Operation and maintenance strategy determination method and device, equipment, readable storage medium and product
By performing semantic recognition and similarity analysis on operation and maintenance data, operation and maintenance strategies based on reference keywords are determined, which solves the problem that AI chatbots have difficulty understanding user intent and improves the reliability and efficiency of operation and maintenance operations.
Patent Information
- Application Number
- CN202410920982.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2024-11-22
AI Technical Summary
Existing AI chatbots based on operation and maintenance tasks lack human-like interaction, struggle to accurately understand user intent, and thus reduce reliability.
By performing semantic recognition on the operation and maintenance data to be processed for the faulty subject, keywords are determined, and reference keywords are determined based on the similarity between the keywords and preset keywords. Combined with the operation and maintenance strategies corresponding to the reference keywords, the target operation and maintenance strategy is determined.
It improves the reliability of AI chatbots in operation and maintenance tasks, and enhances the accuracy and efficiency of user interaction through precise operation and maintenance strategy determination.
Smart Images

Figure CN119005181A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device, equipment, readable storage medium and product for determining an operation and maintenance strategy. Background Art
[0002] With the rapid development of artificial intelligence technology, artificial intelligence (AI) conversational robots have emerged. AI conversational robots are based on artificial intelligence technology and are designed to provide users with intelligent conversational interactions. AI conversational robots allow users to communicate with AI robots through natural language.
[0003] At present, there are AI dialogue robots based on operation and maintenance operations. These AI dialogue robots are designed to assist users in completing operation and maintenance tasks through AI dialogue. However, the existing AI dialogue robots based on operation and maintenance operations lack humanized interaction and are difficult to accurately understand user intentions, which reduces the reliability of these AI dialogue robots. Summary of the invention
[0004] Based on this, it is necessary to provide an operation and maintenance strategy determination method, device, equipment, readable storage medium and product to address the above-mentioned technical problems, which can improve the reliability of AI dialogue robots implemented based on operation and maintenance operations.
[0005] In a first aspect, the present application provides a method for determining an operation and maintenance strategy, comprising:
[0006] Performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed;
[0007] For any keyword, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword;
[0008] According to the operation and maintenance strategy corresponding to the reference keyword, determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0009] In one embodiment, determining a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the operation and maintenance strategy corresponding to the reference keyword includes:
[0010] The operation and maintenance strategy corresponding to the reference keyword is used as the reference operation and maintenance strategy corresponding to the keyword;
[0011] According to at least one reference operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0012] In one of the embodiments, determining a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to at least one reference operation and maintenance strategy includes:
[0013] Combining the reference operation and maintenance strategies corresponding to at least one keyword to obtain at least one candidate operation and maintenance strategy corresponding to the operation and maintenance data to be processed;
[0014] According to the operation and maintenance data to be processed and at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0015] In one of the embodiments, determining a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the operation and maintenance data to be processed and at least one candidate operation and maintenance strategy includes:
[0016] Determine the current status of the fault subject based on the operation and maintenance data to be processed;
[0017] According to the current state of the fault subject and at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0018] In one of the embodiments, determining a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the current state of the fault subject and at least one candidate operation and maintenance strategy includes:
[0019] According to the current state of the fault subject, at least one candidate operation and maintenance strategy is adjusted to obtain at least one adjusted candidate operation and maintenance strategy;
[0020] According to the matching degree between each adjusted candidate operation and maintenance strategy and the operation and maintenance target data, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined; wherein the operation and maintenance target data is extracted from the operation and maintenance data to be processed.
[0021] In one of the embodiments, semantic recognition is performed on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed, including:
[0022] Obtain the original operation and maintenance data of the fault subject;
[0023] Convert the format of the original operation and maintenance data to obtain the operation and maintenance data to be processed;
[0024] The operation and maintenance data to be processed is segmented to obtain at least two segmented words, and at least one keyword in the operation and maintenance data to be processed is determined according to the association relationship between the segmented words.
[0025] In a second aspect, the present application also provides an operation and maintenance strategy determination device, including:
[0026] A keyword determination module, used to perform semantic recognition on the operation and maintenance data to be processed of the fault subject, and obtain at least one keyword in the operation and maintenance data to be processed;
[0027] A reference keyword determination module, for determining the similarity between any keyword and different preset keywords, and taking the preset keywords with a similarity greater than a preset threshold as reference keywords of the keyword;
[0028] The operation and maintenance strategy determination module is used to determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the operation and maintenance strategy corresponding to the reference keyword.
[0029] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0030] Performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed;
[0031] For any keyword, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword;
[0032] According to the operation and maintenance strategy corresponding to the reference keyword, determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:
[0034] Performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed;
[0035] For any keyword, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword;
[0036] According to the operation and maintenance strategy corresponding to the reference keyword, determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0037] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0038] Performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed;
[0039] For any keyword, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword;
[0040] According to the operation and maintenance strategy corresponding to the reference keyword, determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0041] The above-mentioned operation and maintenance strategy determination method, device, equipment, readable storage medium and product, in the process of determining the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed, determine the reference keyword corresponding to the keyword based on the similarity between at least one keyword in the operation and maintenance data to be processed and different preset keywords. Further, based on the operation and maintenance strategy corresponding to the reference keyword, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined. Since the operation and maintenance strategy corresponding to the reference keyword is relatively accurate, determining the target operation and maintenance strategy based on the operation and maintenance strategy corresponding to the reference keyword can improve the accuracy of the target operation and maintenance strategy. In other words, the entire process can improve the reliability of the AI dialogue robot implemented based on the operation and maintenance operation. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0043] Figure 1 A schematic diagram of a flow chart of a method for determining an operation and maintenance strategy in an embodiment;
[0044] Figure 2 A flowchart of steps for determining a target operation and maintenance strategy in one embodiment;
[0045] Figure 3 A flowchart of a keyword determination step in one embodiment;
[0046] Figure 4A A schematic diagram of an operation and maintenance strategy determination system in one embodiment;
[0047] Figure 4B A flowchart of a method for determining an operation and maintenance strategy in another embodiment;
[0048] Figure 5 It is a structural block diagram of an operation and maintenance strategy determination device in one embodiment;
[0049] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0051] In one embodiment, Figure 1 As shown, a method for determining an operation and maintenance strategy is provided. This embodiment uses the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:
[0052] S110, performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed.
[0053] The fault subject may be a device that currently has a fault maintenance requirement, and the pending maintenance data may include the historical maintenance records, current operating status, and fault description information of the fault subject. Keywords in the pending maintenance data can briefly describe the pending maintenance data.
[0054] Exemplarily, in this embodiment, the data to be processed can be input into a pre-trained semantic recognition model to obtain at least one keyword in the operation and maintenance data to be processed. Among them, the semantic recognition model can be a conventional semantic recognition model, and exemplarily, it can be constructed based on a common neural network, which is not described here. Furthermore, in the process of training the semantic recognition model, sample data can be input into the semantic recognition model to obtain predicted keywords corresponding to the sample data. According to the predicted keywords and the keyword labels of the sample data, the model parameters of the semantic recognition model are adjusted to improve the model accuracy of the semantic recognition model.
[0055] S120: for any keyword, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset similarity threshold as reference keywords for the keyword.
[0056] The preset keywords may be words pre-stored in a specified location, and each preset keyword corresponds to a corresponding operation and maintenance strategy. The preset similarity threshold may be determined based on manual experience or through a large number of experiments, and there is no limitation on this. The reference keywords may be used to determine the operation and maintenance strategy corresponding to the keywords.
[0057] Exemplarily, in this embodiment, keywords and different preset keywords can be input into a pre-trained reference keyword determination model to obtain a reference keyword corresponding to the keyword. The reference keyword determination model can be constructed based on a common neural network, which will not be described in detail here. Further, in the process of training the reference keyword determination model, sample vocabulary and at least two preset vocabulary can be input into the reference keyword determination model to obtain a predicted reference vocabulary corresponding to the sample vocabulary. According to the predicted reference vocabulary and reference vocabulary label corresponding to the sample vocabulary, the model parameters of the reference keyword determination model are adjusted to improve the model accuracy of the reference keyword determination model.
[0058] For example, in this embodiment, at least two candidate keywords can be selected from different preset keywords based on manual experience, and further, the keyword and the candidate keywords are input into a pre-trained similarity determination model to obtain the similarity between the keyword and each candidate keyword. Further, the candidate keywords whose similarity is greater than a preset similarity threshold are used as reference keywords of the keyword.
[0059] S130, determining a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the operation and maintenance strategy corresponding to the reference keyword.
[0060] Exemplarily, in this embodiment, each preset keyword can be stored in the form of a knowledge graph, and the knowledge graph not only stores the preset keywords, but also includes operation and maintenance strategies corresponding to the preset keywords.
[0061] In this embodiment, the operation and maintenance strategies corresponding to the reference keywords in the knowledge graph can be used as the operation and maintenance strategies corresponding to the corresponding keywords, and then the fusion results of the operation and maintenance strategies corresponding to the keywords can be used as the target operation and maintenance strategies corresponding to the operation and maintenance data to be processed.
[0062] In the above-mentioned operation and maintenance strategy determination method, in the process of determining the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed, the reference keyword corresponding to the keyword is determined based on the similarity between at least one keyword in the operation and maintenance data to be processed and different preset keywords. Furthermore, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined based on the operation and maintenance strategy corresponding to the reference keyword. Since the operation and maintenance strategy corresponding to the reference keyword is relatively accurate, determining the target operation and maintenance strategy based on the operation and maintenance strategy corresponding to the reference keyword can improve the accuracy of the target operation and maintenance strategy. In other words, the entire process can improve the reliability of the AI dialogue robot implemented based on the operation and maintenance operation.
[0063] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this embodiment, the process of determining the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is described in detail.
[0064] See also Figure 2 The steps for determining the target operation and maintenance strategy shown include:
[0065] S210: Using the operation and maintenance strategy corresponding to the reference keyword as the reference operation and maintenance strategy corresponding to the keyword.
[0066] The operation and maintenance strategies corresponding to different reference keywords may be predetermined and used to characterize the operation and maintenance strategies corresponding to the reference keywords. The reference operation and maintenance strategies may be operation and maintenance strategies that match the keywords. It is understandable that since the number of reference keywords corresponding to a keyword may not be unique, the number of reference operation and maintenance strategies corresponding to a keyword may not be unique.
[0067] In an optional implementation, for any keyword, the operation and maintenance strategies corresponding to the reference keywords of the keyword may be directly used as the reference operation and maintenance strategy corresponding to the keyword.
[0068] In an optional implementation, for any keyword, the matching degree between the operation and maintenance strategies corresponding to the reference keywords of the keyword can be determined, and the operation and maintenance strategy with a matching degree higher than the preset matching degree is used as the reference operation and maintenance strategy corresponding to the keyword. The matching degree between the keyword and the operation and maintenance strategy can be determined based on a preset matching degree determination model, which is not limited. The preset matching degree can be determined based on manual experience or through a large number of experiments, which is not limited.
[0069] S220: Determine a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to at least one reference operation and maintenance strategy.
[0070] The target operation and maintenance strategy may be an optimal operation and maintenance strategy corresponding to the keyword. Usually, the number of target operation and maintenance strategies may be one.
[0071] Exemplarily, in this embodiment, the sorting results of the reference operation and maintenance strategies corresponding to each keyword can be directly used as the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0072] In an optional implementation, the reference operation and maintenance strategies corresponding to at least one keyword may be combined to obtain at least one candidate operation and maintenance strategy corresponding to the operation and maintenance data to be processed; and the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed may be determined based on the operation and maintenance data to be processed and at least one candidate operation and maintenance strategy.
[0073] For example, if there are three keywords, and there are three reference operation and maintenance strategies corresponding to one keyword, then when the reference operation and maintenance strategies are combined, three cubed candidate operation and maintenance strategies can be obtained. Further, the similarity between the operation and maintenance data to be processed and each candidate operation and maintenance strategy is determined, and the candidate operation and maintenance strategy with a higher similarity, such as the highest similarity, is used as the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0074] In another optional implementation, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed can also be determined in the following manner: based on the operation and maintenance data to be processed, determine the current state of the fault subject; based on the current state of the fault subject and at least one candidate operation and maintenance strategy, determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0075] Exemplarily, the current state of the fault subject can be directly reflected in the operation and maintenance data to be processed. In this embodiment, the current state of the fault subject can be extracted from the operation and maintenance data to be processed, and the candidate operation and maintenance strategy with a higher degree of match with the current state of the fault subject, for example, the highest candidate operation and maintenance strategy, is used as the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0076] Among them, the matching degree between the current state of the fault subject and each candidate operation and maintenance strategy can be determined based on a common matching degree determination model. This application does not impose any limitation on the construction method and training process of the matching degree determination model.
[0077] Exemplarily, at least one candidate operation and maintenance strategy can also be adjusted according to the current state of the fault subject to obtain at least one adjusted candidate operation and maintenance strategy; based on the degree of match between each adjusted candidate operation and maintenance strategy and the operation and maintenance purpose data, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined; wherein, the operation and maintenance purpose data is extracted from the operation and maintenance data to be processed, and is used to characterize the main fault causes to be processed of the fault subject described in the operation and maintenance data to be processed.
[0078] For example, based on manual experience, the current state of the fault subject can be analyzed, and each candidate operation and maintenance strategy can be adjusted to obtain at least one adjusted candidate operation and maintenance strategy. Further, the candidate operation and maintenance strategy with a higher degree of match with the operation and maintenance target data, such as the highest degree, is used as the target operation and maintenance strategy for the operation and maintenance data to be processed.
[0079] In the above embodiment, the determination steps of the target operation and maintenance strategy are described in detail, making the determination method of the target operation and maintenance strategy clearer. Further, in the process of determining the target operation and maintenance strategy, the operation and maintenance purpose data and current state of the fault subject are considered, which can make the target operation and maintenance strategy more accurate.
[0080] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this embodiment, the process of determining at least one keyword in the operation and maintenance data to be processed is described in detail.
[0081] See also Figure 3 The keyword determination steps shown include:
[0082] S310, obtaining original operation and maintenance data of the fault subject.
[0083] The original operation and maintenance data of the fault subject may be natural language data output by a user, and may be voice description data or text description data, for example, without limitation.
[0084] In this embodiment, when it is detected that the user inputs natural language data, the natural language data input by the user is used as the original operation and maintenance data of the fault subject.
[0085] S320, converting the format of the original operation and maintenance data to obtain operation and maintenance data to be processed.
[0086] Among them, the purpose of format conversion is to convert the data format of the original operation and maintenance data into processed data that can be recognized by the model, that is, the operation and maintenance data to be processed.
[0087] S330, performing word segmentation processing on the operation and maintenance data to be processed to obtain at least two word segmentation words, and determining at least one keyword in the operation and maintenance data to be processed according to the association relationship between the word segmentation words.
[0088] Exemplarily, the keyword determination step can be as follows: a. Text preprocessing: perform preprocessing operations such as word segmentation, removal of stop words and punctuation marks on the input text (i.e., original operation and maintenance data) to obtain the vocabulary set of the text; b. Graph construction: construct an undirected weighted graph based on the preprocessed vocabulary set, where each node in the graph represents a word and the edge represents the relationship between words; c. Calculate node importance: Calculate the importance score of the node using the idea of the PageRank algorithm. Initially, all nodes are assigned the same weight value. Then iteratively calculate the score of each node until convergence; d. Extract keywords: According to the score of the node, select the node with a higher score as the keyword.
[0089] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this embodiment, the operation and maintenance strategy determination method provided by the present application is described in detail.
[0090] See also Figure 4AThe operation and maintenance strategy determination system shown includes a human-computer interaction interface module, an intelligent recommendation module, and a learning and optimization module. The output end of the human-computer interaction interface module is connected to the natural language processing module, and the output end of the natural language processing module is connected to the semantic recognition module. The AI dialogue robot system implemented by the operation and maintenance operation can help the system understand the semantics and intentions of the user input more accurately by setting up the semantic recognition module, making the dialogue robot system more intelligent, enabling the system to capture user needs more quickly and provide corresponding solutions, thereby improving interaction efficiency and response speed. It can also enable the system to communicate with users more flexibly and intelligently, and provide services that are more in line with user expectations, thereby improving user experience.
[0091] Among them, the human-computer interaction interface module includes a text interaction interface module and a voice interaction interface module, and the natural language processing module includes a voice recognition module, a semantic understanding module, and a named entity recognition module. The semantic recognition module includes a semantic classification module, a slot filling module, a context understanding module, a keyword extraction module, and a semantic similarity calculation module. The dialogue management module includes an intention recognition module and a dialogue flow management module, and the knowledge graph module includes a knowledge base management module and a data extraction module. The intelligent recommendation module includes an intelligent recommendation module and a best practice module, and the learning and optimization module includes a data collection module and a model training module.
[0092] Furthermore, the semantic classification module adopts the support vector machine algorithm, and its specific algorithm steps are as follows: a. Collect training data sets and mark the category of each sample; b. Feature preprocessing: convert sample features into a suitable representation for SVM processing; c. According to the training data set, construct a hyperplane in the feature space to maximize the interval between samples of different categories; d. Optimization problem: use soft interval or hard interval to solve the optimization problem of SVM by minimizing the objective function; e. Find the optimal solution: find the optimal solution of the hyperplane by solving the convex quadratic programming problem or using an optimization algorithm; f. Classification and prediction: classify and predict new samples based on the found hyperplane and the support vector of the training data set.
[0093] The slot filling module adopts dependency syntactic analysis, and its analysis steps are as follows: a. Part-of-speech tagging: First, each word in the input sentence is tagged with the part-of-speech to determine the part-of-speech information of each word; b. Syntactic arc annotation: According to the part-of-speech of the words in the sentence, a dependency tree is constructed. For each word, the dependency relationship between it and other words is annotated to form a syntactic arc; c. Dependency parsing: Parse the syntactic arc to generate a complete dependency tree, which is completed through the transfer-reduce algorithm. Its working principle is as follows: Input: part-of-speech tags and syntactic arc tags; Initialization: All words are initialized as items in the buffer; Iteration: Repeat the following steps until the dependency parsing is completed: Select the action to be performed based on the current state, execute the selected action, and update the stack and buffer; Output: The generated dependency tree; d. Representation of parsing results: Represent the dependency tree as a tree structure or a graph structure for further analysis and application.
[0094] The context understanding module adopts a rule-based matching algorithm, and its algorithm steps are as follows: a. Define rules: First, a set of rules needs to be defined. These rules describe various scenarios that may appear in the conversation and their processing logic. The rules can be defined based on context, intent, entity and other information; b. Build a state machine: According to the defined rules, a finite state machine is constructed. The state machine consists of states and transitions. Each state represents a specific stage or condition of the system conversation, and the transition represents the switching condition between different states; c. Parse input: When the system receives user input, it passes the input to the context understanding module. The module tries to match the current input and context information with the predefined rules based on the current conversation state and rule definition; d. Rule matching: Use the rule matching algorithm to match the user input to determine whether the input conforms to the rules in the current state. If the match is successful, the corresponding operation is performed; if the match fails, the corresponding error handling measures are performed according to the rules or the user is prompted to provide more information; e. Status update: According to the matching results, the system status is updated and the conversation process continues. According to the matching situation, it is decided whether it is necessary to further obtain user information, perform specific operations or generate replies.
[0095] The keyword extraction module uses the TextRank algorithm, and its algorithm steps are as follows: a. Text preprocessing: perform preprocessing operations such as word segmentation, removal of stop words and punctuation marks on the input text to obtain the vocabulary set of the text; b. Graph construction: construct an undirected weighted graph based on the preprocessed vocabulary set, where each node in the graph represents a word and the edge represents the relationship between words; c. Calculate node importance: use the idea of the PageRank algorithm to calculate the importance score of the node. Initially, all nodes are assigned the same weight value. Then iteratively calculate the score of each node until convergence; d. Extract keywords: According to the score of the node, select the node with a higher score as the keyword.
[0096] The named entity recognition module uses the conditional random field algorithm, and its algorithm steps are as follows: a. Feature extraction: preprocess the input text and extract features from it. These features can include part of speech, word form, context information, etc. For the named entity recognition task, commonly used features include the part of speech of the current word, the part of speech of the previous and next words, part of speech tags, word form, etc.; b. Define the label set: In order to perform sequence labeling, it is necessary to define the label set of the named entity; c. Learning model: using the labeled training data set, the CRF model is trained by optimization methods such as gradient descent. The model learns the feature weights by maximizing the log-likelihood function of the training data to improve the accuracy of the label sequence; d. Feature function definition: map the features to numerical values that can represent different label sequences, define feature functions, measure the relationship between features and labels, and help the model judge the possibility of different label sequences; e. Model prediction: use the learned model to predict the test data and find the most likely label sequence; f. Output results: According to the predicted label sequence, the named entities in the text are identified and classified, thereby achieving the purpose of named entity recognition.
[0097] The dialogue management module controls the dialogue flow. After receiving the content processed by the natural language processing module, it guides the dialogue according to the preset logic and strategy and determines the system's response and behavior.
[0098] The intelligent recommendation module includes the intelligent recommendation module and the best practice module, and the learning and optimization module includes the data collection module and the model training module.
[0099] Furthermore, the intelligent recommendation module obtains relevant information from the knowledge graph module based on the questions provided by the user and the current situation, and provides operational suggestions, best practices or solutions to help users solve problems. The learning and optimization module collects user feedback and system learning data, and continuously analyzes and optimizes the system's performance and performance to improve the system's intelligence level and adaptability.
[0100] See also Figure 4B The operation and maintenance strategy determination method shown in the figure is applied to Figure 4A The operation and maintenance strategy determination system shown includes:
[0101] S401, the human-computer interaction interface obtains the original operation and maintenance data of the fault subject.
[0102] S402, the natural language processing module converts the format of the original operation and maintenance data to obtain operation and maintenance data to be processed.
[0103] S403, the semantic recognition module performs word segmentation processing on the operation and maintenance data to be processed to obtain at least two word segmentation words, and determines at least one keyword in the operation and maintenance data to be processed according to the association relationship between the word segmentation words.
[0104] S404, the semantic recognition module determines the similarity between any keyword and different preset keywords, and uses the preset keywords with a similarity greater than a preset similarity threshold as reference keywords.
[0105] S405 , the semantic recognition module uses the operation and maintenance strategy corresponding to the reference keyword as the reference operation and maintenance strategy corresponding to the keyword.
[0106] S406: The semantic recognition module combines the reference operation and maintenance strategies corresponding to the at least one keyword to obtain at least one candidate operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0107] S407, the intelligent recommendation module determines the current state of the fault subject according to the operation and maintenance data to be processed.
[0108] S408: The intelligent recommendation module adjusts at least one candidate operation and maintenance strategy according to the current state of the fault subject to obtain at least one adjusted candidate operation and maintenance strategy.
[0109] S409, the intelligent recommendation module determines the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the matching degree between each adjusted candidate operation and maintenance strategy and the operation and maintenance target data.
[0110] The operation and maintenance purpose data is extracted from the operation and maintenance data to be processed.
[0111] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0112] Based on the same inventive concept, the embodiment of the present application also provides an operation and maintenance strategy determination device for implementing the operation and maintenance strategy determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more operation and maintenance strategy determination device embodiments provided below can refer to the limitations of the operation and maintenance strategy determination method above, and will not be repeated here.
[0113] In an exemplary embodiment, Figure 5As shown, an operation and maintenance strategy determination device is provided, including: a keyword determination module 510, a reference keyword determination module 520 and an operation and maintenance strategy determination module 530, wherein:
[0114] The keyword determination module 510 is used to perform semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed.
[0115] The reference keyword determination module 520 is used to determine the similarity between any keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords of the keyword.
[0116] The operation and maintenance strategy determination module 530 is used to determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the operation and maintenance strategy corresponding to the reference keyword and the operation and maintenance data to be processed.
[0117] In one embodiment, the operation and maintenance strategy determination module 530 includes a first determination unit, which is used to use the operation and maintenance strategy corresponding to the reference keyword as the reference operation and maintenance strategy corresponding to the keyword; and a second determination unit, which is used to determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed based on at least one reference operation and maintenance strategy.
[0118] In one embodiment, the second determination unit includes a first determination sub-unit, which is used to combine the reference operation and maintenance strategies corresponding to at least one keyword to obtain at least one candidate operation and maintenance strategy corresponding to the operation and maintenance data to be processed; and a second determination sub-unit, which is used to determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed based on the operation and maintenance data to be processed and at least one candidate operation and maintenance strategy.
[0119] In one embodiment, the second determination subunit is specifically used to determine the current state of the fault subject according to the operation and maintenance data to be processed; and determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the current state of the fault subject and at least one candidate operation and maintenance strategy.
[0120] In one embodiment, the second determination subunit is specifically used to adjust at least one candidate operation and maintenance strategy according to the current state of the fault subject to obtain at least one adjusted candidate operation and maintenance strategy; and determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the matching degree between each adjusted candidate operation and maintenance strategy and the operation and maintenance target data; wherein the operation and maintenance target data is extracted from the operation and maintenance data to be processed.
[0121] In one embodiment, the keyword determination module 510 includes a data acquisition unit, which is used to acquire the original operation and maintenance data of the fault subject; a data conversion unit, which is used to convert the format of the original operation and maintenance data to obtain the operation and maintenance data to be processed; and a keyword determination unit, which is used to perform word segmentation processing on the operation and maintenance data to be processed to obtain at least two word segmentation words, and determine at least one keyword in the operation and maintenance data to be processed based on the association relationship between the word segmentation words.
[0122] Each module in the above-mentioned operation and maintenance strategy determination device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0123] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for determining an operation and maintenance strategy is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0124] Those skilled in the art will understand that Figure 6The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0125] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0126] Performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed;
[0127] For any keyword, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword;
[0128] According to the operation and maintenance strategy corresponding to the reference keyword, determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0129] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0130] The operation and maintenance strategy corresponding to the reference keyword is used as the reference operation and maintenance strategy corresponding to the keyword;
[0131] According to at least one reference operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0132] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0133] Combining the reference operation and maintenance strategies corresponding to at least one keyword to obtain at least one candidate operation and maintenance strategy corresponding to the operation and maintenance data to be processed;
[0134] According to the operation and maintenance data to be processed and at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0135] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0136] Determine the current status of the fault subject based on the operation and maintenance data to be processed;
[0137] According to the current state of the fault subject and at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0138] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0139] According to the current state of the fault subject, at least one candidate operation and maintenance strategy is adjusted to obtain at least one adjusted candidate operation and maintenance strategy;
[0140] According to the matching degree between each adjusted candidate operation and maintenance strategy and the operation and maintenance target data, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined; wherein the operation and maintenance target data is extracted from the operation and maintenance data to be processed.
[0141] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0142] Obtain the original operation and maintenance data of the fault subject;
[0143] Convert the format of the original operation and maintenance data to obtain the operation and maintenance data to be processed;
[0144] The operation and maintenance data to be processed is segmented to obtain at least two segmented words, and at least one keyword in the operation and maintenance data to be processed is determined according to the association relationship between the segmented words.
[0145] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0146] Performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed;
[0147] For any keyword, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword;
[0148] According to the operation and maintenance strategy corresponding to the reference keyword, determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0149] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0150] The operation and maintenance strategy corresponding to the reference keyword is used as the reference operation and maintenance strategy corresponding to the keyword;
[0151] According to at least one reference operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0152] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0153] Combining the reference operation and maintenance strategies corresponding to at least one keyword to obtain at least one candidate operation and maintenance strategy corresponding to the operation and maintenance data to be processed;
[0154] According to the operation and maintenance data to be processed and at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0155] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0156] Determine the current status of the fault subject based on the operation and maintenance data to be processed;
[0157] According to the current state of the fault subject and at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0158] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0159] According to the current state of the fault subject, at least one candidate operation and maintenance strategy is adjusted to obtain at least one adjusted candidate operation and maintenance strategy;
[0160] According to the matching degree between each adjusted candidate operation and maintenance strategy and the operation and maintenance target data, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined; wherein the operation and maintenance target data is extracted from the operation and maintenance data to be processed.
[0161] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0162] Obtain the original operation and maintenance data of the fault subject;
[0163] Convert the format of the original operation and maintenance data to obtain the operation and maintenance data to be processed;
[0164] The operation and maintenance data to be processed is segmented to obtain at least two segmented words, and at least one keyword in the operation and maintenance data to be processed is determined according to the association relationship between the segmented words.
[0165] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0166] Performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed;
[0167] For any keyword, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword;
[0168] According to the operation and maintenance strategy corresponding to the reference keyword, determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed.
[0169] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0170] The operation and maintenance strategy corresponding to the reference keyword is used as the reference operation and maintenance strategy corresponding to the keyword;
[0171] According to at least one reference operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0172] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0173] Combining the reference operation and maintenance strategies corresponding to at least one keyword to obtain at least one candidate operation and maintenance strategy corresponding to the operation and maintenance data to be processed;
[0174] According to the operation and maintenance data to be processed and at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0175] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0176] Determine the current status of the fault subject based on the operation and maintenance data to be processed;
[0177] According to the current state of the fault subject and at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
[0178] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0179] According to the current state of the fault subject, at least one candidate operation and maintenance strategy is adjusted to obtain at least one adjusted candidate operation and maintenance strategy;
[0180] According to the matching degree between each adjusted candidate operation and maintenance strategy and the operation and maintenance target data, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined; wherein the operation and maintenance target data is extracted from the operation and maintenance data to be processed.
[0181] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0182] Obtain the original operation and maintenance data of the fault subject;
[0183] Convert the format of the original operation and maintenance data to obtain the operation and maintenance data to be processed;
[0184] The operation and maintenance data to be processed is segmented to obtain at least two segmented words, and at least one keyword in the operation and maintenance data to be processed is determined according to the association relationship between the segmented words.
[0185] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0186] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0187] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for determining an operation and maintenance strategy, characterized in that: The method comprises: Performing semantic recognition on the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed; For any of the keywords, determine the similarity between the keyword and different preset keywords, and use the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword; According to the operation and maintenance strategy corresponding to the reference keyword, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
2. The method according to claim 1, characterized in that The step of determining the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the operation and maintenance strategy corresponding to the reference keyword includes: Using the operation and maintenance strategy corresponding to the reference keyword as the reference operation and maintenance strategy corresponding to the keyword; According to at least one reference operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
3. The method according to claim 2, characterized in that The determining, according to the at least one reference operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed includes: Combining the reference operation and maintenance strategies corresponding to at least one of the keywords to obtain at least one candidate operation and maintenance strategy corresponding to the operation and maintenance data to be processed; A target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined according to the operation and maintenance data to be processed and the at least one candidate operation and maintenance strategy.
4. The method according to claim 3, characterized in that The determining, according to the operation and maintenance data to be processed and the at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed includes: Determine the current state of the fault subject according to the operation and maintenance data to be processed; According to the current state of the fault subject and the at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined.
5. The method according to claim 4, characterized in that The determining, according to the current state of the fault subject and the at least one candidate operation and maintenance strategy, a target operation and maintenance strategy corresponding to the operation and maintenance data to be processed includes: According to the current state of the fault subject, the at least one candidate operation and maintenance strategy is adjusted to obtain at least one adjusted candidate operation and maintenance strategy; According to the matching degree between each of the adjusted candidate operation and maintenance strategies and the operation and maintenance target data, the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed is determined; wherein the operation and maintenance target data is extracted from the operation and maintenance data to be processed.
6. The method according to claim 1, characterized in that The semantic recognition of the operation and maintenance data to be processed of the fault subject to obtain at least one keyword in the operation and maintenance data to be processed includes: Obtaining original operation and maintenance data of the fault subject; Converting the format of the original operation and maintenance data to obtain operation and maintenance data to be processed; The operation and maintenance data to be processed is segmented to obtain at least two segmented words, and at least one keyword in the operation and maintenance data to be processed is determined according to the association relationship between the segmented words.
7. A device for determining an operation and maintenance strategy, characterized in that: The device comprises: A keyword determination module, used to perform semantic recognition on the operation and maintenance data to be processed of the fault subject, and obtain at least one keyword in the operation and maintenance data to be processed; A reference keyword determination module, used for determining, for any of the keywords, the similarity between the keyword and different preset keywords, and using the preset keywords with a similarity greater than a preset threshold as reference keywords for the keyword; The operation and maintenance strategy determination module is used to determine the target operation and maintenance strategy corresponding to the operation and maintenance data to be processed according to the operation and maintenance strategy corresponding to the reference keyword and the operation and maintenance data to be processed.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
