Question and answer method, device and equipment based on operation and maintenance business question, medium and product

Abstract

The invention discloses a question answering method, device and equipment based on operation and maintenance business questions, a medium and a product, and relates to the technical field of data processing. The method comprises the steps of obtaining an operation and maintenance service problem; the operation and maintenance service problems are subjected to collaborative analysis according to the pre-constructed knowledge base and a preset algorithm, a solution of the operation and maintenance service problems is determined, and the preset algorithm comprises a vector space model, a mixed recommendation strategy and an auxiliary decision strategy. According to the method, the pre-constructed knowledge base containing rich operation and maintenance business problem templates is pre-constructed, cooperative work is performed in combination with a vector space model, a mixed recommendation strategy and an auxiliary decision strategy, and corresponding solutions are automatically and rapidly matched according to data features, historical experience and an intelligent algorithm, so that the problem processing time is greatly shortened, and the problem processing efficiency is improved. The processing efficiency of the overall operation and maintenance service is effectively improved, and the problems that a current operation and maintenance mode lacks an effective accumulation and application mechanism for new knowledge and experience and the cross-domain problem comprehensive processing difficulty is large are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a question-and-answer method, device, equipment, medium, and product based on operation and maintenance business issues. Background Art

[0002] In today's digital age, the scale and complexity of operations and maintenance for businesses and organizations continues to expand. Massive amounts of operational data are constantly being generated, including server operating parameters, network device status information, and application logs. With the continuous expansion of business and the rapid advancement of technology, the knowledge involved in the operations and maintenance process is becoming increasingly broad, and new problems and failure types are constantly emerging.

[0003] The current operation and maintenance method mainly relies on manual experience and manual query documents to handle problems. Operation and maintenance personnel locate the root cause of the problem through data and find solutions.

[0004] However, this operation and maintenance approach lacks an effective mechanism for accumulating and applying new knowledge and experience. Past solutions and ideas for solving problems are not systematically organized and retained. As a result, when similar problems recur, operation and maintenance personnel often need to explore solutions all over again, resulting in a waste of time and manpower. Due to the interweaving of technologies from different fields, it is difficult to comprehensively address cross-domain issues. For example, when dealing with complex failures involving networks, applications, and hardware devices, traditional operation and maintenance models struggle to quickly and accurately locate the root cause of the problem and provide effective solutions. Furthermore, traditional operation and maintenance systems typically employ fixed rules and methods when handling problems, lacking the ability to adapt to different situations and making it difficult to meet diverse operation and maintenance needs. These issues have severely impacted the efficiency and quality of operation and maintenance services, increasing operation and maintenance costs and risks. Summary of the Invention

[0005] The present invention provides a question-answering method, device, equipment, medium and product based on operation and maintenance business issues to achieve answers to diverse operation and maintenance issues.

[0006] According to a first aspect of the present invention, a question-answering method based on operation and maintenance business questions is provided, comprising:

[0007] Obtain operation and maintenance business issues;

[0008] The operation and maintenance business problem is collaboratively analyzed based on a pre-built knowledge base and a preset algorithm to determine a solution to the operation and maintenance business problem, wherein the preset algorithm includes a vector space model, a hybrid recommendation strategy and an auxiliary decision strategy.

[0009] According to a second aspect of the present invention, a question-answering device based on operation and maintenance business questions is provided, comprising:

[0010] Problem acquisition module, used to obtain operation and maintenance business problems;

[0011] The solution determination module is used to collaboratively analyze the operation and maintenance business problems based on a pre-built knowledge base and preset algorithms to determine solutions to the operation and maintenance business problems, wherein the preset algorithms include vector space models, hybrid recommendation strategies and auxiliary decision strategies.

[0012] According to a third aspect of the present invention, there is provided an electronic device, comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the question-and-answer method based on operation and maintenance business issues described in any embodiment of the present invention.

[0016] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the question-and-answer method based on operation and maintenance business issues described in any embodiment of the present invention when executed.

[0017] According to the fifth aspect of the present invention, an embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the question-and-answer method based on operation and maintenance business issues of any embodiment of the present invention.

[0018] The technical solution of the embodiment of the present invention obtains operation and maintenance business problems; conducts collaborative analysis on the operation and maintenance business problems based on a pre-built knowledge base and preset algorithms, and determines solutions to the operation and maintenance business problems, wherein the preset algorithms include vector space models, hybrid recommendation strategies, and auxiliary decision-making strategies. By pre-building a pre-built knowledge base containing rich operation and maintenance business problem templates, combining vector space models, hybrid recommendation strategies, and auxiliary decision-making strategies to work together, it automatically and quickly matches corresponding solutions based on data features, historical experience, and intelligent algorithms, greatly shortening the time for problem handling, effectively improving the overall operation and maintenance business processing efficiency, and solving the problems of the current operation and maintenance methods lacking an effective accumulation and application mechanism for new knowledge and experience, as well as the difficulty in comprehensive handling of cross-domain problems.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flowchart of a question-and-answer method based on operation and maintenance business questions provided in accordance with the first embodiment of the present invention;

[0022] Figure 2 2 is a schematic diagram of the structure of a question-answering device based on operation and maintenance business questions provided in accordance with the second embodiment of the present invention;

[0023] Figure 3 It is a schematic structural diagram of an electronic device implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] Example 1

[0027] Figure 1A flowchart of a question-and-answer method based on operation and maintenance business issues is provided for the first embodiment of the present invention. This embodiment is applicable to the situation of answering operation and maintenance business issues. The method can be executed by a question-and-answer device based on operation and maintenance business issues. The question-and-answer device based on operation and maintenance business issues can be implemented in the form of hardware and / or software. The question-and-answer device based on operation and maintenance business issues can be configured in an electronic device. Figure 1 As shown, the method includes:

[0028] S110. Obtain operation and maintenance business issues.

[0029] In this embodiment, the operation and maintenance business problem can be understood as a problem related to the operation and maintenance business raised by the user.

[0030] Specifically, the processor may obtain operation and maintenance business issues input by the user.

[0031] S120. Collaboratively analyze the operation and maintenance business problems based on the pre-built knowledge base and preset algorithms to determine solutions to the operation and maintenance business problems. The preset algorithms include vector space models, hybrid recommendation strategies, and auxiliary decision strategies.

[0032] In this embodiment, the pre-built knowledge base can be understood as a collection of templates for a wide range of operational and maintenance problems, each of which is associated with a corresponding standard solution. Pre-set algorithms can be understood as algorithms used to solve operational and maintenance problems, including vector space models, hybrid recommendation strategies, and decision-making support strategies. Solutions can be understood as proposals for resolving operational and maintenance problems.

[0033] Specifically, the processor can match operation and maintenance business problems in a pre-built knowledge base. If a matching template exists, it will be used as a solution. If not, the vector space model, hybrid recommendation strategy and auxiliary decision-making strategy in the preset algorithm will be used to collaboratively analyze and determine the solution to the operation and maintenance business problem.

[0034] The technical solution of the embodiment of the present invention obtains operation and maintenance business problems; conducts collaborative analysis on the operation and maintenance business problems based on a pre-built knowledge base and preset algorithms, and determines solutions to the operation and maintenance business problems, wherein the preset algorithms include vector space models, hybrid recommendation strategies, and auxiliary decision-making strategies. By pre-building a pre-built knowledge base containing rich operation and maintenance business problem templates, combining vector space models, hybrid recommendation strategies, and auxiliary decision-making strategies to work together, it automatically and quickly matches corresponding solutions based on data features, historical experience, and intelligent algorithms, greatly shortening the time for problem handling, effectively improving the overall operation and maintenance business processing efficiency, and solving the problems of the current operation and maintenance methods lacking an effective accumulation and application mechanism for new knowledge and experience, as well as the difficulty in comprehensive handling of cross-domain problems.

[0035] Furthermore, based on the above embodiment, the steps of collaboratively analyzing the operation and maintenance business problems based on the pre-built knowledge base and the preset algorithm and determining the solutions to the operation and maintenance business problems can be refined as follows:

[0036] Through semantic analysis, operation and maintenance business problems are matched in the pre-built knowledge base, and the matched target knowledge template is used as the solution; if the target knowledge template is not matched, the operation and maintenance business problems are matched with historical data through the vector space model and the updated similarity threshold to determine the solution; if the historical data is not matched, the recommended solution is determined and used as the solution through a hybrid recommendation strategy; if the recommended solution is invalid, the solution is determined through an auxiliary decision-making strategy.

[0037] In this embodiment, semantic analysis can be understood as a natural language processing method used to extract key information. The similarity threshold can be understood as a threshold used to screen for operational and maintenance business problems. The target knowledge template can be understood as a template used to answer operational and maintenance business problems. Historical data can be understood as data containing historical operational and maintenance business problems and their solutions.

[0038] Specifically, the processor can first perform semantic analysis on the operation and maintenance business problem through natural language processing technology to extract key information. A pre-built knowledge base contains multiple knowledge templates, each knowledge template is associated with a corresponding standard solution, and the key information is matched with the template in the pre-built knowledge base. If a matching template exists, the target knowledge template is used as the solution. If there is no matching target knowledge template, the operation and maintenance business problem can be represented by a vector through a vector space model, and the similarity value between the vectors is calculated with historical data. For example, the cosine similarity formula can be used to calculate and the historical solutions in the historical data that exceed the similarity threshold are used as solutions to the operation and maintenance business problem. When no historical data is matched, the processor can use a hybrid recommendation strategy to make a comprehensive judgment through the machine learning algorithm and mining algorithm in the hybrid recommendation strategy to determine the solution. If the solution still cannot be determined through the hybrid recommendation strategy, the processor can use the auxiliary decision-making strategy to assist in the decision-making of the operation and maintenance business problem, and provide feedback to the experts in the form of visualization to assist the experts in forming a solution.

[0039] Based on the above embodiment, the steps of determining a recommendation scheme as a solution through a hybrid recommendation strategy can be refined as follows:

[0040] Operation and maintenance business problems are classified through a preset machine learning model to obtain problem classification results; the business rules of operation and maintenance business problems are mined according to the association rule algorithm to generate a set of candidate solutions; the three-dimensional similarity matrix of users, operation and maintenance business problems and solutions is determined based on the collaborative filtering algorithm; the candidate solution set and the three-dimensional similarity matrix are integrated through a weighted voting mechanism to obtain a recommended solution as a solution.

[0041] In this embodiment, the preset machine learning model can be understood as a model for classification, for example, it can include a support vector machine model, etc. The problem classification result can be understood as the result of the classification to which the operation and maintenance business problem is determined. The association rule algorithm Apriori algorithm can be understood as an algorithm for problem mining. Business rules can be understood as a series of regulations, principles and methods followed when carrying out business activities. The candidate solution set can be understood as a set formed by forming multiple solutions. The collaborative filtering algorithm can be understood as a recommendation algorithm based on user behavior data. The user can be understood as the goal of raising operation and maintenance business problems. The three-dimensional similarity matrix can be understood as a matrix constructed in three dimensions for similarity judgment. The weighted voting mechanism can be understood as a voting method that considers the importance of different participants in the decision-making process.

[0042] Specifically, the processor can classify operational issues using a pre-set machine learning model to obtain a classification result. The processor can then mine the business rules of operational issues using the Apriopri algorithm, generating a set of candidate solutions. The processor can then determine a three-dimensional similarity matrix between users, operational issues, and solutions using a collaborative filtering algorithm. Using a weighted voting mechanism, the processor can then fuse the candidate solution set and the three-dimensional similarity matrix to obtain a recommended solution as the solution.

[0043] For example, before using the preset machine learning model, the processor can collect and process the operation and maintenance feedback data to form operation and maintenance feedback data with annotation information, wherein the annotation information includes the problem type, the business field to which it belongs, and the equipment information; and select the key features corresponding to the operation and maintenance business problem for feature conversion. Combine the machine learning algorithm to train the model, and train the model based on the prepared data, for example, a support vector machine can be used, and its decision function for:

[0044]

[0045] Where, is the input vector, y i is the category label of the sample, a i is the Lagrange multiplier, is the kernel function and b is the bias term.

[0046] Based on the above embodiment, a solution may be determined through auxiliary decision-making strategies, including:

[0047] Through the knowledge graph reasoning in the auxiliary decision-making strategy, the shortest reasoning path is determined for feedback; based on the visualization analysis tool in the auxiliary decision-making strategy, the problem feature heat map, the solution implementation effect trend map and the domain knowledge association map are displayed; by receiving the target object's relative shortest reasoning path and the visualization analysis tool, the decision plan determined is used as the solution.

[0048] In this embodiment, knowledge graph reasoning can be understood as a process of inferring unknown facts or relationships using existing facts or relationships in the graph. The shortest reasoning path can be understood as the path with the least number of edges connecting two entities. Visual analysis tools can be understood as displaying in a visual way. The problem feature heat map can be understood as a tool that shows the distribution and frequency of problem features in an intuitive graphical way. The solution implementation effect trend chart can be understood as a chart used to show the effect change trend during the execution of the solution. The domain knowledge association map can be understood as a tool for organizing and displaying knowledge in a specific field in the form of a graph. The target object can be understood as the object used to determine the solution. The decision plan can be understood as a solution determined manually.

[0049] Specifically, the processor can construct a reasoning path from operational problems to faults to solutions based on the knowledge graph, use the Dijkstra algorithm to find the shortest reasoning path, and provide feedback to the target object, providing intelligent decision support for the target object. Based on the visualization analysis tools in the decision support strategy, the processor can display a heat map of problem characteristics, a trend map of solution implementation effects, and a domain knowledge association map, and provide feedback to the target object to assist the target object in making decisions. The processor can receive the target object's shortest reasoning path and the visualization analysis tool, and determine the decision solution as a solution.

[0050] As a first optional embodiment of the first embodiment, after collaboratively analyzing the operation and maintenance business problem based on the pre-built knowledge base, the preset algorithm, and the multi-source data to determine a solution to the operation and maintenance business problem, the following further comprises:

[0051] Obtain user feedback data related to operation and maintenance business issues, and update the pre-built knowledge base and preset algorithms based on solutions and feedback data.

[0052] In this embodiment, the feedback data can be understood as real-time feedback data such as user ratings, solution effectiveness, and feedback data related to the operation and maintenance business problem.

[0053] Specifically, the processor can obtain feedback data related to operation and maintenance business issues from users, pre-process the feedback data, and when the feedback data indicates that the accuracy threshold is too low, update the preset algorithm through the processed feedback data and the actual solution, and also record the solution in the pre-built knowledge base.

[0054] Among them, based on the above embodiment, the steps of updating the pre-built knowledge base and the preset algorithm according to the solution and feedback data can be refined as follows:

[0055] The data of different modal types in the feedback data are preprocessed separately to obtain vectorized data; the vectorized data is enhanced, and the preset machine learning model in the preset algorithm is updated based on the enhanced data; based on the historical matching success rate and the confidence of the question type, the reinforcement learning algorithm is used to adjust the similarity threshold; and the pre-built knowledge base is updated according to the solution determined by the target object.

[0056] In this embodiment, data under different modal types can be understood as the corresponding types after the data from different sources are divided. For example, it can include numerical data of the operating status of the acquisition device (such as real-time parameters such as CPU utilization and memory usage), time series data of network traffic (such as traffic peaks, protocol distribution and other time series features) and text data of application logs (such as error stacks, operation records and other unstructured texts). Vectorized data can be understood as data converted into feature vector form. The historical matching success rate can be understood as the success rate when performing similarity matching. The question type confidence can be understood as an indicator used to measure the accuracy of question classification.

[0057] Specifically, the processor can pre-process the data of different modal types in the feedback data separately to obtain vectorized data. For example, the processor can standardize the numerical data (such as Z-score normalization), perform Fourier transform on the time series data to extract frequency domain features, use the BERT model to generate semantic vectors for the text data, and then splice the three types of feature vectors into a unified dimension feature vector to obtain vectorized data. The processor can enhance and detect anomalies in the vectorized data. The processor can use sliding window sampling combined with generative adversarial networks (GANs) to enhance the time series data, use the isolation forest algorithm to mark and filter abnormal data points, and obtain enhanced data. The processor can update the preset machine learning model in the preset algorithm based on the enhanced data. For example, it can use real-time feedback data such as user ratings and solution effectiveness, and use incremental support vector machines for incremental learning to update the preset machine learning model and optimize the feature weights therein. The processor can use a reinforcement learning algorithm to adjust the similarity threshold based on the historical matching success rate and the confidence level of the question type. The processor can update the pre-built knowledge base based on the solution identified by the target object. The processor can also update the rule base based on new rules mined by the Apriori algorithm, supplementing the frequently unmatched problem templates to iterate the pre-built knowledge base. When monitoring indicators such as problem processing time, matching success rate, and manual intervention rate, targeted optimization is triggered when modules with high failure rates (e.g., template matching failure rate >30%) appear.

[0058] The technical solution of the embodiments of the present invention builds a pre-built knowledge base of rich operation and maintenance business problem templates, combines semantic analysis to quickly match problems, uses a text similarity algorithm through a similarity matching module to find similar problems and solutions from historical data, and uses a preset machine learning model and association rule algorithm to mine the association rules between problems and solutions, recommends preliminary solutions, and combines collaborative filtering algorithms and weighted voting mechanisms to determine the final solution. If the above algorithms still cannot determine a solution, a decision-making support strategy is used to create a visual solution display to assist the target in making a decision and determining a solution. When a solution is obtained, the pre-built knowledge base and algorithm model are automatically updated to ensure the integrity of the solution record and the accuracy of the method. With multiple algorithms working together, the corresponding solution can be automatically matched based on data features, historical experience, and intelligent algorithms. This greatly shortens the problem resolution time and effectively improves the overall operation and maintenance business processing efficiency, enabling operation and maintenance personnel to handle more operation and maintenance tasks in a shorter time. This solves the problem that the current operation and maintenance methods lack an effective mechanism for accumulating and applying new knowledge and experience, as well as the difficulty in comprehensively handling cross-domain problems.

[0059] Example 2

[0060] Figure 2This is a structural diagram of a question-answering device based on operation and maintenance business questions provided in the second embodiment of the present invention. Figure 2 As shown, the device includes:

[0061] Problem acquisition module 21, used to obtain operation and maintenance business problems;

[0062] The solution determination module 22 is used to collaboratively analyze the operation and maintenance business problem based on a pre-built knowledge base and a preset algorithm to determine a solution to the operation and maintenance business problem, wherein the preset algorithm includes a vector space model, a hybrid recommendation strategy and an auxiliary decision strategy.

[0063] The technical solution of the embodiment of the present invention obtains operation and maintenance business problems; conducts collaborative analysis on the operation and maintenance business problems based on a pre-built knowledge base and preset algorithms, and determines solutions to the operation and maintenance business problems, wherein the preset algorithms include vector space models, hybrid recommendation strategies, and auxiliary decision-making strategies. By pre-building a pre-built knowledge base containing rich operation and maintenance business problem templates, combining vector space models, hybrid recommendation strategies, and auxiliary decision-making strategies to work together, it automatically and quickly matches corresponding solutions based on data features, historical experience, and intelligent algorithms, greatly shortening the time for problem handling, effectively improving the overall operation and maintenance business processing efficiency, and solving the problems of the current operation and maintenance methods lacking an effective accumulation and application mechanism for new knowledge and experience, as well as the difficulty in comprehensive handling of cross-domain problems.

[0064] Furthermore, the solution determination module 22 includes:

[0065] A first determining unit is configured to match the operation and maintenance business problem in a pre-built knowledge base through semantic analysis, and use the matched target knowledge template as a solution;

[0066] A second determining unit is configured to match the operation and maintenance business problem with historical data using the vector space model and the updated similarity threshold to determine the solution if no target knowledge template is matched;

[0067] a third determining unit, configured to determine a recommendation scheme as the solution by using the hybrid recommendation strategy if no historical data is matched;

[0068] The fourth determining unit is configured to determine the solution by using the auxiliary decision-making strategy if the recommended solution is invalid.

[0069] The third determining unit is specifically configured to:

[0070] Classify the operation and maintenance business problems through a preset machine learning model to obtain problem classification results;

[0071] Mining the business rules of the operation and maintenance business problem according to the association rule algorithm to generate a set of candidate solutions;

[0072] Determine a three-dimensional similarity matrix of the user, the operation and maintenance business problem, and the solution based on a collaborative filtering algorithm;

[0073] The candidate solution set and the three-dimensional similarity matrix are fused through a weighted voting mechanism to obtain a recommended solution as the solution.

[0074] The fourth determining unit is specifically configured to:

[0075] Determine the shortest reasoning path for feedback through the knowledge graph reasoning in the auxiliary decision-making strategy;

[0076] Based on the visualization analysis tool in the decision-making support strategy, a heat map of problem characteristics, a trend map of solution implementation effects, and a domain knowledge association map are displayed;

[0077] The decision plan determined by receiving the target object relative to the shortest reasoning path and the visual analysis tool is used as the solution.

[0078] Optionally, the module also includes:

[0079] An update module is used to obtain feedback data related to the operation and maintenance business problem from users after collaboratively analyzing the operation and maintenance business problem based on the pre-built knowledge base, the preset algorithm and the multi-source data to determine a solution to the operation and maintenance business problem, and to update the pre-built knowledge base and the preset algorithm based on the solution and the feedback data.

[0080] Furthermore, the update module is specifically configured to:

[0081] Preprocessing the data of different modal types in the feedback data to obtain vectorized data;

[0082] Enhance the vectorized data, and update the preset machine learning model in the preset algorithm based on the enhanced data;

[0083] Based on the historical matching success rate and question type confidence, a reinforcement learning algorithm is used to adjust the similarity threshold;

[0084] The pre-built knowledge base is updated according to the solution determined for the target object.

[0085] The question-and-answer device based on operation and maintenance business issues provided in an embodiment of the present invention can execute the question-and-answer method based on operation and maintenance business issues provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0086] Example 3

[0087] Figure 3 A schematic diagram of the structure of an electronic device 30 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0088] like Figure 3 As shown, the electronic device 30 includes at least one processor 31 and a memory, such as a read-only memory (ROM) 32, a random access memory (RAM) 33, etc., which is communicatively connected to the at least one processor 31. The memory stores a computer program that can be executed by the at least one processor. The processor 31 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 32 or the computer program loaded from the storage unit 38 into the random access memory (RAM) 33. Various programs and data required for the operation of the electronic device 30 can also be stored in the RAM 33. The processor 31, ROM 32, and RAM 33 are connected to each other via a bus 34. An input / output (I / O) interface 35 is also connected to the bus 34.

[0089] Multiple components in the electronic device 30 are connected to the I / O interface 35, including an input unit 36, such as a keyboard, a mouse, etc.; an output unit 37, such as various types of displays, speakers, etc.; a storage unit 38, such as a magnetic disk, an optical disk, etc.; and a communication unit 39, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 39 allows the electronic device 30 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0090] Processor 31 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 31 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 31 executes the various methods and processes described above, such as the question-and-answer method based on operation and maintenance business questions.

[0091] In some embodiments, the question-answering method based on operation and maintenance business questions can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 38. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 30 via the ROM 32 and / or the communication unit 39. When the computer program is loaded into the RAM 33 and executed by the processor 31, one or more steps of the question-answering method based on operation and maintenance business questions described above can be performed. Alternatively, in other embodiments, the processor 31 can be configured to execute the question-answering method based on operation and maintenance business questions in any other appropriate manner (for example, by means of firmware).

[0092] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0094] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0096] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0097] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0098] In one embodiment, the embodiment of the present invention also includes a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the question-and-answer method based on operation and maintenance business issues of any embodiment of the present invention.

[0099] The computer program product may be implemented by writing computer program code for performing the operations of the present invention 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 stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via 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).

[0100] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0101] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A question-answering method based on operation and maintenance business issues, characterized in that: include: Obtain operation and maintenance business issues; The operation and maintenance business problem is collaboratively analyzed based on a pre-built knowledge base and a preset algorithm to determine a solution to the operation and maintenance business problem, wherein the preset algorithm includes a vector space model, a hybrid recommendation strategy and an auxiliary decision strategy.

2. The method according to claim 1, characterized in that The collaborative analysis of the operation and maintenance business problem based on the pre-built knowledge base and the preset algorithm to determine the solution to the operation and maintenance business problem includes: Match the operation and maintenance business problem in the pre-built knowledge base through semantic analysis, and use the matched target knowledge template as the solution; If the target knowledge template is not matched, the operation and maintenance business problem is matched with the historical data using the vector space model and the updated similarity threshold to determine the solution; If no historical data is matched, a recommendation scheme is determined through the hybrid recommendation strategy and used as the solution; If the recommended solution is invalid, the solution is determined through the auxiliary decision-making strategy.

3. The method according to claim 2, characterized in that Determining a recommendation scheme as the solution through the hybrid recommendation strategy includes: Classify the operation and maintenance business problems through a preset machine learning model to obtain problem classification results; Mining the business rules of the operation and maintenance business problem according to the association rule algorithm to generate a set of candidate solutions; Determine a three-dimensional similarity matrix of the user, the operation and maintenance business problem, and the solution based on a collaborative filtering algorithm; The candidate solution set and the three-dimensional similarity matrix are fused through a weighted voting mechanism to obtain a recommended solution as the solution.

4. The method according to claim 2, characterized in that Determining the solution through the auxiliary decision-making strategy includes: Determine the shortest reasoning path for feedback through the knowledge graph reasoning in the auxiliary decision-making strategy; Based on the visualization analysis tool in the decision-making support strategy, a heat map of problem characteristics, a trend map of solution implementation effects, and a domain knowledge association map are displayed; The decision plan determined by receiving the target object relative to the shortest reasoning path and the visual analysis tool is used as the solution.

5. The method according to claim 1, wherein After collaboratively analyzing the operation and maintenance business problem based on the pre-built knowledge base, the preset algorithm, and the multi-source data to determine a solution to the operation and maintenance business problem, the method further includes: Obtain feedback data related to the operation and maintenance business problem from users, and update the pre-built knowledge base and the preset algorithm based on the solution and the feedback data.

6. The method according to claim 5, characterized in that The updating of the pre-built knowledge base and the preset algorithm according to the solution and the feedback data includes: Preprocessing the data of different modal types in the feedback data to obtain vectorized data; Enhance the vectorized data, and update the preset machine learning model in the preset algorithm based on the enhanced data; Based on the historical matching success rate and question type confidence, a reinforcement learning algorithm is used to adjust the similarity threshold; The pre-built knowledge base is updated according to the solution determined for the target object.

7. A question-answering device based on operation and maintenance business issues, characterized in that: include: Problem acquisition module, used to obtain operation and maintenance business problems; The solution determination module is used to collaboratively analyze the operation and maintenance business problems based on a pre-built knowledge base and preset algorithms to determine solutions to the operation and maintenance business problems, wherein the preset algorithms include vector space models, hybrid recommendation strategies and auxiliary decision strategies.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the question-answering method based on operation and maintenance business issues according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the question-answering method based on operation and maintenance business issues according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the question-answering method based on operation and maintenance business issues according to any one of claims 1 to 6.

Images