrong contents of the knowledge base and the database is avoided; the defects of the two banks can be supplemented by the manual judgment of the checking personnel, and the speed of the checking personnel for acquiring the power station development and the regulation change is inevitably faster than the self-adaptive updating of the two banks, so that the operation ticket issuing checking reliability is further guaranteed.

Further, according to the number n of the generated modification opinions, if n is larger than 0, manually checking the modification opinions one by one, checking the ith modification opinion by a checker, judging whether i is equal to n after checking of each modification opinion is finished, if not, enabling i = i +1, and modifying the next modification opinion; if yes, completing the manual check of the modification opinions.

S403, modifying the corresponding position of the operation ticket according to the modification suggestion, and sending the modification suggestion to a front-line staff and an expert for feedback and learning;

it should be noted that, the modification opinions are verified to be correct, that is, the operation ticket is actually wrong, modification is needed, and the wrong content is sent to front-line personnel and experts, so that the teaching and training improvement is absorbed, and the operation ticket is provided for families to learn together, and the ticket output capability of the people is improved; and the error judgment caused by the fact that a checking person is not in operation at one line can be avoided, the reliability of ticket drawing is further improved, and if the updating is larger, the contents of the two storages are manually updated in a supplementary manner by manually editing rules and dictionaries.

S404, the content corresponding to the modification opinions is directly reversely updated in a knowledge base or a database through reverse updating.

It should be noted that the anti-update is to update the knowledge base or the database content to the content opposite to the modification opinion according to the modification opinion. The modification opinion is checked to be wrong, which indicates that the database or the knowledge base has content which is not consistent with the current transformer substation condition and needs to be updated, a checking personnel can check a certain regular expression in the knowledge base corresponding to the alarm and certain equipment information in the database in a reverse updating mode, so that the problem is conveniently positioned, the knowledge base or the database is updated on the spot, the content in the corresponding base is directly updated and modified, and an operation ticket with similar content exists, and the knowledge base and the database can be correctly identified.

In the embodiment, the operation tickets which are checked to be wrong are checked one by one to modify the opinions, so that the operation tickets which really have the errors are modified, the reliability of ticket drawing is improved, and the modification condition is further confirmed; and the two libraries are reversely updated according to the unreal error, so that the contents of the two libraries can be quickly and conveniently modified, and the ticket drawing and checking of the operation ticket can quickly meet the real-time requirement.

The above is a detailed description of a second embodiment of the operation ticket checking method based on text mining provided by the present application, and the following is a detailed description of an operation ticket checking system based on text mining provided by the second aspect of the present application.

Referring to fig. 4, the present embodiment provides an operation ticket checking system based on text mining, including:

the operation ticket database 10 is respectively connected with the text mining module 20 and the self-adaptive updating module 40 and is used for storing historical operation tickets;

the text mining module 20 is configured to perform text mining on the historical operation tickets in the operation ticket database 10, divide electric nouns, verbs and prepositions in the historical operation tickets through text word segmentation and part-of-speech tagging, and identify combination relationships of words of different parts-of-speech; constructing a dictionary by using the electric nouns, and taking the dictionary as a database; obtaining sentence pattern rules according to the combination relation of verbs or prepositions and power namewords, and constructing a knowledge base;

the operation ticket checking module 30 is configured to check the operation ticket to be checked with the database and the knowledge base; if the check result is correct, the ticket drawing is permitted;

and the self-adaptive updating module 40 is used for storing the operation ticket after the ticket drawing as a historical operation ticket into the operation ticket database 10, performing text mining and supplementing the database and the knowledge base.

Optionally, in the text mining module 20, a sentence pattern rule is obtained according to a combination relationship between a verb or a preposition and a power noun, and a knowledge base is constructed, specifically:

and extracting verbs and prepositions, obtaining a sentence pattern rule according to the combination relation of the verbs or prepositions and the power namewords, and constructing a regular expression corresponding to the sentence pattern rule to form a knowledge base.

The third aspect of the present application further provides an operation order checking device based on text mining, including a processor and a memory: the memory is used for storing the program codes and transmitting the program codes to the processor; the processor is used for executing the operation order checking method based on the text mining according to instructions in the program codes.

It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working process of the system and the device described above may refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, systems or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. An operation order checking method based on text mining is characterized by comprising the following steps:

performing text mining on the historical operation tickets in the operation ticket database, dividing electric nouns, verbs and prepositions in the historical operation tickets through text word segmentation and part-of-speech tagging, and identifying the combination relationship of words with different parts-of-speech; constructing a dictionary by using the electric nouns, and taking the dictionary as a database; obtaining sentence pattern rules according to the combination relation of verbs or prepositions and power namewords, and constructing a knowledge base;

checking the operation ticket to be checked by using a database and a knowledge base; if the checking result is correct, the ticket drawing is permitted;

and storing the operation ticket after the ticket drawing as a historical operation ticket into an operation ticket database, performing text mining, and supplementing the database and the knowledge base.

2. The operation ticket checking method based on text mining as claimed in claim 1, wherein the dictionary is constructed by electric nouns, and is used as a database, specifically:

key words such as station names, cabinet names, equipment numbers and equipment names are extracted from the electric nouns, and a three-layer dictionary corresponding to the stations, the cabinets and the equipment is constructed to serve as a database.

3. The operation order checking method based on text mining according to claim 1, wherein a sentence pattern rule is obtained according to a combination relationship between a verb or preposition and a power noun, and a knowledge base is constructed, specifically:

and extracting verbs and prepositions, obtaining a sentence pattern rule according to the combination relation of the verbs or prepositions and the power namewords, and constructing a regular expression corresponding to the sentence pattern rule to form a knowledge base.

4. The operation ticket checking method based on text mining as claimed in claim 1, further comprising after text mining the historical operation ticket:

after the text mining of the preset number of historical operation tickets, counting the occurrence frequency of each word in the dictionary and the occurrence frequency of each sentence pattern rule, and eliminating the word and the sentence pattern rule with the occurrence frequency lower than a threshold value from the database and the knowledge base.

5. The operation ticket checking method based on text mining as claimed in claim 1, wherein after the checking of the operation ticket to be checked with the database and the knowledge base, the method further comprises:

and if the checking result is wrong, generating modification opinions, and manually checking the modification opinions one by one.

6. The operation ticket checking method based on text mining as claimed in claim 5, wherein the manual check of the modification opinions one by one is specifically:

manually checking the modification opinions one by one, and judging whether the modification opinions are correct or not; and if the verification result is that the modification opinions are correct, modifying the corresponding position of the operation ticket according to the modification opinions, and sending the modification opinions to front-line personnel and experts for feedback and learning.

7. The operation ticket checking method based on text mining as claimed in claim 6, wherein the manual checking of the modification opinions one by one, after determining whether the modification opinions are correct, further comprises:

and if the verification result is that the modification opinions are wrong, directly carrying out reverse update on the content corresponding to the modification opinions in a knowledge base or a database through reverse update.

8. An operation order checking system based on text mining is characterized by comprising:

the operation ticket database is respectively connected with the text mining module and the self-adaptive updating module and is used for storing historical operation tickets;

the text mining module is used for performing text mining on the historical operation ticket in the operation ticket database, dividing electric nouns, verbs and prepositions in the historical operation ticket through text word segmentation and part-of-speech tagging, and identifying the combination relation of words with different parts-of-speech; constructing a dictionary by using the electric nouns, and taking the dictionary as a database; obtaining sentence pattern rules according to the combination relation of the verb or preposition and the power name word, and constructing a knowledge base;

the operation ticket checking module is used for checking the operation ticket to be checked by using the database and the knowledge base; if the check result is correct, the ticket drawing is permitted;

and the self-adaptive updating module is used for storing the operation ticket after the ticket drawing as a historical operation ticket into an operation ticket database, performing text mining and supplementing the database and the knowledge base.

9. The operation order checking system based on text mining as claimed in claim 8, wherein in the text mining module, sentence pattern rules are obtained according to a combination relationship between verbs or prepositions and power namers, and a knowledge base is constructed, specifically:

and extracting verbs and prepositions, obtaining sentence pattern rules according to the combination relationship of the verbs or prepositions and the power namewords, and constructing regular expressions corresponding to the sentence pattern rules to form a knowledge base.

10. An operation order checking device based on text mining, characterized in that the device comprises a processor and a memory:

the memory is used for storing program codes and transmitting the program codes to the processor;

the processor is used for executing the operation order checking method based on text mining according to any one of claims 1 to 7 according to the instructions in the program code.

Images