Operation and maintenance analysis data processing method and system based on enhanced knowledge graph

Abstract

The present invention discloses an operation and maintenance analysis data processing method and system based on an enhanced knowledge graph, the method comprising: obtaining the operation and maintenance problems of target users for a target system; decomposing the operation and maintenance problems according to a preset problem decomposition algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problems; organizing the multiple main parts based on preset language organization rules to obtain reorganized problem data; inputting the problem data and the problem types into a knowledge graph model corresponding to the target system to obtain the answer results corresponding to the operation and maintenance problems. It can be seen that the present invention can improve the efficiency of answering the user's operation and maintenance problems, fundamentally improve the efficiency and effect of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an operation and maintenance analysis data processing method and system based on an enhanced knowledge graph. Background Art

[0002] In the operation and maintenance services of computer systems or software systems, problem users or newly joined operation and maintenance engineers often need to have a certain understanding of the basic operation problems of the system in a short period of time to improve the efficiency and effectiveness of operation and maintenance. When solving the needs of such knowledge answer requests, most of the existing technologies only provide compiled documents for users to query, and do not fully utilize the advantages of knowledge graph algorithms and databases to achieve more automated and efficient knowledge answers. Therefore, their operation and maintenance efficiency is low and the user experience is poor. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an operation and maintenance analysis data processing method and system based on an enhanced knowledge graph, which can improve the efficiency of answering users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for processing operation and maintenance analysis data based on an enhanced knowledge graph, the method comprising:

[0005] Obtain the target user's operation and maintenance issues for the target system;

[0006] Decomposing the operation and maintenance problem according to a preset problem decomposition algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problem;

[0007] Organizing the multiple main parts based on preset language organization rules to obtain reorganized question data;

[0008] The problem data and the problem type are input into the knowledge graph model corresponding to the target system to obtain the answer result corresponding to the operation and maintenance problem.

[0009] As an optional implementation, in the first aspect of the present invention, the target system is a hardware system, a software system, a computing power server system or a power production equipment system.

[0010] As an optional embodiment, in the first aspect of the present invention, the main body part is a subject part, a predicate part, an object part, a user type part, a question type part, a question object part, a verb part, a preposition part or a noun part.

[0011] As an optional implementation, in the first aspect of the present invention, the problem type is a crash problem, an experience problem, a response speed problem, a software problem, a hardware problem, a manual problem, or a policy problem.

[0012] As an optional implementation, in the first aspect of the present invention, the operation and maintenance problem is decomposed according to a preset problem decomposition algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problem, including:

[0013] Based on multiple preset word segmentation algorithms, the operation and maintenance problem is segmented multiple times to obtain multiple word segmentation results; the word segmentation results include multiple phrases;

[0014] For each of the main parts, each of the word groups in each of the word segmentation results is input into the probability prediction algorithm model corresponding to the main part to obtain the prediction probability corresponding to each of the word groups;

[0015] Determine the phrase whose predicted probability is higher than a preset probability threshold as the data content corresponding to the main part;

[0016] The problem type corresponding to the operation and maintenance problem is determined according to the data content corresponding to the problem type part and the problem object part.

[0017] As an optional implementation manner, in the first aspect of the present invention, determining the problem type corresponding to the operation and maintenance problem according to the data content corresponding to the problem type part and the problem object part includes:

[0018] Generate corresponding question data according to the data content corresponding to the question type part and the question object part based on a preset prompt word combination rule;

[0019] The question data is input into the trained LLM model to obtain the question type corresponding to the operation and maintenance question.

[0020] As an optional implementation, in the first aspect of the present invention, the organizing the multiple main parts based on the preset language organization rules to obtain the reorganized question data includes:

[0021] Based on the preset main part connection relationship, determine multiple connection combinations corresponding to the multiple main parts;

[0022] For each of the connection combinations, any one of the phrases in the data content of each of the main parts of the connection combination is determined as the main part data corresponding to the corresponding main part, and the main part data of all the main parts corresponding to the connection combination are sequentially connected to obtain the organization problem corresponding to the connection combination;

[0023] Repeat the previous step to obtain multiple organizational questions corresponding to the connection combination; wherein the data similarity between different organizational questions is lower than a preset similarity threshold;

[0024] Based on the neural network algorithm, the question data with the highest coherence are screened out from all the organizational questions corresponding to all the connection combinations.

[0025] As an optional implementation, in the first aspect of the present invention, the neural network algorithm is used to select the most consistent problem data from all the organizational problems corresponding to all the connection combinations, including:

[0026] Inputting each of the organizational questions corresponding to each of the connection combinations into a trained coherence prediction neural network to obtain a coherence parameter corresponding to each of the organizational questions corresponding to each of the connection combinations; the coherence prediction neural network is trained using a training data set including a plurality of training question texts and corresponding coherence annotations;

[0027] Calculating an average value of the coherence parameters corresponding to all the organizational problems corresponding to each of the connection combinations to obtain the combined coherence corresponding to each of the connection combinations;

[0028] The organization question with the highest coherence parameter corresponding to the connection combination with the highest combination coherence is determined as the reorganized question data.

[0029] A second aspect of an embodiment of the present invention discloses an operation and maintenance analysis data processing system based on an enhanced knowledge graph, the system comprising:

[0030] The acquisition module is used to obtain the operation and maintenance issues of the target system from the target user;

[0031] A disassembly module, used to disassemble the operation and maintenance problem according to a preset problem disassembly algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problem;

[0032] An organization module, used for organizing the plurality of main parts based on a preset language organization rule to obtain reorganized question data;

[0033] The answer module is used to input the problem data and the problem type into the knowledge graph model corresponding to the target system to obtain the answer result corresponding to the operation and maintenance problem.

[0034] As an optional implementation, in the second aspect of the present invention, the target system is a hardware system, a software system, a computing power server system or a power production equipment system.

[0035] As an optional implementation, in the second aspect of the present invention, the main body part is a subject part, a predicate part, an object part, a user type part, a question type part, a question object part, a verb part, a preposition part or a noun part.

[0036] As an optional implementation, in the second aspect of the present invention, the problem type is a crash problem, an experience problem, a response speed problem, a software problem, a hardware problem, a manual problem, or a policy problem.

[0037] As an optional implementation, in the second aspect of the present invention, the disassembly module disassembles the operation and maintenance problem according to a preset problem disassembly algorithm to obtain a specific method of multiple main parts and problem types corresponding to the operation and maintenance problem, including:

[0038] Based on multiple preset word segmentation algorithms, the operation and maintenance problem is segmented multiple times to obtain multiple word segmentation results; the word segmentation results include multiple phrases;

[0039] For each of the main parts, each of the word groups in each of the word segmentation results is input into the probability prediction algorithm model corresponding to the main part to obtain the prediction probability corresponding to each of the word groups;

[0040] Determine the phrase whose predicted probability is higher than a preset probability threshold as the data content corresponding to the main part;

[0041] The problem type corresponding to the operation and maintenance problem is determined according to the data content corresponding to the problem type part and the problem object part.

[0042] As an optional implementation, in the second aspect of the present invention, the specific manner in which the disassembly module determines the problem type corresponding to the operation and maintenance problem according to the data content corresponding to the problem type part and the problem object part includes:

[0043] Generate corresponding question data according to the data content corresponding to the question type part and the question object part based on a preset prompt word combination rule;

[0044] The question data is input into the trained LLM model to obtain the question type corresponding to the operation and maintenance question.

[0045] As an optional implementation, in the second aspect of the present invention, the organization module organizes the multiple main parts based on a preset language organization rule to obtain a specific manner of reorganizing the question data, including:

[0046] Based on the preset main part connection relationship, determine multiple connection combinations corresponding to the multiple main parts;

[0047] For each of the connection combinations, any one of the phrases in the data content of each of the main parts of the connection combination is determined as the main part data corresponding to the corresponding main part, and the main part data of all the main parts corresponding to the connection combination are sequentially connected to obtain the organization problem corresponding to the connection combination;

[0048] Repeat the previous step to obtain multiple organizational questions corresponding to the connection combination; wherein the data similarity between different organizational questions is lower than a preset similarity threshold;

[0049] Based on the neural network algorithm, the question data with the highest coherence are screened out from all the organizational questions corresponding to all the connection combinations.

[0050] As an optional implementation, in the second aspect of the present invention, the specific manner in which the organization module selects the most coherent question data from all the organization questions corresponding to all the connection combinations based on a neural network algorithm includes:

[0051] Inputting each of the organizational questions corresponding to each of the connection combinations into a trained coherence prediction neural network to obtain a coherence parameter corresponding to each of the organizational questions corresponding to each of the connection combinations; the coherence prediction neural network is trained using a training data set including a plurality of training question texts and corresponding coherence annotations;

[0052] Calculating an average value of the coherence parameters corresponding to all the organizational problems corresponding to each of the connection combinations to obtain the combined coherence corresponding to each of the connection combinations;

[0053] The organization question with the highest coherence parameter corresponding to the connection combination with the highest combination coherence is determined as the reorganized question data.

[0054] The third aspect of the present invention discloses another operation and maintenance analysis data processing system based on enhanced knowledge graph, the system comprising:

[0055] A memory storing executable program code;

[0056] a processor coupled to the memory;

[0057] The processor calls the executable program code stored in the memory to execute part or all of the steps in the operation and maintenance analysis data processing method based on enhanced knowledge graph disclosed in the first aspect of the present invention.

[0058] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the operation and maintenance analysis data processing method based on enhanced knowledge graph disclosed in the first aspect of the present invention.

[0059] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0060] The present invention can decompose operation and maintenance problems into multiple main parts based on the problem decomposition algorithm, and then obtain more accurate reorganized problems based on organizational rules, and then accurately answer the problems according to the problem type and the knowledge graph model corresponding to the system, thereby improving the efficiency of answering users' operation and maintenance problems, fundamentally improving the efficiency and effectiveness of system operation and maintenance, reducing operation and maintenance costs, and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] 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.

[0062] Figure 1 It is a flow chart of an operation and maintenance analysis data processing method based on an enhanced knowledge graph disclosed in an embodiment of the present invention.

[0063] Figure 2 It is a structural diagram of an operation and maintenance analysis data processing system based on an enhanced knowledge graph disclosed in an embodiment of the present invention.

[0064] Figure 3 It is a structural diagram of another operation and maintenance analysis data processing system based on enhanced knowledge graph disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work are within the scope of protection of the present invention.

[0066] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0067] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0068] The present invention discloses an operation and maintenance analysis data processing method and system based on enhanced knowledge graph, which can decompose the operation and maintenance problem into multiple main parts based on the problem decomposition algorithm, and then obtain more accurate reorganized problems based on the organization rules, and then accurately answer the problems according to the problem type and the knowledge graph model corresponding to the system, thereby improving the efficiency of answering the user's operation and maintenance problems, fundamentally improving the efficiency and effect of system operation and maintenance, reducing operation and maintenance costs, and improving user experience. The following are detailed descriptions.

[0069] Embodiment 1

[0070] See also Figure 1 , Figure 1 It is a flowchart of a method for processing operation and maintenance analysis data based on enhanced knowledge graph disclosed in an embodiment of the present invention. Figure 1 The described operation and maintenance analysis data processing method based on enhanced knowledge graph can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the operation and maintenance analysis data processing method based on the enhanced knowledge graph may include the following operations:

[0071] 101. Obtain the target user’s operation and maintenance issues regarding the target system.

[0072] 102. Decompose the operation and maintenance problem according to a preset problem decomposition algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problem.

[0073] 103. Based on preset language organization rules, multiple main parts are organized to obtain reorganized question data.

[0074] 104. Input the problem data and problem type into the knowledge graph model corresponding to the target system to obtain the solution results corresponding to the operation and maintenance problems.

[0075] It can be seen that the above-mentioned embodiments of the invention can decompose the operation and maintenance problems into multiple main parts based on the problem decomposition algorithm, and then obtain more accurate reorganized problems based on the organization rules, and then accurately answer the problems according to the problem type and the knowledge graph model corresponding to the system, thereby improving the efficiency of answering the user's operation and maintenance problems, fundamentally improving the efficiency and effectiveness of system operation and maintenance, reducing operation and maintenance costs, and improving user experience.

[0076] As an optional embodiment, in the above steps, the target system is a hardware system, a software system, a computing power server system or a power production equipment system.

[0077] It can be seen that through the above optional embodiments, the type of target system is limited, which can more accurately characterize the knowledge characteristics of the target system, so as to facilitate the solution of subsequent operation and maintenance problems, assist in improving the efficiency of solving user operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0078] As an optional embodiment, in the above steps, the main body part is a subject part, a predicate part, an object part, a user type part, a question type part, a question object part, a verb part, a preposition part or a noun part.

[0079] It can be seen that through the above optional embodiments, the type of the main part is limited, which can more accurately characterize the main parts of different language properties in the user's operation and maintenance problems, so as to facilitate the subsequent answers to the operation and maintenance problems, and assist in improving the efficiency of answering the user's operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0080] As an optional embodiment, in the above steps, the problem type is a crash problem, an experience problem, a response speed problem, a software problem, a hardware problem, a manual problem or a policy problem.

[0081] It can be seen that through the above optional embodiments, the types of problem types are limited, which can more accurately characterize the objects of user operation and maintenance problems, facilitate the subsequent solutions to operation and maintenance problems, and assist in improving the efficiency of solving user operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0082] As an optional embodiment, in the above steps, the operation and maintenance problem is decomposed according to a preset problem decomposition algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problem, including:

[0083] Based on multiple preset word segmentation algorithms, the operation and maintenance problem is segmented multiple times to obtain multiple word segmentation results; optionally, the word segmentation results include multiple phrases;

[0084] For each main part, each phrase in each word segmentation result is input into the probability prediction algorithm model corresponding to the main part to obtain the prediction probability corresponding to each phrase;

[0085] Determine the phrases whose predicted probability is higher than a preset probability threshold as the data content corresponding to the main part;

[0086] Determine the problem type corresponding to the operation and maintenance problem based on the data content corresponding to the problem type part and the problem object part.

[0087] It can be seen that through the above-mentioned optional embodiments, multiple word segmentations can be performed based on multiple word segmentation algorithms, and then the data content corresponding to different subjects can be determined based on the probability prediction models corresponding to different subject parts, and the type of question can be determined based on the data content corresponding to the question type part and the question object part, so as to facilitate the subsequent answers to operation and maintenance problems, assist in improving the efficiency of answering users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0088] As an optional embodiment, in the above steps, determining the problem type corresponding to the operation and maintenance problem according to the data content corresponding to the problem type part and the problem object part includes:

[0089] According to the data content corresponding to the question type part and the question object part, based on the preset prompt word combination rules, the corresponding question data is generated;

[0090] Input the question data into the trained LLM model to obtain the question types corresponding to the operation and maintenance problems.

[0091] It can be seen that through the above optional embodiments, the type of question can be determined according to the data content corresponding to the question type part and the question object part through the LLM model and prompt word combination rules, so as to facilitate the answer to subsequent operation and maintenance problems, assist in improving the efficiency of answering users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0092] As an optional embodiment, in the above steps, the multiple main parts are organized based on a preset language organization rule to obtain reorganized question data, including:

[0093] Based on the preset connection relationship between the main parts, determine multiple connection combinations corresponding to the multiple main parts;

[0094] For each connection combination, any phrase in the data content of each main part of the connection combination is determined as the main part data corresponding to the corresponding main part, and the main part data of all the main parts corresponding to the connection combination are connected in sequence to obtain the organization problem corresponding to the connection combination;

[0095] Repeat the previous step to obtain multiple organizational questions corresponding to the connection combination; optionally, the data similarity between different organizational questions is lower than a preset similarity threshold;

[0096] Based on the neural network algorithm, the problem data with the highest coherence are screened out from all organizational problems corresponding to all connection combinations.

[0097] It can be seen that through the above-mentioned optional embodiments, it is possible to repeatedly determine multiple connection combinations corresponding to multiple main parts through the preset main part connection relationship, and then exhaustively traverse multiple phrases of the data content in different main parts to obtain multiple organizational problems corresponding to different connection combinations, and perform consistency screening based on neural networks to obtain problem data that can be used to answer, so as to facilitate the answering of subsequent operation and maintenance problems, assist in improving the efficiency of answering users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0098] As an optional embodiment, in the above steps, based on the neural network algorithm, the question data with the highest coherence is screened out from all organizational questions corresponding to all connection combinations, including:

[0099] Inputting each organizational question corresponding to each connection combination into a trained coherence prediction neural network to obtain a coherence parameter corresponding to each organizational question corresponding to each connection combination; optionally, the coherence prediction neural network is trained using a training data set including a plurality of training question texts and corresponding coherence annotations;

[0100] Calculate the average value of the coherence parameters corresponding to all organizational problems corresponding to each connection combination to obtain the combined coherence corresponding to each connection combination;

[0101] The organization question with the highest coherence parameter corresponding to the connection combination with the highest combination coherence is determined as the reorganized question data.

[0102] It can be seen that through the above-mentioned optional embodiments, it is possible to perform consistency screening through the consistency prediction neural network to screen out the problem data with the highest consistency from all organizational problems corresponding to all connection combinations, so as to facilitate the solution of subsequent operation and maintenance problems, assist in improving the efficiency of solving users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0103] Embodiment 2

[0104] See also Figure 2 , Figure 2 : is a schematic diagram of the structure of an operation and maintenance analysis data processing system based on an enhanced knowledge graph disclosed in an embodiment of the present invention. Figure 2 The operation and maintenance analysis data processing system based on enhanced knowledge graph described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the operation and maintenance analysis data processing system based on the enhanced knowledge graph may include:

[0105] The acquisition module 201 is used to acquire the operation and maintenance issues of the target user for the target system.

[0106] The decomposition module 202 is used to decompose the operation and maintenance problem according to a preset problem decomposition algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problem.

[0107] The organization module 203 is used to organize the multiple main parts based on the preset language organization rules to obtain reorganized question data.

[0108] The answer module 204 is used to input the problem data and problem type into the knowledge graph model corresponding to the target system to obtain the answer result corresponding to the operation and maintenance problem.

[0109] It can be seen that the above-mentioned embodiments of the invention can decompose the operation and maintenance problems into multiple main parts based on the problem decomposition algorithm, and then obtain more accurate reorganized problems based on the organization rules, and then accurately answer the problems according to the problem type and the knowledge graph model corresponding to the system, thereby improving the efficiency of answering the user's operation and maintenance problems, fundamentally improving the efficiency and effectiveness of system operation and maintenance, reducing operation and maintenance costs, and improving user experience.

[0110] As an optional embodiment, the target system is a hardware system, a software system, a computing power server system or a power production equipment system.

[0111] It can be seen that through the above optional embodiments, the type of target system is limited, which can more accurately characterize the knowledge characteristics of the target system, so as to facilitate the solution of subsequent operation and maintenance problems, assist in improving the efficiency of solving user operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0112] As an optional embodiment, the main body part is a subject part, a predicate part, an object part, a user type part, a question type part, a question object part, a verb part, a preposition part or a noun part.

[0113] It can be seen that through the above optional embodiments, the type of the main part is limited, which can more accurately characterize the main parts of different language properties in the user's operation and maintenance problems, so as to facilitate the subsequent answers to the operation and maintenance problems, and assist in improving the efficiency of answering the user's operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0114] As an optional embodiment, the problem type is a crash problem, an experience problem, a response speed problem, a software problem, a hardware problem, a manual problem, or a policy problem.

[0115] It can be seen that through the above optional embodiments, the types of problem types are limited, which can more accurately characterize the objects of user operation and maintenance problems, facilitate the subsequent solutions to operation and maintenance problems, and assist in improving the efficiency of solving user operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0116] As an optional embodiment, the disassembly module disassembles the operation and maintenance problem according to a preset problem disassembly algorithm to obtain a plurality of main parts and problem types corresponding to the operation and maintenance problem, including:

[0117] Based on multiple preset word segmentation algorithms, the operation and maintenance problem is segmented multiple times to obtain multiple word segmentation results; optionally, the word segmentation results include multiple phrases;

[0118] For each main part, each phrase in each word segmentation result is input into the probability prediction algorithm model corresponding to the main part to obtain the prediction probability corresponding to each phrase;

[0119] Determine the phrases whose predicted probability is higher than a preset probability threshold as the data content corresponding to the main part;

[0120] Determine the problem type corresponding to the operation and maintenance problem based on the data content corresponding to the problem type part and the problem object part.

[0121] It can be seen that through the above-mentioned optional embodiments, multiple word segmentations can be performed based on multiple word segmentation algorithms, and then the data content corresponding to different subjects can be determined based on the probability prediction models corresponding to different subject parts, and the type of question can be determined based on the data content corresponding to the question type part and the question object part, so as to facilitate the subsequent answers to operation and maintenance problems, assist in improving the efficiency of answering users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0122] As an optional embodiment, the specific manner in which the disassembly module determines the problem type corresponding to the operation and maintenance problem according to the data content corresponding to the problem type part and the problem object part includes:

[0123] According to the data content corresponding to the question type part and the question object part, based on the preset prompt word combination rules, the corresponding question data is generated;

[0124] Input the question data into the trained LLM model to obtain the question types corresponding to the operation and maintenance problems.

[0125] It can be seen that through the above optional embodiments, the type of question can be determined according to the data content corresponding to the question type part and the question object part through the LLM model and prompt word combination rules, so as to facilitate the answer to subsequent operation and maintenance problems, assist in improving the efficiency of answering users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0126] As an optional embodiment, the organization module organizes the multiple main parts based on the preset language organization rules to obtain the reorganized question data in a specific manner, including:

[0127] Based on the preset connection relationship between the main parts, determine multiple connection combinations corresponding to the multiple main parts;

[0128] For each connection combination, any phrase in the data content of each main part of the connection combination is determined as the main part data corresponding to the corresponding main part, and the main part data of all the main parts corresponding to the connection combination are connected in sequence to obtain the organization problem corresponding to the connection combination;

[0129] Repeat the previous step to obtain multiple organizational questions corresponding to the connection combination; optionally, the data similarity between different organizational questions is lower than a preset similarity threshold;

[0130] Based on the neural network algorithm, the problem data with the highest coherence are screened out from all organizational problems corresponding to all connection combinations.

[0131] It can be seen that through the above-mentioned optional embodiments, it is possible to repeatedly determine multiple connection combinations corresponding to multiple main parts through the preset main part connection relationship, and then exhaustively traverse multiple phrases of the data content in different main parts to obtain multiple organizational problems corresponding to different connection combinations, and perform consistency screening based on neural networks to obtain problem data that can be used to answer, so as to facilitate the answering of subsequent operation and maintenance problems, assist in improving the efficiency of answering users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0132] As an optional embodiment, the specific method of the organization module to select the most coherent question data from all organization questions corresponding to all connection combinations based on the neural network algorithm includes:

[0133] Inputting each organizational question corresponding to each connection combination into a trained coherence prediction neural network to obtain a coherence parameter corresponding to each organizational question corresponding to each connection combination; optionally, the coherence prediction neural network is trained using a training data set including a plurality of training question texts and corresponding coherence annotations;

[0134] Calculate the average value of the coherence parameters corresponding to all organizational problems corresponding to each connection combination to obtain the combined coherence corresponding to each connection combination;

[0135] The organization question with the highest coherence parameter corresponding to the connection combination with the highest combination coherence is determined as the reorganized question data.

[0136] It can be seen that through the above-mentioned optional embodiments, it is possible to perform consistency screening through the consistency prediction neural network to screen out the problem data with the highest consistency from all organizational problems corresponding to all connection combinations, so as to facilitate the solution of subsequent operation and maintenance problems, assist in improving the efficiency of solving users' operation and maintenance problems, fundamentally improve the efficiency and effectiveness of system operation and maintenance, reduce operation and maintenance costs, and improve user experience.

[0137] Embodiment 3

[0138] See also Figure 3 , Figure 3 It is another operation and maintenance analysis data processing system based on enhanced knowledge graph disclosed in an embodiment of the present invention. Figure 3 The described operation and maintenance analysis data processing system based on enhanced knowledge graph is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the operation and maintenance analysis data processing system based on the enhanced knowledge graph may include:

[0139] A memory 301 storing executable program codes;

[0140] a processor 302 coupled to the memory 301;

[0141] Among them, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the operation and maintenance analysis data processing method based on the enhanced knowledge graph described in Example 1.

[0142] Embodiment 4

[0143] An embodiment of the present invention discloses a computer-readable storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the operation and maintenance analysis data processing method based on an enhanced knowledge graph described in Embodiment 1.

[0144] Embodiment 5

[0145] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the operation and maintenance analysis data processing method based on an enhanced knowledge graph described in Example 1.

[0146] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0147] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0148] For the convenience of description, the above device is described by dividing it into various units according to its functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0149] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0150] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0151] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0153] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0154] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0155] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0156] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0157] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0158] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0159] Finally, it should be noted that the operation and maintenance analysis data processing method and system based on enhanced knowledge graph disclosed in the embodiment of the present invention discloses only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing operation and maintenance analysis data based on enhanced knowledge graph, characterized in that: The method comprises: Obtain the target user's operation and maintenance issues for the target system; The operation and maintenance problem is decomposed according to a preset problem decomposition algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problem, including: Based on multiple preset word segmentation algorithms, the operation and maintenance problem is segmented multiple times to obtain multiple word segmentation results; the word segmentation results include multiple phrases; For each of the main parts, each of the word groups in each of the word segmentation results is input into the probability prediction algorithm model corresponding to the main part to obtain the prediction probability corresponding to each of the word groups; Determine the phrase whose predicted probability is higher than a preset probability threshold as the data content corresponding to the main part; Determine the problem type corresponding to the operation and maintenance problem according to the data content corresponding to the problem type part and the problem object part; The multiple main parts are organized based on preset language organization rules to obtain reorganized question data, including: Based on the preset main part connection relationship, determine multiple connection combinations corresponding to the multiple main parts; For each of the connection combinations, any one of the phrases in the data content of each of the main parts of the connection combination is determined as the main part data corresponding to the corresponding main part, and the main part data of all the main parts corresponding to the connection combination are sequentially connected to obtain the organization problem corresponding to the connection combination; Repeat the previous step to obtain multiple organizational questions corresponding to the connection combination; wherein the data similarity between different organizational questions is lower than a preset similarity threshold; Inputting each of the organizational questions corresponding to each of the connection combinations into a trained coherence prediction neural network to obtain a coherence parameter corresponding to each of the organizational questions corresponding to each of the connection combinations; the coherence prediction neural network is trained using a training data set including a plurality of training question texts and corresponding coherence annotations; Calculating an average value of the coherence parameters corresponding to all the organizational problems corresponding to each of the connection combinations to obtain the combined coherence corresponding to each of the connection combinations; Determine the organization question with the highest coherence parameter corresponding to the connection combination with the highest combination coherence as the reorganized question data; The problem data and the problem type are input into the knowledge graph model corresponding to the target system to obtain the answer result corresponding to the operation and maintenance problem.

2. The operation and maintenance analysis data processing method based on enhanced knowledge graph according to claim 1 is characterized in that: The target system is a hardware system, a software system, a computing power server system or a power production equipment system.

3. The operation and maintenance analysis data processing method based on enhanced knowledge graph according to claim 2 is characterized in that: The main body part is a subject part, a predicate part, an object part, a user type part, a question type part, a question object part, a verb part, a preposition part or a noun part.

4. The operation and maintenance analysis data processing method based on enhanced knowledge graph according to claim 3 is characterized in that: The types of problems include crash problems, experience problems, response speed problems, software problems, hardware problems, manual problems or policy problems.

5. The operation and maintenance analysis data processing method based on enhanced knowledge graph according to claim 1 is characterized in that: Determining the problem type corresponding to the operation and maintenance problem according to the data content corresponding to the problem type part and the problem object part includes: Generate corresponding question data according to the data content corresponding to the question type part and the question object part based on a preset prompt word combination rule; The question data is input into the trained LLM model to obtain the question type corresponding to the operation and maintenance question.

6. An operation and maintenance analysis data processing system based on enhanced knowledge graph, characterized in that: The system comprises: The acquisition module is used to obtain the operation and maintenance issues of the target system from the target user; The disassembly module is used to disassemble the operation and maintenance problem according to a preset problem disassembly algorithm to obtain multiple main parts and problem types corresponding to the operation and maintenance problem, including: Based on multiple preset word segmentation algorithms, the operation and maintenance problem is segmented multiple times to obtain multiple word segmentation results; the word segmentation results include multiple phrases; For each of the main parts, each of the word groups in each of the word segmentation results is input into the probability prediction algorithm model corresponding to the main part to obtain the prediction probability corresponding to each of the word groups; Determine the phrase whose predicted probability is higher than a preset probability threshold as the data content corresponding to the main part; Determine the problem type corresponding to the operation and maintenance problem according to the data content corresponding to the problem type part and the problem object part; The organization module is used to organize the multiple main parts based on a preset language organization rule to obtain reorganized question data, including: Based on the preset main part connection relationship, determine multiple connection combinations corresponding to the multiple main parts; For each of the connection combinations, any one of the phrases in the data content of each of the main parts of the connection combination is determined as the main part data corresponding to the corresponding main part, and the main part data of all the main parts corresponding to the connection combination are sequentially connected to obtain the organization problem corresponding to the connection combination; Repeat the previous step to obtain multiple organizational questions corresponding to the connection combination; wherein the data similarity between different organizational questions is lower than a preset similarity threshold; Inputting each of the organizational questions corresponding to each of the connection combinations into a trained coherence prediction neural network to obtain a coherence parameter corresponding to each of the organizational questions corresponding to each of the connection combinations; the coherence prediction neural network is trained using a training data set including a plurality of training question texts and corresponding coherence annotations; Calculating an average value of the coherence parameters corresponding to all the organizational problems corresponding to each of the connection combinations to obtain the combined coherence corresponding to each of the connection combinations; Determine the organization question with the highest coherence parameter corresponding to the connection combination with the highest combination coherence as the reorganized question data; The answer module is used to input the problem data and the problem type into the knowledge graph model corresponding to the target system to obtain the answer result corresponding to the operation and maintenance problem.

7. An operation and maintenance analysis data processing system based on enhanced knowledge graph, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the operation and maintenance analysis data processing method based on the enhanced knowledge graph as described in any one of claims 1-5.

Images