Intelligent question-answering method, device and equipment for safe production of power plant and storage medium
Through intelligent question-and-answer method, large language models are used to generate replies, which solves the problem of insufficient employee experience accumulation in power plant safety production and improves the stability of power plant safety production.
Patent Information
- Application Number
- CN202411695764.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-25
- Publication Date
- 2025-03-18
Smart Images
Figure CN119646148A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart power plants, and in particular to an intelligent question-and-answer method, device, equipment and storage medium for safe production in power plants. Background Art
[0002] With the development of science and technology, all kinds of equipment need electricity to drive. As the manufacturer and storage of electric energy, the stability and efficiency of the operation of power plants are of paramount importance. However, the working environment inside power plants is complex and densely populated. The staff have little experience in dealing with various working conditions and mainly rely on old employees to teach, thereby promoting the rapid growth of new employees. However, this method requires a lot of energy and cannot determine whether there are omissions. The learning efficiency of new employees is low, which affects the stability of power plant safety production.
[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention
[0004] The main purpose of the present invention is to provide an intelligent question-and-answer method, device, equipment and storage medium for power plant safety production, aiming to solve the technical problem in the prior art that employees have little experience in power plant safety production, which reduces the stability of power plant safety production.
[0005] To achieve the above object, the present invention provides an intelligent question-answering method for power plant safety production, the method comprising the following steps:
[0006] Receive user's question request;
[0007] Extracting keywords from the question request;
[0008] Reconstruct the question according to the keyword to obtain at least one question information;
[0009] Performing structural analysis on each question information and the question request to obtain a similarity parameter between each question information and the question request;
[0010] Determine target question information among each question information according to the similarity parameter;
[0011] The target question information is respectively input into the trained large language model to obtain target answer information, and the target answer information is used to provide auxiliary explanation of the question request.
[0012] Optionally, reconstructing the question according to the keyword to obtain at least one question information includes:
[0013] When it is detected that the keyword triggers the preset intelligent question and answer condition, extracting a target keyword from the keyword, wherein the target keyword is the remaining keyword other than the keyword that triggers the preset intelligent question and answer condition;
[0014] Expanding the meaning of the target keyword to obtain a target keyword sequence;
[0015] Keyword reorganization is performed based on the target keyword sequence to obtain at least one question information.
[0016] Optionally, the performing semantic expansion on the target keyword to obtain a target keyword sequence includes:
[0017] Performing semantic analysis on the target keyword to obtain a vector representation of the target keyword;
[0018] Searching for candidate vector representations and candidate synonyms that have at least one dimension of the same attribute as the vector representation through a power plant safety production dictionary;
[0019] Determining similarity parameters between the candidate synonyms and the target keyword, and determining a target synonym based on the similarity parameters;
[0020] The target keyword and the target synonym are associated to obtain a target keyword sequence.
[0021] Optionally, performing structural analysis on each piece of question information and the question request to obtain a similarity parameter between each piece of question information and the question request includes:
[0022] Extracting each question information and keywords of the question request respectively;
[0023] Convert each question information and the keywords of the question request into corresponding vector representations respectively;
[0024] Generate a first text vector representation of each question information and a second text vector representation of the question request according to the vector representation of the keywords of each question information and the question request;
[0025] The vector representation similarity is calculated according to the first text vector representation and the second text vector representation to obtain a similarity parameter between each question information and the question request.
[0026] Optionally, calculating the vector representation similarity according to the first text vector representation and the second text vector representation includes:
[0027] Calculate a target Euclidean distance, a target cosine parameter, and a Jaccard similarity according to the first text vector representation and the second text vector representation;
[0028] Calculating the target Euclidean distance, target cosine parameter and similarity threshold corresponding to the Jaccard similarity;
[0029] The maximum value of the similarity threshold corresponding to the target Euclidean distance, the target cosine parameter and the Jaccard similarity is recorded as a vector representing the similarity.
[0030] Optionally, the intelligent question-answering method for power plant safety production further includes:
[0031] Determine the power plant equipment to be operated according to the target reply information;
[0032] The auxiliary operation information of the power plant equipment to be operated is determined according to the power plant safety production management regulations, and the auxiliary operation information at least includes precautions, operation procedures and accident handling procedures of the equipment to be operated.
[0033] In addition, to achieve the above-mentioned purpose, the present invention also proposes an intelligent question-answering device for power plant safety production, the intelligent question-answering device for power plant safety production comprising:
[0034] A monitoring module, used for receiving a user's question request;
[0035] An extraction module, used to extract keywords from the question request;
[0036] A reconstruction module, used to reconstruct the question according to the keyword to obtain at least one question information;
[0037] An analysis module, used to perform structural analysis on each question information and the question request to obtain a similarity parameter between each question information and the question request;
[0038] A determination module, used for determining target question information among each question information according to the similarity parameter;
[0039] The question-answering module is used to input the target question information into the trained large language model respectively to obtain target answer information, and the target answer information is used to provide auxiliary explanation of the question request.
[0040] In addition, to achieve the above-mentioned purpose, the present invention also proposes an intelligent question and answer device for power plant safety production, the intelligent question and answer device for power plant safety production comprising: a memory, a processor, and an intelligent question and answer program for power plant safety production stored in the memory and executable on the processor, the intelligent question and answer program for power plant safety production being configured to implement the steps of the intelligent question and answer method for power plant safety production as described above.
[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which is stored an intelligent question and answer program for power plant safety production, and when the intelligent question and answer program for power plant safety production is executed by a processor, the steps of the intelligent question and answer method for power plant safety production as described above are implemented.
[0042] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the intelligent question-and-answer method for power plant safety production as described above.
[0043] One or more technical solutions proposed in the present invention have at least the following technical effects: the present invention discloses an intelligent question-answering method for power plant safety production, the intelligent question-answering method for power plant safety production comprising: receiving a user's question request; extracting keywords in the question request; reconstructing questions according to the keywords to obtain at least one question information; performing structural analysis on each question information and the question request to obtain a similarity parameter between each question information and the question request; determining target question information in each question information according to the similarity parameter; inputting the target question information into a trained large language model to obtain target reply information. Compared with the prior art, the present invention detects the user's question request and reconstructs the question request based on keywords in the user's question request to improve the breadth of the user's questions, and then performs structural analysis on the reconstructed question information and the question request to determine the most likely target question based on the similarity between each question information and the question request, thereby improving the recognition of the user's questions, and finally generates corresponding reply information through the trained large language model, thereby providing relevant auxiliary explanations for the question request issued by the user, solving the questions given by the user during the production process of the power plant, and avoiding the technical problems in the prior art that the employees have low experience in power plant safety production accumulation and the stability of power plant safety production is reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0046] Figure 1 A schematic flow chart of a first embodiment of an intelligent question-answering method for power plant safety production according to the present invention;
[0047] Figure 2 A flow chart of a second embodiment of the intelligent question-answering method for power plant safety production according to the present invention;
[0048] Figure 3 A structural block diagram of the first embodiment of the intelligent question-answering device for power plant safety production according to the present invention;
[0049] Figure 4 It is a structural diagram of an intelligent question-and-answer device for power plant safety production in a hardware operating environment involved in an embodiment of the present invention.
[0050] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0051] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0053] Based on this, the embodiment of the present invention provides an intelligent question-answering method for power plant safety production, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of an intelligent question-answering method for power plant safety production according to the present invention.
[0054] In this embodiment, the intelligent question-answering method for power plant safety production includes:
[0055] Step S10: receiving a user's question request.
[0056] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, an intelligent question and answer system for power plant safety production, etc. The following takes the intelligent question and answer system for power plant safety production as an example to illustrate this embodiment and the following embodiments.
[0057] It should be noted that the user's question request can be a question text input based on the intelligent question and answer platform, or it can be an audio signal collected by a sound collection device. Different forms of question requests will be uniformly converted into text format to facilitate subsequent keyword extraction and question reconstruction, thereby improving the universality of intelligent question and answer.
[0058] Step S20: extracting keywords from the question request.
[0059] After the user's question request is converted into text format, the natural language processing model can be used to identify characters or words with special meanings in the text, thereby identifying the user's intention. In the process of extracting keywords, some character groups or words that have no effect on the text can be eliminated based on part of speech, context connection relationship, etc. For example: for the question text of "How can I quickly restart the steam turbine?", the keywords are "quickly", "restart", and "steam turbine", and other characters are invalid characters and can be eliminated.
[0060] Step S30: Reconstruct the question according to the keyword to obtain at least one question information.
[0061] It can be understood that question reconstruction refers to reconstructing the question text through words with similar meanings to the extracted keywords, thereby optimizing the query expression effect of the text and improving the efficiency and accuracy of the answers given by the model to meet the user's question request.
[0062] Step S40: Perform structural analysis on each piece of question information and the question request to obtain a similarity parameter between each piece of question information and the question request.
[0063] Structural analysis of the reconstructed question information and the user's original question request can be performed to calculate the similarity between each question information and the question request, thereby eliminating questions that do not conform to the original meaning after question reconstruction. In particular, for keywords with multiple meanings, similar keywords with different meanings may be generated in different fields, which may cause the generated question information to deviate too much from the user's original question request when the question is reconstructed.
[0064] Step S50: determining target question information among each question information according to the similarity parameter.
[0065] By comparing the similarity parameters of each question information and question request with the preset threshold, several question information with greater similarity are extracted as target question information, thereby improving the accuracy of subsequent model query answers.
[0066] Step S60: input the target question information into the trained large language model respectively to obtain target answer information, and the target answer information is used to provide auxiliary explanation of the question request.
[0067] It is understandable that the trained large language model can be a large prediction model (LLM) based on artificial intelligence, or it can be other models that can achieve the same or similar functions, thereby solving user questions or providing problem solutions.
[0068] Furthermore, the intelligent question-answering method for power plant safety production also includes:
[0069] Determine the power plant equipment to be operated according to the target reply information;
[0070] The auxiliary operation information of the power plant equipment to be operated is determined according to the power plant safety production management regulations, and the auxiliary operation information at least includes precautions, operation procedures and accident handling procedures of the equipment to be operated.
[0071] In the specific implementation, in the power plant environment, only relevant operating standards or questions within the power plant will be answered. After the intelligent question-and-answer platform gives auxiliary explanations based on the user's question request, it can further provide power plant equipment related to the question request and provide auxiliary operating information for the equipment to be operated, thereby reducing the risk of improper operation of the equipment due to unclear equipment precautions, operating procedures, etc., and providing equipment accident handling procedures to reduce losses caused by accidents and create a safe production environment for power plants.
[0072] This embodiment detects the user's question request and reconstructs the question request based on the keywords in the user's question request to improve the breadth of the user's question. Then, by structurally analyzing the reconstructed question information and the question request, the most likely target question is determined based on the similarity between each question information and the question request, thereby improving the recognition of the user's question. Finally, the corresponding reply information is generated through the trained large language model, thereby providing relevant auxiliary explanations for the question request issued by the user, solving the questions raised by the user in the production process of the power plant, and avoiding the technical problem in the prior art that the employees have little experience in power plant safety production and reduce the stability of power plant safety production.
[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S30, comprising:
[0074] Step S301: when it is detected that the keyword triggers the preset intelligent question and answer condition, a target keyword is extracted from the keyword, where the target keyword is the remaining keyword other than the keyword that triggers the preset intelligent question and answer condition.
[0075] Step S302: Expand the meaning of the target keyword to obtain a target keyword sequence.
[0076] Step S303: reorganize keywords based on the target keyword sequence to obtain at least one question information.
[0077] It should be noted that the preset intelligent question and answer conditions can be specific keywords related to power plant safety production. For example, the keywords contain "electricity", "specific equipment name" or specific names, etc., so as to avoid false triggering when the intelligent question and answer platform is awakened by voice, affecting the effective use rate of the intelligent question and answer platform.
[0078] Expanding the meaning of keywords refers to the way of changing keywords to another field or another meaning through word meaning evolution, semantic analysis, word embedding technology, vocabulary derivation, cognitive mechanism, semantic extension, root and affix memory method, etc. Specifically, taking a balloon as an example, the balloon is expanded in shape to a sphere, and then expanded in component to an air bag or air bag, and expanded in vocabulary derivation to anger, etc. This embodiment does not make any specific restrictions on this.
[0079] After the keyword is expanded, the derivative words of the same keyword are summarized and added to the keyword sequence corresponding to the keyword. When the keyword is reorganized, at least one derivative word is replaced with the keyword to form a new question. For example, how to make a balloon fly? By replacing the balloon with a sphere, the question information after question reconstruction can be how to make the sphere fly.
[0080] Further, the word expansion of the target keyword to obtain a target keyword sequence includes:
[0081] Performing semantic analysis on the target keyword to obtain a vector representation of the target keyword;
[0082] Searching for candidate vector representations and candidate synonyms that have at least one dimension of the same attribute as the vector representation through a power plant safety production dictionary;
[0083] Determining similarity parameters between the candidate synonyms and the target keyword, and determining a target synonym based on the similarity parameters;
[0084] The target keyword and the target synonym are associated to obtain a target keyword sequence.
[0085] It should be noted that performing semantic analysis on the target keyword to obtain the vector representation of the target keyword can be performed by converting each target keyword into a vector through a trained Word2Vec model, thereby obtaining the vector representation of the target keyword.
[0086] The power plant safety production dictionary records the vector representations of various equipment and operations in the power plant safety production process. The extracted keywords may contain words that are not applied to the power plant safety production process, resulting in the corresponding vector representation in the subsequent similarity calculation process. Will seriously affect the result of similarity judgment. Therefore, this embodiment uses the power plant safety production dictionary to query candidate vector representations and candidate synonyms that have at least one dimension with the vector representation. The same attribute improves the accuracy and professionalism of the similarity calculation. The at least one dimension mentioned above includes but is not limited to attributes, parts of speech, reference features, and contextual associations.
[0087] Determining the target synonym according to the similarity parameter may be taking the candidate synonym with the largest similarity parameter as the target synonym, thereby improving the association between the synonym and the safe production of the power plant.
[0088] Accordingly, the step S40 includes:
[0089] S401: extracting each question information and keywords of the question request respectively.
[0090] S402: Convert each piece of question information and the keywords of the question request into corresponding vector representations respectively.
[0091] S403: Generate a first text vector representation of each question information and a second text vector representation of the question request according to the vector representation of each question information and the keyword of the question request.
[0092] S404: Calculate vector representation similarity according to the first text vector representation and the second text vector representation to obtain similarity parameters between each question information and the question request.
[0093] It should be noted that the specific process of generating the vector representation of the question text based on the vector representation of the keyword can be to weight each keyword according to the defect and inverse document frequency of each keyword in the question text, so as to combine the weight and vector representation of each keyword to calculate the vector representation of each question text, specifically:
[0094] TF-IDF(t,d)=TF(t,d)×IDF(t)
[0095] Among them, TF is the word frequency of the keyword in the question text, and IDF is the inverse document frequency of the keyword in the question text.
[0096]
[0097] Among them, n t,d is the number of times keyword t appears in question document d, and N is the total number of words in question document d.
[0098]
[0099] Where N is the total number of documents in the corpus and |d∈D:t∈d||d∈D:t∈d| is the number of documents containing keyword t.
[0100] Further, the calculating the vector representation similarity according to the first text vector representation and the second text vector representation includes:
[0101] Calculate a target Euclidean distance, a target cosine parameter, and a Jaccard similarity according to the first text vector representation and the second text vector representation;
[0102] Calculating the target Euclidean distance, target cosine parameter and similarity threshold corresponding to the Jaccard similarity;
[0103] The maximum value of the similarity threshold corresponding to the target Euclidean distance, the target cosine parameter and the Jaccard similarity is recorded as a vector representing the similarity.
[0104] It should be noted that the method used to calculate the similarity of keywords is different from the method used to calculate the similarity between texts. The specific reason is that the similarity of keywords is affected by their context and context, and in the process of text vector conversion, the similarity corresponding to the question text will basically be covered by the vector representation of the keyword, and the variable is small. Therefore, in this embodiment, the target Euclidean distance, target cosine parameter and Jaccard similarity between the first text vector representation and the second text vector representation can be calculated respectively, and the maximum value of the three can be taken as the similarity parameter between each question information and the question request, so as to select the target question information and improve the question diversity after the question reconstruction.
[0105] This embodiment extracts target keywords from the keywords when it is detected that the keywords trigger the preset intelligent question and answer conditions, and the target keywords are the remaining keywords in the keywords other than those that trigger the preset intelligent question and answer conditions; performs word meaning expansion on the target keywords to obtain a target keyword sequence; performs keyword reorganization based on the target keyword sequence to obtain at least one question information, and extracts keywords of each question information and the question request respectively; converts the keywords of each question information and the question request into corresponding vector representations respectively; generates a first text vector representation of each question information and a second text vector representation of the question request according to the vector representations of the keywords of each question information and the question request; calculates the vector representation similarity according to the first text vector representation and the second text vector representation to obtain a similarity parameter of each question information and the question request, expands the keyword meaning, and reorganizes the questions based on the expanded keyword sequence to improve the diversity of questions, and then calculates the similarity between each question information and the question request, thereby narrowing the question and answer field, reducing invalid questions and answers, and better meeting the user's questioning needs.
[0106] This application also provides an intelligent question-and-answer device for power plant safety production, please refer to Figure 3 The intelligent question-answering device for power plant safety production includes:
[0107] The monitoring module 10 is used to receive a user's question request.
[0108] The extraction module 20 is used to extract keywords from the question request.
[0109] The reconstruction module 30 is used to reconstruct the question according to the keyword to obtain at least one question information.
[0110] The analysis module 40 is used to perform structural analysis on each question information and the question request to obtain a similarity parameter between each question information and the question request.
[0111] The determination module 50 is used to determine the target question information among the question information according to the similarity parameter.
[0112] The question-answering module 60 is used to input the target question information into the trained large language model to obtain target answer information.
[0113] This embodiment detects the user's question request and reconstructs the question request based on the keywords in the user's question request to improve the breadth of the user's question. Then, by structurally analyzing the reconstructed question information and the question request, the most likely target question is determined based on the similarity between each question information and the question request, thereby improving the recognition of the user's question. Finally, the corresponding reply information is generated through the trained large language model, thereby providing relevant auxiliary explanations for the question request issued by the user, solving the questions raised by the user in the production process of the power plant, and avoiding the technical problem in the prior art that the employees have little experience in power plant safety production and reduce the stability of power plant safety production.
[0114] In one embodiment, the reconstruction module 30 is also used to extract target keywords from the keywords when it is detected that the keywords trigger preset intelligent question and answer conditions, and the target keywords are the remaining keywords in the keywords other than those that trigger the preset intelligent question and answer conditions; expand the meaning of the target keywords to obtain a target keyword sequence; and reorganize keywords based on the target keyword sequence to obtain at least one question information.
[0115] In one embodiment, the reconstruction module 30 is also used to perform semantic analysis on the target keyword to obtain a vector representation of the target keyword; query the power plant safety production dictionary for candidate vector representations and candidate synonyms that have at least one dimension with the same attribute as the vector representation; determine similarity parameters between the candidate synonyms and the target keyword, and determine a target synonym based on the similarity parameters; and associate the target keyword with the target synonym to obtain a target keyword sequence.
[0116] In one embodiment, the analysis module 40 is further used to extract keywords of each question information and the question request respectively; convert the keywords of each question information and the question request into corresponding vector representations respectively; generate a first text vector representation of each question information and a second text vector representation of the question request according to the vector representations of the keywords of each question information and the question request; calculate the vector representation similarity according to the first text vector representation and the second text vector representation to obtain the similarity parameter of each question information and the question request.
[0117] In one embodiment, the analysis module 40 is also used to calculate the target Euclidean distance, target cosine parameter and Jaccard similarity based on the first text vector representation and the second text vector representation; calculate the similarity thresholds corresponding to the target Euclidean distance, target cosine parameter and Jaccard similarity; and record the maximum value of the similarity thresholds corresponding to the target Euclidean distance, target cosine parameter and Jaccard similarity as the vector representation similarity.
[0118] In one embodiment, the question and answer module 60 is also used to determine the power plant equipment to be operated based on the target answer information; determine the operation auxiliary information of the power plant equipment to be operated based on the power plant safety production management regulations, and the operation auxiliary information at least includes the precautions, operation procedures and accident handling procedures of the equipment to be operated.
[0119] The present application provides an intelligent question-and-answer device for power plant safety production, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent question-and-answer method for power plant safety production in the above-mentioned embodiment one.
[0120] Reference below Figure 4 , which shows a schematic diagram of the structure of an intelligent question-and-answer device suitable for realizing the safe production of a power plant in an embodiment of the present application. The intelligent question-and-answer device for safe production of a power plant in an embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The intelligent question-and-answer device for safe production in a power plant shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0121] like Figure 4As shown, the intelligent question-answering device for power plant safety production may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the intelligent question-answering device for power plant safety production are also stored in RAM1004. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the intelligent question-and-answer device for power plant safety production to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an intelligent question-and-answer device for power plant safety production with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.
[0122] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0123] The intelligent question-and-answer device for power plant safety production provided by this application adopts the intelligent question-and-answer method for power plant safety production in the above-mentioned embodiment, which can solve the technical problems of intelligent question-and-answer for power plant safety production. Compared with the prior art, the beneficial effects of the intelligent question-and-answer device for power plant safety production provided by this application are the same as the beneficial effects of the intelligent question-and-answer method for power plant safety production provided by the above-mentioned embodiment, and other technical features in the intelligent question-and-answer device for power plant safety production are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0124] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0125] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0126] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the intelligent question-and-answer method for power plant safety production in the above-mentioned embodiment.
[0127] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0128] The computer-readable storage medium may be included in the intelligent question-and-answer device for power plant safety production; or it may exist independently without being assembled into the intelligent question-and-answer device for power plant safety production.
[0129] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the intelligent question-and-answer device for power plant safety production, the intelligent question-and-answer device for power plant safety production becomes: intelligent question-and-answer for power plant safety production.
[0130] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0131] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0132] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0133] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned intelligent question-and-answer method for power plant safety production, and can solve the technical problems of intelligent question-and-answer for power plant safety production. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the intelligent question-and-answer method for power plant safety production provided in the above-mentioned embodiment, and will not be repeated here.
[0134] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the intelligent question-and-answer method for safe production of a power plant as described above.
[0135] The computer program product provided by this application can solve the technical problem of intelligent question-answering for power plant safety production. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the intelligent question-answering method for power plant safety production provided by the above embodiment, and will not be repeated here.
[0136] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. An intelligent question-answering method for power plant safety production, characterized in that: The intelligent question-answering method for power plant safety production includes: Receive user's question request; Extracting keywords from the question request; Reconstruct the question according to the keyword to obtain at least one question information; Performing structural analysis on each question information and the question request to obtain a similarity parameter between each question information and the question request; Determine target question information among each question information according to the similarity parameter; The target question information is respectively input into the trained large language model to obtain target answer information, and the target answer information is used to provide auxiliary explanation of the question request.
2. The method according to claim 1, characterized in that The step of reconstructing the question according to the keyword to obtain at least one question information includes: When it is detected that the keyword triggers the preset intelligent question and answer condition, extracting a target keyword from the keyword, wherein the target keyword is the remaining keyword other than the keyword that triggers the preset intelligent question and answer condition; Expanding the meaning of the target keyword to obtain a target keyword sequence; Keyword reorganization is performed based on the target keyword sequence to obtain at least one question information.
3. The method according to claim 2, characterized in that The step of performing word expansion on the target keyword to obtain a target keyword sequence includes: Performing semantic analysis on the target keyword to obtain a vector representation of the target keyword; Searching for candidate vector representations and candidate synonyms that have at least one dimension of the same attribute as the vector representation through a power plant safety production dictionary; Determining similarity parameters between the candidate synonyms and the target keyword, and determining a target synonym based on the similarity parameters; The target keyword and the target synonym are associated to obtain a target keyword sequence.
4. The method according to claim 1, characterized in that The structural analysis of each question information and the question request is performed to obtain similarity parameters between each question information and the question request, including: Extracting each question information and keywords of the question request respectively; Convert each question information and the keywords of the question request into corresponding vector representations respectively; Generate a first text vector representation of each question information and a second text vector representation of the question request according to the vector representation of the keywords of each question information and the question request; The vector representation similarity is calculated according to the first text vector representation and the second text vector representation to obtain a similarity parameter between each question information and the question request.
5. The method according to claim 4, characterized in that The calculating the vector representation similarity according to the first text vector representation and the second text vector representation comprises: Calculate a target Euclidean distance, a target cosine parameter, and a Jaccard similarity according to the first text vector representation and the second text vector representation; Calculating the target Euclidean distance, target cosine parameter and similarity threshold corresponding to the Jaccard similarity; The maximum value of the similarity threshold corresponding to the target Euclidean distance, the target cosine parameter and the Jaccard similarity is recorded as a vector representing the similarity.
6. The method according to claim 1, characterized in that The intelligent question-answering method for power plant safety production also includes: Determine the power plant equipment to be operated according to the target reply information; The auxiliary operation information of the power plant equipment to be operated is determined according to the power plant safety production management regulations, and the auxiliary operation information at least includes precautions, operation procedures and accident handling procedures of the equipment to be operated.
7. An intelligent question-answering device for power plant safety production, characterized in that: The intelligent question-answering device for power plant safety production comprises: A monitoring module, used for receiving a user's question request; An extraction module, used to extract keywords from the question request; A reconstruction module, used to reconstruct the question according to the keyword to obtain at least one question information; An analysis module, used to perform structural analysis on each question information and the question request to obtain a similarity parameter between each question information and the question request; A determination module, used for determining target question information among each question information according to the similarity parameter; The question-answering module is used to input the target question information into the trained large language model respectively to obtain target answer information, and the target answer information is used to provide auxiliary explanation of the question request.
8. An intelligent question-answering device for power plant safety production, characterized in that: The intelligent question-and-answer device for power plant safety production includes: a memory, a processor, and an intelligent question-and-answer program for power plant safety production stored in the memory and executable on the processor, wherein the intelligent question-and-answer program for power plant safety production is configured to implement the steps of the intelligent question-and-answer method for power plant safety production as described in any one of claims 1 to 6.
9. A storage medium, characterized in that: The storage medium stores an intelligent question-and-answer program for power plant safety production, which, when executed by a processor, implements the steps of the intelligent question-and-answer method for power plant safety production as described in any one of claims 1 to 6.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the intelligent question-answering method for safe production of a power plant according to any one of claims 1 to 6 are implemented.