CN117252163A - Implementation method and device of electronic manual, electronic equipment and readable medium - Google Patents
Implementation method and device of electronic manual, electronic equipment and readable medium Download PDFInfo
- Publication number
- CN117252163A CN117252163A CN202311265953.6A CN202311265953A CN117252163A CN 117252163 A CN117252163 A CN 117252163A CN 202311265953 A CN202311265953 A CN 202311265953A CN 117252163 A CN117252163 A CN 117252163A
- Authority
- CN
- China
- Prior art keywords
- electronic manual
- document
- electronic
- question
- information
- 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 62
- 238000012549 training Methods 0.000 claims description 32
- 239000013598 vector Substances 0.000 claims description 32
- 238000012423 maintenance Methods 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 13
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 claims description 5
- 238000012545 processing Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000013519 translation 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
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides an implementation method, an implementation device, an electronic device and a readable medium of an electronic manual, wherein the implementation method of the electronic manual comprises the following steps: acquiring application attribute information of an electronic manual to be generated; determining a scene document corresponding to the pre-stored scene document according to the application attribute information; invoking context information and a large language identification model corresponding to the scene document; an electronic manual is generated from the context information, the scene document, and the language identification model. Through the embodiment of the disclosure, the index rule of the electronic manual is optimized, the data redundancy of the electronic manual is reduced, and the question-answering efficiency and reliability of the electronic manual are improved.
Description
Technical Field
The disclosure relates to the field of information technology, and in particular relates to an implementation method and device of an electronic manual, electronic equipment and a readable medium.
Background
At present, the contents of the electronic manual are manufactured on a platform according to the experience of a business expert or reference data, so that different electronic manuals are efficiently created for a group by users in order to reduce the manufacturing threshold and the manufacturing efficiency of the electronic manual.
In the related technology, on one hand, the electronic manual supports the input of equipment or part names, models, types, application industries and uploading related manuals, including maintenance manuals, use specifications and the like, and on the other hand, the electronic manual also provides a question-answering function, namely, after inputting problem description information, the related knowledge of equipment parts can be output.
However, due to the limitation of the length of the prompt word of the electronic manual, when the electronic manual contains more contents, the rules for classifying and storing the contents are not uniform, so that not only are redundant data generated in the electronic manual, but also the accuracy of the electronic manual is reduced, and a plurality of irrelevant or unreliable results are generated in the electronic manual.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
It is an object of the present disclosure to provide an implementation method, apparatus, electronic device, and readable medium for an electronic manual, which overcome, at least to some extent, the problems of the electronic manual due to limitations and disadvantages of the related art.
According to a first aspect of embodiments of the present disclosure, there is provided a method for implementing an electronic manual, including: acquiring application attribute information of an electronic manual to be generated; determining a scene document corresponding to the electronic manual according to the application attribute information; invoking context information and a large language identification model corresponding to the scene document; and generating the electronic manual according to the context information, the scene document and the language identification model.
In an exemplary embodiment of the present disclosure, before determining the corresponding scene document in the pre-stored document database according to the application attribute information, the method further includes:
acquiring maintenance record information, wherein the maintenance record information comprises at least one of a historical maintenance record, a maintenance manual and a service manual;
extracting a theme, keywords and text content according to the maintenance record information;
and vectorizing the topics, keywords and text contents stored in the specified format, and storing the vectorized topics, keywords and text contents in a search engine.
In an exemplary embodiment of the present disclosure, further comprising:
acquiring expert experience document records corresponding to the maintenance record information;
the document database is generated from the search engine and the expert experience document record.
In an exemplary embodiment of the present disclosure, further comprising:
receiving feedback information of a client applying the electronic manual;
and correcting the expert experience document record according to the feedback information.
In an exemplary embodiment of the present disclosure, further comprising:
invoking LangChain to process the topics, keywords and text content stored in the search engine to generate a question-answer sample for training an original language recognition model;
training the original language identification model based on the question-answer samples;
and determining the language identification model according to the plurality of trained original language identification models.
In one exemplary embodiment of the present disclosure, invoking LangChain to process the topics, keywords, and text content stored to the search engine to generate a question-answer sample for training an original language recognition model comprises:
invoking Langchain to index the topics, the keywords and the text content stored in the search engine so as to determine corresponding question text vectors, a specified number of answer text vectors matched with the question text vectors and context information related to the answer text vectors in the scene document;
and generating the question-answer sample according to the question text vector, the answer text vector and the context information.
In an exemplary embodiment of the present disclosure, further comprising:
and modifying training parameters of the original language identification model by adopting the Lora fine tuning model, wherein the training parameters comprise training times and/or learning rate.
According to a second aspect of the embodiments of the present disclosure, there is provided an implementation apparatus of an electronic manual, including:
the acquisition module is used for acquiring application attribute information of the electronic manual to be generated;
the determining module is used for determining a scene document corresponding to the electronic manual according to the application attribute information;
the calling module is used for calling the context information and the large language identification model corresponding to the scene document;
a generation module arranged to generate the electronic manual from the context information, the scene document and the language identification model.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: a memory; and a processor coupled to the memory, the processor configured to perform the method of any of the above based on instructions stored in the memory.
According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements a method of implementing an electronic manual as set forth in any one of the above.
According to the embodiment of the disclosure, the application attribute information of the electronic manual to be generated is obtained, the scene document corresponding to the electronic manual is determined according to the application attribute information, the context information and the large language identification model corresponding to the scene document are further called, and finally the electronic manual is generated according to the context information, the scene document and the language identification model, so that the index rule of the electronic manual is optimized, the data redundancy of the electronic manual is reduced, and the question-answering efficiency and the reliability of the electronic manual are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.
FIG. 1 shows a schematic diagram of an exemplary system architecture for an implementation of an electronic manual to which embodiments of the present invention may be applied;
FIG. 2 is a flow chart of a method of implementing an electronic manual in an exemplary embodiment of the present disclosure;
FIG. 3 is a flow chart of another method of implementing an electronic manual in an exemplary embodiment of the present disclosure;
FIG. 4 is a flow chart of another method of implementing an electronic manual in an exemplary embodiment of the present disclosure;
FIG. 5 is a flow chart of another method of implementing an electronic manual in an exemplary embodiment of the present disclosure;
FIG. 6 is a flow chart of another method of implementing an electronic manual in an exemplary embodiment of the present disclosure;
FIG. 7 is a flow chart of another method of implementing an electronic manual in an exemplary embodiment of the present disclosure;
FIG. 8 is a flow chart of another method of implementing an electronic manual in an exemplary embodiment of the present disclosure;
FIG. 9 is an interactive schematic diagram of an implementation of an electronic manual in an exemplary embodiment of the present disclosure;
FIG. 10 is a block diagram of an implementation of an electronic manual in an exemplary embodiment of the present disclosure;
fig. 11 is a block diagram of an electronic device in an exemplary embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are only schematic illustrations of the present disclosure, in which the same reference numerals denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
FIG. 1 shows a schematic diagram of an exemplary system architecture for an implementation of an electronic manual to which embodiments of the present invention may be applied.
As shown in fig. 1, the system architecture 100 may include one or more of terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 105 may be a server cluster formed by a plurality of servers.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. The terminal devices 101, 102, 103 may be various electronic devices with display screens including, but not limited to, smartphones, tablet computers, portable computers, desktop computers, and the like.
In some embodiments, the implementation method of the electronic manual provided by the embodiments of the present invention is generally performed by the server 105, and accordingly, the implementation apparatus of the electronic manual is generally disposed in the terminal device 103 (may also be the terminal device 101 or 102). In other embodiments, some terminals may have similar functionality as server devices to perform the method.
The following describes example embodiments of the present disclosure in detail with reference to the accompanying drawings.
Fig. 2 is a flow chart of a method of implementing an electronic manual in an exemplary embodiment of the present disclosure.
Referring to fig. 2, the implementation method of the electronic manual may include:
step S202, application attribute information of an electronic manual to be generated is acquired.
In the above-described embodiment, the application attribute information includes attribute information of the electronic manual in a specified application scenario, for example, a manual name, creator, use scenario, release state, version information, creation time, update time, and the like, but is not limited thereto.
And step S204, determining a scene document corresponding to the electronic manual according to the application attribute information.
In the above embodiment, the scenario document is used to describe information of the usage scenario of the electronic document, such as after-sales scenario, maintenance scenario, customer usage description scenario, etc., but not limited thereto, that is, a large number of documents are split, and the large language recognition model is trained by adopting a data source with relatively strong correlation in different scenarios, so as to obtain the basic large language model with independent training in different application scenarios.
Step S206, calling the context information and the large language identification model corresponding to the scene document.
In the above embodiment, by invoking the context information and the large language recognition model corresponding to the scene document, on one hand, the reliability of the question-answering mechanism of the electronic manual can be improved through the context information, namely, questions and corresponding answers can be more clearly described through the context information, on the other hand, the question-answering model of the electronic manual more suitable for the scene can be determined through the large language recognition model training, on the other hand, when the electronic manual is manufactured, each scene and technical term are recognized through the scene document, a data source with higher relativity (namely, the context information) is queried in a knowledge base, a prompt word is pre-generated, and then the large language recognition model generates the corresponding electronic manual, so that irrelevant contents and errors are reduced, redundant data in the electronic manual are also reduced, and the index efficiency and reliability of the question-answering mechanism of the electronic manual are improved.
Step S208, the electronic manual is generated according to the context information, the scene document and the language identification model.
According to the embodiment of the disclosure, the application attribute information of the electronic manual to be generated is obtained, the scene document corresponding to the electronic manual is determined according to the application attribute information, a large language recognition model is comprehensively generated through a plurality of trained voice recognition models, the context information and the large language recognition model corresponding to the scene document are further called, and finally the electronic manual is generated according to the context information, the scene document and the language recognition model, so that the index rule of the electronic manual is optimized, the data redundancy of the electronic manual is reduced, and the question-answer efficiency and the reliability of the electronic manual are improved.
Next, each step of the implementation method of the electronic manual will be described in detail.
In an exemplary embodiment of the present disclosure, as shown in fig. 3, before determining a corresponding scene document in the pre-stored document database according to the application attribute information, the method further includes:
step S302, service record information including at least one of a history service record, a service manual, and a service manual is acquired.
In the above embodiment, the solved maintenance problem or the maintenance instruction or the relevant answer of the use instruction can be determined by acquiring the maintenance record information, so that the correspondence between the problem and the answer in each application scenario is determined.
And step S304, extracting the theme, the keywords and the text content according to the maintenance record information.
In step S306, the topics, keywords and text content stored in the specified format are vectorized and stored in the search engine.
In the embodiment, through extracting the theme, the keywords and the text content and vectorizing, the context information is established and determined based on the extracted theme, the keywords and the text content according to the related document, so that the prompt word in a more accurate question-answering mode is generated, and the indexing efficiency of a question-answering mechanism in a large language identification model is further improved.
In an exemplary embodiment of the present disclosure, as shown in fig. 4, the implementation method of the electronic manual further includes:
step S402, acquiring expert experience document records corresponding to the maintenance record information.
Step S404, generating the document database according to the search engine and the expert experience document record.
In the embodiment, the richer answer content is determined through expert experience document records and is summarized to a document database, so that a more comprehensive question-answer scheme is provided for a large language identification model based on the richer answer content.
In an exemplary embodiment of the present disclosure, as shown in fig. 5, the implementation method of the electronic manual further includes:
step S502, receiving feedback information of a client applying the electronic manual.
And step S504, carrying out correction processing on the expert experience document record according to the feedback information.
In the embodiment, the expert experience document is timely corrected and supplemented by receiving the feedback information of the client applying the electronic manual, so that the reliability and accuracy of the question-answer scheme of the electronic manual are further improved.
In an exemplary embodiment of the present disclosure, as shown in fig. 6, the implementation method of the electronic manual further includes:
step S602, call LangChain to process the subject, the keyword and the text content stored in the search engine, so as to generate a question-answer sample for training an original language recognition model.
In the above embodiment, langChain is a framework for developing an application program driven by LLM, which includes two core functions, the first is to connect the LLM model with an external data source, and the second is to allow the LLM model to interact with the environment, that is, langChain loads topics, keywords and text content stored in a search engine through a loader, and converts the topic into question-answer samples that can be used to train an original language recognition model.
Step S604, training the original language recognition model based on the question-answer samples.
In the above embodiment, training is performed on any original language recognition model based on any set of question-answer samples to obtain the speech recognition model under each scene, so that the electronic manual also meets the question-answer requirements of each scene.
Step S606, determining the language identification model according to the plurality of trained original language identification models.
In the above embodiment, the language recognition model is determined through the plurality of trained original language recognition models, so that the plurality of original language recognition models can be combined and summarized, and finally, the comprehensive language recognition model applicable to a plurality of application scenes is obtained, so that redundant data is reduced, and accuracy and reliability of a question-answer scheme are improved.
In one exemplary embodiment of the present disclosure, invoking LangChain to process the topics, keywords, and text content stored to the search engine to generate a question-answer sample for training an original language recognition model, as shown in fig. 7, includes:
step S702, invoking LangChain to index the topics, keywords and text contents stored in the search engine, so as to determine corresponding question text vectors, a specified number of answer text vectors matched with the question text vectors, and context information related to the answer text vectors in the scene document.
Step S704, generating the question-answer sample according to the question text vector, the answer text vector and the context information.
In the above embodiment, the LangChain is invoked to index the subject, the keyword and the text content stored in the search engine, and the question-answering sample is generated according to the question text vector, the answer text vector and the context information, that is, a relatively accurate context information is set for inputting the question text vector and the answer text vector, so that the reliability and the comprehensiveness of the question-answering scheme provided by the electronic manual are improved based on the question-answering sample.
Further, the question and answer samples are submitted to the LLM model for training.
In the above embodiment, the LLM model, i.e. Large Language Model, and the large language recognition model may perform tasks such as text summarization, translation, emotion analysis, and classification, and the problem text vector, the answer text vector, and the context information are submitted to the LLM model through the prompt, where the context information helps to enhance understanding of the LLM model on the problem text vector and the answer text vector, and further improves reliability and accuracy of the LLM model.
In an exemplary embodiment of the present disclosure, as shown in fig. 8, the implementation method of the electronic manual further includes:
step S802, modifying training parameters of the original language identification model by adopting a Lora fine tuning model, wherein the training parameters comprise training times and/or learning rate.
In the above embodiment, the Lora fine tuning model is used as a lightweight fine tuning model, and runs to indirectly train some dense layers in the neural network by optimizing the rank decomposition matrix of the dense layer change in the adaptation process, and meanwhile, the weight of the pre-training is kept unchanged, which not only can avoid the over fitting of the training model by adjusting the training parameters, but also can improve the efficiency and reliability of the training model.
In one exemplary embodiment of the present disclosure, as shown in fig. 9, an implementation framework 900 of the electronic manual includes the following core interaction flows:
(1) And submitting scene and description information for making the electronic manual.
(2) And (5) performing scene recognition, and calling RouterChain of the LLM model to select a document conforming to the specified scene of the client.
Wherein the content sources of the knowledge base include search engines and expert-supplemented documents.
Specifically, a document (history maintenance record, maintenance manual, user manual) finished by an expert is obtained through uploading the document, the document is converted into formatted data, a LangChain Index interface is called to import the document, the document is preprocessed, the text can be segmented into text segments, the text is further extracted through a natural language processing module to obtain a theme and a keyword, the theme, the keyword and the text segments are used as one line and stored in a csv format, on one hand, the LangChain model is called to send a sample record in the csv format to a training platform, and on the other hand, index is stored in a search engine based on the sample record in the vectorization csv format.
(3) The prompt management module interacts with the electronic manual making module to cache session information in the one-time making process.
(4) And executing electronic manual production.
(5) And outputting the electronic manual document, acquiring the evaluation manual of the producer, feeding back the evaluation manual, and supplementing the document to a knowledge base according to the feedback result.
(6) And uploading the generated electronic manual to an electronic manual management platform.
Corresponding to the above method embodiments, the present disclosure further provides an implementation apparatus of an electronic manual, which may be used to perform the above method embodiments.
Fig. 10 is a block diagram of an implementation apparatus of an electronic manual in an exemplary embodiment of the present disclosure.
Referring to fig. 10, an implementation apparatus 1000 of an electronic manual may include:
an obtaining module 1002, configured to obtain application attribute information of an electronic manual to be generated.
And a determining module 1004, configured to determine a scene document corresponding to the electronic manual according to the application attribute information.
And a calling module 1006, configured to call the context information and the large language identification model corresponding to the scene document.
A generation module 1008 arranged to generate the electronic manual from the context information, the scene document and the language identification model.
In an exemplary embodiment of the present disclosure, the obtaining module 1002 is further configured to:
acquiring maintenance record information, wherein the maintenance record information comprises at least one of a historical maintenance record, a maintenance manual and a service manual;
extracting a theme, keywords and text content according to the maintenance record information;
and vectorizing the topics, keywords and text contents stored in the specified format, and storing the vectorized topics, keywords and text contents in a search engine.
In an exemplary embodiment of the present disclosure, the obtaining module 1002 is further configured to:
acquiring expert experience document records corresponding to the maintenance record information;
the document database is generated from the search engine and the expert experience document record.
In an exemplary embodiment of the present disclosure, the obtaining module 1002 is further configured to:
receiving feedback information of a client applying the electronic manual;
and correcting the expert experience document record according to the feedback information.
In one exemplary embodiment of the present disclosure, the invocation module 1006 is further configured to:
invoking LangChain to process the topics, keywords and text content stored in the search engine to generate a question-answer sample for training an original language recognition model;
training the original language identification model based on the question-answer samples;
and determining the language identification model according to the plurality of trained original language identification models.
In one exemplary embodiment of the present disclosure, the invocation module 1006 is further configured to:
invoking Langchain to index the topics, the keywords and the text content stored in the search engine so as to determine corresponding question text vectors, a specified number of answer text vectors matched with the question text vectors and context information related to the answer text vectors in the scene document;
and generating the question-answer sample according to the question text vector, the answer text vector and the context information.
In an exemplary embodiment of the present disclosure, the generating module 1008 is further configured to:
and modifying training parameters of the original language identification model by adopting the Lora fine tuning model, wherein the training parameters comprise training times and/or learning rate.
Since each function of the apparatus 1000 is described in detail in the corresponding method embodiments, the disclosure is not repeated herein.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.
Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 1100 according to this embodiment of the invention is described below with reference to fig. 11. The electronic device 1100 shown in fig. 11 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 11, the electronic device 1100 is embodied in the form of a general purpose computing device. Components of electronic device 1100 may include, but are not limited to: the at least one processing unit 1110, the at least one memory unit 1120, a bus 1130 connecting the different system components, including the memory unit 1120 and the processing unit 1110.
Wherein the storage unit stores program code that is executable by the processing unit 1110 such that the processing unit 1110 performs steps according to various exemplary embodiments of the present invention described in the above-described "exemplary methods" section of the present specification. For example, the processing unit 1110 may perform the methods as shown in the embodiments of the present disclosure.
The storage unit 1120 may include a readable medium in the form of a volatile storage unit, such as a Random Access Memory (RAM) 11201 and/or a cache memory 11202, and may further include a Read Only Memory (ROM) 11203.
The storage unit 1120 may also include a program/utility 11204 having a set (at least one) of program modules 11205, such program modules 11205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
The bus 1130 may be a local bus representing one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a bus using any of a variety of bus architectures.
The electronic device 1100 may also communicate with one or more external devices 1140 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 1100, and/or any devices (e.g., routers, modems, etc.) that enable the electronic device 1100 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 1150. Also, electronic device 1100 can communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 1160. As shown, network adapter 1160 communicates with other modules of electronic device 1100 via bus 1130. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 1100, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.
In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.
The program product for implementing the above-described method according to an embodiment of the present invention may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a 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.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is 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 (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with 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 readable signal medium may also be any readable medium that is not a 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 readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
Furthermore, the above-described drawings are only schematic illustrations of processes included in the method according to the exemplary embodiment of the present invention, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (10)
1. The implementation method of the electronic manual is characterized by comprising the following steps of:
acquiring application attribute information of an electronic manual to be generated;
determining a scene document corresponding to the electronic manual according to the application attribute information;
invoking context information and a large language identification model corresponding to the scene document;
and generating the electronic manual according to the context information, the scene document and the language identification model.
2. The method for implementing an electronic manual according to claim 1, further comprising, before determining a corresponding scene document in said pre-stored document database according to said application attribute information:
acquiring maintenance record information, wherein the maintenance record information comprises at least one of a historical maintenance record, a maintenance manual and a service manual;
extracting a theme, keywords and text content according to the maintenance record information;
and vectorizing the topics, keywords and text contents stored in the specified format, and storing the vectorized topics, keywords and text contents in a search engine.
3. The method for implementing an electronic manual according to claim 2, further comprising:
acquiring expert experience document records corresponding to the maintenance record information;
the document database is generated from the search engine and the expert experience document record.
4. The method for implementing an electronic manual of claim 3, further comprising:
receiving feedback information of a client applying the electronic manual;
and correcting the expert experience document record according to the feedback information.
5. The method for implementing an electronic manual according to claim 2, further comprising:
invoking LangChain to process the topics, keywords and text content stored in the search engine to generate a question-answer sample for training an original language recognition model;
training the original language identification model based on the question-answer samples;
and determining the language identification model according to the plurality of trained original language identification models.
6. The method of claim 5, wherein invoking LangChain to process the topics, keywords, and text content stored to the search engine to generate a question-answer sample for training an original language recognition model comprises:
invoking Langchain to index the topics, the keywords and the text content stored in the search engine so as to determine corresponding question text vectors, a specified number of answer text vectors matched with the question text vectors and context information related to the answer text vectors in the scene document;
and generating the question-answer sample according to the question text vector, the answer text vector and the context information.
7. The method for implementing an electronic manual according to claim 5 or 6, further comprising:
and modifying training parameters of the original language identification model by adopting the Lora fine tuning model, wherein the training parameters comprise training times and/or learning rate.
8. An implementation device of an electronic manual, comprising:
the acquisition module is used for acquiring application attribute information of the electronic manual to be generated;
the determining module is used for determining a scene document corresponding to the electronic manual according to the application attribute information;
the calling module is used for calling the context information and the large language identification model corresponding to the scene document;
a generation module arranged to generate the electronic manual from the context information, the scene document and the language identification model.
9. An electronic device, comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the method of implementing the electronic manual of any of claims 1-7 based on instructions stored in the memory.
10. A computer-readable storage medium having stored thereon a program which, when executed by a processor, implements a method of implementing an electronic manual according to any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311265953.6A CN117252163A (en) | 2023-09-27 | 2023-09-27 | Implementation method and device of electronic manual, electronic equipment and readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311265953.6A CN117252163A (en) | 2023-09-27 | 2023-09-27 | Implementation method and device of electronic manual, electronic equipment and readable medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117252163A true CN117252163A (en) | 2023-12-19 |
Family
ID=89134658
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311265953.6A Pending CN117252163A (en) | 2023-09-27 | 2023-09-27 | Implementation method and device of electronic manual, electronic equipment and readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117252163A (en) |
-
2023
- 2023-09-27 CN CN202311265953.6A patent/CN117252163A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11816439B2 (en) | Multi-turn dialogue response generation with template generation | |
CN115438176B (en) | Method and equipment for generating downstream task model and executing task | |
CN111666416B (en) | Method and device for generating semantic matching model | |
US10977155B1 (en) | System for providing autonomous discovery of field or navigation constraints | |
WO2023201975A1 (en) | Difference description sentence generation method and apparatus, and device and medium | |
CN116820429B (en) | Training method and device of code processing model, electronic equipment and storage medium | |
CN111930914A (en) | Question generation method and device, electronic equipment and computer-readable storage medium | |
CN117370373A (en) | Data processing method, device, electronic equipment and storage medium | |
US8315874B2 (en) | Voice user interface authoring tool | |
US20210233520A1 (en) | Contextual multi-channel speech to text | |
US20220027768A1 (en) | Natural Language Enrichment Using Action Explanations | |
CN113051895A (en) | Method, apparatus, electronic device, medium, and program product for speech recognition | |
WO2024073087A1 (en) | Revision of and attribution for output of text generation models | |
CN117521625A (en) | Question answering method, question answering device, electronic equipment and medium | |
CN112329429B (en) | Text similarity learning method, device, equipment and storage medium | |
US20240020538A1 (en) | Systems and methods for real-time search based generative artificial intelligence | |
CN117009113A (en) | Method and device for calling artificial intelligent model, computer equipment and storage medium | |
CN116909435A (en) | Data processing method and device, electronic equipment and storage medium | |
JP2023002475A (en) | Computer system, computer program and computer-implemented method (causal knowledge identification and extraction) | |
CN114626388A (en) | Intention recognition method and device, electronic equipment and storage medium | |
CN117252163A (en) | Implementation method and device of electronic manual, electronic equipment and readable medium | |
CN112749553A (en) | Text information processing method and device for video file and server | |
CN113343668B (en) | Method and device for solving selected questions, electronic equipment and readable storage medium | |
CN116776870B (en) | Intention recognition method, device, computer equipment and medium | |
CN113761157B (en) | Method and device for generating answer sentence |
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 |