CN117094304A - Prompting method and system for technical standard revision applied to power grid field - Google Patents
Prompting method and system for technical standard revision applied to power grid field Download PDFInfo
- Publication number
- CN117094304A CN117094304A CN202311347980.8A CN202311347980A CN117094304A CN 117094304 A CN117094304 A CN 117094304A CN 202311347980 A CN202311347980 A CN 202311347980A CN 117094304 A CN117094304 A CN 117094304A
- Authority
- CN
- China
- Prior art keywords
- technical standard
- power grid
- technical
- context
- target
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000000284 extract Substances 0.000 claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 57
- 238000012545 processing Methods 0.000 claims description 15
- 230000004044 response Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 10
- 230000000873 masking effect Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 18
- 238000013473 artificial intelligence Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012015 optical character recognition Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 241000157593 Milvus Species 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a prompting method and a prompting system for technical standard system revision applied to the field of power grids, wherein the method comprises the following steps: determining an auxiliary power grid field technical standard file related to a target technical standard system revision template; determining first context contents of each technical index vacancy to be filled in a selected area on the target technical standard revision template; generating corresponding first prompt engineering information according to the first context content of all technical index gaps to be filled; inputting the first prompting engineering information into a generated artificial intelligent model, so that the generated artificial intelligent model can extract a first prior art index text conforming to each first context content from technical standard files of the auxiliary power grid field respectively; and aiming at each first context content, displaying all the first prior art index texts corresponding to the target first context content as prompt information of the technical index gaps to be filled corresponding to the target first context content.
Description
Technical Field
The disclosure relates to the technical field of computers, and in particular relates to a prompting method, a prompting system and electronic equipment for technical standard system revision applied to the field of power grids.
Background
With the development of the technology in the power grid field, technical standards in the power grid field need to be revised. Currently, the technical standards in the power grid field are revised by means of a technical standard revision template; specifically, the revision staff can generate a technical standard revision template according to the actual revision requirement, technical contents required to be normalized and limited and a plurality of technical index vacancies to be filled are recorded in the technical standard revision template, and the subsequent revision staff can fill corresponding technical index information in the technical index vacancies to be filled in the technical standard revision template. However, because the technical indexes to be filled in the technical standard revision templates in the existing power grid field have more vacancies and wider knowledge areas, the problems that the filled technical indexes are unreasonable and need to be adjusted repeatedly often occur under the condition that no auxiliary prompt information is available for revision personnel, and the whole process of filling the templates is long in time consumption, low in efficiency and large in workload.
Disclosure of Invention
The disclosure aims at solving at least one of the technical problems in the prior art, and provides a prompting method, a prompting system and electronic equipment for revising technical standard systems applied to the field of power grids.
In a first aspect, an embodiment of the present disclosure provides a method for prompting technical standard system revisions applied to a power grid field, including:
determining at least one auxiliary power grid domain technical standard file related to a target technical standard revision template;
determining a first context content of each technical index empty to be filled in a selected area on the target technical standard revision template in response to the selection and auxiliary request operations;
generating corresponding first prompt engineering information according to the first context contents of all the technical index gaps to be filled, wherein the first prompt engineering information comprises: the first questioning questions indicate that first prior art index texts conforming to the first context content are respectively extracted from the auxiliary power grid domain technical standard files;
inputting the first prompting engineering information into a pre-trained generation type artificial intelligent model, so that the generation type artificial intelligent model can extract first prior art index texts conforming to the first context content from the auxiliary power grid field technical standard files according to the first prompting engineering information;
And aiming at each first context content, displaying all first prior art index texts corresponding to the target first context content as prompt information of technical index gaps to be filled corresponding to the target first context content.
In some embodiments, the step of determining at least one auxiliary grid domain technical standard file associated with the target technical standard regulatory revision template comprises:
screening out a power grid domain technical standard file with similarity to the technical title name recorded in the target technical standard system revision template being greater than a first similarity threshold from a preset power grid domain technical standard file library, and taking the power grid domain technical standard file as the auxiliary power grid domain technical standard file related to the target technical standard system revision template;
or screening out a power grid domain technical standard file with similarity to the technical abstract content recorded in the target technical standard system revision template being greater than a second similarity threshold from a preset power grid domain technical standard file library, and taking the power grid domain technical standard file as the auxiliary power grid domain technical standard file related to the target technical standard system revision template;
or, screening out a power grid domain technical standard file which is set in advance and has similarity to the technical abstract content recorded in the target technical standard revision template larger than a first similarity threshold and has similarity to the technical abstract content recorded in the target technical standard revision template larger than a second similarity threshold from a preset power grid domain technical standard file library, and taking the power grid domain technical standard file as the auxiliary power grid domain technical standard file related to the target technical standard revision template;
Or according to the selected operation of the user, using the power grid domain technical standard file selected by the user from a preset power grid domain technical standard file library as the auxiliary power grid domain technical standard file related to the target technical standard revision template;
or, according to the uploading operation of the user, using the technical standard file of the power grid domain uploaded by the user as the technical standard file of the auxiliary power grid domain related to the revised template of the target technical standard system.
In some embodiments, the first hint information further includes: contextual information of the first question;
the step of generating corresponding first prompt engineering information according to the first context content of all the technical index gaps to be filled comprises the following steps:
generating a corresponding first prompt engineering template according to all the first context contents, wherein the first prompt engineering template comprises: a first question;
extracting semantic feature vectors of all the first context contents to obtain first semantic feature vectors of the first context contents;
for each first context content, a plurality of grid domain technical standard text blocks with the maximum semantic feature vector similarity with the target first context content are inquired from a preset grid domain technical standard feature vector database to serve as grid domain technical standard text blocks corresponding to the target first context content, and a plurality of grid domain technical standard text blocks and semantic feature vectors corresponding to the grid domain technical standard text blocks are recorded in the grid domain technical standard feature vector database;
And taking all the technical standard text blocks in the power grid field corresponding to the first context content as the context information of the first question, and embedding the context information into the first prompt engineering template to obtain first prompt engineering information.
In some embodiments, before the step of querying, from the preset power grid domain technical standard feature vector database, a plurality of power grid domain technical standard text blocks having the greatest similarity with the semantic feature vector between the target first context content, the method further includes: generating a technical standard feature vector database in the power grid field;
acquiring a power grid domain technical standard file serving as a corpus from a preset power grid domain technical standard file library;
text block segmentation is carried out on the structured text in the technical standard file of the power grid field, which is used as the corpus, so that a plurality of technical standard text blocks of the power grid field are obtained;
and extracting the semantic feature vector of the technical standard text block in each power grid field to obtain the semantic feature vector of the technical standard text block in each power grid field.
In some embodiments, after the step of generating the grid domain technical standard feature vector database, further comprising:
and retraining the generated artificial intelligent model by using the technical standard feature vector database in the power grid field.
In some embodiments, further comprising:
determining at least one power grid domain technical standard file for comparison related to the target technical standard revision template;
in response to a select and compare request operation, determining each filled technical indicator in a selected area on the target technical standard revision template, masking each filled technical indicator, and extracting second context of each masked portion;
generating corresponding second prompt engineering information according to the second context contents of all the mask parts, wherein the second prompt engineering information comprises: the second questioning questions indicate that second prior art index texts conforming to the second context content are respectively extracted from the technical standard files of the power grid field for comparison;
inputting the second prompting engineering information into a pre-trained generation type artificial intelligent model, so that the generation type artificial intelligent model can extract second prior art index texts conforming to the second context content from the technical standard files of the contrast power grid field according to the second prompting engineering information;
And displaying all the second prior art index texts corresponding to the target second context contents as the comparison information of the filled technical indexes corresponding to the mask parts corresponding to the target second context contents for each second context contents.
In some embodiments, displaying all the second prior art index text corresponding to the target second context content as the comparison information of the filled technical index corresponding to the mask portion corresponding to the target second prompt engineering information further includes:
aiming at each filled technical index, similarity calculation is carried out on the target filled technical index and each second prior art index text in the corresponding comparison information;
and generating reminding information aiming at the target filled technical index when the similarity between the target filled technical index and at least one second prior art index text in the corresponding comparison information is smaller than or equal to a preset similarity threshold value.
In a second aspect, an embodiment of the present disclosure further provides a prompting system applied to revisions of technical standards in the power grid field, which is configured to implement the prompting method provided in the first aspect, where the prompting system includes:
The first determining module is used for determining at least one auxiliary power grid domain technical standard file related to the target technical standard revision template;
a first processing module, configured to determine, in response to a selection and assistance request operation, a first context of each technical index space to be filled in a selected area on the target technical standard revision template;
the first generation module is used for generating corresponding first prompt engineering information according to the first context content of all the technical index vacancies to be filled, and the first prompt engineering information comprises: the first questioning questions indicate that first prior art index texts conforming to the first context content are respectively extracted from the auxiliary power grid domain technical standard files;
the first input module is used for inputting the prompt engineering information into a pre-trained generated artificial intelligent model so that the generated artificial intelligent model can extract first prior art index texts conforming to the first context content from the auxiliary power grid domain technical standard files according to the first prompt engineering information;
And the prompt module is used for displaying all the first prior art index texts corresponding to the target first context contents as prompt information of the technical index gaps to be filled corresponding to the target first context contents aiming at each first context content.
In some embodiments, the hint system further comprises:
the second determining module is used for determining at least one technical standard file of the power grid field for comparison, which is related to the target technical standard revision template;
a second processing module, configured to determine each filled technical index in the selected area on the target technical standard revision template in response to the selection and comparison request operation, mask each filled technical index, and extract a second context of the mask portion;
the second generating module is configured to generate corresponding second prompt engineering information according to second context contents of all the mask portions, where the second prompt engineering information includes: the second questioning questions indicate that second prior art index texts conforming to the second context content are respectively extracted from the technical standard files of the power grid field for comparison;
The second input module is used for inputting the second prompting engineering information into a pre-trained generated artificial intelligent model so that the generated artificial intelligent model can extract second prior art index texts conforming to the second context content from the technical standard files of the power grid field for comparison according to the second prompting engineering information;
and the comparison module is used for displaying all the second prior art index texts corresponding to the target second context contents as comparison information of the filled technical indexes corresponding to the mask parts corresponding to the target second context contents aiming at each second context content.
In a third aspect, an embodiment of the present disclosure further provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any of the hinting methods as provided in the first aspect.
Drawings
Fig. 1 is a flowchart of a prompting method applied to technical standard system revision in the power grid field according to an embodiment of the present disclosure;
FIG. 2 is an example of a technical standards revision template in the present disclosure;
fig. 3 is a schematic diagram of generating corresponding prompt engineering information based on context information corresponding to a technical index vacancy to be filled in a selected area a in an embodiment of the disclosure;
fig. 4 is a schematic diagram of generating corresponding prompt engineering information based on context information corresponding to a technical index vacancy to be filled in a selected area B in an embodiment of the disclosure;
fig. 5 is a schematic diagram showing a hint information corresponding to a technical index space to be filled in a selected area a according to an embodiment of the present disclosure;
FIG. 6 is a flowchart of an alternative method for implementing step S102 in an embodiment of the present disclosure;
FIG. 7 is another schematic diagram of generating corresponding alert engineering information for context information corresponding to a technical index slot to be filled in the selected area B;
FIG. 8 is a flowchart of another prompting method for technical standard system revisions applied to the power grid domain according to an embodiment of the present disclosure;
fig. 9 is a block diagram of a prompting system for technical standard system revision applied to the power grid field according to an embodiment of the present disclosure;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
In order that those skilled in the art will better understand the technical solutions of the present disclosure, the present disclosure will be described in further detail with reference to the accompanying drawings and detailed description.
Unless defined otherwise, technical or scientific terms used in this disclosure should be given the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The terms "first," "second," and the like, as used in this disclosure, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. Likewise, the terms "a," "an," or "the" and similar terms do not denote a limitation of quantity, but rather denote the presence of at least one. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also change accordingly when the absolute position of the object being described changes.
In the present disclosure, the generation type artificial intelligence (Artificial Intelligence Generated Content, abbreviated as AIGC) refers to a technology for generating related content with proper generalization capability through learning and recognition of existing data based on a technical method for generating artificial intelligence such as an countermeasure network, a large-scale pre-training model, and the like; the AIGC technology has the core idea that an artificial intelligence algorithm is utilized to generate content with certain originality and quality, and through training a model and learning of a large amount of data, the AIGC can generate the content related to the input condition or instruction. For example, by entering keywords, descriptions, or samples, the AIGC may generate articles, images, audio, etc. that match it.
In the present disclosure, mainly the artificial intelligence text generation (AI Text Generation) capability of the AIGC model is utilized, using Artificial Intelligence (AI) algorithms and models to generate text that mimics human written content. It involves training a machine learning model on a large dataset of existing text to generate new text that is similar in style, mood, and content to the input data. Specifically, prompt engineering (Prompt engineering) information including a question is input to the AIGC model, and the AIGC model can extract an answer conforming to the question from the prompt engineering information and based on a specified material, i.e., generate an answer text conforming to the question. The present disclosure does not develop a description of the internal working principles of the AIGC model.
Fig. 1 is a flowchart of a prompting method applied to technical standard system revision in the power grid field according to an embodiment of the present disclosure. Fig. 2 is an example of a technical standards revision template in the present disclosure. Fig. 3 is a schematic diagram of generating corresponding prompt engineering information based on context information corresponding to a technical index vacancy to be filled in a selected area a in an embodiment of the disclosure. Fig. 4 is a schematic diagram of generating corresponding prompt engineering information based on context information corresponding to a technical index vacancy to be filled in a selected area B in an embodiment of the disclosure. As shown in fig. 1 to 4, the prompting method includes:
and step S101, determining at least one auxiliary power grid domain technical standard file related to the target technical standard revision template.
In general, the technical title name, the technical abstract content, the technical content required to be normalized/defined, and some technical index gaps to be filled are recorded in the target technical standard system revision template.
In some embodiments, the auxiliary grid domain technical standard file may be determined in the following manner:
(1) Screening out power grid domain technical standard files with similarity larger than a first similarity threshold (which can be preset according to actual needs, for example, 80%) with technical title names recorded in a target technical standard system revision template from a preset power grid domain technical standard file library, and taking the power grid domain technical standard files as auxiliary power grid domain technical standard files related to the target technical standard system revision template;
(2) Screening out a power grid domain technical standard file with similarity larger than a second similarity threshold (which can be preset according to actual needs, for example, 85%) with the technical abstract content recorded in a target technical standard system revision template from a preset power grid domain technical standard file library, and taking the power grid domain technical standard file as an auxiliary power grid domain technical standard file related to the target technical standard system revision template;
(3) And screening out the power grid domain technical standard files with the similarity to the technical abstract content recorded in the target technical standard system revision template being larger than a first similarity threshold and the similarity to the technical abstract content recorded in the target technical standard system revision template being larger than a second similarity threshold from a preset power grid domain technical standard file library, and taking the power grid domain technical standard files as auxiliary power grid domain technical standard files related to the target technical standard system revision template.
(4) And according to the selected operation of the user, taking the power grid domain technical standard file selected by the user from a preset power grid domain technical standard file library as an auxiliary power grid domain technical standard file related to the target technical standard system revision template.
(5) And according to uploading operation of the user, taking the technical standard file of the power grid domain uploaded by the user as the technical standard file of the auxiliary power grid domain related to the revised template of the target technical standard.
The technical standard documents of the power grid domain are stored in advance in the technical standard document library of the power grid domain, and the corresponding technical standard documents of the auxiliary power grid domain are automatically screened out from the preset technical standard document library of the power grid domain by the system in the schemes (1) - (3), so that the workload of revision making personnel can be reduced.
Step S102, responding to the selected and auxiliary request operation, determining the first context content of each technical index empty position to be filled in the selected area on the target technical standard revision template.
The reviser may then define a selected area in the target technical standard reviser template as desired, for example by framing a selected area with a mouse, and the system may then identify the content within the selected area by optical character recognition (Optical Character Recognition, abbreviated OCR).
Taking the area a as the selected area selected by the reviser shown in fig. 2 as an example, the content "3" recognized by OCR at this time, the supply voltage deviation of the distribution transformer should satisfy: ______ ", at this time, the system may determine that a technical index space Y to be filled exists in the above content according to the content identified by OCR, and extract a context corresponding to the technical index space Y to be filled according to a preset context information extraction algorithm, where, as an example, the context information extracted for the technical index space Y to be filled is: "3. Supply voltage deviation of distribution transformer should satisfy: "
Of course, a plurality of technical index gaps to be filled in can also be included in the area selected by the user. Taking the selected area selected by the reviser as area B in fig. 2 as an example, the system can identify that there are 4 technical index slots X1-X4 to be filled in the selected area B. As an example, the context extraction results for the technical index slots X1 to X4 to be filled according to a preset context information extraction algorithm are as follows:
the context information corresponding to the technical index vacancy X1 to be filled is as follows: "the floor power distribution voltage device installed outdoors should be equipped with the security fence around, fence height";
the context information corresponding to the technical index vacancy X2 to be filled is as follows: "the floor power distribution voltage device installed outdoors should set up the security fence around, the clearance between the fence bars";
the context information corresponding to the technical index vacancy X3 to be filled is as follows: "the floor power distribution voltage device installed outdoors should set up the security fence around, fence distance transformer outline clear distance";
the context information corresponding to the technical index vacancy X4 to be filled is as follows: "the foundation of a floor-mounted distribution voltage device installed outdoors should be satisfied".
The above-mentioned context information corresponding to the technical index gaps X1 to X4 to be filled is only an alternative embodiment in the disclosure, and it does not limit the technical solution in the disclosure. In practical application, for the same technical index space to be filled, the context information extracted by adopting different context extraction algorithms may be the same or different, and the disclosure is not limited to the selected context extraction algorithm.
Step S103, corresponding first prompt engineering information is generated according to the first context content of all technical index gaps to be filled, wherein the first prompt engineering information comprises: and the first questioning questions indicate that first prior art index texts conforming to the first context contents are respectively extracted from the technical standard files of the auxiliary power grid fields.
In the embodiment of the disclosure, each technical index empty position to be filled in has corresponding first context contents, and corresponding first question questions can be generated based on the first context contents.
Fig. 3 is a schematic diagram of generating corresponding prompt engineering information for context information corresponding to a technical index vacancy to be filled in the selected area a.
Fig. 4 is a schematic diagram of generating corresponding prompt engineering information for context information corresponding to a technical index vacancy to be filled in the selected area B. The first question in fig. 4 may be regarded as a set of a plurality of sub-questions corresponding to the technical index slots X1 to X4 to be filled in one by one.
It should be noted that, the technical problem of the present disclosure is not limited to a specific text form of the "first question problem", and only needs to indicate that the meaning of the first prior art index text corresponding to each first context content is extracted from each auxiliary power grid domain technical standard file.
Step S104, inputting the first prompting engineering information into a pre-trained generation type artificial intelligent model, so that the generation type artificial intelligent model can extract first prior art index texts conforming to the first context content from the technical standard files of the auxiliary power grid field according to the first prompting engineering information.
Step 105, for each first context, displaying all the first technical index texts corresponding to the target first context as the prompt information of the technical index gaps to be filled corresponding to the target first context.
In the embodiment of the disclosure, corresponding first prompt engineering information is generated according to the first context content of each technical index vacancy to be filled, the first prompt engineering information is input into a pre-trained AIGC model, the AIGC model extracts first prior art index texts conforming to each first context content from each auxiliary power grid field technical standard file according to the first prompt engineering information, and finally all the first prior art index texts corresponding to each first context content are displayed as prompt information of the technical index vacancy to be filled corresponding to each first context content, so that a revision personnel can refer to filling the technical index vacancy to be filled.
Fig. 5 is a schematic diagram showing a hint information corresponding to a technical index space to be filled in a selected area a according to an embodiment of the present disclosure. As shown in fig. 5, the prompt information corresponding to the technical index space Y to be filled includes: the AIGC model extracts first prior art index texts which accord with first context contents corresponding to the technical index gaps Y to be filled from technical standard files of the auxiliary power grid field respectively. If the AIGC model cannot extract the prior art index text conforming to the first context content corresponding to the technical index vacancy Y to be filled from a certain auxiliary power grid domain technical standard file, the result of extracting the AIGC model from the auxiliary power grid domain technical standard file is not displayed, or the result of extracting the AIGC model from the auxiliary power grid domain technical standard file is displayed as "null".
In some embodiments, for the user to refer better, the prompt information further includes source information of each of the first prior art indicator texts, where the source information is used to indicate from which auxiliary grid domain technical standard file the corresponding first prior art indicator text originates, for example, the source information may be a standard code of the auxiliary grid domain technical standard file.
In the embodiment of the disclosure, corresponding first prompt engineering information is generated according to the filling requirement text in the to-be-filled power grid field form, the first prompt engineering information comprises a first question, the first prompt engineering information is input into a pre-trained AIGC model, the AIGC model indicates to extract first prior art index texts conforming to each first context content from each auxiliary power grid field technical standard file according to the prompt engineering information, and finally, all the first prior art index texts corresponding to each first context content are displayed as prompt information of to-be-filled technical index vacancies corresponding to the corresponding first context content, so that a reviser can fill corresponding content in the corresponding to-be-filled technical index vacancies according to the prompt information to improve the filling efficiency of the reviser to a certain extent.
Fig. 6 is a flowchart of an alternative method for implementing step S102 in an embodiment of the disclosure. Fig. 7 is another schematic diagram of generating corresponding prompt engineering information for the context information corresponding to the technical index empty to be filled in the selected area B. As shown in fig. 6 and 7, in some embodiments, the first hint information further includes: context information of the first question; step S103 includes:
Step S1031, generating a corresponding first prompting engineering template according to all the first context contents, where the first prompting engineering template includes: a first question.
The process of generating the first question may be referred to above, and will not be described in detail herein.
Step S1032, extracting semantic feature vectors of all the first context contents to obtain first semantic feature vectors of the first context contents.
In step S202, the semantic feature vector may be extracted from each first context by a preset semantic feature vector extraction model (e.g., an Embedding model), so as to obtain a first semantic feature vector of each first context.
Step 1033, for each first context, a plurality of power grid domain technical standard text blocks with the maximum similarity of semantic feature vectors with the target first context are queried from a preset power grid domain technical standard feature vector database, so as to be used as power grid domain technical standard text blocks corresponding to the target first context, and the plurality of power grid domain technical standard text blocks and the semantic feature vectors corresponding to the power grid domain technical standard text blocks are recorded in the power grid domain technical standard feature vector database.
The technical standard feature vector database of the power grid field records a plurality of technical standard text blocks of the power grid field and semantic feature vectors corresponding to the technical standard text blocks of the power grid field.
In this disclosure, a vector database is a database that is dedicated to storing and querying vectors, which provides vector similarity searches by providing dedicated indexes such as k-NN indexes.
In some embodiments, before performing step S1033, further comprises: and (3) a step of a technical standard feature vector database in the power grid field. In some embodiments, the generating the power grid domain technical standard feature vector database specifically includes: firstly, acquiring a power grid domain technical standard file serving as a corpus from a preset power grid domain technical standard file library; then, text block segmentation is carried out on the structured text in the technical standard file of the power grid field, which is used as the corpus, so as to obtain a plurality of technical standard text blocks of the power grid field; and finally, extracting semantic feature vectors of the technical standard text blocks in the power grid fields to obtain the semantic feature vectors of the technical standard text blocks in the power grid fields.
In some embodiments, in the process of generating the technical standard document library in the power grid domain, text block segmentation can be performed on the structured text data by using a large language model (Large Language Model, abbreviated as LLM), and semantic feature vector extraction processing can be performed on the technical standard text blocks in each power grid domain by using an embedded model.
In some embodiments, the grid domain technical standard feature vector database may employ a chroma vector database or a milvus vector database.
In step S1033, for the target first context, a semantic feature vector similarity (for example, a cosine similarity between semantic feature vectors) between the target first context and each power grid domain technical standard text block in the power grid domain technical standard feature vector database may be calculated, and then, according to a certain filtering rule, a plurality of power grid domain technical standard text blocks with the largest semantic feature vector similarity with the target first context are screened out. For example, the power grid domain technical standard text blocks with the similarity of the semantic feature vectors between the first context content and the target being greater than the similarity threshold can be selected by setting the similarity threshold and then screening, or the front K (for example, K takes a positive integer, for example, k=1) power grid domain technical standard text blocks with the maximum similarity of the semantic feature vectors between the first context content and the target being directly screened.
In the present disclosure, the number of the technical standard text blocks in the power grid domain corresponding to each first context may be the same or different, which is not limited in the present disclosure. The power grid domain technical standard text block corresponding to each first context content can be used for the AIGC model to better understand the semantics of the corresponding first context content.
Step S1034, embedding the technical standard text blocks of the power grid field corresponding to all the first context contents into a first prompt engineering template to obtain first prompt engineering information, wherein the technical standard text blocks of the power grid field are used as context information of the first question.
Referring to fig. 7, the first prompt engineering information includes not only the first question, but also the context information of the first question.
In some embodiments, after the step of generating the grid domain technical standard feature vector database, further comprising: and retraining the generated artificial intelligent model by using a technical standard feature vector database in the power grid field. By retraining the AIGC model by using the technical standard feature vector database in the power grid field, the understanding of the AIGC model to the technical standard text content in the power grid field can be improved, question questions about the technical standard in the power grid field can be better answered, and the accuracy of the final generated result of the AIGC model can be improved.
It should be noted that, when the number of technical index vacancies to be filled in is multiple in the area selected by the user, the first question in the first prompting engineering information may be regarded as a set of multiple sub-questions for different technical index vacancies to be filled in (first context to be filled in), that is, the first question includes multiple sub-questions corresponding to the technical index vacancies to be filled in (first context to be filled in) one by one, and each sub-question indicates that the first prior art index text corresponding to the corresponding first context is extracted from the technical standard file of each auxiliary power grid domain; the context information of each sub-problem is a power grid domain technical standard text block of the corresponding first context content.
Fig. 8 is a flowchart of another prompting method applied to technical standard system revision in the power grid field according to an embodiment of the present disclosure. As shown in fig. 8, this presentation method includes not only steps S101 to S105 in the previous embodiment but also steps S201 to S205, and only steps S201 to S205 will be described in detail below.
Step S201, determining at least one technical standard file for comparison related to the target technical standard revision template.
Similar to the method for determining the technical standard file of the auxiliary power grid domain, the corresponding technical standard file of the auxiliary power grid domain can be screened from a preset technical standard file library of the power grid domain based on the technical title name and/or the technical abstract content; the technical standard file of the power grid domain for comparison can also be determined based on the selected operation or uploading operation of the user.
In the implementation of the present disclosure, the auxiliary grid domain technical standard file determined in step S101 may be the same as or different from the reference grid domain technical standard file determined in step S201.
Step S202, responding to the selection and comparison request operation, determining each filled technical index in the selected area on the target technical standard revision template, masking each filled technical index, and extracting the second context content of each masking part.
The "filled-in technical index" in the target technical standard system revised template refers to the content filled in the "technical index blank to be filled" in the target technical standard system revised template.
In practical application, after a user inputs corresponding filled technical indexes at 1 or more to-be-filled technical index gaps, the user hopes to compare the filled technical indexes at the 1 or more to-be-filled technical index gaps with related indexes in the existing technical standard file of the power grid field for comparison. At this time, the user only needs to select the corresponding area.
Similar to the previous process of extracting the first context content of each technical index vacancy to be filled, in the present disclosure, the filled technical index located at the technical index vacancy to be filled is first subjected to mask processing, and then the second context content corresponding to each mask portion is extracted. That is, the mask portion, the technical index to be filled in empty space and the second context content are in one-to-one correspondence.
Step S203, generating corresponding second prompting engineering information according to the second context contents of all mask portions, where the second prompting engineering information includes: and the second question instruction is used for respectively extracting second prior art index texts conforming to the second context content from the technical standard files of the power grid domain for comparison.
Similar to the process of generating the first question based on the first context content in step S103 described above, a corresponding second prompt engineering message is generated in the present disclosure based on the second context content of all mask portions within the user selected area.
In some embodiments, the second prompt engineering information further includes context information of the second question, and the specific acquiring process may refer to the previous description of acquiring the context information of the first question, which is not described herein.
Step S204, inputting the second prompting engineering information into a pre-trained generation type artificial intelligent model, so that the generation type artificial intelligent model can extract second prior art index texts conforming to the second context content from the technical standard files of the power grid field for comparison according to the second prompting engineering information.
Step S205, for each second context, displaying all the second prior art index texts corresponding to the target second context as the comparison information of the filled technical index corresponding to the mask part corresponding to the target second context.
For the description of step S204 and step S205, reference may be made to the content of the previous embodiments, and the description thereof will not be repeated here.
In some embodiments, the comparison information further includes source information corresponding to each of the second prior art indicator texts, where the source information is used to indicate from which comparison grid domain technical standard file the corresponding second prior art indicator text originates, and for example, the source information may be a standard code of the comparison grid domain technical standard file.
In some embodiments, in performing step S205, further includes: aiming at each filled technical index, similarity calculation is carried out on the target filled technical index and each second prior art index text in the corresponding comparison information; when the similarity between the target filled technical index and at least one second prior art index text in the corresponding comparison information is smaller than or equal to a preset similarity threshold, reminding information is generated for the target filled technical index (for example, elevation lighting processing is carried out on the target filled technical index, or a revision staff is reminded to check the accuracy of the target filled technical index).
In the embodiment of the present disclosure, before the reviser fills the technical index to be filled with the corresponding technical index, the steps S101 to S105 may provide prompt information for the reviser to make the reference before filling by the reviser; through steps S201 to S205, after the reviser fills the corresponding technical index into the technical index space to be filled, the reviser is provided with comparison information for the reviser to make the comparison before filling.
Based on the same inventive concept, the embodiment of the disclosure also provides a prompting system applied to technical standard system revision in the power grid field. Fig. 9 is a block diagram of a prompting system applied to technical standard system revision in the power grid field according to an embodiment of the present disclosure. As shown in fig. 9, the prompting system may be used to implement the prompting method provided in the foregoing embodiment, where the prompting system includes: the first determining module 1a, the first processing module 2a, the first generating module 3a, the first input module 4a and the prompting module 5a.
The first determining module 1a is configured to determine at least one auxiliary grid domain technical standard file related to the target technical standard revision template.
The first processing module 2a is configured to determine, in response to the selection and assistance request operations, a first context of each technical index slot to be filled in the selected area on the target technical standard modification template.
The first generating module 3a is configured to generate corresponding first prompt engineering information according to the first context content of all to-be-filled technical index gaps, where the first prompt engineering information includes: and the first questioning questions indicate that first prior art index texts conforming to the first context contents are respectively extracted from the technical standard files of the auxiliary power grid fields.
The first input module 4a is configured to input the prompting engineering information into a pre-trained generated artificial intelligence model, so that the generated artificial intelligence model extracts, according to the first prompting engineering information, a first prior art index text conforming to each first context from each auxiliary power grid domain technical standard file.
The prompting module 5a is configured to display, for each first context, all the first prior art indicator texts corresponding to the target first context as prompting information of the technical indicator space to be filled corresponding to the target first context.
In some embodiments, the prompting system further comprises: a second determination module 1b, a second processing module 2b, a second generation module 3b, a second input module 4b and a comparison module 5b.
The second determining module 1b is configured to determine at least one technical standard file for comparison related to the target technical standard revision template.
The second processing module 2b is configured to determine, in response to the selection and comparison request operation, each filled technical index in the selected area on the target technical standard modification template, mask each filled technical index, and extract the second context of the mask portion.
The second generating module 3b is configured to generate corresponding second prompt engineering information according to the second context content of all mask portions, where the second prompt engineering information includes: and the second question instruction is used for respectively extracting second prior art index texts conforming to the second context content from the technical standard files of the power grid domain for comparison.
The second input module 4b is configured to input second prompt engineering information into the pre-trained generated artificial intelligent model, so that the generated artificial intelligent model extracts second prior art index text that meets the second context from the technical standard documents of the power grid domain for comparison according to the second prompt engineering information.
The comparing module 5b is configured to display, for each second context, all the second prior art index texts corresponding to the target second context as the comparison information of the filled technical index corresponding to the mask portion corresponding to the target second context.
For a specific description of each module, reference may be made to the corresponding content in the previous embodiment, which is not repeated here.
Based on the same inventive concept, the embodiment of the disclosure also provides electronic equipment. Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure. As shown in fig. 10, an embodiment of the present disclosure provides an electronic device including: one or more processors 101, memory 102, one or more I/O interfaces 103. The memory 102 stores one or more programs, which when executed by the one or more processors, cause the one or more processors to implement a prompting method for revising technical standards applicable to the power grid domain as in any of the above embodiments; one or more I/O interfaces 103 are coupled between the processor and the memory and are configured to enable information interaction between the processor and the memory.
Wherein the processor 101 is a device having data processing capabilities, including but not limited to a Central Processing Unit (CPU) or the like; memory 102 is a device having data storage capability including, but not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically charged erasable programmable read-only memory (EEPROM), FLASH memory (FLASH); an I/O interface (read/write interface) 103 is connected between the processor 101 and the memory 102 to enable information interaction between the processor 101 and the memory 102, including but not limited to a data Bus (Bus) or the like.
In some embodiments, processor 101, memory 102, and I/O interface 103 are connected to each other via bus 104, and thus to other components of the computing device.
In some embodiments, the one or more processors 101 comprise a field programmable gate array.
According to an embodiment of the present disclosure, there is also provided a computer-readable medium. The computer readable medium has stored thereon a computer program, wherein the program when executed by a processor implements the steps of any of the embodiments described above as applied to a prompting method of grid domain technical standard regulatory revisions.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a machine-readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via a communication portion, and/or installed from a removable medium. The above-described functions defined in the system of the present disclosure are performed when the computer program is executed by a Central Processing Unit (CPU).
It should be noted that the computer readable medium shown in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The circuits or sub-circuits described in the embodiments of the present disclosure may be implemented in software or may be implemented in hardware. The described circuits or sub-circuits may also be provided in a processor, for example described as: a processor, comprising: the processing module comprises a writing sub-circuit and a reading sub-circuit. The names of these circuits or sub-circuits do not constitute limitations on the circuits or sub-circuits themselves in some cases, and for example, a receiving circuit may also be described as "receiving a video signal".
It is to be understood that the above embodiments are merely exemplary embodiments employed to illustrate the principles of the present disclosure, however, the present disclosure is not limited thereto. Various modifications and improvements may be made by those skilled in the art without departing from the spirit and substance of the disclosure, and are also considered to be within the scope of the disclosure.
Claims (10)
1. A prompting method for technical standard system revision applied to the power grid field is characterized by comprising the following steps:
determining at least one auxiliary power grid domain technical standard file related to a target technical standard revision template;
determining a first context content of each technical index empty to be filled in a selected area on the target technical standard revision template in response to the selection and auxiliary request operations;
generating corresponding first prompt engineering information according to the first context contents of all the technical index gaps to be filled, wherein the first prompt engineering information comprises: the first questioning questions indicate that first prior art index texts conforming to the first context content are respectively extracted from the auxiliary power grid domain technical standard files;
Inputting the first prompting engineering information into a pre-trained generation type artificial intelligent model, so that the generation type artificial intelligent model can extract first prior art index texts conforming to the first context content from the auxiliary power grid field technical standard files according to the first prompting engineering information;
and aiming at each first context content, displaying all first prior art index texts corresponding to the target first context content as prompt information of technical index gaps to be filled corresponding to the target first context content.
2. The method of claim 1, wherein determining at least one ancillary grid domain technical standard file associated with the target technical standard revision template comprises:
screening out a power grid domain technical standard file with similarity to the technical title name recorded in the target technical standard system revision template being greater than a first similarity threshold from a preset power grid domain technical standard file library, and taking the power grid domain technical standard file as the auxiliary power grid domain technical standard file related to the target technical standard system revision template;
Or screening out a power grid domain technical standard file with similarity to the technical abstract content recorded in the target technical standard system revision template being greater than a second similarity threshold from a preset power grid domain technical standard file library, and taking the power grid domain technical standard file as the auxiliary power grid domain technical standard file related to the target technical standard system revision template;
or, screening out a power grid domain technical standard file which is set in advance and has similarity to the technical abstract content recorded in the target technical standard revision template larger than a first similarity threshold and has similarity to the technical abstract content recorded in the target technical standard revision template larger than a second similarity threshold from a preset power grid domain technical standard file library, and taking the power grid domain technical standard file as the auxiliary power grid domain technical standard file related to the target technical standard revision template;
or according to the selected operation of the user, using the power grid domain technical standard file selected by the user from a preset power grid domain technical standard file library as the auxiliary power grid domain technical standard file related to the target technical standard revision template;
or, according to the uploading operation of the user, using the technical standard file of the power grid domain uploaded by the user as the technical standard file of the auxiliary power grid domain related to the revised template of the target technical standard system.
3. The method of claim 1, wherein the first hint information further comprises: contextual information of the first question;
the step of generating corresponding first prompt engineering information according to the first context content of all the technical index gaps to be filled comprises the following steps:
generating a corresponding first prompt engineering template according to all the first context contents, wherein the first prompt engineering template comprises: a first question;
extracting semantic feature vectors of all the first context contents to obtain first semantic feature vectors of the first context contents;
for each first context content, a plurality of grid domain technical standard text blocks with the maximum semantic feature vector similarity with the target first context content are inquired from a preset grid domain technical standard feature vector database to serve as grid domain technical standard text blocks corresponding to the target first context content, and a plurality of grid domain technical standard text blocks and semantic feature vectors corresponding to the grid domain technical standard text blocks are recorded in the grid domain technical standard feature vector database;
And taking all the technical standard text blocks in the power grid field corresponding to the first context content as the context information of the first question, and embedding the context information into the first prompt engineering template to obtain first prompt engineering information.
4. A prompting method according to claim 3, further comprising, before the step of querying a plurality of grid domain technical standard text blocks having the greatest similarity with the semantic feature vector between the target first context from a preset grid domain technical standard feature vector database: generating a technical standard feature vector database in the power grid field;
acquiring a power grid domain technical standard file serving as a corpus from a preset power grid domain technical standard file library;
text block segmentation is carried out on the structured text in the technical standard file of the power grid field, which is used as the corpus, so that a plurality of technical standard text blocks of the power grid field are obtained;
and extracting the semantic feature vector of the technical standard text block in each power grid field to obtain the semantic feature vector of the technical standard text block in each power grid field.
5. The form filling method according to claim 4, further comprising, after the step of generating the grid domain technical standard feature vector database:
And retraining the generated artificial intelligent model by using the technical standard feature vector database in the power grid field.
6. The prompting method according to claim 1, further comprising:
determining at least one power grid domain technical standard file for comparison related to the target technical standard revision template;
in response to a select and compare request operation, determining each filled technical indicator in a selected area on the target technical standard revision template, masking each filled technical indicator, and extracting second context of each masked portion;
generating corresponding second prompt engineering information according to the second context contents of all the mask parts, wherein the second prompt engineering information comprises: the second questioning questions indicate that second prior art index texts conforming to the second context content are respectively extracted from the technical standard files of the power grid field for comparison;
inputting the second prompting engineering information into a pre-trained generation type artificial intelligent model, so that the generation type artificial intelligent model can extract second prior art index texts conforming to the second context content from the technical standard files of the contrast power grid field according to the second prompting engineering information;
And displaying all the second prior art index texts corresponding to the target second context contents as the comparison information of the filled technical indexes corresponding to the mask parts corresponding to the target second context contents for each second context contents.
7. The presentation method according to claim 6, wherein displaying all the second prior art index text corresponding to the target second context content as the comparison information of the filled technical index corresponding to the mask portion corresponding to the target second presentation project information, further comprises:
aiming at each filled technical index, similarity calculation is carried out on the target filled technical index and each second prior art index text in the corresponding comparison information;
and generating reminding information aiming at the target filled technical index when the similarity between the target filled technical index and at least one second prior art index text in the corresponding comparison information is smaller than or equal to a preset similarity threshold value.
8. A prompting system for revising technical standards in the field of electric networks, which is used to implement the prompting method according to any one of claims 1 to 7, the prompting system comprising:
The first determining module is used for determining at least one auxiliary power grid domain technical standard file related to the target technical standard revision template;
a first processing module, configured to determine, in response to a selection and assistance request operation, a first context of each technical index space to be filled in a selected area on the target technical standard revision template;
the first generation module is used for generating corresponding first prompt engineering information according to the first context content of all the technical index vacancies to be filled, and the first prompt engineering information comprises: the first questioning questions indicate that first prior art index texts conforming to the first context content are respectively extracted from the auxiliary power grid domain technical standard files;
the first input module is used for inputting the prompt engineering information into a pre-trained generated artificial intelligent model so that the generated artificial intelligent model can extract first prior art index texts conforming to the first context content from the auxiliary power grid domain technical standard files according to the first prompt engineering information;
And the prompt module is used for displaying all the first prior art index texts corresponding to the target first context contents as prompt information of the technical index gaps to be filled corresponding to the target first context contents aiming at each first context content.
9. A reminder system according to claim 8, which is operable to implement the reminder method of claim 6 or 7, the reminder system further comprising:
the second determining module is used for determining at least one technical standard file of the power grid field for comparison, which is related to the target technical standard revision template;
a second processing module, configured to determine each filled technical index in the selected area on the target technical standard revision template in response to the selection and comparison request operation, mask each filled technical index, and extract a second context of the mask portion;
the second generating module is configured to generate corresponding second prompt engineering information according to second context contents of all the mask portions, where the second prompt engineering information includes: the second questioning questions indicate that second prior art index texts conforming to the second context content are respectively extracted from the technical standard files of the power grid field for comparison;
The second input module is used for inputting the second prompting engineering information into a pre-trained generated artificial intelligent model so that the generated artificial intelligent model can extract second prior art index texts conforming to the second context content from the technical standard files of the power grid field for comparison according to the second prompting engineering information;
and the comparison module is used for displaying all the second prior art index texts corresponding to the target second context contents as comparison information of the filled technical indexes corresponding to the mask parts corresponding to the target second context contents aiming at each second context content.
10. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, causes the one or more processors to implement the hinting method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311347980.8A CN117094304B (en) | 2023-10-18 | 2023-10-18 | Prompting method and system for technical standard revision applied to power grid field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311347980.8A CN117094304B (en) | 2023-10-18 | 2023-10-18 | Prompting method and system for technical standard revision applied to power grid field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117094304A true CN117094304A (en) | 2023-11-21 |
| CN117094304B CN117094304B (en) | 2024-01-23 |
Family
ID=88772075
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311347980.8A Active CN117094304B (en) | 2023-10-18 | 2023-10-18 | Prompting method and system for technical standard revision applied to power grid field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117094304B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014220118A1 (en) * | 2014-08-12 | 2016-02-18 | VESCON GmbH | Method and system for the computer-aided generation of technical documentation for the description of a technical installation |
| CN109409678A (en) * | 2018-09-28 | 2019-03-01 | 南方电网科学研究院有限责任公司 | A kind of high-efficiency multi-function technical standard information system applied to power grid |
| CN111767382A (en) * | 2020-06-30 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Method and device for generating feedback information and terminal equipment |
| CN111932412A (en) * | 2020-09-04 | 2020-11-13 | 汪宏杰 | Contract drafting and revising method, device, storage medium and equipment |
| CN113011185A (en) * | 2020-07-17 | 2021-06-22 | 上海浦东华宇信息技术有限公司 | Legal field text analysis and identification method, system, storage medium and terminal |
| CN113609833A (en) * | 2021-08-12 | 2021-11-05 | 深圳平安智汇企业信息管理有限公司 | Dynamic generation method and device of file, computer equipment and storage medium |
| CN113792177A (en) * | 2021-08-05 | 2021-12-14 | 杭州电子科技大学 | Scene character visual question-answering method based on knowledge-guided deep attention network |
| CN113902402A (en) * | 2021-09-28 | 2022-01-07 | 合肥高维数据技术有限公司 | Document auxiliary filling method, system, storage medium and device based on AR technology |
| CN114547467A (en) * | 2022-02-28 | 2022-05-27 | 广东小天才科技有限公司 | Question searching method and device, terminal equipment and readable storage medium |
| US20220222284A1 (en) * | 2021-01-11 | 2022-07-14 | Tata Consultancy Services Limited | System and method for automated information extraction from scanned documents |
| CN114842483A (en) * | 2022-06-27 | 2022-08-02 | 齐鲁工业大学 | Standard file information extraction method and system based on neural network and template matching |
| CN115249016A (en) * | 2021-04-26 | 2022-10-28 | 中国移动通信有限公司研究院 | Text processing method, device and equipment and readable storage medium |
| CN115659938A (en) * | 2022-11-03 | 2023-01-31 | 江苏中博通信有限公司 | Purchasing file writing auxiliary system based on intelligent supply chain |
| CN115879728A (en) * | 2022-12-27 | 2023-03-31 | 武汉中超电网建设监理有限公司 | Based on capital construction overall process platform system |
| CN116595202A (en) * | 2023-05-09 | 2023-08-15 | 上海交通大学 | Automatic slide generation method and system based on AIGC technology |
| CN116644728A (en) * | 2023-05-09 | 2023-08-25 | 三峡高科信息技术有限责任公司 | Contract generation method and system based on clause digitization |
| CN116823537A (en) * | 2023-05-26 | 2023-09-29 | 支付宝(杭州)信息技术有限公司 | Insurance report processing method and device, storage medium and electronic equipment |
-
2023
- 2023-10-18 CN CN202311347980.8A patent/CN117094304B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014220118A1 (en) * | 2014-08-12 | 2016-02-18 | VESCON GmbH | Method and system for the computer-aided generation of technical documentation for the description of a technical installation |
| CN109409678A (en) * | 2018-09-28 | 2019-03-01 | 南方电网科学研究院有限责任公司 | A kind of high-efficiency multi-function technical standard information system applied to power grid |
| CN111767382A (en) * | 2020-06-30 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Method and device for generating feedback information and terminal equipment |
| CN113011185A (en) * | 2020-07-17 | 2021-06-22 | 上海浦东华宇信息技术有限公司 | Legal field text analysis and identification method, system, storage medium and terminal |
| CN111932412A (en) * | 2020-09-04 | 2020-11-13 | 汪宏杰 | Contract drafting and revising method, device, storage medium and equipment |
| US20220222284A1 (en) * | 2021-01-11 | 2022-07-14 | Tata Consultancy Services Limited | System and method for automated information extraction from scanned documents |
| CN115249016A (en) * | 2021-04-26 | 2022-10-28 | 中国移动通信有限公司研究院 | Text processing method, device and equipment and readable storage medium |
| CN113792177A (en) * | 2021-08-05 | 2021-12-14 | 杭州电子科技大学 | Scene character visual question-answering method based on knowledge-guided deep attention network |
| CN113609833A (en) * | 2021-08-12 | 2021-11-05 | 深圳平安智汇企业信息管理有限公司 | Dynamic generation method and device of file, computer equipment and storage medium |
| CN113902402A (en) * | 2021-09-28 | 2022-01-07 | 合肥高维数据技术有限公司 | Document auxiliary filling method, system, storage medium and device based on AR technology |
| CN114547467A (en) * | 2022-02-28 | 2022-05-27 | 广东小天才科技有限公司 | Question searching method and device, terminal equipment and readable storage medium |
| CN114842483A (en) * | 2022-06-27 | 2022-08-02 | 齐鲁工业大学 | Standard file information extraction method and system based on neural network and template matching |
| CN115659938A (en) * | 2022-11-03 | 2023-01-31 | 江苏中博通信有限公司 | Purchasing file writing auxiliary system based on intelligent supply chain |
| CN115879728A (en) * | 2022-12-27 | 2023-03-31 | 武汉中超电网建设监理有限公司 | Based on capital construction overall process platform system |
| CN116595202A (en) * | 2023-05-09 | 2023-08-15 | 上海交通大学 | Automatic slide generation method and system based on AIGC technology |
| CN116644728A (en) * | 2023-05-09 | 2023-08-25 | 三峡高科信息技术有限责任公司 | Contract generation method and system based on clause digitization |
| CN116823537A (en) * | 2023-05-26 | 2023-09-29 | 支付宝(杭州)信息技术有限公司 | Insurance report processing method and device, storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 徐文渊等: "基于人工智能的市场主体异常行为模型", 《微型电脑应用》, vol. 39, no. 8, pages 36 - 39 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117094304B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3052638A1 (en) | Systems and methods for automatic semantic token tagging | |
| CN114155543A (en) | Neural network training method, document image understanding method, device and equipment | |
| CN114580424A (en) | Labeling method and device for named entity identification of legal document | |
| CN113821622A (en) | Answer retrieval method and device based on artificial intelligence, electronic equipment and medium | |
| CN115640394A (en) | Text classification method, text classification device, computer equipment and storage medium | |
| CN115905528A (en) | Event multi-label classification method and device with time sequence characteristics and electronic equipment | |
| CN114821590A (en) | Document information extraction method, device, equipment and medium | |
| CN115238670A (en) | Information text extraction method, device, equipment and storage medium | |
| CN115757731A (en) | Dialogue question rewriting method, device, computer equipment and storage medium | |
| CN117094304B (en) | Prompting method and system for technical standard revision applied to power grid field | |
| CN113704393A (en) | Keyword extraction method, device, equipment and medium | |
| CN116681063A (en) | Method and system for processing template of bidding document based on natural language processing | |
| CN117033649A (en) | Training method and device for text processing model, electronic equipment and storage medium | |
| CN112487154B (en) | Intelligent search method based on natural language | |
| CN114707017A (en) | Visual question answering method and device, electronic equipment and storage medium | |
| CN112749251B (en) | Text processing method, device, computer equipment and storage medium | |
| CN114662496A (en) | Information identification method, device, equipment, storage medium and product | |
| CN113988020A (en) | Engineering technical label book compiling method, device, equipment and storage medium | |
| CN109933788B (en) | Type determining method, device, equipment and medium | |
| CN112085522A (en) | Construction cost data processing method, system, device and medium for engineering project | |
| CN111199170B (en) | Formula file identification method and device, electronic equipment and storage medium | |
| CN114118072A (en) | Document structuring method and device, electronic equipment and computer readable storage medium | |
| CN115269851B (en) | Article classification method, apparatus, electronic device, storage medium and program product | |
| CN114444470B (en) | Method, device, medium and equipment for recognizing domain named entities in patent text | |
| US20230129503A1 (en) | Automated design of process automation facilities |
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 |