CN117648909A - Electric power system document data management system and method based on artificial intelligence - Google Patents
Electric power system document data management system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN117648909A CN117648909A CN202410120142.5A CN202410120142A CN117648909A CN 117648909 A CN117648909 A CN 117648909A CN 202410120142 A CN202410120142 A CN 202410120142A CN 117648909 A CN117648909 A CN 117648909A
- Authority
- CN
- China
- Prior art keywords
- document
- template
- user
- templates
- users
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000013523 data management Methods 0.000 title claims abstract description 16
- 238000007726 management method Methods 0.000 claims abstract description 32
- 230000005540 biological transmission Effects 0.000 claims abstract description 28
- 238000007405 data analysis Methods 0.000 claims abstract description 15
- 238000013500 data storage Methods 0.000 claims abstract description 13
- 238000012216 screening Methods 0.000 claims description 42
- 238000004458 analytical method Methods 0.000 claims description 15
- 239000000203 mixture Substances 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 8
- 238000012937 correction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data management, in particular to an artificial intelligence-based system and a method for managing document data of an electric power system, which comprise the following steps: the system comprises a document data storage module, a document data analysis module, an intelligent recommendation management module and a recommendation data transmission management module; storing the document template information and the history use information of the document template through a document data storage module; scoring the different document templates by a document data analysis module; dividing users into two types of users of non-mixed type use templates or users of mixed type use templates through an intelligent recommendation management module, and selecting different document template recommendation modes for different types of users; the document template recommended for the users who use the templates in a non-mixed mode is screened and transmitted through the recommended data transmission management module, so that the applicability and the useful value of the document template recommendation for different types of users are improved, and the efficiency of editing the documents of the electric power system for the different types of users is improved.
Description
Technical Field
The invention relates to the technical field of data management, in particular to an artificial intelligence-based system and method for managing document data of an electric power system.
Background
With the breakthrough development of information technology, particularly artificial intelligence technology, the utilization mode of text data has changed greatly, and the important trend has been from simple storage, classification, intelligent analysis, understanding and pushing, so that the artificial intelligence technology is applied to the aspect of intelligent document writing assistance of an electric power system, the artificial intelligence technology is utilized to help staff to improve the efficiency and quality of document material writing, the pressure of the staff can be reduced, the quality improvement and synergy of the power-assisted intelligent office management can be realized, and the transformation of enterprise digitization and intelligent management service can be really promoted;
when the document is drawn in an auxiliary mode of recommending the document template to related personnel, as different personnel have different use situations of the received recommended document template, for the personnel who can select different edition contents from a plurality of templates again as references to draw the document after receiving the document template, when selecting the edition contents, only the score of the whole document template is selected as references, and no score result of each edition content is selected as references, obviously, a single mode of recommending the complete document template according to the score is not applicable to the personnel of the corresponding type in the prior art, and the efficiency of editing the document of the electric power system by the personnel of the corresponding type is not improved.
Therefore, there is a need for an artificial intelligence based system and method for managing document data in a power system to solve the above problems.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based system and an artificial intelligence-based method for managing document data of an electric power system, so as to solve the problems in the background art.
In order to solve the technical problems, the invention provides the following technical scheme: an artificial intelligence based power system document data management system, the system comprising: the system comprises a document data storage module, a document data analysis module, an intelligent recommendation management module and a recommendation data transmission management module;
the output end of the document data storage module is connected with the input end of the document data analysis module, the output end of the document data analysis module is connected with the input ends of the intelligent recommendation management module and the recommendation data transmission management module, and the output end of the intelligent recommendation management module is connected with the input end of the recommendation data transmission management module;
storing the document template information and the historical use information of the document template by the user through the document data storage module;
scoring the different document templates by the document data analysis module;
dividing the users into two types of users of non-mixed type use templates or users of mixed type use templates according to the historical use information of the users on the document templates by the intelligent recommendation management module, and selecting different document template recommendation modes for different types of users;
and screening and transmitting the document templates recommended for the users who use the templates in a non-mixed mode through the recommended data transmission management module.
Further, the document data storage module comprises a document template storage unit, a composition information storage unit and a use information storage unit;
the output end of the document template storage unit is connected with the input end of the composition information storage unit, and the output end of the composition information storage unit is connected with the input end of the use information storage unit;
the document template storage unit is used for storing document template texts into a document corpus;
the composition information storage unit is used for storing composition part information of different document template texts, and comprises the number of sections composing the corresponding document template text and name information of each section;
the use information storage unit is used for storing the document template information used by the user in the past, and comprises the number of times of writing the document by using the complete template, the total number of times of using the document template and score information of the document template when writing the document by using the complete template;
the usage information storage unit is also used for storing the document of the document which is edited by the user.
Further, the document data analysis module comprises a use information calling unit and a document template scoring unit;
the input end of the use information calling unit is connected with the output end of the use information storage unit, and the output end of the use information calling unit is connected with the input end of the document template scoring unit;
the use information retrieving unit is used for retrieving the document of the document which is edited by the user at present into the document template scoring unit, and the document of the document which is edited by the user at present is retrieved after the authority is granted by the user;
the document template scoring unit is used for extracting keywords from document documents which are edited by a user, matching the extracted keywords with document template texts stored in a document corpus, calculating scoring score information of the document templates by using a BM25 algorithm, and sequencing the document templates according to scoring scores from high to low, wherein the scoring score range is [0, 100],0 is the lowest score, and 100 is the highest score.
Further, the intelligent recommendation management module comprises a user type estimating unit and a recommendation mode selecting unit;
the input end of the user type estimating unit is connected with the output end of the using information calling unit, and the output end of the user type estimating unit is connected with the input end of the recommending mode selecting unit;
the user type estimating unit is used for acquiring the number of times that different users use the complete template to write the document and the total number of times that the document template is used, analyzing the mixing degree of the different users when using the template, comparing the mixing degree, and estimating the user type as the user of the non-mixed type template or the user of the mixed type template according to the comparison result;
the recommending mode selecting unit is used for selecting recommending modes of the document templates for different types of users according to the estimated user types: for users who use templates without mixing, the recommended way of selection is: recommending the complete document templates to the user according to the order of the scoring scores from high to low; for a user using templates in a hybrid manner, the recommended mode selected is: dividing the complete document template text into a plurality of sections according to component information, scoring the plurality of sections, comparing scoring scores of the same section contents of different document template texts, recommending corresponding section contents of each document template to a user according to the sequence of the scoring scores from high to low, and scoring the section contents in the same way as scoring the complete document templates: extracting keywords from a document of a document which is edited by a user, matching the extracted keywords with a single edition content of a document template text stored in a document corpus, and calculating scoring score information of the edition content corresponding to the document template by using a BM25 algorithm.
Further, the recommended data transmission management module comprises a scoring trust analysis unit, a recommended content screening unit and a recommended content transmission unit;
the input end of the scoring trust degree analysis unit is connected with the output ends of the using information calling unit and the recommending mode selection unit, the output ends of the scoring trust degree analysis unit and the document template scoring unit are connected with the input end of the recommending content screening unit, and the output end of the recommending content screening unit is connected with the input end of the recommending content transmission unit;
the score trust degree analysis unit is used for calling score information of the document template when the user of the non-mixed type use template writes the document by using the complete template, analyzing the trust degree of the user of the non-mixed type use template on the score, and setting the minimum requirement score of different users on the document template;
the recommended content screening unit is used for establishing a recommended content screening model according to the trust degree and the lowest demand score, analyzing the trust degree of the current user for the score if the current user is a user using the template in a non-mixed mode, substituting the trust degree into the recommended content screening model, acquiring the lowest demand score of the current user for the document template, and screening out the template with the score higher than the lowest demand score in the document template;
the recommended content transmission unit is used for transmitting the selected document templates to the user terminal according to the order of the scoring scores from high to low.
An artificial intelligence-based power system document data management method comprises the following steps:
z1: storing the document template information and the historical use information of the document template by a user;
z2: scoring different document templates;
z3: analyzing the user types according to the historical use information of the user on the document template, and classifying the users into two types of users of the non-mixed type use template or users of the mixed type use template;
z4: selecting different document template recommendation modes for different types of users;
z5: and screening and transmitting the document templates recommended for the users using the templates in a non-mixed mode.
Further, in step Z1: the method comprises the steps of storing document template texts into a document corpus, storing component information of different document template texts, including the number of sections forming corresponding document template texts and the name information of each section, storing document template information used by a user in the past, including the number of times of writing documents by using a complete template, the total number of times of using the document template and score information of the document template when writing documents by using the complete template, and storing document documents edited by the user currently.
Further, in step Z2: extracting keywords from a document of a document which is edited by a user, matching the extracted keywords with document template texts stored in a document corpus, calculating score information of the document templates by using a BM25 algorithm, and sequencing the document templates from high score to low score;
and matching the document content edited by the user with the template content by utilizing an artificial intelligence technology, and scoring the document template, so that the accuracy of the scoring result is improved.
Further, in step Z3: the collection of times of calling different users to write the document by using the complete template is N= { N 1 ，N 2 ，…，N c The total number of times corresponding to the past use of the document template by the user is M= { M 1 ，M 2 ，…，M c Where c represents the number of users, according to the formulaComputing a mix of random users using templatesDegree of closure Q i The mixing degree of c users when using templates is calculated in the same way, the c users are ordered according to the order of the mixing degree from big to small, the ordered users are divided into d groups, the mixing degree of each user in the former group when using the templates is higher than that of the latter group, a random grouping result is obtained, and the average value set of the mixing degree of each user in the d groups when using the templates is K= { K 1 ，K 2 ，…，K d "according to the formula>Calculating goodness L of random one grouping result, wherein N j Representing the number of times the jth user has written a document using the complete template in the past, M j Represents the total number of times the jth user uses the document template in the past, K f And (3) expressing the average value of the mixing degree when f-th group users use the templates in one grouping result, analyzing the goodness of different grouping results in the same mode, obtaining the grouping result with the highest goodness, screening out the users in the first two groups from the grouping result with the highest goodness, dividing the users in the first two groups into users of the mixed type use templates, and dividing the rest users into users of the non-mixed type use templates.
Further, in step Z4: for a user using templates in a hybrid manner, the recommended mode selected is: dividing the complete document template text into a plurality of sections according to component information, scoring the plurality of sections, comparing scoring scores of the same section content of different document template texts, and recommending corresponding section content of each document template to a user according to the sequence of the scoring scores from high to low; for users who use templates without mixing, the recommended way of selection is: recommending the complete document templates to the user according to the order of the scoring scores from high to low;
the behavior data of the template used by the user when writing the official document is collected through the big data technology: the custom of writing documents by using a complete template or the custom of referring to writing documents by using a split template, the use of the split template to refer to writing documents refers to picking different edition contents from a plurality of document templates as reference writing documents, analyzing the mixing degree of users when using the templates according to behavior data, dividing the users into two types of users using the templates in a mixed mode and users using the templates in a non-mixed mode, and giving different document template recommending modes for different types of users: users who do not use templates in a mixed mode habitually use complete document templates to refer to written documents, and recommending complete document templates according to scoring scores for corresponding types of users; the users of the mixed template are habitually used to select different edition contents from a plurality of document templates recommended to the users to reference and write documents, but the users are all the edition contents independently selected in the past, the score of each edition content is not used as a reference, the divided edition contents are recommended and split for the users of the corresponding types according to the score, the users of the mixed template are helped to quickly select the proper edition contents as the references to write documents, the efficiency of the users of the corresponding types for editing the documents of the electric power system is improved, and the applicability of the document template recommendation mode to the users of the different types is improved.
Further, in step Z5: when a user who calls a random non-mixed template uses the complete template to write a document, the Score set of the used document template is score= { Score 1 ，Score 2 ，…，Score r Wherein r represents the number of document templates used by the corresponding user according to the formulaCalculating trust B of corresponding user for scoring e Wherein a represents an a-th document template used by a corresponding user in the past, and the lowest demand score of the corresponding user on the document template is analyzed to be I e ：/>The lowest demand scores of the rest users for the document templates are the confidence level of the corresponding users for the scores minus the number of the document templates used by the corresponding users and +.>Product of (1), wherein->Representing the influence coefficient of the number of used document templates, < ->The confidence level set of the user who obtains m unmixed usage templates on the score is B= { B 1 ，B 2 ，…，B e ，…，B m The lowest demand score set for the document template is i= { I } 1 ，I 2 ，…，I e ，…，I m Data points { (B) 1 ，I 1 ），（B 2 ，I 2 ），…，（B m ，I m ) Performing straight line fitting, and establishing a recommended content screening model:
；
wherein,and->Representing a fitting coefficient, and if the current user is a user using a template in a non-mixed mode, obtaining that the trust degree of the current user on the score is B ’ Will B ’ Substituting into a recommended content screening model: let x=b ’ The lowest demand score of the current user for the document template is obtained as follows: />Score in the document template is higher than +.>The templates of the document are screened out, and the screened document templates are transmitted to the current user terminal according to the order of the scoring scores from high to low;
in the prior art, after scoring the document templates is finished, the document templates are recommended to users needing to compose documents according to the sequence from high score to low score, the templates are useful for partial users, the templates are useless for partial users, a uniform transmission mode can cause invalid data transmission, data transmission resources are occupied, the standards of using the document templates by different users are judged by analyzing the score of the document templates used by different users in the past, the lowest demand score of the document templates by the users is analyzed, the trust degree and the lowest demand score are subjected to data fitting to establish a recommended content screening model, the correction of the analysis result of the lowest demand score is facilitated, the accuracy of the analysis result is improved, the trust degree of the users currently belonging to the user type of the non-mixed type using templates is substituted into the recommended content screening model, the lowest demand score of the current users is analyzed, the document templates not higher than the lowest demand score of the current users are deleted, the rest templates are recommended to the current users, and the occupied data transmission resources of the current users are reduced while the value of the recommended content is facilitated to be improved.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the edited document content of the user is matched with the template content through an artificial intelligence technology, the document templates are scored, the document templates are recommended to the user who needs to write the document of the electric power system according to the sequence of the scoring scores from high to low, and the behavior data of the templates used when the user writes the document in the past are collected through a big data technology: the custom of writing documents by using a complete template or the custom of referring to writing documents by using a split template, the use of the split template to refer to writing documents refers to picking different edition contents from a plurality of document templates as reference writing documents, analyzing the mixing degree of users when using the templates according to behavior data, dividing the users into two types of users using the templates in a mixed mode and users using the templates in a non-mixed mode, and giving different document template recommending modes for different types of users: users who do not use templates in a mixed mode habitually use complete document templates to refer to written documents, and recommending complete document templates according to scoring scores for corresponding types of users; the users of the mixed type use templates habitually select different edition contents from a plurality of document templates recommended to the users to reference and write documents, but the users are all the edition contents independently selected in the past, the score of each edition content is not used as a reference, the divided edition contents are recommended and split for the users of the corresponding type according to the score, the users of the mixed type use templates are helped to quickly select the proper edition contents as the references to write documents, the efficiency of the users of the corresponding type for editing the documents of the electric power system is improved, and the applicability of the document template recommendation mode to the users of the different types is improved;
the standard of the document templates used by different users is judged by analyzing the score scores of the document templates used by the different users in the past, the minimum demand scores of the document templates are analyzed and the user performs data fitting on the trust and the minimum demand scores to establish a recommended content screening model, so that the correction of the minimum demand score analysis result is facilitated, the accuracy of the analysis result is improved, the trust of the user type currently belonging to the non-mixed use template to the score is substituted into the recommended content screening model, the minimum demand scores of the current user are analyzed, the document templates not higher than the minimum demand scores are deleted, the residual templates are recommended to the current user, and the occupation of data transmission resources is reduced while the useful value of the recommended content to the user is facilitated.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a block diagram of an artificial intelligence based power system document data management system of the present invention;
FIG. 2 is a flow chart of an artificial intelligence based method for managing document data in an electrical power system.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention is further described below with reference to fig. 1-2 and the specific embodiments.
Example 1: as shown in fig. 1, the present embodiment provides an artificial intelligence-based power system document data management system, which includes: the system comprises a document data storage module, a document data analysis module, an intelligent recommendation management module and a recommendation data transmission management module; storing the document template information and the historical use information of the user on the document template through a document data storage module; scoring the different document templates by a document data analysis module; dividing the users into two types of users of non-mixed type use templates or users of mixed type use templates according to the historical use information of the users on the document templates by the intelligent recommendation management module, and selecting different document template recommendation modes for different types of users; and screening and transmitting the document templates recommended for the users who use the templates in a non-mixed mode through a recommended data transmission management module.
The document data storage module comprises a document template storage unit, a composition information storage unit and a use information storage unit; the document template storage unit is used for storing the document template text into a document corpus; the composition information storage unit is used for storing composition part information of different document template texts, including the number of sections composing the corresponding document template text and the name information of each section; the use information storage unit is used for storing the information of the document templates used by the user in the past, and comprises the times of writing the documents by using the complete template, the total times of using the document templates and score information of the document templates when writing the documents by using the complete template; the usage information storage unit is also used for storing the document of the document which is edited by the user.
The document data analysis module comprises a use information calling unit and a document template scoring unit; the use information calling unit is used for calling the document of the document which is edited by the user to the document template scoring unit, and the document of the document which is edited by the user is called after the user grants permission; the document template scoring unit is used for extracting keywords from document documents which are edited by a user, matching the extracted keywords with document template texts stored in a document corpus, calculating scoring score information of the document templates by using a BM25 algorithm, and sequencing the document templates according to the scoring scores from high to low, wherein the scoring score ranges are [0, 100],0 is the lowest score, and 100 is the highest score.
The intelligent recommendation management module comprises a user type estimating unit and a recommendation mode selecting unit; the user type estimating unit is used for acquiring the times of writing the document by using the complete template and the total times of using the document template by different users, analyzing the mixing degree of the templates used by different users, comparing the mixing degree, and estimating the user type as the user of the non-mixed template or the user of the mixed template according to the comparison result; the recommendation mode selection unit is used for selecting recommendation modes of the document templates for different types of users according to the estimated user types: for users who use templates without mixing, the recommended way of selection is: recommending the complete document templates to the user according to the order of the scoring scores from high to low; for a user using templates in a hybrid manner, the recommended mode selected is: dividing the complete document template text into a plurality of sections according to component information, scoring the plurality of sections, comparing scoring scores of the same section contents of different document template texts, recommending corresponding section contents of each document template to a user according to the sequence of the scoring scores from high to low, and scoring the section contents in the same way as scoring the complete document templates: extracting keywords from a document of a document which is edited by a user, matching the extracted keywords with a single edition content of a document template text stored in a document corpus, and calculating scoring score information of the edition content corresponding to the document template by using a BM25 algorithm.
The recommended data transmission management module comprises a scoring trust analysis unit, a recommended content screening unit and a recommended content transmission unit; the score trust degree analysis unit is used for calling score information of the document template when the user of the non-mixed type use template writes the document by using the complete template, analyzing the trust degree of the user of the non-mixed type use template on the score, and setting the minimum demand score of different users on the document template; the recommended content screening unit is used for establishing a recommended content screening model according to the trust degree and the minimum demand score, analyzing the trust degree of the current user for the score if the current user is a user of the non-mixed use template, substituting the trust degree into the recommended content screening model, acquiring the minimum demand score of the current user for the document template, and screening out the template with the score higher than the minimum demand score in the document template; and the recommended content transmission unit is used for transmitting the selected document templates to the user terminal according to the order of the scoring scores from high to low.
Example 2: as shown in fig. 2, the embodiment provides an artificial intelligence-based power system document data management method, which is implemented based on the data management system in the embodiment, and specifically includes the following steps:
z1: storing document template information and historical use information of a user on the document template, storing document template texts into a document corpus, storing component part information of different document template texts, including the number of sections forming corresponding document template texts and name information of each section, storing document template information used by the user in the past, including the number of times of writing documents by using a complete template, the total number of times of using the document template and score information of the document template when writing documents by using the complete template, and storing document documents edited by the user at present;
z2: scoring different document templates, extracting keywords from document documents which are edited by a user, matching the extracted keywords with document template texts stored in a document corpus, calculating scoring score information of the document templates by using a BM25 algorithm, and sequencing the document templates from high score to low score;
z3: the collection of times of calling different users to write the document by using the complete template is N= { N 1 ，N 2 ，…，N c The total number of times corresponding to the past use of the document template by the user is M= { M 1 ，M 2 ，…，M c Where c represents the number of users, according to the formulaCalculating the mixing degree Q when one user uses the template randomly i The mixing degree of c users when using templates is calculated in the same way, the c users are ordered according to the order of the mixing degree from big to small, the ordered users are divided into d groups, the mixing degree of each user in the former group when using the templates is higher than that of the latter group, a random grouping result is obtained, and the average value set of the mixing degree of each user in the d groups when using the templates is K= { K 1 ，K 2 ，…，K d According to the formula }Calculating goodness L of random one grouping result, wherein N j Representing the number of times the jth user has written a document using the complete template in the past, M j Represents the total number of times the jth user uses the document template in the past, K f The method comprises the steps of representing the average value of the mixing degree when f-th group users use templates in a random grouping result, analyzing the goodness of different grouping results in the same mode, obtaining the grouping result with the highest goodness, screening out the users in the first two groups from the grouping result with the highest goodness, dividing the users in the first two groups into users of the mixed type using templates, and dividing the rest users into users of the non-mixed type using templates;
z4: for a user using templates in a hybrid manner, the recommended mode selected is: dividing the complete document template text into a plurality of sections according to component information, scoring the plurality of sections, comparing scoring scores of the same section content of different document template texts, and recommending corresponding section content of each document template to a user according to the sequence of the scoring scores from high to low; for users who use templates without mixing, the recommended way of selection is: recommending the complete document templates to the user according to the order of the scoring scores from high to low;
z5: screening and transmitting the document templates recommended for users of the non-mixed type use templates, wherein when the users of random non-mixed type use templates write documents by using the complete templates in the past, the Score set of the used document templates is score= { Score 1 ，Score 2 ，…，Score r Wherein r represents the number of document templates used by the corresponding user according to the formulaCalculating trust B of corresponding user for scoring e Wherein a represents an a-th document template used by a corresponding user in the past, and the lowest demand score of the corresponding user on the document template is set as I e ：/>The lowest demand scores of the rest users for the document templates are the confidence level of the corresponding users for the scores minus the number of the document templates used by the corresponding users and +.>Product of (1), wherein->Representing the influence coefficient of the number of used document templates, < ->The confidence level set of the user who obtains m unmixed usage templates on the score is B= { B 1 ，B 2 ，…，B e ，…，B m The lowest demand score set for the document template is i= { I } 1 ，I 2 ，…，I e ，…，I m Data points { (B) 1 ，I 1 ），（B 2 ，I 2 ），…，（B m ，I m ) Performing straight line fitting, and establishing a recommended content screening model: />The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>And->Representing fitting coefficients +.>，/>If the current user is a user using the template in a non-mixed mode, obtaining that the trust degree of the current user on the score is B ’ Will B ’ Substituting into a recommended content screening model: let x=b ’ The lowest demand score of the current user for the document template is obtained as follows: />Score in the document template is higher than +.>The templates of the document are screened out, and the screened document templates are transmitted to the current user terminal according to the order of the scoring scores from high to low;
for example: when a user who calls up three random non-mixed templates uses the complete templates to write a document, the score sets of the used document templates are {90, 92, 85}, {99, 98, 95, 97} and {80, 75, 70, 72, 82}, respectively, so that the confidence level sets of the three non-mixed templates for the score of the user are {89.7, 97.3 and 75.8}, and the setting is carried outAnalyzing to obtain that the minimum requirement score set of the corresponding user for the document template is {87.6, 94.5, 72.3}, and establishing a recommended content screening model: />Obtaining the trust degree of the user of the current non-mixed type use template on the score as B ’ =80, mix B ’ Substituting into a recommended content screening model: let x=b ’ And (80) obtaining the lowest demand score of the current user on the document templates as 76.9, screening out templates with score scores higher than 76.9 in the document templates, and transmitting the screened document templates to the current user terminal according to the sequence of the score scores from high to low.
Finally, it should be noted that: the foregoing is merely a preferred example of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An artificial intelligence-based power system document data management system is characterized in that: the system comprises: the system comprises a document data storage module, a document data analysis module, an intelligent recommendation management module and a recommendation data transmission management module;
the output end of the document data storage module is connected with the input end of the document data analysis module, the output end of the document data analysis module is connected with the input ends of the intelligent recommendation management module and the recommendation data transmission management module, and the output end of the intelligent recommendation management module is connected with the input end of the recommendation data transmission management module;
storing the document template information and the historical use information of the document template by the user through the document data storage module;
scoring the different document templates by the document data analysis module;
dividing the users into two types of users of non-mixed type use templates or users of mixed type use templates according to the historical use information of the users on the document templates by the intelligent recommendation management module, and selecting different document template recommendation modes for different types of users;
and screening and transmitting the document templates recommended for the users who use the templates in a non-mixed mode through the recommended data transmission management module.
2. An artificial intelligence based power system document data management system according to claim 1 wherein: the document data storage module comprises a document template storage unit, a composition information storage unit and a use information storage unit;
the output end of the document template storage unit is connected with the input end of the composition information storage unit, and the output end of the composition information storage unit is connected with the input end of the use information storage unit;
the document template storage unit is used for storing document template texts into a document corpus;
the composition information storage unit is used for storing composition part information of different document template texts, and comprises the number of sections composing the corresponding document template text and name information of each section;
the use information storage unit is used for storing the document template information used by the user in the past, and comprises the number of times of writing the document by using the complete template, the total number of times of using the document template and score information of the document template when writing the document by using the complete template;
the usage information storage unit is also used for storing the document of the document which is edited by the user.
3. An artificial intelligence based power system document data management system according to claim 2 wherein: the document data analysis module comprises a use information calling unit and a document template scoring unit;
the input end of the use information calling unit is connected with the output end of the use information storage unit, and the output end of the use information calling unit is connected with the input end of the document template scoring unit;
the use information retrieving unit is used for retrieving the document of the document edited by the user to the document template scoring unit;
the document template scoring unit is used for extracting keywords from document documents which are edited by a user, matching the extracted keywords with document template texts stored in a document corpus, calculating scoring score information of the document templates by using a BM25 algorithm, and sequencing the document templates from high score to low score.
4. An artificial intelligence based power system document data management system according to claim 3 wherein: the intelligent recommendation management module comprises a user type estimating unit and a recommendation mode selecting unit;
the input end of the user type estimating unit is connected with the output end of the using information calling unit, and the output end of the user type estimating unit is connected with the input end of the recommending mode selecting unit;
the user type estimating unit is used for acquiring the number of times that different users use the complete template to write the document and the total number of times that the document template is used, analyzing the mixing degree of the different users when using the template, comparing the mixing degree, and estimating the user type as the user of the non-mixed type template or the user of the mixed type template according to the comparison result;
the recommending mode selecting unit is used for selecting recommending modes of the document templates for different types of users according to the estimated user types: for users who use templates without mixing, the recommended way of selection is: recommending the complete document templates to the user according to the order of the scoring scores from high to low; for a user using templates in a hybrid manner, the recommended mode selected is: dividing the complete document template text into a plurality of sections according to the component information, scoring the plurality of sections, comparing scoring scores of the same section contents of different document template texts, and recommending the corresponding section contents of each document template to a user according to the sequence of the scoring scores from high to low.
5. The artificial intelligence based power system document data management system of claim 4, wherein: the recommended data transmission management module comprises a scoring trust analysis unit, a recommended content screening unit and a recommended content transmission unit;
the input end of the scoring trust degree analysis unit is connected with the output ends of the using information calling unit and the recommending mode selection unit, the output ends of the scoring trust degree analysis unit and the document template scoring unit are connected with the input end of the recommending content screening unit, and the output end of the recommending content screening unit is connected with the input end of the recommending content transmission unit;
the score trust degree analysis unit is used for calling score information of the document template when the user of the non-mixed type use template writes the document by using the complete template, analyzing the trust degree of the user of the non-mixed type use template on the score, and setting the minimum requirement score of different users on the document template;
the recommended content screening unit is used for establishing a recommended content screening model according to the trust degree and the lowest demand score, analyzing the trust degree of the current user for the score if the current user is a user using the template in a non-mixed mode, substituting the trust degree into the recommended content screening model, acquiring the lowest demand score of the current user for the document template, and screening out the template with the score higher than the lowest demand score in the document template;
the recommended content transmission unit is used for transmitting the selected document templates to the user terminal according to the order of the scoring scores from high to low.
6. An artificial intelligence-based power system document data management method is characterized in that: the method comprises the following steps:
z1: storing the document template information and the historical use information of the document template by a user;
z2: scoring different document templates;
z3: analyzing the user types according to the historical use information of the user on the document template, and classifying the users into two types of users of the non-mixed type use template or users of the mixed type use template;
z4: selecting different document template recommendation modes for different types of users;
z5: and screening and transmitting the document templates recommended for the users using the templates in a non-mixed mode.
7. The method for managing the document data of the electric power system based on the artificial intelligence according to claim 6, wherein the method comprises the following steps: in step Z1: storing the document template texts into a document corpus, storing component information of different document template texts, including the number of sections forming the corresponding document template texts and the name information of each section, storing document template information which is used by a user in the past, including the number of times of writing documents by using a complete template, the total number of times of using the document template and score information of the document template when writing documents by using the complete template, and storing document documents which are edited by the user at present;
in step Z2: extracting keywords from a document of a document which is edited by a user, matching the extracted keywords with document template texts stored in a document corpus, calculating score information of the document templates by using a BM25 algorithm, and sequencing the document templates from high score to low score.
8. The method for managing the document data of the electric power system based on the artificial intelligence as claimed in claim 7, wherein: in step Z3: the collection of times of calling different users to write the document by using the complete template is N= { N 1 ，N 2 ，…，N c The total number of times corresponding to the past use of the document template by the user is M= { M 1 ，M 2 ，…，M c Where c represents the number of users, according to the formulaCalculating the mixing degree Q when one user uses the template randomly i The mixing degree of c users when using the templates is calculated in the same way, the c users are ordered according to the order of the mixing degree from big to small, the ordered users are divided into d groups, and a random grouping result is obtained, wherein the average value set of the mixing degree of each group of users in the d groups when using the templates is K= { K 1 ，K 2 ，…，K d "according to the formula>Calculating goodness of random one grouping resultL, where N j Representing the number of times the jth user has written a document using the complete template in the past, M j Represents the total number of times the jth user uses the document template in the past, K f And (3) expressing the average value of the mixing degree when f-th group users use the templates in one grouping result, analyzing the goodness of different grouping results in the same mode, obtaining the grouping result with the highest goodness, screening out the users in the first two groups from the grouping result with the highest goodness, dividing the users in the first two groups into users of the mixed type use templates, and dividing the rest users into users of the non-mixed type use templates.
9. The method for managing the document data of the electric power system based on the artificial intelligence according to claim 8, wherein the method comprises the following steps: in step Z4: for a user using templates in a hybrid manner, the recommended mode selected is: dividing the complete document template text into a plurality of sections according to component information, scoring the plurality of sections, comparing scoring scores of the same section content of different document template texts, and recommending corresponding section content of each document template to a user according to the sequence of the scoring scores from high to low; for users who use templates without mixing, the recommended way of selection is: and recommending the complete document templates to the user according to the order of the scoring scores from high to low.
10. The method for managing the document data of the electric power system based on the artificial intelligence as claimed in claim 7, wherein: in step Z5: when a user who calls a random non-mixed template uses the complete template to write a document, the Score set of the used document template is score= { Score 1 ，Score 2 ，…，Score r Wherein r represents the number of document templates used by the corresponding user according to the formulaCalculating trust B of corresponding user for scoring e Wherein a represents an a-th document template used by a corresponding user in the past, and the corresponding user is set for the document templateIs scored as I e ：/>Wherein->Representing the influence coefficient of the number of used document templates, < ->The confidence level set of the user who obtains m unmixed usage templates on the score is B= { B 1 ，B 2 ，…，B e ，…，B m The lowest demand score set for the document template is i= { I } 1 ，I 2 ，…，I e ，…，I m Data points { (B) 1 ，I 1 ），（B 2 ，I 2 ），…，（B m ，I m ) Performing straight line fitting, and establishing a recommended content screening model:
；
wherein,and->Representing a fitting coefficient, and if the current user is a user using a template in a non-mixed mode, obtaining that the trust degree of the current user on the score is B ’ Will B ’ Substituting into a recommended content screening model: let x=b ’ The lowest demand score of the current user for the document template is obtained as follows: />Score in the document template is higher than +.>And (3) screening out the templates of the selected document templates, and transmitting the selected document templates to the current user terminal according to the order of the scoring scores from high to low.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410120142.5A CN117648909B (en) | 2024-01-29 | 2024-01-29 | Electric power system document data management system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410120142.5A CN117648909B (en) | 2024-01-29 | 2024-01-29 | Electric power system document data management system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117648909A true CN117648909A (en) | 2024-03-05 |
| CN117648909B CN117648909B (en) | 2024-04-12 |
Family
ID=90043673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410120142.5A Active CN117648909B (en) | 2024-01-29 | 2024-01-29 | Electric power system document data management system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117648909B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104469517A (en) * | 2014-12-12 | 2015-03-25 | 华为技术有限公司 | User interface presentation method, terminal and server |
| CN107728995A (en) * | 2017-11-28 | 2018-02-23 | 北京洪泰同创信息技术有限公司 | A kind of technical documentation auxiliary writing system and method |
| US20180225739A1 (en) * | 2015-07-31 | 2018-08-09 | Piksel, Inc. | Recommendation system |
| CN110413977A (en) * | 2019-08-02 | 2019-11-05 | 山东浪潮通软信息科技有限公司 | A method of based on bookmark techniques dynamic generation contract text |
| CN110941713A (en) * | 2018-09-21 | 2020-03-31 | 上海仪电（集团）有限公司中央研究院 | Self-optimization financial information plate classification method based on topic model |
| US20200183943A1 (en) * | 2018-12-05 | 2020-06-11 | Snap Inc. | Ui and devices for ranking user generated content |
| CN111680482A (en) * | 2020-05-07 | 2020-09-18 | 车智互联（北京）科技有限公司 | Title image-text generation method and computing device |
| CN112069782A (en) * | 2020-09-08 | 2020-12-11 | 中国平安财产保险股份有限公司 | Document template generation method and device, electronic equipment and storage medium |
| CN112711937A (en) * | 2021-01-18 | 2021-04-27 | 腾讯科技（深圳）有限公司 | Template recommendation method, device, equipment and storage medium |
| CN112749536A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Document generation method, device and equipment |
| CN112989025A (en) * | 2021-04-13 | 2021-06-18 | 山东科技大学 | Text writing real-time recommendation method based on topic model and user behavior data |
| CN113254574A (en) * | 2021-03-15 | 2021-08-13 | 河北地质大学 | Method, device and system for auxiliary generation of customs official documents |
| CN113961811A (en) * | 2021-10-28 | 2022-01-21 | 平安科技（深圳）有限公司 | Conversational recommendation method, device, equipment and medium based on event map |
| CN115618808A (en) * | 2022-10-26 | 2023-01-17 | 北京字跳网络技术有限公司 | Document typesetting method and device, electronic equipment and storage medium |
| CN116089701A (en) * | 2022-11-17 | 2023-05-09 | 国家电网有限公司大数据中心 | Personalized recommendation method and device |
| CN116090416A (en) * | 2023-04-10 | 2023-05-09 | 中国电子技术标准化研究院 | Standard writing method, system, equipment and medium based on standard knowledge graph |
| CN116701669A (en) * | 2023-06-09 | 2023-09-05 | 科大讯飞股份有限公司 | Method, device, equipment and storage medium for generating multimedia content |
| CN116975254A (en) * | 2023-06-30 | 2023-10-31 | 腾讯科技（深圳）有限公司 | Visual data presentation method, visual data presentation device and storage medium |
-
2024
- 2024-01-29 CN CN202410120142.5A patent/CN117648909B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104469517A (en) * | 2014-12-12 | 2015-03-25 | 华为技术有限公司 | User interface presentation method, terminal and server |
| US20180225739A1 (en) * | 2015-07-31 | 2018-08-09 | Piksel, Inc. | Recommendation system |
| CN107728995A (en) * | 2017-11-28 | 2018-02-23 | 北京洪泰同创信息技术有限公司 | A kind of technical documentation auxiliary writing system and method |
| CN110941713A (en) * | 2018-09-21 | 2020-03-31 | 上海仪电（集团）有限公司中央研究院 | Self-optimization financial information plate classification method based on topic model |
| US20200183943A1 (en) * | 2018-12-05 | 2020-06-11 | Snap Inc. | Ui and devices for ranking user generated content |
| CN110413977A (en) * | 2019-08-02 | 2019-11-05 | 山东浪潮通软信息科技有限公司 | A method of based on bookmark techniques dynamic generation contract text |
| CN112749536A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Document generation method, device and equipment |
| CN111680482A (en) * | 2020-05-07 | 2020-09-18 | 车智互联（北京）科技有限公司 | Title image-text generation method and computing device |
| CN112069782A (en) * | 2020-09-08 | 2020-12-11 | 中国平安财产保险股份有限公司 | Document template generation method and device, electronic equipment and storage medium |
| CN112711937A (en) * | 2021-01-18 | 2021-04-27 | 腾讯科技（深圳）有限公司 | Template recommendation method, device, equipment and storage medium |
| CN113254574A (en) * | 2021-03-15 | 2021-08-13 | 河北地质大学 | Method, device and system for auxiliary generation of customs official documents |
| CN112989025A (en) * | 2021-04-13 | 2021-06-18 | 山东科技大学 | Text writing real-time recommendation method based on topic model and user behavior data |
| CN113961811A (en) * | 2021-10-28 | 2022-01-21 | 平安科技（深圳）有限公司 | Conversational recommendation method, device, equipment and medium based on event map |
| CN115618808A (en) * | 2022-10-26 | 2023-01-17 | 北京字跳网络技术有限公司 | Document typesetting method and device, electronic equipment and storage medium |
| CN116089701A (en) * | 2022-11-17 | 2023-05-09 | 国家电网有限公司大数据中心 | Personalized recommendation method and device |
| CN116090416A (en) * | 2023-04-10 | 2023-05-09 | 中国电子技术标准化研究院 | Standard writing method, system, equipment and medium based on standard knowledge graph |
| CN116701669A (en) * | 2023-06-09 | 2023-09-05 | 科大讯飞股份有限公司 | Method, device, equipment and storage medium for generating multimedia content |
| CN116975254A (en) * | 2023-06-30 | 2023-10-31 | 腾讯科技（深圳）有限公司 | Visual data presentation method, visual data presentation device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 龙婧;徐文峰;罗启星;: "面向智能写作的混合推荐模型研究", 电力信息与通信技术, no. 04, 15 April 2019 (2019-04-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117648909B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1464013B1 (en) | Systems, methods, and software for classifying documents | |
| CN111930966B (en) | Intelligent policy matching method and system for digital government affairs | |
| US6401086B1 (en) | Method for automatically generating a summarized text by a computer | |
| CN110516057B (en) | Petition question answering method and device | |
| CN109599187A (en) | A kind of online interrogation point examines method, server, terminal, equipment and medium | |
| US20110179077A1 (en) | Retrieval system and method of searching of information in the Internet | |
| CN117648909B (en) | Electric power system document data management system and method based on artificial intelligence | |
| CN112532755B (en) | Interest list pushing system based on heterogeneous information network | |
| CN116825259B (en) | Medical data management method based on Internet of things | |
| CN113886684A (en) | Network recruitment intelligent recommendation method and system and computer readable storage medium | |
| CN117171331A (en) | Professional field information interaction method, device and equipment based on large language model | |
| CN109783483A (en) | A kind of method, apparatus of data preparation, computer storage medium and terminal | |
| CN116383366B (en) | Response information determining method, electronic equipment and storage medium | |
| CN117076692A (en) | File online management method and system | |
| CN113742498B (en) | Knowledge graph construction and updating method | |
| CN112883704B (en) | Big data similar text duplicate removal preprocessing method and device and terminal equipment | |
| CN113139581B (en) | Image classification method and system based on multi-image fusion | |
| CN114417010A (en) | Knowledge graph construction method and device for real-time workflow and storage medium | |
| CN110674330A (en) | Expression management method and device, electronic equipment and storage medium | |
| CN111813976A (en) | Method and device for customizing graphic trademark and storage medium | |
| CN109977269B (en) | Data self-adaptive fusion method for XML file | |
| CN107977455A (en) | Ceb files full-text search method, device and computer-readable recording medium | |
| AU772287B2 (en) | System and method for high speed, high volume tabulation of data | |
| KR20100064136A (en) | Multimedia data search method | |
| CN114722173A (en) | Technical service consultation management system based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |