Intelligent fault handling method and system for power grid service website

Abstract

The present invention discloses an intelligent fault handling method and system for a power grid service website, wherein the method comprises: obtaining an input type according to a first service request submitted by a user; inputting the first service request into the matching processing model to obtain a first fault analysis result; obtaining a first matching result according to the first fault analysis result and a power service knowledge base; obtaining a second matching result between a first user type and a power service knowledge base; obtaining a first discreteness of the second matching result and the first matching result, and when the first discreteness meets a first predetermined condition, performing power fault handling according to the processing method in the first matching result according to the first matching result. The method solves the technical problem that the power grid service platform in the prior art has a slow response speed to the user power fault handling, low information processing efficiency, and leads to an imperfect construction of the platform service system.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to an intelligent fault handling method and system for a power grid service website. Background Art

[0002] "Internet +" has opened a new era of public services, integrating online innovative achievements with the economy, society, and people's livelihood to form new forms of social development and seek innovative development. It is a service project that conforms to the development of the times and the will of the people, and can optimize resource allocation to the maximum extent, open up new channels for energy services, and meet the personalized and diversified needs of end users. The power grid service website is an integrated power service platform that realizes functions such as user electricity information query, electricity payment, power outage information query, service point information query, service supervision, and fault reporting. During the commissioning of the power grid service platform, with the increasing number of business access and users, the platform is often not efficient enough in handling faults during the user's electricity use.

[0003] In the process of implementing the technical solution of the invention in the embodiment of the present application, the inventors of the present application found that the above technology has at least the following technical problems:

[0004] The power grid service platform has a slow response speed to user power failures and low information processing efficiency, resulting in an incomplete construction of the platform service system. Summary of the invention

[0005] The embodiment of the present application provides an intelligent fault handling method and system for a power grid service website, which solves the technical problem that the power grid service platform in the prior art has a slow response speed to the user's power failure handling, low information processing efficiency, and leads to an imperfect construction of the platform service system. The technical purpose of improving the efficiency and accuracy of power failure handling is achieved by building a power failure database and performing intelligent analysis of power failures based on artificial intelligence.

[0006] In view of the above problems, an embodiment of the present application provides an intelligent fault handling method and system for a power grid service website.

[0007] In a first aspect, the present application provides an intelligent fault handling method for a power grid service website, wherein the method includes: obtaining a first service request; obtaining a first request input type according to the first service request; obtaining a preset model library; performing model matching from the preset model library according to the first request input type to obtain a matching processing model; inputting the first service request into the matching processing model to obtain a first fault analysis result; obtaining a power service knowledge base; obtaining a first matching result according to the first fault analysis result and the power service knowledge base; obtaining a first user type according to the first service request; obtaining a second matching result according to the first user type and the power service knowledge base; obtaining a first discreteness according to the second matching result and the first matching result, the first discreteness being the discreteness between the second matching result and the first matching result; judging whether the first discreteness satisfies a first predetermined condition; and when satisfied, obtaining a first processing instruction according to the first matching result, the first processing instruction being used to perform power fault handling according to the processing method in the first matching result.

[0008] On the other hand, the present application also provides an intelligent fault handling system for a power grid service website, wherein the system includes: a first acquisition unit, the first acquisition unit is used to obtain a first service request; a second acquisition unit, the second acquisition unit is used to obtain a first request input type according to the first service request; a third acquisition unit, the third acquisition unit is used to obtain a preset model library; a fourth acquisition unit, the fourth acquisition unit is used to perform model matching from the preset model library according to the first request input type to obtain a matching processing model; a first input unit, the first input unit is used to input the first service request into the matching processing model to obtain a first fault analysis result; a fifth acquisition unit, the fifth acquisition unit is used to obtain a power service knowledge base; a sixth acquisition unit, the sixth acquisition unit is used to obtain a first fault analysis result, the ... An electric power service knowledge base is provided to obtain a first matching result; a seventh obtaining unit is used to obtain a first user type according to the first service request; an eighth obtaining unit is used to obtain a second matching result according to the first user type and the electric power service knowledge base; a ninth obtaining unit is used to obtain a first discreteness according to the second matching result and the first matching result, the first discreteness being the discreteness between the second matching result and the first matching result; a first judging unit is used to judge whether the first discreteness satisfies a first predetermined condition; a tenth obtaining unit is used to obtain a first processing instruction according to the first matching result when the condition is satisfied, the first processing instruction being used to perform electric power fault processing according to the processing method in the first matching result.

[0009] On the other hand, an embodiment of the present application also provides an intelligent fault handling learning system for a power grid service website, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the program.

[0010] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0011] By using big data information processing technology to build an information processing model database, different neural network models are matched from the database according to different fault types for fault analysis; a power service knowledge base is built to match the output of the neural network model with the knowledge base, thereby correcting and improving the fault analysis results, and further determining the final fault analysis results through discrete analysis. The technical purpose of improving the efficiency and accuracy of power fault processing by building a power fault database and conducting intelligent analysis of power faults based on artificial intelligence is achieved.

[0012] The above description is an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A flowchart of an intelligent fault handling method for a power grid service website according to an embodiment of the present application;

[0014] Figure 2 This is a structural diagram of an intelligent fault handling system for a power grid service website according to an embodiment of the present application;

[0015] Figure 3 It is a schematic diagram of the structure of an exemplary electronic device according to an embodiment of the present application.

[0016] Explanation of the figure marks: first obtaining unit 11, second obtaining unit 12, third obtaining unit 13, fourth obtaining unit 14, first input unit 15, fifth obtaining unit 16, sixth obtaining unit 17, seventh obtaining unit 18, eighth obtaining unit 19, ninth obtaining unit 20, first judging unit 21, tenth obtaining unit 22, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0017] The embodiment of the present application provides an intelligent fault handling method and system for a power grid service website, which solves the technical problem that the power grid service platform in the prior art has a slow response speed to the user's power failure handling, low information processing efficiency, and leads to an imperfect construction of the platform service system. The technical purpose of improving the efficiency and accuracy of power failure handling is achieved by building a power failure database and performing intelligent analysis of power failures based on artificial intelligence.

[0018] Below, example embodiments of the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein.

[0019] Application Overview

[0020] The power grid service website is an integrated power service platform that realizes functions such as user power consumption information query, power consumption payment, power outage information query, service outlet information query, service supervision, fault reporting, etc. During the commissioning of the power grid service platform, with the increasing number of business access and users, the platform is often not efficient enough in handling faults in the user's power consumption process. There are also technical problems in the prior art that the power grid service platform has a slow response speed to the user's power consumption fault handling and low information processing efficiency, resulting in an imperfect construction of the platform service system.

[0021] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows:

[0022] The present application provides an intelligent fault handling method for a power grid service website, wherein the method includes: obtaining a first service request; obtaining a first request input type according to the first service request; obtaining a preset model library; performing model matching from the preset model library according to the first request input type to obtain a matching processing model; inputting the first service request into the matching processing model to obtain a first fault analysis result; obtaining a power service knowledge base; obtaining a first matching result according to the first fault analysis result and the power service knowledge base; obtaining a first user type according to the first service request; obtaining a second matching result according to the first user type and the power service knowledge base; obtaining a first discreteness according to the second matching result and the first matching result, the first discreteness being the discreteness between the second matching result and the first matching result; judging whether the first discreteness satisfies a first predetermined condition; and when satisfied, obtaining a first processing instruction according to the first matching result, the first processing instruction being used to perform power fault handling according to the processing method in the first matching result.

[0023] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0024] Embodiment 1

[0025] like Figure 1 As shown, an embodiment of the present application provides an intelligent fault handling method for a power grid service website, wherein the method includes:

[0026] Step S100: obtaining a first service request;

[0027] Specifically, the user service end of the power grid service platform provides users with functions such as registration, login, business processing, fee payment, information interaction, identity verification, and fault reporting, and includes an application publishing management portal provided for developers and an operation management platform provided for service publishers. When a power failure occurs, the first service request can be obtained by the user reporting a power failure, or the platform detects the power failure through real-time information collection, thereby obtaining a fault reporting request. After obtaining the first service request, the platform sends the obtained first service request to the relevant fault handling service center, and the relevant service center performs fault analysis and subsequent processing. The first service request is a fault reporting request when a fault occurs in the electronic system, including the fault content and the corresponding electrical equipment and power location information, which lays the foundation for the service platform to further handle the fault.

[0028] Step S200: obtaining a first request input type according to the first service request;

[0029] Specifically, the first request input type is the fault form of the power failure. For example, the first request input type can be divided into: disconnection fault, cable fault, disconnection switch fault, transformer fault, component detachment, etc. according to the fault equipment; it can be divided into: insulation aging, weather reasons, geographical environment factors, construction reasons according to the fault cause; it can be divided into grounding fault, short circuit fault, disconnection fault, etc. according to the electrical principle. After the platform obtains the first service request, it extracts information from the first service request to obtain the first request input type, and then performs the next step of processing the power failure according to the first request input type.

[0030] Step S300: obtaining a preset model library;

[0031] Step S400: performing model matching from the preset model library according to the first request input type to obtain a matching processing model;

[0032] Specifically, the first preset model library is a different neural network model for analyzing fault handling methods corresponding to different power fault forms. Based on big data information processing technology, the platform constructs a preset model database based on historical fault handling data information. Neural Networks (NN) is a complex network system formed by a large number of simple processing units (called neurons) that are widely interconnected. It reflects many basic characteristics of human brain functions and is a highly complex nonlinear dynamic learning system. It can obtain an accurate output result of the fault handling method by training and learning the input data. Since different fault forms correspond to different data training models, the data processing model corresponding to the first request input type is obtained by matching the model from the preset model library according to the first request input type, so that the data training and output result information are more accurate.

[0033] Step S500: inputting the first service request into the matching processing model to obtain a first fault analysis result;

[0034] Specifically, the first service request is used as input data and input into the matching processing model for data training. The matching processing model has the characteristics of continuous learning and gaining experience to process data, so that the first fault analysis result is more accurate. The first fault analysis result includes the fault analysis result obtained by training and learning the content and form of the fault service request, including the impact information of the fault on the power system, such as the current change value, the state of the faulty equipment, etc. The fault processing result is obtained based on the neural network model, making the process of fault analysis and processing more efficient and intelligent.

[0035] Step S600: obtaining a power service knowledge base;

[0036] Step S700: obtaining a first matching result according to the first fault analysis result and the power service knowledge base;

[0037] Specifically, the power service knowledge base is established based on big data, and includes component information of each power component in the power system connected to the power grid service website, power data information, normal power consumption characteristics and equipment information of each electrical appliance, as well as fault line characteristics, electrical appliance fault characteristics, fault circuit current change values, etc. By constructing the power service knowledge base, the system can obtain the first matching result by matching the analysis result with the power service knowledge base when obtaining the fault characteristics, equipment status and other characteristics in the first fault analysis result, including obtaining the fault cause and related component information corresponding to the power service knowledge base based on the first fault analysis result, thereby further supplementing and improving the fault analysis result, laying a foundation for fault handling.

[0038] Step S800: Obtaining a first user type according to the first service request;

[0039] Step S900: obtaining a second matching result according to the first user type and the power service knowledge base;

[0040] Specifically, when a power system fails, different types of users have different types of power consumption intensities and factors affecting power consumption. For example, user types include catering, commercial buildings, residential buildings, office buildings, construction units, factories, etc. If the first user type is a construction unit, the line is easily affected by the pollution level and construction nature of the construction site, and is prone to line aging and other failures. Therefore, according to the first service request, the first user type is obtained, and the first user type is input into the power service database for matching, and the range of fault occurrence types corresponding to the user type is obtained, that is, the second matching result, so that the fault can be analyzed more accurately.

[0041] Step S1000: obtaining a first discreteness according to the second matching result and the first matching result, where the first discreteness is a discreteness between the second matching result and the first matching result;

[0042] Specifically, the degree of discreteness is used to characterize the size of the difference between individuals. The larger the first discreteness is, the larger the difference between the second matching result and the first matching result is; conversely, the smaller the difference between the second matching result and the first matching result is. Due to the different types of power faults of different user types, if the fault information in the second matching result is more consistent with the fault information in the first matching result, the smaller the first discreteness is, the higher the accuracy of the first matching result is. By obtaining the first discreteness, the accuracy of fault analysis is improved.

[0043] Step S1100: determining whether the first discreteness satisfies a first predetermined condition;

[0044] Step S1200: When satisfied, a first processing instruction is obtained according to the first matching result, wherein the first processing instruction is used to perform power fault processing according to the processing method in the first matching result.

[0045] Specifically, when the first matching result has the first accuracy, the condition for the next step of fault processing is met. Based on the first accuracy, the similarity between the first matching result and the second matching result is obtained, that is, the threshold of the first discreteness is determined, that is, the first predetermined condition. When the first discreteness meets the first predetermined condition, the first matching result is sent to the system, and the system obtains the first processing instruction. The fault processing method is decided based on the fault information in the first matching result, and after the processing method is obtained, the processing method information is automatically sent to the user and the relevant fault reporting and processing responsible person. By stipulating the first predetermined condition, the accuracy of fault analysis results obtained based on artificial intelligence is further improved.

[0046] Furthermore, step S200 in the embodiment of the present application further includes:

[0047] Step S210: obtaining a first request input form according to the first request input type;

[0048] Step S220: obtaining a first form, a second form, and up to an Nth form according to the first request input form, where N is a natural number greater than 2;

[0049] Step S230: obtaining first-format content according to the first service request and the first format;

[0050] Step S240: obtaining content in a second format according to the first service request and the second format;

[0051] Step S250: until the Nth format content is obtained according to the first service request and the Nth format;

[0052] Step S260: obtaining content proportion information according to the first form content, the second form content, and up to the Nth form content;

[0053] Step S270: Arrange the content proportion information from large to small to obtain first proportion information, where the first proportion information is the form information and form content that are ranked first;

[0054] Step S280: obtaining form information of the first proportion information according to the first proportion information, and matching from the preset model library according to the form information of the first proportion information to obtain a first form model;

[0055] Step S290: obtaining the formal content of the first proportion information from the first proportion information, and inputting the formal content of the first proportion information into the first formal model to obtain a second fault analysis result;

[0056] Step S2100: obtaining second proportion information, where the second proportion information is the second-ranked form information and form content;

[0057] Step S2110: matching from the preset model library according to the form information of the second proportion information to obtain a second form model;

[0058] Step S2120: inputting the formal content of the second proportion information into the second formal model to obtain a third fault analysis result;

[0059] Step S2130: until the N+1th fault analysis result is obtained according to the Nth proportion information;

[0060] Step S2140: setting the second fault analysis result as a discrete center;

[0061] Step S2150: obtaining a second discreteness according to the second fault analysis result, the third fault analysis result, and up to the N+1th fault analysis result;

[0062] Step S2160: determining whether the second discreteness satisfies the first predetermined condition;

[0063] Step S2170: When satisfied, determine a final fault analysis result according to the second fault analysis result, the third fault analysis result, and the Nth fault analysis result.

[0064] Specifically, since the power grid service platform includes multiple platforms such as websites, mini-programs, and APPs for business architecture, users can obtain information and power services on multiple platforms. The first request input form includes the fault reporting request information of the user received by the system from each platform, and the request input form includes multiple forms such as text, image, and voice. Since different information input forms contain different amounts of information, the content information of each form such as the first form, the second form, and the Nth form is obtained respectively, and the amount of content data contained in each form is analyzed to obtain the content proportion in each form. By sorting the content of each form according to the size of the content proportion, the information input form corresponding to the top content proportion is obtained, that is, the information input form containing the largest amount of information, and the fault content in this form is analyzed first, thereby ensuring the efficiency of information processing.

[0065] Further, after determining the request form for priority analysis, model matching is performed based on the form content, and the form content of the second proportion information is input into the second form model for training and learning, and the third fault analysis result is obtained through continuous learning. After completing the fault analysis of the form content of the second proportion information, fault analysis is performed on the content information of the first form, the second form, and up to the Nth form respectively, and the second fault analysis result is used as the discrete center to calculate the degree of discreteness between each fault analysis result relative to the second fault analysis result, the second discreteness. If the second discreteness satisfies the first predetermined condition, that is, the closer each fault analysis result is to the second fault analysis result, the higher the reference of each fault analysis result obtained based on different form information. Therefore, the result is corrected according to different fault analysis results, so as to obtain the final first fault analysis result.

[0066] Furthermore, step S2160 of the embodiment of the present application also includes:

[0067] Step S2161: when the second dispersion does not meet the first predetermined condition, cluster analysis is performed according to the second fault analysis result, the third fault analysis result, and up to the N+1th fault analysis result to obtain a first clustering result;

[0068] Step S2162: Obtain the final fault analysis result according to the first clustering result.

[0069] Specifically, cluster analysis refers to the analysis process of grouping a collection of physical or abstract objects into multiple classes composed of similar objects, and the goal is to collect data for classification based on similarity. When the second discreteness does not meet the first predetermined condition, the differences between different fault analysis results obtained based on different forms of content are large, and it is necessary to further perform cluster analysis on the second fault analysis result, the third fault analysis result, and the N+1th fault analysis result. Through cluster analysis, the content information with the highest repetition value in the above fault analysis results is obtained, that is, the first cluster result is obtained. Therefore, based on the first cluster result, the first fault analysis result is corrected to determine the final fault analysis result. By performing cluster analysis on content analysis results of different forms, the purpose of obtaining data similarity content to correct the data processing results is achieved, so that the results are more accurate.

[0070] Furthermore, step S1100 in the embodiment of the present application also includes:

[0071] Step S1110: when the first dispersion does not satisfy the first predetermined condition, obtaining first user location information according to the first service request;

[0072] Step S1120: Obtaining first user power element information according to the first user type and the first user location information;

[0073] Step S1130: obtaining an element fault analysis result according to the first user power element information and the first fault analysis result;

[0074] Step S1140: obtaining a third matching result according to the element fault analysis result and the power service knowledge base;

[0075] Step S1150: Obtain a second processing instruction according to the third matching result.

[0076] Specifically, when the first discreteness does not meet the first predetermined condition, based on the Internet of Things and big data technology, the specific electricity location information of the user who requested the fault report is obtained, so as to combine the user location and the user's electricity type, and obtain the electricity element information in the first user's power system by building a feature database, including line layout information and main component information. Then, based on the first user's power element information and the first fault analysis result output by the neural network model, the fault analysis result corresponding to each power element is obtained. The element fault analysis result includes the corresponding abnormal state of each circuit element, the fault cause of each corresponding part, etc., so as to obtain the fault handling method for each element in the first power circuit element information according to the fault content corresponding to each element and the power service knowledge base, that is, to obtain the third matching result. By obtaining the fault handling content of each element separately, the fault handling is made more refined, thereby achieving the technical purpose of improving the efficiency and success rate of fault handling.

[0077] Furthermore, step S2170 of the embodiment of the present application also includes:

[0078] Step S2171: constructing a processing data record library according to the first processing instruction, the first matching result, and the first user location information;

[0079] Step S2172: Obtaining a preset time threshold;

[0080] Step S2173: within the preset time threshold, obtaining a first processing aggregate amount according to the processing data record library, wherein the first processing aggregate amount is the number of processing records identical to the first processing instruction, the first matching result, and the first user location information;

[0081] Step S2174: When the first processing aggregation amount reaches the aggregation threshold, a first warning instruction is obtained.

[0082] Specifically, the system can collect and store the fault handling content, fault analysis results, fault occurrence time, fault occurrence location and other information in each fault reporting information in the historical work log, so as to construct the processing data record library based on the content information in the historical work log. Within the preset time threshold, the number of fault handling times of the same location, fault type and content is obtained according to the processing data record library, that is, the first processing aggregation. If the first processing aggregation reaches the aggregation threshold, it indicates that the fault is frequent and the fault part needs to be repaired or replaced. Therefore, by obtaining the first warning instruction, warning information is sent to the fault-frequent area to intelligently monitor the safety of electricity use.

[0083] Furthermore, step S2173 of the embodiment of the present application also includes:

[0084] Step S21731: obtaining position aggregation feature information according to the first processing aggregation amount and the processing data record library;

[0085] Step S21732: obtaining the aggregated location user information according to the location aggregated feature information, wherein the aggregated location user information does not exist in the processed data record library;

[0086] Step S21733: Obtaining first power reminder information according to the first processing instruction;

[0087] Step S21734: Obtain a first group reminder instruction based on the user information of the gathering location and the first power reminder information, wherein the first group reminder instruction is used to group-send the first power reminder information to the users of the gathering location.

[0088] Specifically, according to the first processing aggregate and the processing data record library, the aggregation characteristics of different locations of the processing aggregate are obtained. For example, if the user type is the catering industry, the location aggregation characteristic of this location is a high density of people. Based on big data technology, the personnel information of non-local power system users gathered at this location, that is, the user information of the aggregation location, is obtained, and the first power reminder information is obtained by the system, and the reminder information is sent to the user mobile terminal of each aggregated user, so as to realize timely reminders of potential power risks at the location of the aggregated users, thereby further ensuring power safety.

[0089] Furthermore, step S400 in the embodiment of the present application also includes:

[0090] Step S410: obtaining first service request content information according to the first service request;

[0091] Step S420: taking the first service request content information as first input information;

[0092] Step S430: inputting the first input information into the matching processing model, wherein the matching processing model is obtained by training multiple sets of training data, each set of data in the multiple sets of training data includes the first input information and identification information for identifying the first fault analysis result;

[0093] Step S440: obtaining an output result of the matching processing model, wherein the output result includes the first fault analysis result.

[0094] Specifically, the matching processing model is a neural network model, and the neural network model is obtained by training multiple sets of training data. The process of training the neural network model by training data is essentially a supervised learning process. Each set of training data in the multiple sets of training data includes the first input information and identification information for identifying the first fault analysis result; using the first input information and the identification information for identifying the first input information, multiple sets of training data are formed. When the first input information is obtained, the neural network model will output the identification information of the first fault analysis result to verify the first fault analysis result output by the neural network model. If the output first fault analysis result is consistent with the identified first fault analysis result, the supervised learning of this data is completed, and the supervised learning of the next set of data is carried out; if the output first fault analysis result is inconsistent with the identified first fault analysis result, the neural network model itself is adjusted until the neural network model reaches the expected accuracy, and then the supervised learning of the next set of data is carried out. Through the training data, the neural network model itself is continuously corrected and optimized, and the accuracy of the neural network model in processing the data is improved through the supervised learning process, thereby making the first fault analysis result more accurate.

[0095] In summary, the intelligent fault handling method for a power grid service website provided in the embodiment of the present application has the following technical effects:

[0096] 1. By using big data information processing technology to build an information processing model database, different neural network models are matched from the database according to different fault types for fault analysis; a power service knowledge base is built to match the output of the neural network model with the knowledge base, so as to correct and improve the fault analysis results, and further determine the final fault analysis results through discrete analysis. The technical purpose of improving the efficiency and accuracy of power fault handling by building a power fault database and conducting intelligent analysis of power faults based on artificial intelligence is achieved.

[0097] 2. Since the neural network model is used for training and learning, the first input information is input into the matching processing model. Based on the characteristics of the training model that can continuously learn and gain experience to process data, the first fault analysis result obtained is more accurate.

[0098] 3. By performing fault analysis on content information uploaded by users in different forms and clustering the results, the data is clustered and similarity mined to obtain content information with the highest similarity. The fault analysis results are then corrected based on the clustering results, making the final fault analysis results more accurate.

[0099] Embodiment 2

[0100] Based on the same inventive concept as the intelligent fault handling method of a power grid service website in the aforementioned embodiment, the present invention also provides an intelligent fault handling system for a power grid service website, such as Figure 2 As shown, the system comprises:

[0101] A first obtaining unit 11, wherein the first obtaining unit 11 is used to obtain a first service request;

[0102] A second obtaining unit 12, the second obtaining unit 12 is used to obtain a first request input type according to the first service request;

[0103] A third obtaining unit 13, wherein the third obtaining unit 13 is used to obtain a preset model library;

[0104] A fourth obtaining unit 14, the fourth obtaining unit 14 is used to perform model matching from the preset model library according to the first request input type to obtain a matching processing model;

[0105] A first input unit 15, the first input unit 15 is used to input the first service request into the matching processing model to obtain a first fault analysis result;

[0106] A fifth obtaining unit 16, wherein the fifth obtaining unit 16 is used to obtain a power service knowledge base;

[0107] A sixth obtaining unit 17, wherein the sixth obtaining unit 17 is configured to obtain a first matching result according to the first fault analysis result and the power service knowledge base;

[0108] a seventh obtaining unit 18, wherein the seventh obtaining unit 18 is configured to obtain a first user type according to the first service request;

[0109] An eighth obtaining unit 19, wherein the eighth obtaining unit 19 is used to obtain a second matching result according to the first user type and the power service knowledge base;

[0110] A ninth obtaining unit 20, the ninth obtaining unit 20 is used to obtain a first discreteness according to the second matching result and the first matching result, the first discreteness being a discreteness between the second matching result and the first matching result;

[0111] A first judging unit 21, the first judging unit 21 is used to judge whether the first discreteness satisfies a first predetermined condition;

[0112] The tenth obtaining unit 22 is used to obtain a first processing instruction according to the first matching result when the condition is met, and the first processing instruction is used to perform power fault processing according to the processing method in the first matching result.

[0113] Furthermore, the system also includes:

[0114] an eleventh obtaining unit, the eleventh obtaining unit being configured to obtain a first request input form according to the first request input type;

[0115] a twelfth obtaining unit, the twelfth obtaining unit being used to obtain a first form, a second form, and up to an Nth form according to the first request input form, wherein N is a natural number greater than 2;

[0116] a thirteenth obtaining unit, configured to obtain content in a first format according to the first service request and the first format;

[0117] a fourteenth obtaining unit, configured to obtain content in a second format according to the first service request and the second format;

[0118] a fifteenth obtaining unit, the fifteenth obtaining unit being configured to obtain content in an Nth format according to the first service request and the Nth format;

[0119] A sixteenth obtaining unit, the sixteenth obtaining unit being configured to obtain content proportion information according to the first form of content, the second form of content, and up to the Nth form of content;

[0120] a seventeenth obtaining unit, the seventeenth obtaining unit being used to arrange the content proportion information from large to small to obtain first proportion information, wherein the first proportion information is the form information and the form content arranged first;

[0121] an eighteenth obtaining unit, the eighteenth obtaining unit being configured to obtain form information of the first proportion information according to the first proportion information, and to perform matching from the preset model library according to the form information of the first proportion information to obtain a first form model;

[0122] a nineteenth obtaining unit, the nineteenth obtaining unit being configured to obtain a form content of the first proportion information according to the first proportion information, and input the form content of the first proportion information into the first form model to obtain a second fault analysis result;

[0123] a twentieth obtaining unit, the twentieth obtaining unit being used to obtain second proportion information, the second proportion information being the second-ranked form information and form content;

[0124] A twenty-first obtaining unit, the twenty-first obtaining unit is used to match from the preset model library according to the form information of the second proportion information to obtain a second form model;

[0125] A second input unit, the second input unit is used to input the form content of the second proportion information into the second form model to obtain a third fault analysis result;

[0126] A twenty-second obtaining unit, the twenty-second obtaining unit being used to obtain an N+1th fault analysis result according to the Nth proportion information;

[0127] A twenty-third obtaining unit, the twenty-third obtaining unit is used to set the second fault analysis result as a discrete center;

[0128] a twenty-fourth obtaining unit, the twenty-fourth obtaining unit being configured to obtain a second discreteness according to the second fault analysis result, the third fault analysis result, and up to the N+1th fault analysis result;

[0129] a second judging unit, the second judging unit being used to judge whether the second dispersion satisfies the first predetermined condition;

[0130] The twenty-fifth obtaining unit is used to determine a final fault analysis result according to the second fault analysis result, the third fault analysis result, and the Nth fault analysis result when conditions are met.

[0131] Furthermore, the system also includes:

[0132] a twenty-sixth obtaining unit, configured to, when the second discreteness does not satisfy the first predetermined condition, perform cluster analysis according to the second fault analysis result, the third fault analysis result, and up to the N+1th fault analysis result to obtain a first clustering result;

[0133] The twenty-seventh obtaining unit is used to obtain the final fault analysis result according to the first clustering result.

[0134] Furthermore, the system also includes:

[0135] a twenty-eighth obtaining unit, configured to obtain first user location information according to the first service request when the first dispersion does not satisfy the first predetermined condition;

[0136] a twenty-ninth obtaining unit, the twenty-ninth obtaining unit being configured to obtain first user power element information according to the first user type and the first user location information;

[0137] a 30th obtaining unit, configured to obtain an element fault analysis result according to the first user power element information and the first fault analysis result;

[0138] a thirty-first obtaining unit, the thirty-first obtaining unit being configured to obtain a third matching result according to the element fault analysis result and the power service knowledge base;

[0139] A thirty-second obtaining unit is used to obtain a second processing instruction according to the third matching result.

[0140] Furthermore, the system also includes:

[0141] A thirty-third obtaining unit, the thirty-third obtaining unit is used to construct a processing data record library according to the first processing instruction, the first matching result, and the first user location information;

[0142] A thirty-fourth obtaining unit, the thirty-fourth obtaining unit is used to obtain a preset time threshold;

[0143] a thirty-fifth obtaining unit, the thirty-fifth obtaining unit being used to obtain, within the preset time threshold, a first processing aggregate amount according to the processing data record library, the first processing aggregate amount being the number of processing records identical to the first processing instruction, the first matching result, and the first user location information;

[0144] The fortieth obtaining unit is used to obtain a first early warning instruction when the first processing aggregation amount reaches an aggregation threshold.

[0145] Furthermore, the system also includes:

[0146] a forty-first obtaining unit, the forty-first obtaining unit being used to obtain position aggregation feature information according to the first processing aggregation amount and the processing data record library;

[0147] a 42nd obtaining unit, the 42nd obtaining unit being used to obtain the aggregated location user information according to the location aggregated feature information, the aggregated location user information not existing in the processed data record library;

[0148] a forty-third obtaining unit, the forty-third obtaining unit being configured to obtain first power reminder information according to the first processing instruction;

[0149] The forty-fourth obtaining unit is used to obtain a first group reminder instruction according to the user information of the gathering location and the first power reminder information, and the first group reminder instruction is used to group-send the first power reminder information to the users of the gathering location.

[0150] Furthermore, the system also includes:

[0151] a forty-fifth obtaining unit, the forty-fifth obtaining unit being configured to obtain first service request content information according to the first service request;

[0152] a forty-sixth obtaining unit, the forty-sixth obtaining unit being configured to use the first service request content information as first input information;

[0153] a third input unit, the third input unit being used to input the first input information into the matching processing model, the matching processing model being obtained by training with multiple sets of training data, each set of data in the multiple sets of training data comprising the first input information and identification information for identifying a first fault analysis result;

[0154] A forty-seventh obtaining unit, the forty-seventh obtaining unit is used to obtain an output result of the matching processing model, the output result including the first fault analysis result.

[0155] The foregoing Figure 1 The intelligent fault handling method and specific examples of a power grid service website in Example 1 are also applicable to an intelligent fault handling system of a power grid service website in this embodiment. Through the above detailed description of the intelligent fault handling method of a power grid service website, technical personnel in this field can clearly know the intelligent fault handling system of a power grid service website in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0156] Exemplary Electronic Devices

[0157] Reference below Figure 3 To describe the electronic device of the embodiment of the present application.

[0158] Figure 3 The figure shows a schematic structural diagram of an electronic device according to an embodiment of the present application.

[0159] Based on the inventive concept of the intelligent fault handling method for a power grid service website in the aforementioned embodiment, the present invention also provides an intelligent fault handling system for a power grid service website, on which a computer program is stored, and when the program is executed by a processor, the steps of any method of the intelligent fault handling method for a power grid service website described above are implemented.

[0160] Among them, Figure 3In the embodiment of the present invention, a bus architecture (represented by bus 300) is shown, which may include any number of interconnected buses and bridges, and bus 300 links various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are not further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium.

[0161] The processor 302 is responsible for managing the bus 300 and general processing, while the memory 304 may be used to store data used by the processor 302 when performing operations.

[0162] The present application provides an intelligent fault handling method for a power grid service website, wherein the method includes: obtaining a first service request; obtaining a first request input type according to the first service request; obtaining a preset model library; performing model matching from the preset model library according to the first request input type to obtain a matching processing model; inputting the first service request into the matching processing model to obtain a first fault analysis result; obtaining a power service knowledge base; obtaining a first matching result according to the first fault analysis result and the power service knowledge base; obtaining a first user type according to the first service request; obtaining a second matching result according to the first user type and the power service knowledge base; obtaining a first discreteness according to the second matching result and the first matching result, the first discreteness being the discreteness between the second matching result and the first matching result; judging whether the first discreteness satisfies a first predetermined condition; and when satisfied, obtaining a first processing instruction according to the first matching result, the first processing instruction being used to perform power fault handling according to the processing method in the first matching result.

[0163] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0164] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks 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 generate 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 system that specifies the functions of a box or multiple boxes.

[0165] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0166] 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 of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0167] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent fault handling method for a power grid service website, in, The method comprises: Get the first service request; According to the first service request, obtaining a first request input type; Get a library of preset models; Performing model matching from the preset model library according to the first request input type to obtain a matching processing model; Inputting the first service request into the matching processing model to obtain a first fault analysis result; Access to the electric service knowledge base; Obtaining a first matching result according to the first fault analysis result and the power service knowledge base; Obtaining a first user type according to the first service request; Obtaining a second matching result according to the first user type and the power service knowledge base; Obtaining a first discreteness according to the second matching result and the first matching result, where the first discreteness is a discreteness between the second matching result and the first matching result; Determining whether the first discreteness satisfies a first predetermined condition; When the condition is satisfied, obtaining a first processing instruction according to the first matching result, wherein the first processing instruction is used to process the power fault according to the processing method in the first matching result; The method comprises: Obtaining a first request input form according to the first request input type; According to the first request input form, a first form, a second form, and up to an Nth form are obtained, wherein N is a natural number greater than 2; Obtaining first-format content according to the first service request and the first format; Obtaining content in a second format according to the first service request and the second format; Until the Nth format content is obtained according to the first service request and the Nth format; Obtaining content proportion information according to the first form content, the second form content, and up to the Nth form content; Arrange the content proportion information from large to small to obtain first proportion information, where the first proportion information is the form information and form content that are ranked first; Obtaining form information of the first proportion information according to the first proportion information, and matching from the preset model library according to the form information of the first proportion information to obtain a first form model; Obtaining the formal content of the first proportion information according to the first proportion information, and inputting the formal content of the first proportion information into the first formal model to obtain a second fault analysis result; Obtaining second proportion information, where the second proportion information is the second-ranked form information and form content; According to the form information of the second proportion information, matching is performed from the preset model library to obtain a second form model; Inputting the formal content of the second proportion information into the second formal model to obtain a third fault analysis result; Until the N+1th fault analysis result is obtained according to the Nth proportion information; Setting the second fault analysis result as a discrete center; Obtaining a second discreteness according to the second fault analysis result, the third fault analysis result, and up to the N+1th fault analysis result; Determining whether the second discreteness satisfies the first predetermined condition; When the conditions are met, a final fault analysis result is determined according to the second fault analysis result, the third fault analysis result, and the Nth fault analysis result.

2. The method according to claim 1, in, After determining whether the second dispersion satisfies the first predetermined condition, the method further comprises: When the second dispersion does not meet the first predetermined condition, performing cluster analysis according to the second fault analysis result, the third fault analysis result, and up to the N+1th fault analysis result to obtain a first clustering result; The final fault analysis result is obtained according to the first clustering result.

3. The method according to claim 1, in, After determining whether the first discreteness satisfies a first predetermined condition, the method further comprises: When the first dispersion does not satisfy the first predetermined condition, obtaining first user location information according to the first service request; Obtaining first user power element information according to the first user type and the first user location information; Obtaining an element fault analysis result according to the first user power element information and the first fault analysis result; Obtaining a third matching result according to the element fault analysis result and the power service knowledge base; A second processing instruction is obtained according to the third matching result.

4. The method according to claim 3, in, When the condition is satisfied, after obtaining the first processing instruction according to the first matching result, the method includes: Constructing a processing data record library according to the first processing instruction, the first matching result, and the first user location information; Get the preset time threshold; Within the preset time threshold, obtaining a first processing aggregate amount according to the processing data record library, wherein the first processing aggregate amount is the number of processing records identical to the first processing instruction, the first matching result, and the first user location information; When the first processing accumulation amount reaches an accumulation threshold, a first early warning instruction is obtained.

5. The method according to claim 4, in, The method comprises: Obtaining location aggregation feature information according to the first processing aggregation amount and the processing data record library; According to the location aggregation feature information, obtaining the aggregation location user information, the aggregation location user information does not exist in the processing data record library; According to the first processing instruction, obtaining first power reminder information; A first group reminder instruction is obtained according to the user information of the gathering location and the first power reminder information, and the first group reminder instruction is used to group send the first power reminder information to the users of the gathering location.

6. The method according to claim 1, in, The step of inputting the first service request into the matching processing model to obtain a first fault analysis result includes: According to the first service request, obtaining first service request content information; Using the first service request content information as first input information; Inputting the first input information into the matching processing model, wherein the matching processing model is obtained by training multiple sets of training data, each set of data in the multiple sets of training data includes the first input information and identification information for identifying a first fault analysis result; An output result of the matching processing model is obtained, wherein the output result includes the first fault analysis result.

7. An intelligent fault handling system for a power grid service website, in, The system is used to perform the steps of the method according to any one of claims 1 to 6, and the system comprises: A first obtaining unit, wherein the first obtaining unit is used to obtain a first service request; a second obtaining unit, the second obtaining unit being configured to obtain a first request input type according to the first service request; A third obtaining unit, the third obtaining unit is used to obtain a preset model library; a fourth obtaining unit, the fourth obtaining unit being configured to perform model matching from the preset model library according to the first request input type to obtain a matching processing model; a first input unit, the first input unit being used to input the first service request into the matching processing model to obtain a first fault analysis result; a fifth obtaining unit, the fifth obtaining unit being used to obtain a power service knowledge base; a sixth obtaining unit, the sixth obtaining unit being configured to obtain a first matching result according to the first fault analysis result and the power service knowledge base; a seventh obtaining unit, configured to obtain a first user type according to the first service request; an eighth obtaining unit, the eighth obtaining unit being configured to obtain a second matching result according to the first user type and the power service knowledge base; a ninth obtaining unit, configured to obtain a first discreteness according to the second matching result and the first matching result, wherein the first discreteness is a discreteness between the second matching result and the first matching result; a first judging unit, configured to judge whether the first dispersion satisfies a first predetermined condition; A tenth obtaining unit, wherein the tenth obtaining unit is used to obtain a first processing instruction according to the first matching result when the condition is satisfied, wherein the first processing instruction is used to perform power fault processing according to the processing method in the first matching result.

8. An intelligent fault handling system for a power grid service website, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, in, When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images