CN117494672A - Method and device for generating industry document and computer readable storage medium - Google Patents
Method and device for generating industry document and computer readable storage medium Download PDFInfo
- Publication number
- CN117494672A CN117494672A CN202311506829.4A CN202311506829A CN117494672A CN 117494672 A CN117494672 A CN 117494672A CN 202311506829 A CN202311506829 A CN 202311506829A CN 117494672 A CN117494672 A CN 117494672A
- Authority
- CN
- China
- Prior art keywords
- document
- industry
- generating
- evaluation
- content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000011156 evaluation Methods 0.000 claims abstract description 186
- 238000005457 optimization Methods 0.000 claims abstract description 54
- 230000004044 response Effects 0.000 claims abstract description 21
- 238000012790 confirmation Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 38
- 238000003058 natural language processing Methods 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 17
- 230000008451 emotion Effects 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000015654 memory Effects 0.000 description 24
- 238000005516 engineering process Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000011161 development Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 239000000284 extract Substances 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012015 optical character recognition Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012797 qualification Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000012549 training Methods 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
-
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of text processing, and discloses a method and a device for generating an industry document and a computer readable storage medium, wherein the method comprises the following steps: responding to a first instruction of a user, and acquiring a corresponding specification document and a document generation requirement; generating a first industry document based on the specification document and the document generation requirement; responding to a second instruction of a user, and extracting an evaluation rule based on a preset industry database and a standard document; analyzing and evaluating the first industrial document based on the evaluation rule, and generating an optimization scheme; in response to the confirmation indication of the user, a second industry document is generated based on the optimization scheme. According to the method and the device, after the first industry document is generated through the standard document and the document generation requirement, the first industry document can be optimized according to the second instruction of the user, so that the second industry document is obtained, the searching efficiency of data and data can be improved, and meanwhile, the integrity of the industry document is improved.
Description
Technical Field
The present invention relates to the field of text processing technology, and in particular, to a method and apparatus for generating an industry document, and a computer readable storage medium.
Background
The generation of industry documents (such as a standard book, a project acceptance document and the like) mainly depends on manual writing, so that a great deal of time cost and labor cost are consumed, writing errors are easy to occur, and the traditional manual writing of the industry documents often has the problems of non-uniform patterns and non-standard, and is not beneficial to standardized management of the industry.
With the continuous development of computer science and technology, intelligent text output based on artificial intelligence has gained a lot of attention, and can realize understanding, analysis and automatic generation of text required by human beings of text content, which has higher application value for a lot of document processing tasks in the industry field. However, the automatic generation scheme now in widespread use is basically a document recognition describing an optical character recognition (Optical Character Recognition, OCR) technology based; file parsing based on natural language processing (Natural Language Processing, NLP) techniques to help identify strings; the quick filling of the bidding document can be realized based on the database, but the actual content still needs to be filled manually, so that the related technology only improves the searching efficiency of data and data, and can not realize automatic generation of the complete industry document.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, and a computer readable storage medium for generating an industry document, so as to solve the technical problem that in the related art, only the searching efficiency of data and data is improved, and automatic generation of a complete industry document cannot be achieved.
In a first aspect, the present invention provides a method for generating an industry document, the method comprising: responding to a first instruction of a user, and acquiring a corresponding specification document and a document generation requirement; generating a first industry document based on the specification document and the document generation requirement; responding to a second instruction of a user, and extracting an evaluation rule based on a preset industry database and a standard document; analyzing and evaluating the first industrial document based on the evaluation rule, and generating a first optimization scheme; in response to the confirmation indication of the user, a second industry document is generated based on the first optimization scheme.
According to the method for generating the industry document, after the first industry document is generated through the standard document and the document generation requirement, the first industry document can be optimized according to the second indication of the user, so that the second industry document is obtained, the searching efficiency of data and information can be improved, and meanwhile, the integrity of the industry document is improved.
In an alternative embodiment, before generating the industry document based on the first optimization scheme in response to the confirmation indication by the user, the method further comprises: adjusting the evaluation rule in response to the auxiliary evaluation rule confirmed by the user; and analyzing and evaluating the first industry document based on the adjusted evaluation rule, and generating a second optimization scheme.
According to the method for generating the industry document, the auxiliary evaluation rule is confirmed by the user, and the evaluation rule is adjusted according to the auxiliary evaluation rule, so that the evaluation rule can focus on the requirement of the user, and the winning rate of the industry document can be improved.
In an alternative embodiment, generating a first business document based on the canonical document and the document generation requirement includes: analyzing the standard document by a natural language processing method, and extracting information to be filled in the standard document; and extracting the content in the industry content generation information to be filled based on the document generation requirement and a preset industry database, and generating a first industry document.
According to the method for generating the industrial document, the standard document is analyzed through the natural language processing method, and the first industrial document can be intelligently generated according to the document generation requirement and the mode of extracting the data corresponding to the information to be filled from the preset industrial database, so that the generation efficiency of the first industrial document is improved, and meanwhile, the accuracy of the content in the first industrial document is guaranteed.
In an alternative embodiment, parsing the canonical document through a natural language processing method, extracting the information to be filled in the canonical document includes: word segmentation processing is carried out on the standard document based on a natural language processing database, and word information is extracted; extracting document demand information from the canonical document by using named entity recognition; clustering the document demand information to obtain a document demand collection; extracting scoring content from the canonical document based on the scoring keywords; extracting scoring points from the canonical document by using an emotion analysis method and a semantic analysis method; generating a scoring set based on scoring content and scoring points; extracting a format description sentence from the specification document based on the format keyword; extracting each output field in the format description statement by utilizing syntactic analysis; finding out the field description of each output field through semantic matching, and extracting the field meaning explanation; and generating the to-be-filled information based on the document demand collection, the grading collection and the field meaning interpretation.
According to the method for generating the industry document, the efficiency and the accuracy of extracting the information to be filled in the standard document can be improved through the determined document requirement set, the scoring set and the field meaning interpretation.
In an alternative embodiment, extracting evaluation rules based on a preset industry database and a specification document includes: extracting corresponding evaluation parameters and evaluation weights from the specification document based on a preset industry database; and generating an evaluation rule based on the evaluation parameters and the evaluation weights.
According to the method for generating the industry document, whether the first industry document can meet the winning bid requirement can be accurately determined by extracting the evaluation parameters and the evaluation weights in the standard document from the preset industry database.
In an alternative embodiment, the analyzing and evaluating the first business document based on the evaluation rule, and generating the optimization scheme includes: extracting to-be-evaluated content corresponding to the evaluation parameters from the first industrial document; evaluating the content to be evaluated based on the evaluation rule to generate an evaluation result; analyzing the content to be adjusted in the content to be evaluated based on the evaluation result; a first optimization scheme is generated based on the content that needs to be adjusted.
According to the method for generating the industry document, the content to be evaluated in the first industry document is evaluated through the evaluation rule, so that the content with larger influence in the content to be evaluated can be determined, and further adjustment is performed on the content, so that the generated second industry document can meet the winning bid requirement more.
In an alternative embodiment, adjusting the evaluation rules in response to the user-validated auxiliary evaluation rules includes: extracting evaluation parameters and evaluation weights corresponding to the auxiliary evaluation rules from the specification document based on a preset industry database; and adjusting the evaluation rule based on the evaluation parameter and the evaluation weight.
According to the method for generating the industry document, the evaluation rule is matched with the requirement of the user by combining the auxiliary evaluation rule determined by the user and extracting the evaluation parameter and the evaluation weight from the preset industry database, so that the generated second industry document is matched with the requirement of the user.
In an alternative embodiment, the analyzing and evaluating the first industry document based on the adjusted evaluation rule, and generating the second optimization scheme includes: extracting to-be-evaluated content corresponding to the evaluation parameters from the first industrial document; evaluating the content to be evaluated based on the adjusted evaluation rule to generate an evaluation result; analyzing the content to be adjusted in the content to be evaluated based on the evaluation result; a second optimization scheme is generated based on the content that needs to be adjusted.
According to the method for generating the industry document, the content to be evaluated in the first industry document is evaluated through the adjusted evaluation rule, so that the content with larger influence in the content to be evaluated can be determined, and further adjustment is performed on the content, so that the generated second industry document can meet the winning bid requirement more.
In a second aspect, the present invention provides an apparatus for generating an industry document, the apparatus comprising: the acquisition module is used for responding to the first indication of the user and acquiring corresponding specification documents and document generation requirements; the first generation module is used for generating a first industry document based on the specification document and the document generation requirement; the extraction module is used for responding to the second instruction of the user and extracting evaluation rules based on a preset industry database and a specification document; the analysis generation module is used for carrying out analysis and evaluation on the first industry document based on the evaluation rule and generating an optimization scheme; and the second generation module is used for responding to the confirmation indication of the user and generating an industry document based on the optimization scheme.
In a third aspect, the present invention provides a computer device comprising: the system comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions, so that the method for generating the industry document according to the first aspect or any corresponding implementation mode of the first aspect is executed.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the method for generating an industry document according to the first aspect or any of the embodiments corresponding thereto.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow diagram of a method of generating an industry document according to an embodiment of the invention;
FIG. 2 is a flow diagram of a method of generating another industry document according to an embodiment of the invention;
FIG. 3 is a flow diagram of a method of generating an additional business document according to an embodiment of the present invention;
FIG. 4 is a schematic architecture diagram of an industry document generation method according to an embodiment of the invention;
FIG. 5 is a flow diagram of yet another method of generating an industrial document according to an embodiment of the present invention;
FIG. 6 is a block diagram of an apparatus for generating an industry document according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the related technology, with the continuous development of computer science and technology, intelligent text output based on artificial intelligence has gained a lot of attention, and can realize understanding, analysis and automatic generation of text required by human beings of text content, which has higher application value for a lot of document processing tasks in the industry field.
However, the automatic generation schemes now in widespread use, essentially describe recognition of credentials based on OCR technology; file analysis based on NLP technology helps to identify string labels; the quick filling of the bidding document can be realized based on the database, but the actual content still needs to be filled manually, so that the related technology only improves the searching efficiency of data and data, and can not realize automatic generation of the complete industry document.
Based on the above, the embodiment of the invention provides a method for generating an industry document, which can optimize a first industry document according to a second instruction of a user after the first industry document is generated through a standard document and a document generation requirement, so that a second industry document is obtained, the searching efficiency of data and data can be improved, and meanwhile, the integrity of the industry document is improved.
In accordance with an embodiment of the present invention, there is provided an embodiment of a method of generating an industry document, it being noted that the steps shown in the flowchart of the figures may be performed in a computer system, such as a set of computer executable instructions, and that, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order other than that shown or described herein.
In this embodiment, a method for generating an industry document is provided, which may be used in a computer device, such as a computer, a server, etc., fig. 1 is a flowchart of a method for generating an industry document according to an embodiment of the present invention, and as shown in fig. 1, the flowchart includes the following steps:
step S101, corresponding canonical documents and document generation requirements are acquired in response to a first instruction of a user.
The first indication may be an indication generated by a user via a mouse click, a keyboard selection, or a touch screen. When the user issues a first instruction for the uploaded file (such as the bidding document), the computer device may correspondingly obtain the corresponding canonical document and document generation requirement from the uploaded document in response to the first instruction issued by the user.
The canonical document may define a framework for the content of the corresponding user upload file (e.g., bid file). Specifically, the specification document may include, but is not limited to, the number of software copyright rights, the number of qualification certificates, the number of honor certificates, and the like, or may include each functional module, hardware, operation and maintenance, and the like of software.
The document generation requirements may be requirements (e.g., document generation format, document generation content) for the corresponding user to upload a file (e.g., bid file), without specific limitation. For example: the requirement to upload the file may be to fill out revenue data for the last three years, and the document generation requirement is to add revenue data for the last three years to the canonical document. For another example: the requirement to upload a file may be to add intellectual property content and the document generation requirement may be to add specific content in the intellectual property to a canonical document. The computer equipment can add the software copyright quantity, qualification certificate quantity, honor certificate quantity and the like under the intellectual property according to the document generation requirement.
Step S102, a first industry document is generated based on the specification document and the document generation requirement.
The first business document may be a document generated from document generation requirements and specification documents. Wherein, as is apparent from the above, after the specification document and the document generation requirement are determined, the computer device may generate the first business document by adding the content to the specification document according to the document generation requirement.
It should be noted that the first industry document may be obtained from a disk paleo NLP large model. The mode of constructing the antique NLP large model can be to construct a company database, wherein the company database comprises a company past bidding library, a company honor qualification library, a company project contract information library, a company case library, a company product library and the like. And constructing a large model of the ancient Chinese character NLP by taking data in a company database as a training set. And then taking the standard document and the document generation requirement as input, and automatically generating a first industrial document meeting the project requirement.
Step S103, responding to a second instruction of the user, and extracting evaluation rules based on a preset industry database and a specification document.
The second indication may be an indication generated by a user via a mouse click, a keyboard selection, or a touch screen. When the user sends the second instruction, the computer equipment can correspondingly respond to the second instruction sent by the user and extract the evaluation rule of the corresponding specification document from the preset industry database. Wherein the evaluation rule may be how to evaluate the generated first business document. The specific evaluation process is described in detail below.
The preset industry database may include basic information of a company, product information, industry conventional solution information to which the company belongs, and the like, which is not particularly limited herein. For example: company a name, product a produced, company B name, product B produced, etc.
And step S104, analyzing and evaluating the first industry document based on the evaluation rule, and generating a first optimization scheme.
After the evaluation rule is extracted, the computer equipment can analyze and evaluate the first industrial document through the evaluation rule to generate a first optimization scheme. The first optimization scheme may be an optimization scheme that is adjusted for undesirable content in the first industry document. For example: taking a bid file as an example, the first industry document may be a bid file. The score of the first industrial document after evaluation is 80 and does not meet the requirement, so that the content which does not meet the requirement needs to be analyzed according to the first industrial document, and a first optimization scheme for adjusting the content is provided.
Step S105, generating a second industry document based on the first optimization scheme in response to the confirmation instruction of the user.
The confirmation indication may be an indication generated by a user via a mouse click, a keyboard selection, or a touch screen. When the user sends a confirmation instruction, the computer equipment can correspondingly respond to the confirmation instruction sent by the user, and adjust the first industry document through the first optimization scheme to generate a second industry document. For example: taking a bidding document as an example, the bidding document preliminary score is 80 points. Through comparison of preset industry databases, aiming at the past bidding strategies, the first industry document offers too high price, and further optimization is suggested.
According to the method for generating the industry document, after the first industry document is generated through the standard document and the document generation requirement, the first industry document can be optimized according to the second indication of the user, so that the second industry document is obtained, the searching efficiency of data and information can be improved, and meanwhile, the integrity of the industry document is improved.
In an alternative embodiment, in order to make the second industry document more satisfactory to the user' S needs, the method further includes, before step S105:
and a step a1, adjusting the evaluation rule in response to the auxiliary evaluation rule confirmed by the user.
The auxiliary evaluation rule may be a rule input by a user through a mouse click, a keyboard selection, a voice, or a touch screen. When the user sends out the auxiliary evaluation rule, the computer device can respond to the auxiliary evaluation rule sent out by the user and adjust the evaluation rule through the auxiliary evaluation rule correspondingly. Wherein the auxiliary evaluation rule may be a user-personalized suggestion. For example: taking a bid document as an example, where the user wants the bid document to bid for the item at a lower cost, with a suitable bid, with a highest profit, etc., the user's auxiliary evaluation rules may be sent to the computer device to cause the computer device to adjust the evaluation rules.
Specifically, the step a1 includes:
and a step a11, extracting the evaluation parameters and the evaluation weights corresponding to the auxiliary evaluation rules from the standard document based on a preset industry database.
The auxiliary evaluation rule has an emphasis point aimed by the user, such as lower cost, highest profit, and the like, and is not particularly limited herein, so that the evaluation parameters and the evaluation weights corresponding to the auxiliary evaluation rule can be extracted from the standard document according to the auxiliary evaluation rule of the user and a preset industry database.
And a step a12 of adjusting the evaluation rule based on the evaluation parameter and the evaluation weight.
After the computer equipment acquires the evaluation parameters and the evaluation weights corresponding to the auxiliary evaluation rules, the evaluation rules need to be further adjusted according to the evaluation parameters and the evaluation weights, namely, the evaluation weights and the evaluation parameters of other parts in the evaluation rules are modified.
And a step a2, analyzing and evaluating the first industry document based on the adjusted evaluation rule, and generating a second optimization scheme.
The computer equipment analyzes and evaluates the first industrial document again according to the adjusted evaluation rule, namely automatically identifies the content corresponding to the first industrial document and the adjusted evaluation rule, thereby determining the content with larger influence in the first industrial document. For example: taking a bid file as an example, the first industry document may be a bid file. After evaluating the first industry document, the optimization of the human relation graph parameters of the display method is suggested. The second optimization scheme can be that the function of displaying the legal person relationship graph parameters is modified from the knowledge graph technology to the function of displaying the legal person relationship graph parameters by adopting a data visual display mode; therefore, the technical difficulty can be reduced, the development and operation cost is reduced, the recommended quotation is reduced by 2 ten thousand yuan, the profit prediction is still improved by 10%, and the total score of the bidding book is improved to 85 points.
Specifically, the step a2 includes:
and a step a21, extracting the content to be evaluated corresponding to the evaluation parameters from the first industry document.
And a step a22 of evaluating the content to be evaluated based on the adjusted evaluation rule to generate an evaluation result.
The computer equipment can extract the content to be evaluated from the first industry document, and the computer equipment evaluates the content to be evaluated again according to the adjusted evaluation rule to generate an evaluation result. Wherein, as the evaluation weight and the evaluation parameter in the adjusted evaluation rule are changed, the generated evaluation result is changed.
And a step a23 of analyzing the content to be evaluated, which needs to be adjusted, based on the evaluation result.
Step a24, generating a second optimization scheme based on the content needing to be adjusted.
And according to the evaluation result, analyzing which contents in the contents to be evaluated do not meet the requirements, adjusting the contents which do not meet the requirements, and then generating a second optimization scheme according to the adjusted contents. For example: taking a bid file as an example, the first industry document may be a bid file. Wherein, after evaluating the first industry file, the copyright number of the display software suggests optimization. The second optimization scheme can be that the function of realizing the copyright quantity of the display software by the knowledge graph technology is modified into the function of realizing the copyright quantity of the display software by adopting a data visual display mode; therefore, the technical difficulty can be reduced, the development and operation cost is reduced, the recommended quotation is reduced by 2 ten thousand yuan, the profit prediction is still improved by 20%, and the total score of the bidding book is improved to 90 minutes.
According to the method for generating the industry document, the auxiliary evaluation rule is confirmed by the user, and the evaluation rule is adjusted according to the auxiliary evaluation rule, so that the evaluation rule can focus on the requirement of the user, and the winning rate of the industry document can be improved.
In this embodiment, a method for generating an industry document is provided, which may be used in the computer device, such as a computer, a server, etc., and fig. 2 is a flowchart of a method for generating an industry document according to an embodiment of the present invention, as shown in fig. 2, where the flowchart includes the following steps:
step S201, corresponding canonical documents and document generation requirements are acquired in response to a first instruction of a user. Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S202, a first industry document is generated based on the specification document and the document generation requirement.
Specifically, the step S202 includes:
in step S2021, the specification document is parsed by the natural language processing method, and the information to be filled in the specification document is extracted.
Natural language processing methods work through machine learning. The machine learning system stores words and combinations thereof as any other form of data. Phrases, sentences, sometimes even the content of the whole book are entered into the machine learning engine and processed therein using either rules of language or the actual language habits of the person, or both. The computer then uses this data to find patterns and infer the next results. Take translation software as an example: in French, "I want to park" is "Je vais au parc", so machine learning predicts that "I want to store" will also start with "Je vais au". Therefore, the information to be filled in the standard document can be extracted through a natural language processing method.
Specifically, the step S2021 includes:
and b1, performing word segmentation processing on the standard document based on the natural language processing database, and extracting word information.
A natural language processing database refers to a database for storing and querying language-dependent data. Specifically, a HanLP database, a Jieba database, etc., may be included, and are not particularly limited herein. The natural language processing database may perform word segmentation processing on the canonical document, extract word information, clean text, and remove irrelevant contents, such as punctuation, special symbols, and the like, which are not limited herein.
And b2, extracting document requirement information from the standard document by using named entity recognition.
The document demand information may be sentences containing keywords of need, demand, etc. Specifically, a rule template for demand description may be constructed and sentences containing document demand information are identified using named entities. Information such as products, functions, objects and the like is extracted from the specification document, dependency syntax analysis is used, and requirements of the guest structure representation are extracted. Wherein the dependency syntax is used to describe dependencies between words.
And b3, clustering the document demand information to obtain a document demand collection.
The document requirement collection may be a combination of sentences containing keywords of need, requirement, etc. Specifically, sentences with similar semantics are analyzed, and a document demand collection is obtained through clustering processing. Alternatively, the clustering method may be a K-MEANS clustering algorithm, a mean shift clustering algorithm, a DBSCAN clustering algorithm, or the like, which is not particularly limited herein.
And b4, extracting scoring content from the canonical document based on the scoring keywords.
The scoring keywords may be scoring keywords that contain importance, must, etc. Specifically, a rule template for scoring keywords is constructed, syntactic analysis is carried out on scoring, weighting and other word-guided clauses, and scoring content is extracted.
And b5, extracting grading key points from the standard document by using an emotion analysis method and a semantic analysis method.
The emotion analysis method is a process of analyzing, processing and extracting subjective texts with emotion colors by utilizing natural language processing and text mining technologies. Specifically, the method may be naive bayes emotion analysis, deep learning LSTM, pre-trained rule-based VADER model, etc., and is not particularly limited herein.
The semantic analysis method is to learn and understand semantic content represented by a text segment by using various machine learning algorithms.
The computer equipment can judge the grading tendency contained in the sentences through an emotion analysis method, and then adopts a semantic analysis method to extract grading points from the standard documents.
And b6, generating a scoring set based on the scoring content and the scoring points.
After the computer device obtains the scoring content and the scoring gist, the scoring content and the scoring gist may be combined to generate a scoring set.
And b7, extracting the format description statement from the specification document based on the format keyword.
The format keyword may be one including input, printing, and the like, and is not particularly limited herein. Specifically, the format description sentence is identified according to the format keyword, and the format description sentence is extracted from the specification document.
And b8, extracting each output field in the format description statement by utilizing syntactic analysis.
The syntactic analysis may be a sentence component analysis method, a hierarchical analysis method, a variation analysis method, or the like, and is not particularly limited herein. Taking a sentence component analysis method as an example, analyzing the format description sentence by the sentence component analysis method, and finding out two central words, namely a noun central word and a verb central word, of the whole structure at one time during analysis, wherein the two central words, namely the noun central word and the verb central word, serve as main components of the structure, namely a main word and a predicate, and other components are attached to the main word and the predicate respectively. The analysis process is as follows: firstly, the main components of the whole structure are clearly seen, which is the subject and which is the predicate; then, whether the verb of the predicate is a passing verb is judged to determine whether the predicate is followed by a coherent component object or not; finally, all additional components before and after predicates are pointed out and added before the main and the guest, and then each output field is extracted.
And b9, finding out the field description of each output field through semantic matching, and extracting the field meaning explanation.
After each output field is determined, the field description of each output field is found through semantic matching, and the field meaning explanation is extracted.
And b10, generating to-be-filled information based on the document requirement set, the grading set and the field meaning interpretation.
Because the to-be-filled information consists of the document requirement set, the grading set and the field meaning, the computer equipment can generate the to-be-filled information after acquiring the document requirement set, the grading set and the field meaning.
Step S2022 extracts the content in the industry content generation information to be filled based on the document generation requirement and the preset industry database, and generates the first industry document.
As can be seen from the above content, the document generation requirement can be a requirement (such as a document generation format and document generation content) in the uploading file, and the preset industry database can include basic information, product information, industry conventional solution information of the company, and the like, so that the industry content corresponding to the uploading file can be extracted according to the document generation requirement and the preset industry database, thereby taking the industry content as the content in the information to be filled, and generating the first industry document according to the content in the information to be filled.
In step S203, in response to the second instruction of the user, an evaluation rule is extracted based on the preset industry database and the specification document. Please refer to step S103 in the embodiment shown in fig. 1, which is not described here again
And S204, analyzing and evaluating the first industry document based on the evaluation rule, and generating a first optimization scheme. Please refer to step S104 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S205, in response to the confirmation instruction of the user, generating a second industry document based on the first optimization scheme. Please refer to step S105 in the embodiment shown in fig. 1 in detail, which is not described herein.
According to the method for generating the industrial document, the standard document is analyzed through the natural language processing method, and the first industrial document can be intelligently generated according to the document generation requirement and the mode of extracting the data corresponding to the information to be filled from the preset industrial database, so that the generation efficiency of the first industrial document is improved, and meanwhile, the accuracy of the content in the first industrial document is guaranteed.
In this embodiment, a method for generating an industry document is provided, which may be used in the above-mentioned computer device, such as a computer, a server, etc., and fig. 3 is a flowchart of a method for generating an industry document according to an embodiment of the present invention, as shown in fig. 3, where the flowchart includes the following steps:
Step S301, corresponding canonical documents and document generation requirements are acquired in response to a first instruction of a user. Please refer to step S201 in the embodiment shown in fig. 2 in detail, which is not described herein.
Step S302, a first industry document is generated based on the specification document and the document generation requirement. Please refer to step S202 in the embodiment shown in fig. 2, which is not described herein.
Step S303, responding to a second instruction of the user, and extracting evaluation rules based on a preset industry database and a specification document.
Specifically, the step S303 includes:
step S3031, corresponding evaluation parameters and evaluation weights are extracted from the standard document based on a preset industry database.
The standard document comprises evaluation parameters and evaluation weights corresponding to different factors, and the evaluation parameters and the evaluation weights corresponding to each factor can be extracted from the standard document according to a preset industry database.
Step S3032, an evaluation rule is generated based on the evaluation parameters and the evaluation weights.
Scoring rules: f1, F2, F3, F4 correspond to the technical parameter, business parameter, bid offer parameter, priority purchase policy parameter, respectively; a1, A2, A3, A4 correspond to the technical parameters, business parameters, bid and offer parameter weights, respectively. Total coefficient=a1×f1+a2×f2+a3×f3+a4×f4.
F1 contains the sub-parameters: f11, F12 and F1n respectively correspond to the technical requirements explicitly required in the uploading files (such as the bidding documents), such as administrative division code changing module development and maintenance, whole population data query interface upgrading maintenance, terminal data encryption and decryption functions and the like;
f2 contains the sub-parameters: f21, F22, F23, F24, F2n correspond to the business requirements explicitly required in the above-mentioned upload files (e.g. bidding documents), such as technical capability, service capability, similar performance, etc. The technical capability parameters can be further subdivided into parameters such as F211, F212, F21n, and the like, which respectively represent the number of software copyright rights, the number of qualification certificates, the number of honor certificates, and the like;
f3 contains the sub-parameters: f31, F32, F33, F34 and F3n correspond to each functional module, hardware, operation and maintenance of software respectively;
f4 contains the sub-parameters: f41, F42, F43, F44 and F4n respectively correspond to the preferential purchasing and grading requirements explicitly required in the bidding documents, such as small and medium enterprises, two types of products and the like; wherein the coefficients of F1, F2, F3 and F4 are the sum of the coefficients of the sub-items.
Specifically, the step S3032 may include:
and c1, extracting the content to be evaluated corresponding to the evaluation parameters from the first industry document.
And c2, evaluating the content to be evaluated based on the evaluation rule, and generating an evaluation result.
The computer device may extract the content to be evaluated from within the first industry document. And the computer equipment re-evaluates the content to be evaluated according to the adjusted evaluation rule to generate an evaluation result. Wherein, since the evaluation weight and the evaluation parameter in the adjusted evaluation rule have been changed, the generated evaluation result can be changed.
And c3, analyzing the content to be regulated in the content to be evaluated based on the evaluation result.
And c4, generating a first optimization scheme based on the content needing to be adjusted.
According to the evaluation result, which contents in the contents to be evaluated do not meet the requirements can be analyzed, the contents which do not meet the requirements are required to be adjusted, and then a first optimization scheme is generated according to the adjusted contents. For example: taking a bid file as an example, the first industry document may be a bid file. Wherein, after evaluating the first industry file, the copyright number of the display software suggests optimization. The first optimization scheme can be that the function of realizing the copyright quantity of the display software by the knowledge graph technology is modified into the function of realizing the copyright quantity of the display software by adopting a data visual display mode; therefore, the technical difficulty can be reduced, the development and operation cost is reduced, the recommended quotation is reduced by 2 ten thousand yuan, the profit prediction is still improved by 20%, and the total score of the bidding book is improved to 90 minutes.
And step S304, analyzing and evaluating the first industry document based on the evaluation rule, and generating a first optimization scheme. Please refer to step S203 in the embodiment shown in fig. 2 in detail, which is not described herein.
Step S305, in response to the confirmation instruction of the user, generating a second industry document based on the first optimization scheme. Please refer to step S205 in the embodiment shown in fig. 2 in detail, which is not described herein.
According to the method for generating the industry document, the content to be evaluated in the first industry document is evaluated through the evaluation rule, so that the content with larger influence in the content to be evaluated can be determined, and further adjustment is performed on the content, so that the generated second industry document can meet the winning bid requirement more.
The large model (such as the ancient NLP large model) adopts a multi-model collaboration scheme, simulates the writing flow of the first industry document and the second industry document, and provides an automatic optimization function according to output content. In an alternative embodiment, FIG. 4 illustrates an architectural diagram of an industry document generation method, and FIG. 5 illustrates a flow diagram of an industry document generation method.
The overall architecture is divided into: a collaboration layer and a model layer.
The role of the collaboration layer is to assist the model layer in completing tasks, and also to be the underlying dependencies of the model layer. Specifically, the collaboration layer assigns roles to each large model, specifically may define a set of roles, such as technicians, auditors, etc., and define some attributes for each role, such as role names, targets, constraints, etc., without specific limitation. And storing the context of each large language model into a database for calling by other large language models.
The model layer functions to receive user information and output the final industry document. Specifically, information is exchanged among the large models through the collaboration layer, and finally, the output flow of the whole industry document can be finished only by the requirement of a user. In particular, the model layer may include a model a and a model B. Wherein, model a: and the technician role is responsible for outputting the first industry document according to the specification document and the document generation requirement. Model B: and the auditor role is responsible for understanding the scoring rule and scoring the output of the model A according to the scoring rule. And generating a modification instruction below the scoring standard, and then performing multiple iterations by the model A according to the instruction and the user modification opinion until the scoring standard is reached.
Referring to fig. 4, the documents in fig. 4 may be bidding documents, and the bidding documents are processed by a natural language processing method (i.e., NLP technology in fig. 4) to obtain bidding requirements, scoring criteria and bidding formats. The bidding requirements can be requirements generated for the file, the bidding format can be a canonical document, and the scoring standard can be an evaluation rule. And then extracting corresponding data from the company bidding database and feeding the data to a model A by the cooperation layer, generating a first draft (namely a first business document) by the model A according to bidding requirements and bidding formats, and then sending the first business document to a model B by the cooperation layer, wherein the model B evaluates the first business document and gives feedback. Wherein the user may add auxiliary scoring rules, i.e. i want a "XX" tab in fig. 4, for example: i want a lower cost, proper bid, highest profit bid. Feedback is then given again by the auxiliary scoring rules, the content of which may be a modified "XX" section, for example: and modifying the knowledge graph technology into a data visual display mode.
It should be noted that the collaboration layer may include a dialog context as well as document sharing. Wherein the dialog context may be stored in a dialog database. Document sharing is used to enable document sharing between model a and model B.
In connection with FIG. 5, the bid documents of FIG. 5 may be a first industry document and a second industry document, the bid documents may be the documents uploaded to the computer server as described above, the bid requirements may be requirements for the documents, and the bid formats may be canonical documents. The user inputs the bid file into a computer server, the computer server analyzes the bid requirement and bid format of the bid file through a cooperation layer to generate a first industry document, and then evaluates the first industry document through a model B and gives an improvement suggestion, namely a first optimization scheme. The auxiliary scoring rule can be added, the scoring rule is modified according to the auxiliary scoring rule, the first business document is again evaluated according to the modified scoring rule, and specific optimization suggestions, namely a second optimization scheme, are given.
The embodiment also provides an industry document generating device, which is used for realizing the embodiment and the preferred implementation manner, and the description is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The present embodiment provides an industry document generation apparatus, as shown in fig. 6, including: an obtaining module 601, configured to obtain a corresponding canonical document and a document generation requirement in response to a first instruction of a user; a first generating module 602, configured to generate a first industry document based on the specification document and the document generation requirement; an extracting module 603, configured to extract an evaluation rule based on a preset industry database and a specification document in response to a second instruction of the user; the analysis generating module 604 is used for analyzing and evaluating the first industry document based on the evaluation rule and generating an optimization scheme; a second generation module 605 is configured to generate a second industry document based on the optimization scheme in response to the confirmation indication of the user.
In an alternative embodiment, the apparatus further comprises: the adjusting module is used for responding to the auxiliary evaluation rule confirmed by the user and adjusting the evaluation rule; and the evaluation generation module is used for analyzing and evaluating the first industry document based on the adjusted evaluation rule and generating a second optimization scheme.
In an alternative embodiment, the first generation module 602 includes: the first extraction unit is used for analyzing the standard document by a natural language processing method and extracting information to be filled in the standard document; the second extraction unit is used for extracting the content in the industry content generation information to be filled based on the document generation requirement and a preset industry database to generate a first industry document.
In an alternative embodiment, the first extraction unit comprises: the first extraction subunit is used for carrying out word segmentation processing on the standard document based on the natural language processing database and extracting word information; the second extraction subunit is used for extracting document requirement information from the standard document by using named entity identification; the clustering subunit is used for carrying out clustering processing on the document demand information to obtain a document demand collection; a third extraction subunit, configured to extract scoring content from the canonical document based on the scoring keyword; a fourth extraction subunit, configured to extract a scoring gist from the canonical document using an emotion analysis method and a semantic analysis method; the first generation subunit is used for generating a scoring set based on scoring content and scoring points; a fifth extraction subunit for extracting the format description sentence from the canonical document based on the format keyword; a sixth extraction subunit for extracting each output field in the format description sentence by using syntactic analysis; a seventh extraction subunit, configured to find a field description of each output field through semantic matching, and extract a field meaning explanation; and the second generation subunit is used for generating the to-be-filled information based on the document requirement set, the grading set and the field meaning interpretation.
In an alternative embodiment, the extraction module 603 includes: the third extraction unit is used for extracting corresponding evaluation parameters and evaluation weights from the standard document based on a preset industry database; and the first generation unit is used for generating an evaluation rule based on the evaluation parameter and the evaluation weight.
In an alternative embodiment, the analysis generation module 604 includes: the fourth extraction unit is used for extracting the content to be evaluated corresponding to the evaluation parameters from the first industry document; the second generation unit is used for evaluating the content to be evaluated based on the evaluation rule to generate an evaluation result; the first analysis unit is used for analyzing the content to be adjusted in the content to be evaluated based on the evaluation result; and the third generating unit is used for generating a first optimization scheme based on the content needing to be adjusted.
In an alternative embodiment, the adjustment module includes: a fifth extraction unit, configured to extract, from the canonical document, an evaluation parameter and an evaluation weight corresponding to the auxiliary evaluation rule based on a preset industry database; and the adjusting unit is used for adjusting the evaluation rule based on the evaluation parameter and the evaluation weight.
In an alternative embodiment, the evaluation generation module comprises: the sixth extraction unit is used for extracting the content to be evaluated corresponding to the evaluation parameters from the first industry document; the evaluation unit is used for evaluating the content to be evaluated based on the adjusted evaluation rule and generating an evaluation result; the second analysis unit is used for analyzing the content to be adjusted in the content to be evaluated based on the evaluation result; and the fourth generating unit is used for generating a second optimization scheme based on the content needing to be adjusted.
Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.
The industry documentation generation apparatus in this embodiment is presented in terms of functional units, where the units refer to ASIC (Application Specific Integrated Circuit ) circuits, processors and memories executing one or more software or fixed programs, and/or other devices that can provide the functionality described above.
The embodiment of the invention also provides computer equipment, which is provided with the device for generating the industry document shown in the figure 6.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 7, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 7.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform a method for implementing the embodiments described above.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device also includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (10)
1. A method for generating an industry document, the method comprising:
responding to a first instruction of a user, and acquiring a corresponding specification document and a document generation requirement;
generating a first industry document based on the specification document and the document generation requirement;
responding to a second instruction of a user, and extracting an evaluation rule based on a preset industry database and the specification document;
analyzing and evaluating the first business document based on the evaluation rule, and generating a first optimization scheme;
and generating a second industry document based on the first optimization scheme in response to the confirmation instruction of the user.
2. The method of generating an industry document according to claim 1, wherein before generating a second industry document based on the first optimization scheme in response to a confirmation instruction of a user, the method further comprises:
adjusting the evaluation rule in response to the user-confirmed auxiliary evaluation rule;
And analyzing and evaluating the first industrial document based on the adjusted evaluation rule, and generating a second optimization scheme.
3. The method for generating an industry document according to claim 1, wherein generating a first industry document based on the specification document and a document generation requirement comprises:
analyzing the standard document by a natural language processing method, and extracting information to be filled in the standard document;
and extracting industry content to generate content in the information to be filled based on the document generation requirement and a preset industry database, and generating the first industry document.
4. The method for generating an industry document according to claim 3, wherein the parsing the specification document by a natural language processing method, extracting information to be filled in the specification document, comprises:
word segmentation processing is carried out on the standard document based on a natural language processing database, and word information is extracted;
extracting document requirement information from the canonical document by using named entity recognition;
clustering the document demand information to obtain a document demand collection;
extracting scoring content from the canonical document based on the scoring keywords;
Extracting scoring points from the canonical document by using an emotion analysis method and a semantic analysis method;
generating a scoring set based on the scoring content and scoring points;
extracting a format description sentence from the specification document based on a format keyword;
extracting each output field in the format description statement by utilizing syntactic analysis;
finding out the field description of each output field through semantic matching, and extracting field meaning explanation;
and generating the to-be-filled information based on the document demand collection, the grading collection and the field meaning interpretation.
5. The method for generating an industry document according to claim 1, wherein the extracting evaluation rules based on the preset industry database and the specification document comprises:
extracting corresponding evaluation parameters and evaluation weights from the specification document based on a preset industry database;
the evaluation rule is generated based on the evaluation parameters and the evaluation weights.
6. The method for generating an industry document according to claim 5, wherein the analyzing and evaluating the first industry document based on the evaluation rule and generating a first optimization scheme includes:
extracting to-be-evaluated content corresponding to the evaluation parameters from the first industry document;
Evaluating the content to be evaluated based on the evaluation rule to generate an evaluation result;
analyzing the content to be regulated in the content to be evaluated based on the evaluation result;
and generating the first optimization scheme based on the content needing to be adjusted.
7. The method of claim 2, wherein adjusting the evaluation rule in response to the user-validated auxiliary evaluation rule comprises:
extracting evaluation parameters and evaluation weights corresponding to the auxiliary evaluation rules from the specification document based on a preset industry database;
and adjusting the evaluation rule based on the evaluation parameter and the evaluation weight.
8. The method for generating an industry document according to claim 7, wherein the analyzing and evaluating the first industry document based on the adjusted evaluation rule, and generating a second optimization scheme, comprises:
extracting to-be-evaluated content corresponding to the evaluation parameters from the first industry document;
evaluating the content to be evaluated based on the adjusted evaluation rule to generate an evaluation result;
analyzing the content to be regulated in the content to be evaluated based on the evaluation result;
And generating the second optimization scheme based on the content needing to be adjusted.
9. An apparatus for generating an industry document, the apparatus comprising:
the acquisition module is used for responding to the first indication of the user and acquiring corresponding specification documents and document generation requirements;
the first generation module is used for generating a first industry document based on the specification document and the document generation requirement;
the extraction module is used for responding to a second instruction of the user and extracting an evaluation rule based on a preset industry database and the specification document;
the analysis generation module is used for carrying out analysis and evaluation on the first business document based on the evaluation rule and generating an optimization scheme;
and the second generation module is used for responding to the confirmation indication of the user and generating a second industry document based on the optimization scheme.
10. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the method of generating an industry document according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311506829.4A CN117494672A (en) | 2023-11-13 | 2023-11-13 | Method and device for generating industry document and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311506829.4A CN117494672A (en) | 2023-11-13 | 2023-11-13 | Method and device for generating industry document and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117494672A true CN117494672A (en) | 2024-02-02 |
Family
ID=89670464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311506829.4A Pending CN117494672A (en) | 2023-11-13 | 2023-11-13 | Method and device for generating industry document and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117494672A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130151238A1 (en) * | 2011-12-12 | 2013-06-13 | International Business Machines Corporation | Generation of Natural Language Processing Model for an Information Domain |
| CN110795923A (en) * | 2019-11-01 | 2020-02-14 | 达而观信息科技（上海）有限公司 | Automatic generation system and generation method of technical document based on natural language processing |
| KR20210086849A (en) * | 2019-12-31 | 2021-07-09 | 주식회사 리걸인사이트 | Method for generating document |
| CN115688868A (en) * | 2022-12-30 | 2023-02-03 | 荣耀终端有限公司 | Model training method and computing device |
| CN116402022A (en) * | 2023-03-02 | 2023-07-07 | 中银金融科技有限公司 | Document generation method, device, electronic equipment and storage medium |
| CN116469505A (en) * | 2023-04-18 | 2023-07-21 | 平安科技（深圳）有限公司 | Data processing method, device, computer equipment and readable storage medium |
-
2023
- 2023-11-13 CN CN202311506829.4A patent/CN117494672A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130151238A1 (en) * | 2011-12-12 | 2013-06-13 | International Business Machines Corporation | Generation of Natural Language Processing Model for an Information Domain |
| CN110795923A (en) * | 2019-11-01 | 2020-02-14 | 达而观信息科技（上海）有限公司 | Automatic generation system and generation method of technical document based on natural language processing |
| KR20210086849A (en) * | 2019-12-31 | 2021-07-09 | 주식회사 리걸인사이트 | Method for generating document |
| CN115688868A (en) * | 2022-12-30 | 2023-02-03 | 荣耀终端有限公司 | Model training method and computing device |
| CN116402022A (en) * | 2023-03-02 | 2023-07-07 | 中银金融科技有限公司 | Document generation method, device, electronic equipment and storage medium |
| CN116469505A (en) * | 2023-04-18 | 2023-07-21 | 平安科技（深圳）有限公司 | Data processing method, device, computer equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11989519B2 (en) | Applied artificial intelligence technology for using natural language processing and concept expression templates to train a natural language generation system | |
| US10896212B2 (en) | System and methods for automating trademark and service mark searches | |
| US20210256543A1 (en) | Predictive Analytics Diagnostic System and Results on Market Viability and Audience Metrics for Scripted Media | |
| Luiz et al. | A feature-oriented sentiment rating for mobile app reviews | |
| US8972408B1 (en) | Methods, systems, and articles of manufacture for addressing popular topics in a social sphere | |
| US20200356363A1 (en) | Methods and systems for automatically generating documentation for software | |
| US20110099052A1 (en) | Automatic checking of expectation-fulfillment schemes | |
| MXPA04011788A (en) | Learning and using generalized string patterns for information extraction. | |
| WO2020229889A1 (en) | Natural language text generation using semantic objects | |
| US20220414463A1 (en) | Automated troubleshooter | |
| US20230186033A1 (en) | Guided text generation for task-oriented dialogue | |
| CN115098634A (en) | Semantic dependency relationship fusion feature-based public opinion text sentiment analysis method | |
| CN114997288A (en) | Design resource association method | |
| US20190295110A1 (en) | Performance analytics system for scripted media | |
| Huang et al. | Web product ranking using opinion mining | |
| Gonzalez-Mora et al. | Model-driven development of web apis to access integrated tabular open data | |
| CN104750484A (en) | Code abstract generation method based on maximum entropy model | |
| Antić | Python Natural Language Processing Cookbook: Over 50 recipes to understand, analyze, and generate text for implementing language processing tasks | |
| CN117494672A (en) | Method and device for generating industry document and computer readable storage medium | |
| US11017172B2 (en) | Proposition identification in natural language and usage thereof for search and retrieval | |
| US20230325606A1 (en) | Method for extracting information from an unstructured data source | |
| US11995394B1 (en) | Language-guided document editing | |
| US11868313B1 (en) | Apparatus and method for generating an article | |
| CN117540004B (en) | Industrial domain intelligent question-answering method and system based on knowledge graph and user behavior | |
| Jakubícek et al. | Walking the tightrope between linguistics and language engineering |
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 |