Power grid business service method and device, equipment and storage medium

Abstract

The invention relates to a power grid business service method and device, equipment and a storage medium, and belongs to the technical field of power grid services, and the method comprises the steps: determining a main service work order associated with an initial service work order under the condition that the initial service work order initiated by a client terminal is received; and obtaining a current service link of the service link associated with the main service work order. And feeding back a business service result to the client terminal according to the current service link. Compared with the prior art, under the condition that the initial service work order is received, the associated main service work order can be determined based on the initial service work order, the business service result can be fed back to the user based on the current service link of the main service work order, and the service work order does not need to be circulated, so that the system resource waste is effectively reduced, and the user experience is improved. And the business service response speed is improved, and the user satisfaction is improved.

Description

Technical Field

[0001] This application relates to the field of power grid service technology, and in particular to a power grid business service method, apparatus, equipment and storage medium. Background Technology

[0002] With the informatization development of power grid enterprises, the number of business systems in the customer service field has been increasing. These include systems such as the operation and maintenance coordination system responsible for on-site operations and fault handling, the meter reading and collection system managing electricity bill calculation and payment, and the customer service dispatch and call center system, which serves as the main customer access point. These systems were independently planned and constructed by different departments based on business needs and technical conditions at different times. While this gradual and decentralized construction model met the needs of power grid informatization development, it also led to the current complex situation of numerous systems and heterogeneous architectures. These systems differ significantly in their underlying technology stacks, database types, data models, and even development languages, forming solid technical barriers that make effective integration and data interaction between systems extremely difficult. This has created insurmountable "information silos" and "process breakpoints" within the enterprise, severely hindering the smooth flow of cross-business processes.

[0003] In the traditional model, when a customer service system receives a service order from a customer, even if the event associated with that service order is the same as that associated with other service orders, it still needs to generate a consultation order in the customer service system and a repair order in the operation and maintenance system for each service order. Afterwards, it may also need to process electricity deductions in the meter reading and billing system. For example, for a power grid fault event, different customers may initiate fault handling progress inquiries through different systems. For each inquiry order, each system executes a complete query process, resulting in redundant service processes. Moreover, the transfer of work orders between different systems is highly dependent on manual operation. Therefore, the existing power grid service methods not only cause significant resource waste and prolong the end-to-end problem resolution cycle, resulting in poor service response timeliness, but also increase service risks due to information transcription errors. Summary of the Invention

[0004] Therefore, it is necessary to provide a power grid business service method, apparatus, equipment, and storage medium that can effectively save system resources and improve service response speed in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for providing power grid business services. The method includes:

[0006] Upon receiving an initial service order initiated by a client terminal, determine the primary service order associated with the initial service order;

[0007] Get the current service stage of the service chain associated with the main service order;

[0008] Based on the current service stage, provide feedback on the business service results to the customer terminal.

[0009] In one embodiment, determining the primary service order associated with the initial service order includes:

[0010] The original work order information of the initial service work order is standardized to obtain the standard work order information of the initial service work order.

[0011] Based on the standard work order information and the first work order information of the first service work order contained in the candidate problem pool, select the target problem pool corresponding to the initial service work order from the candidate problem pool;

[0012] Based on the main service work order associated with the target issue pool, determine the main service work order associated with the initial service work order.

[0013] In one embodiment, the original work order information of the initial service work order is standardized to obtain the standard work order information of the initial service work order, including:

[0014] Based on the mapping rule knowledge base, the initial fields contained in the original work order information of the initial service work order are standardized to obtain the target fields;

[0015] Based on the business ontology dictionary and standardization rules, the initial values ​​of the target fields are standardized to obtain the standard values ​​of the target fields;

[0016] The standard values ​​of the target field are optimized to obtain the optimized values ​​of the target field.

[0017] Based on the target field and the optimized value corresponding to the target field, the standard work order information of the initial service work order is obtained.

[0018] In one embodiment, based on standard work order information and the first work order information of the first service work order contained in the candidate problem pool, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool, including:

[0019] Based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool; wherein, the cluster center information is determined based on the first work order information of the first service work order contained in the candidate problem pool.

[0020] In one embodiment, based on standard work order information and cluster center information of the problem clusters associated with the candidate problem pool, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool, including:

[0021] Semantic analysis is performed on the problem description in the service description field of standard work order information to obtain a text semantic vector;

[0022] Determine the customer's geographic coordinates based on the geographic location field in the standard work order information;

[0023] Determine the event timestamp based on the time field in the standard work order information;

[0024] Based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service work order is selected from the candidate issue pool.

[0025] In one embodiment, the cluster center information includes the center location coordinates, center time, and center semantic vector; based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service order is selected from the candidate issue pool, including:

[0026] For each candidate question pool, a text similarity score is determined based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool.

[0027] The spatial similarity score is determined based on the customer's geospatial coordinates and the coordinates of the center location of the question clusters associated with the candidate question pool;

[0028] The time similarity score is determined based on the event timestamp and the center time of the question cluster associated with the candidate question pool;

[0029] Based on text similarity score, spatial similarity score, and event similarity score, the comprehensive similarity score between the initial service order and the candidate issue pool is determined;

[0030] Based on the comprehensive similarity score between the initial service order and each candidate problem pool, the target problem pool corresponding to the initial service order is selected from the candidate problem pools.

[0031] In one embodiment, the method further includes:

[0032] For each first service link in the service chain, the risk index of the first service link is determined based on the actual time consumed by the first service link and the standard time consumed by the first service link.

[0033] Based on the risk index and weighting coefficient of the first service link that is currently active, determine the current total risk index of the service link;

[0034] If the current total risk index exceeds the index threshold, a risk alarm message will be sent to the operations and maintenance team.

[0035] Secondly, this application also provides a power grid business service device. The device includes:

[0036] The first determining module is used to determine the main service order associated with the initial service order when it receives the initial service order initiated by the client terminal.

[0037] The acquisition module is used to acquire the current service link of the service chain associated with the main service work order;

[0038] The first sending module is used to send feedback on the business service results to the client terminal based on the current service stage.

[0039] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0040] Upon receiving an initial service order initiated by a client terminal, determine the primary service order associated with the initial service order;

[0041] Get the current service stage of the service chain associated with the main service order;

[0042] Based on the current service stage, provide feedback on the business service results to the customer terminal.

[0043] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0044] Upon receiving an initial service order initiated by a client terminal, determine the primary service order associated with the initial service order;

[0045] Get the current service stage of the service chain associated with the main service order;

[0046] Based on the current service stage, provide feedback on the business service results to the customer terminal.

[0047] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0048] Upon receiving an initial service order initiated by a client terminal, determine the primary service order associated with the initial service order;

[0049] Get the current service stage of the service chain associated with the main service order;

[0050] Based on the current service stage, provide feedback on the business service results to the customer terminal.

[0051] The aforementioned power grid service method, apparatus, equipment, and storage medium, upon receiving an initial service work order initiated by a customer terminal, determine the associated master service work order. It then obtains the current service stage of the service link associated with the master service work order. Based on the current service stage, it provides feedback on the service result to the customer terminal. Compared to existing technologies, this application, upon receiving an initial service work order, can determine the associated master service work order based on the initial service work order and provide feedback on the service result to the user based on the current service stage of the master service work order. This eliminates the need for service work order transfer, effectively reducing system resource waste, improving service response speed, and enhancing user satisfaction. Attached Figure Description

[0052] Figure 1 This is an application environment diagram of the power grid service method provided in this embodiment;

[0053] Figure 2 A flowchart illustrating the first power grid service method provided in this embodiment;

[0054] Figure 3 This is a flowchart illustrating the process of determining the main service work order provided in this embodiment;

[0055] Figure 4 This is a flowchart illustrating the process of determining the target problem pool provided in this embodiment;

[0056] Figure 5 This is a flowchart illustrating the second power grid service method provided in this embodiment;

[0057] Figure 6 A flowchart illustrating the third power grid service method provided in this embodiment;

[0058] Figure 7 This is a structural block diagram of a power grid service device provided in this embodiment;

[0059] Figure 8 This is an internal structural diagram of the computer device provided in this embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] With the informatization development of power grid enterprises, the number of business systems in the customer service field has been increasing. These include systems such as the operation and maintenance coordination system responsible for on-site operations and fault handling, the meter reading and collection system managing electricity bill calculation and payment, and the customer service dispatch and call center system, which serves as the main customer access point. These systems were independently planned and constructed by different departments based on business needs and technical conditions at different times. While this gradual and decentralized construction model met the needs of power grid informatization development, it also led to the current complex situation of numerous systems and heterogeneous architectures. These systems differ significantly in their underlying technology stacks, database types, data models, and even development languages, forming solid technical barriers that make effective integration and data interaction between systems extremely difficult. This has created insurmountable "information silos" and "process breakpoints" within the enterprise, severely hindering the smooth flow of cross-business processes.

[0062] In the traditional model, when a customer service system receives a service order from a customer, even if the event associated with that service order is the same as that associated with other service orders, it still needs to generate a consultation order in the customer service system and a repair order in the operation and maintenance system for each service order. Afterwards, it may also need to process electricity deductions in the meter reading and billing system. For example, for a power grid fault event, different customers may initiate fault handling progress inquiries through different systems. For each inquiry order, each system executes a complete query process, resulting in redundant service processes. Moreover, the transfer of work orders between different systems is highly dependent on manual operation. Therefore, the existing power grid service methods not only cause significant resource waste and prolong the end-to-end problem resolution cycle, resulting in poor service response timeliness, but also increase service risks due to information transcription errors.

[0063] To address the aforementioned technical problems, the power grid service method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, upon receiving an initial service order from a client terminal, the server determines the primary service order associated with the initial service order. The server then obtains the current service stage of the service chain associated with the primary service order. Based on the current service stage, the server sends the service result back to the client terminal.

[0064] Here, "server" can refer to a standalone server or a server cluster. "Train" refers to a railcar in the railway industry. "Client terminal" refers to user-side terminal equipment, such as smartphones, computers, and other smart terminals.

[0065] In one embodiment, such as Figure 2 As shown, a power grid business service method is provided, which is applied to... Figure 1Taking the server in the example, the following steps are included:

[0066] S201: Upon receiving an initial service work order initiated by a client terminal, determine the main service work order associated with the initial service work order.

[0067] In this context, the customer terminal refers to the terminal device on the customer side that initiates the power grid service, i.e., the initial service order. This device could be a mobile phone or computer. The initial service order is a standardized document or data record generated based on the customer's service request.

[0068] Optionally, in this embodiment, the initial service work order can be generated based on a service request received from a customer through a customer terminal. Alternatively, it can be generated by a client application based on a service request initiated by a customer. It can also be an initial service work order received from a customer system, generated by the customer system based on a service request. The service request can be a progress query for fault handling, such as a power grid fault or power grid equipment damage, or a fault reporting request. The customer system can be a distribution system, a meter reading and billing system, a customer service system, etc.

[0069] As an optional implementation of this application, upon receiving an initial service order initiated by a client terminal, event analysis is performed on the initial service order to obtain the target event. The target event is then matched with each candidate event, and the service order corresponding to the successfully matched candidate event is taken as the target service segment. For example, all the service orders are related to power grid faults in the same area.

[0070] S202, obtain the current service link of the service chain associated with the main service work order.

[0071] The service link refers to the service process link associated with the main service work order. The current service stage refers to the current service stage of the main service work order, such as "in fault location" or "in emergency repair operation".

[0072] Optionally, in this embodiment, the service chain can be created based on an event chain model, which can be represented by a directed acyclic graph, i.e., using... ;in, It is a collection of nodes, each node This represents a key business status in the service process, such as "accepted", "dispatched", "fault located", "repair in progress", "power restored", etc. It is a set of edges, each directed edge Indicates from state arrive The legitimate flow process. In this embodiment, the entire lifecycle of customer service events can be modeled and monitored in real time based on an event chain model.

[0073] As an optional implementation of this application, the directed acyclic graph (DAG) corresponding to the service link associated with the main service work order is obtained, and the current service stage of the service link associated with the main service work order is determined based on the current service progress indicated by the DAG. For example, if the DAG indicates that the current stage is "fault location", then the current service stage is "fault location".

[0074] Another optional implementation method in this application is to initiate a query request to the operation and maintenance system to obtain the current service link of the service link associated with the main service work order.

[0075] S203, based on the current service stage, provides feedback on the business service results to the customer terminal.

[0076] As an optional implementation of this application, the current service step is taken as the business service result and the business service result is fed back to the client terminal.

[0077] Another optional implementation of this application embodiment involves obtaining the remaining processing time of the current service stage. Based on the current service stage and its remaining processing time, a service result is generated. The service result is then fed back to the client terminal. The remaining processing time can be predicted by the operation and maintenance team or a predictive model based on the event processing status. For example, if the event is a power grid failure, the operation and maintenance team predicts the remaining processing time based on the current repair progress. For instance, the service result could be that the system is currently "under repair," and power is expected to be restored in 30 minutes.

[0078] In this embodiment, upon receiving an initial service ticket initiated by a client terminal, the associated primary service ticket is determined. The current service stage of the service chain associated with the primary service ticket is obtained. Based on the current service stage, the service result is fed back to the client terminal. Compared to existing technologies, this application, upon receiving an initial service ticket, can determine the associated primary service ticket based on the initial service ticket and, based on the current service stage of the primary service ticket, feed back the service result to the user. This eliminates the need for service ticket routing, effectively reducing system resource waste, improving service response speed, and enhancing user satisfaction.

[0079] In one embodiment, to more accurately determine the primary service order associated with the initial service order, such as Figure 3 As shown, the optional implementation methods for determining the master service order associated with the initial service order include:

[0080] S301, standardize the original work order information of the initial service work order to obtain the standard work order information of the initial service work order.

[0081] As an optional implementation of this application, the original work order information of the initial service work order is input into the information processing tool, and the information processing tool performs standardization processing on the original work order information of the initial service work order to obtain the standard work order information of the initial service work order.

[0082] Another optional implementation of this application embodiment is as follows: Based on the mapping rule knowledge base, the initial fields contained in the original work order information of the initial service work order are standardized to obtain the target fields. Based on the business ontology dictionary and standardization rules, the initial values ​​of the target fields are standardized to obtain the standard values ​​of the target fields. The standard values ​​of the target fields are optimized to obtain the optimized values ​​of the target fields. Based on the target fields and their corresponding optimized values, the standard work order information of the initial service work order is obtained. In this embodiment, an optional implementation of standardizing the initial fields contained in the original work order information of the initial service work order to obtain the target fields based on the mapping rule knowledge base is as follows: using a pattern mapping operator... Execution, pre-configured for each source system Each power system has constructed an independent mapping rule knowledge base. The mapping rule knowledge base defines the initial fields. With target field The structural correspondence between them. For example, it maps semantically similar but differently named initial fields (such as "user address" and "table address") from different systems to a standard geographic location field. The output of this stage is a structure that is... A fully aligned intermediate data object whose internal values ​​are not yet standardized. In this embodiment, the initial values ​​of the target field are standardized according to the business ontology dictionary and standardization rules to obtain the standard values ​​of the target field. An optional implementation method is to use the value range normalization operator. Continuing execution, this operator focuses on The values ​​of each target field are semantically aligned based on a predefined business ontology dictionary and standardization rules. For example, for the business type field... This invention addresses diverse customer expressions such as "power failure," "line trip," and "no power," through... The standardized business term "power outage repair" is used for... The first in Initial values ​​of each target field Its normalization process can be expressed as: ;in, It is for standard fields A specific range transformation function. After this stage is completed, intermediate records with unified structure and semantics are generated. In this embodiment, the standard value of the target field is optimized to obtain the optimized value of the target field. An optional implementation method is to use an operator... Complete the final quality control and utilize To ensure data integrity and format consistency, it handles outliers, format errors, and missing key information that may exist in the standard values ​​of target fields. For example, it unifies various date strings into ISO 8601 standard timestamps, or when address information is complete but geographic coordinates are missing, it calls the geographic information service interface for reverse parsing and data augmentation to obtain optimized values ​​for each target field.

[0083] Optionally, in this embodiment, the standard work order information includes at least one of the following: the customer's globally unique identifier, the customer's geospatial coordinates, the event timestamp, the event problem description information, the business type, and the current lifecycle status of the work order.

[0084] S302, based on the standard work order information and the first work order information of the first service work order contained in the candidate problem pool, select the target problem pool corresponding to the initial service work order from the candidate problem pool.

[0085] As an optional implementation of this application, for each candidate problem pool, the standard work order information is compared with the first work order information of the first service work orders included in the candidate problem pool to obtain the similarity value between the standard work order information and the first work order information of all the first service work orders included in the candidate problem pool; the average similarity value of the first work order information of all the first service work orders included in the candidate problem pool is determined, and the average similarity value is used as the similarity value between the standard work order information and the candidate problem pool. For each candidate problem pool, the candidate problem pool pointed to by the highest similarity value is used as the target problem pool corresponding to the initial service work order.

[0086] Another optional implementation of this application involves inputting standard work order information and the first work order information of the first service work order contained in the candidate problem pool into a similarity analysis model. The similarity analysis model then outputs the similarity value between the standard work order information and each candidate problem pool. For each candidate problem pool, the candidate problem pool pointing to by the highest similarity value is taken as the target problem pool corresponding to the initial service work order. The similarity analysis model can be a trained neural network model.

[0087] As another optional implementation of this application, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool based on the standard work order information and the cluster center information of the problem cluster associated with the candidate problem pool; wherein, the cluster center information is determined based on the first work order information of the first service work order contained in the candidate problem pool.

[0088] It should be noted that the first service order information included in the candidate problem pool is also standardized service order information. The processing can refer to the standardization of the original service order information in the above embodiment. The specific implementation plan for the standard service order information will not be elaborated here.

[0089] S303, Based on the main service work order associated with the target problem pool, determine the main service work order associated with the initial service work order.

[0090] Optionally, in this embodiment, the master service order associated with the target problem pool can be a service order obtained by merging all first service orders in the target problem pool. The service order information of the master service order is determined based on the first service order information of the first service orders, for example, by taking the average. The master service order can also be the first service order received first, that is, the earliest created service order.

[0091] In this embodiment, the original work order information of the initial service work order is standardized to obtain standard work order information for the initial service work order. Based on the standard work order information and the first work order information of the first service work orders included in the candidate problem pool, a target problem pool corresponding to the initial service work order is selected from the candidate problem pool. Based on the main service work order associated with the target problem pool, the main service work order associated with the initial service work order is determined. This embodiment improves both the accuracy and efficiency of determining the main service work order by standardizing the initial service work order to obtain standard service work orders under unified rules, and by determining the target problem pool based on the standard service work orders.

[0092] In one embodiment, to more accurately determine the target problem pool corresponding to the initial service order, such as Figure 4 As shown, one possible implementation method for selecting the target problem pool corresponding to the initial service work order from the candidate problem pool based on standard work order information and cluster center information of problem clusters associated with the candidate problem pool includes:

[0093] S401, perform semantic analysis on the problem description in the service description field of the standard work order information to obtain the text semantic vector.

[0094] Optionally, in this embodiment, the standard work order information includes a service description field, wherein the value of the service description field is a problem description.

[0095] Optionally, in this embodiment, a pre-trained language model is used as the embedding function. The problem description in the service description field is mapped to a high-dimensional vector space to obtain a text semantic vector.

[0096] S402, determine the customer's geospatial coordinates based on the geolocation field in the standard work order information.

[0097] Optionally, in this embodiment, the standard work order information includes a geographic location field. The geographic location associated with this geographic location field is mapped to a pre-created coordinate system (e.g., a geodetic coordinate system) to obtain the customer's geospatial coordinates associated with the geographic location field.

[0098] S403, determine the event timestamp based on the time field in the standard work order information.

[0099] Optionally, in this embodiment, the standard work order information includes a time field, and the value of the time field is used as the event timestamp.

[0100] S404: Based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, select the target issue pool corresponding to the initial service work order from the candidate issue pool.

[0101] Optionally, in this embodiment, the cluster center information includes center location coordinates, center time, and center semantic vector. Optionally, in this embodiment, the center location coordinates can be obtained by averaging the geographic coordinates of all first service work orders in the target problem pool. That is, the average geographic coordinates of the first service work orders included in the target problem pool are used as the center location coordinates in the cluster center information of the problem cluster associated with the target problem pool. In this embodiment, the center time is determined by averaging the event timestamps of all first service work orders in the target problem pool. In this embodiment, the center semantic vector is obtained by averaging the semantic vectors corresponding to the problem descriptions of all first service work orders in the target problem pool. Alternatively, it can be obtained based on the semantic vector corresponding to the problem description of the first service work order closest to the cluster center. For example, the semantic vector corresponding to the problem description of the first service work order closest to the cluster center can be used as the center semantic vector. Based on this embodiment, the problem clusters corresponding to each candidate problem pool are pre-clustered based on semantic vectors, geographic coordinates, and event timestamps as clustering conditions, clustering all first service work orders. This ensures that service work orders for the same event are clustered into the same candidate problem pool.

[0102] Optionally, in this embodiment, for each candidate question pool, a text similarity score is determined based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool. A spatial similarity score is determined based on the customer's geospatial coordinates and the central location coordinates of the question cluster associated with the candidate question pool. A temporal similarity score is determined based on the event timestamp and the event timestamp of the question cluster associated with the candidate question pool. A comprehensive similarity score between the initial service order and the candidate question pools is determined based on the text similarity score, spatial similarity score, and event similarity score. Based on the comprehensive similarity score between the initial service order and each candidate question pool, the target question pool corresponding to the initial service order is selected from the candidate question pools.

[0103] In this embodiment, an optional implementation method for determining the text similarity score based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool is to use cosine similarity to calculate the closeness of the two vectors in the semantic space, thereby obtaining the text similarity score. : Among them, V a V represents a text semantic vector; b This represents the central semantic vector; the score. The range of values ​​is The closer the value is to 1, the more similar the problems described by the two vectors are in terms of content.

[0104] In this embodiment, an optional implementation for determining the spatial similarity score based on the customer's geospatial coordinates and the center coordinates of the question clusters associated with the candidate question pool is to calculate the Euclidean distance between them. Among them, g ea Indicates the customer's geospatial coordinates; g eb This represents the coordinates of the center position. Subsequently, a Gaussian decay function is used to convert it into a spatial similarity score. : ;in, It is the spatial attenuation coefficient, which defines a geographic correlation radius and characterizes the spatial range that the same event may affect.

[0105] In this embodiment, an optional implementation method for determining the time similarity score based on the center time of the question clusters associated with the candidate question pool is to use a Gaussian decay function to measure their temporal proximity and obtain the time similarity score. This method can smoothly reflect the intuitive perception that "the closer the time, the stronger the correlation": ; where t ea Indicates the event timestamp; t eb Indicates the center time; It is an adjustable time decay coefficient, which physically defines an effective time window. Work order relevance will drop sharply beyond this window.

[0106] Based on the above embodiments, an optional implementation method for determining the comprehensive similarity score between the initial service order and the candidate problem pool according to the text similarity score, spatial similarity score, and event similarity score is to perform a weighted summation of the text similarity score, spatial similarity score, and event similarity score, and use the summation result as the comprehensive similarity score between the initial service order and the candidate problem pool; specifically, based on the following formula... The overall similarity score is determined; among which, The preset weighting coefficients satisfy... .

[0107] In this embodiment, an optional implementation method for selecting the target problem pool corresponding to the initial service work order from the candidate problem pools based on the comprehensive similarity score between the initial service work order and each candidate problem pool is to take the candidate problem pool pointed to by the largest comprehensive similarity score as the target problem pool corresponding to the initial service work order.

[0108] In this embodiment, semantic analysis is performed on the problem description in the service description field of the standard work order information to obtain a text semantic vector. The customer's geospatial coordinates are determined based on the geographic location field in the standard work order information. The event timestamp is determined based on the time field in the standard work order information. Based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the problem clusters associated with the candidate problem pools, the target problem pool corresponding to the initial service work order is selected from the candidate problem pools. This embodiment effectively improves the accuracy of the determined target problem pool.

[0109] In one instance, to promptly identify risks in the service chain, such as Figure 5 As shown, an optional implementation of a power distribution service method includes:

[0110] S501, for each first service link in the service chain, determine the risk index of the first service link based on the actual time consumed by the first service link and the standard time consumed by the first service link.

[0111] The first service link refers to each service link in the service chain. The standard processing time can be a benchmark for processing time determined based on historical service order information.

[0112] Optionally, in this embodiment, the service link is a directed acyclic graph, and the first service link is the service link corresponding to each node in the directed acyclic graph.

[0113] Optionally, in this embodiment, the risk index of the first service stage can be determined using the following formula: ; where, in the formula This represents the cumulative time spent on the first service step, i.e., the actual time spent; t si,j This indicates the standard time taken for the first service step.

[0114] S502, determine the current total risk index of the service link based on the risk index and weight coefficient of the first service link that is currently active.

[0115] Optionally, in this embodiment, the current total risk index of the service link can be determined using the following formula: ;in, This represents the weighting coefficient of the first service stage; Indicates at time The set of nodes that are currently active.

[0116] S503 sends a risk alarm to the operations and maintenance department when the current total risk index exceeds the index threshold.

[0117] In this embodiment, for each first service link in the service chain, a risk index is determined based on the actual time consumed and the standard time consumed by the first service link. The current total risk index of the service chain is determined based on the risk index and weighting coefficient of the currently active first service link. If the current total risk index exceeds a threshold, a risk alarm is sent to the operations and maintenance (O&M) system. This embodiment allows for timely monitoring of service time consumption risks and timely sending of risk alarms to the O&M or management system, preventing customer complaints due to excessively long service times.

[0118] Building upon the above embodiments, this application further includes intelligent analysis of customer service feedback based on a large language model (LLM). Optionally, customer feedback results are obtained, and service quality assessment results are determined based on these results. The feedback results include at least one of customer sentiment information and satisfaction information. Specifically, after completing the full monitoring of a customer service event, the crucial service quality closed-loop stage begins. The core of this step is to utilize the deep semantic understanding and generation capabilities of a large language model (LLM) to perform multi-dimensional, structured intelligent analysis of customer feedback. This invention not only processes unstructured customer feedback text but also innovatively links it to the event chain generated in step three, which contains complete process data. By integrating these elements, we can achieve precise insights from macro-level sentiment assessment to micro-level attribution.

[0119] Once a service chain reaches its final state (i.e., service completion) and customer feedback is collected, this invention will initiate an intelligent analysis process. The input data consists of two parts: first, the customer's original feedback text, denoted as... Second, the structured process history extracted from the service chain corresponding to the event is denoted as... This resume It includes all the service nodes that the event went through. circulation links and the actual time spent in each step Key information such as...

[0120] By designing a sophisticated analysis task prompt, denoted as... The two sets of input information are integrated and then submitted to the large language model. Processing is then performed. The model invocation process can be formally represented as follows:

[0121]

[0122] in, This is a standardized, structured analysis result (e.g., in JSON format) output by the model. (Hint) The instruction model performs several key analysis tasks in parallel: First, it determines the sentiment polarity and outputs a continuous quantitative sentiment score. This allows for a more refined measurement of sentiment than traditional positive / negative / neutral classifications; secondly, from... Extract a set of keywords that reflect the core concerns of customers. Secondly, and this is also a key innovation of the present invention, the model needs to be based on... The semantic content, and refer to The process data provided in the system attributes customer praise or criticism to specific service points. or circulation links Finally, generate a concise natural language summary report that incorporates all the above analytical elements.

[0123] Through the above process, this invention transforms unstructured customer feedback into structured data that can be used for quantitative statistics. Based on this, the present invention can construct higher-level service quality evaluation indicators. For example, the present invention can target any specific service link in the event chain. Calculate its exclusive service quality index This index is derived by aggregating all customer feedback sentiment scores attributed to this stage.

[0124]

[0125] In this formula, It is attributed to the process. The total number of feedback, It is the first The sentiment score of each relevant feedback item. A consistently low score. Value, combined with a set of frequently occurring keywords in the relevant feedback. This analysis can reveal specific weaknesses in the service process to managers with remarkable precision (e.g., the "distribution process"). of The data is relatively low, and the associated trending terms are mostly "long waiting time".

[0126] Ultimately, this invention, through continuous and automated analysis and aggregation of all feedback data, generates a quality index dashboard and a trend chart of hot issues covering all service links. These data-driven insights provide power grid companies with direct and reliable decision-making basis for optimizing service standards, adjusting resource allocation, and improving operational processes, thus forming a complete and self-optimizing intelligent closed loop of the IMIM-HS method from problem identification to service improvement.

[0127] In one embodiment, such as Figure 6 As shown, one possible implementation of the power grid business service method is as follows:

[0128] S601: Upon receiving an initial service work order initiated by a client terminal, the system standardizes the initial fields contained in the original work order information of the initial service work order according to the mapping rule knowledge base to obtain the target fields.

[0129] S602, based on the business ontology dictionary and standardization rules, standardize the initial values ​​of the target field to obtain the standard values ​​of the target field.

[0130] S603 optimizes the standard value of the target field to obtain the optimized value of the target field.

[0131] S604. Based on the target field and the optimized value corresponding to the target field, obtain the standard work order information for the initial service work order.

[0132] S605 performs semantic analysis on the problem description in the service description field of the standard work order information to obtain a text semantic vector.

[0133] S606 determines the customer's geographic coordinates based on the geographic location field in the standard work order information.

[0134] S607, determine the event timestamp based on the time field in the standard work order information.

[0135] S608. For each candidate question pool, determine the text similarity score based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool.

[0136] S609 determines the spatial similarity score based on the customer's geospatial coordinates and the coordinates of the center location of the question cluster associated with the candidate question pool.

[0137] S610, determine the time similarity score based on the event timestamp and the center time of the question cluster associated with the candidate question pool.

[0138] S611. Based on the text similarity score, spatial similarity score, and event similarity score, determine the comprehensive similarity score between the initial service order and the candidate problem pool.

[0139] S612, Based on the comprehensive similarity score between the initial service work order and each candidate problem pool, select the target problem pool corresponding to the initial service work order from the candidate problem pools.

[0140] S613, Based on the main service work order associated with the target problem pool, determine the main service work order associated with the initial service work order.

[0141] S614, obtain the current service link of the service chain associated with the main service work order.

[0142] S615 provides feedback on the service results to the customer terminal based on the current service process.

[0143] This embodiment also includes the step of sending risk alarm information to the operation and maintenance terminal, as follows:

[0144] For each first service link in the service chain, the risk index of the first service link is determined based on the actual time consumed by the first service link and the standard time consumed by the first service link.

[0145] Based on the risk index and weighting coefficient of the first service link that is currently active, determine the current total risk index of the service link;

[0146] If the current total risk index exceeds the index threshold, a risk alarm message will be sent to the operations and maintenance team.

[0147] This application, upon receiving an initial service ticket initiated by a client terminal, determines the associated primary service ticket. It then obtains the current service stage of the service chain associated with the primary service ticket. Based on the current service stage, it provides feedback on the service result to the client terminal. Compared to existing technologies, this application, upon receiving an initial service ticket, can determine the associated primary service ticket based on the initial service ticket and provide feedback on the service result to the user based on the current service stage of the primary service ticket. This eliminates the need for service ticket routing, effectively reducing system resource waste, improving service response speed, and enhancing user satisfaction.

[0148] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0149] Based on the same inventive concept, this application also provides a power grid service apparatus for implementing the power grid service method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more power grid service apparatus embodiments provided below can be found in the limitations of the power grid service method described above, and will not be repeated here.

[0150] In one embodiment, such as Figure 7 As shown, a power grid service device 1 is provided, comprising: a first determining module 10, an acquiring module 20, and a first sending module 30, wherein:

[0151] The first determining module 10 is used to determine the main service work order associated with the initial service work order when it receives the initial service work order initiated by the client terminal.

[0152] The acquisition module 20 is used to acquire the current service link of the service chain associated with the main service work order;

[0153] The first sending module 30 is used to send the service results back to the client terminal based on the current service stage.

[0154] In one embodiment, the first determining module is further specifically used for:

[0155] The original work order information of the initial service work order is standardized to obtain the standard work order information of the initial service work order.

[0156] Based on the standard work order information and the first work order information of the first service work order contained in the candidate problem pool, select the target problem pool corresponding to the initial service work order from the candidate problem pool;

[0157] Based on the main service work order associated with the target issue pool, determine the main service work order associated with the initial service work order.

[0158] In one embodiment, the first determining module is further specifically used for:

[0159] Based on the mapping rule knowledge base, the initial fields contained in the original work order information of the initial service work order are standardized to obtain the target fields;

[0160] Based on the business ontology dictionary and standardization rules, the initial values ​​of the target fields are standardized to obtain the standard values ​​of the target fields;

[0161] The standard values ​​of the target field are optimized to obtain the optimized values ​​of the target field.

[0162] Based on the target field and the optimized value corresponding to the target field, the standard work order information of the initial service work order is obtained.

[0163] In one embodiment, the first determining module is further specifically used for:

[0164] Based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool; wherein, the cluster center information is determined based on the first work order information of the first service work order contained in the candidate problem pool.

[0165] In one embodiment, the first determining module is further specifically used for:

[0166] Semantic analysis is performed on the problem description in the service description field of standard work order information to obtain a text semantic vector;

[0167] Determine the customer's geographic coordinates based on the geographic location field in the standard work order information;

[0168] Determine the event timestamp based on the time field in the standard work order information;

[0169] Based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service work order is selected from the candidate issue pool.

[0170] In one embodiment, the cluster center information includes center location coordinates, center time, and center semantic vector; the first determining module is further specifically used for:

[0171] For each candidate question pool, a text similarity score is determined based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool.

[0172] The spatial similarity score is determined based on the customer's geospatial coordinates and the coordinates of the center location of the question clusters associated with the candidate question pool;

[0173] The time similarity score is determined based on the event timestamp and the center time of the question cluster associated with the candidate question pool;

[0174] Based on text similarity score, spatial similarity score, and event similarity score, the comprehensive similarity score between the initial service order and the candidate issue pool is determined;

[0175] Based on the comprehensive similarity score between the initial service order and each candidate problem pool, the target problem pool corresponding to the initial service order is selected from the candidate problem pools.

[0176] In one embodiment, a power grid service device 1 further includes:

[0177] The second determining module is used to determine the risk index of each first service link in the service link based on the actual time consumed by the first service link and the standard time consumed by the first service link.

[0178] The third determination module is used to determine the current total risk index of the service link based on the risk index and weight coefficient of the first service link that is currently active.

[0179] The second sending module is used to send risk alarm information to the operation and maintenance end when the current total risk index is greater than the index threshold.

[0180] Each module in the aforementioned power grid service device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0181] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database is used for data related to power grid business services. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a power grid business service method.

[0182] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0183] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0184] Upon receiving an initial service order initiated by a client terminal, determine the primary service order associated with the initial service order;

[0185] Get the current service stage of the service chain associated with the main service order;

[0186] Based on the current service stage, provide feedback on the business service results to the customer terminal.

[0187] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the master service order associated with the initial service order, including:

[0188] The original work order information of the initial service work order is standardized to obtain the standard work order information of the initial service work order.

[0189] Based on the standard work order information and the first work order information of the first service work order contained in the candidate problem pool, select the target problem pool corresponding to the initial service work order from the candidate problem pool;

[0190] Based on the main service work order associated with the target issue pool, determine the main service work order associated with the initial service work order.

[0191] In one embodiment, when the processor executes the computer program, it further performs the following steps: standardizing the original work order information of the initial service work order to obtain the standard work order information of the initial service work order, including:

[0192] Based on the mapping rule knowledge base, the initial fields contained in the original work order information of the initial service work order are standardized to obtain the target fields;

[0193] Based on the business ontology dictionary and standardization rules, the initial values ​​of the target fields are standardized to obtain the standard values ​​of the target fields;

[0194] The standard values ​​of the target field are optimized to obtain the optimized values ​​of the target field.

[0195] Based on the target field and the optimized value corresponding to the target field, the standard work order information of the initial service work order is obtained.

[0196] In one embodiment, when the processor executes the computer program, it further performs the following steps: selecting a target problem pool corresponding to the initial service work order from the candidate problem pool based on standard work order information and the first work order information of the first service work order contained in the candidate problem pool, including:

[0197] Based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool; wherein, the cluster center information is determined based on the first work order information of the first service work order contained in the candidate problem pool.

[0198] In one embodiment, when the processor executes the computer program, it further performs the following steps: selecting the target problem pool corresponding to the initial service work order from the candidate problem pool based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, including:

[0199] Semantic analysis is performed on the problem description in the service description field of standard work order information to obtain a text semantic vector;

[0200] Determine the customer's geographic coordinates based on the geographic location field in the standard work order information;

[0201] Determine the event timestamp based on the time field in the standard work order information;

[0202] Based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service work order is selected from the candidate issue pool.

[0203] In one embodiment, when the processor executes the computer program, it further implements the following steps: the cluster center information includes the center location coordinates, center time, and center semantic vector; based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service order is selected from the candidate issue pool, including:

[0204] For each candidate question pool, a text similarity score is determined based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool.

[0205] The spatial similarity score is determined based on the customer's geospatial coordinates and the coordinates of the center location of the question clusters associated with the candidate question pool;

[0206] The time similarity score is determined based on the event timestamp and the center time of the question cluster associated with the candidate question pool;

[0207] Based on text similarity score, spatial similarity score, and event similarity score, the comprehensive similarity score between the initial service order and the candidate issue pool is determined;

[0208] Based on the comprehensive similarity score between the initial service order and each candidate problem pool, the target problem pool corresponding to the initial service order is selected from the candidate problem pools.

[0209] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0210] For each first service link in the service chain, the risk index of the first service link is determined based on the actual time consumed by the first service link and the standard time consumed by the first service link.

[0211] Based on the risk index and weighting coefficient of the first service link that is currently active, determine the current total risk index of the service link;

[0212] If the current total risk index exceeds the index threshold, a risk alarm message will be sent to the operations and maintenance team.

[0213] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0214] Upon receiving an initial service order initiated by a client terminal, determine the primary service order associated with the initial service order;

[0215] Get the current service stage of the service chain associated with the main service order;

[0216] Based on the current service stage, provide feedback on the business service results to the customer terminal.

[0217] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the master service order associated with the initial service order, including:

[0218] The original work order information of the initial service work order is standardized to obtain the standard work order information of the initial service work order.

[0219] Based on the standard work order information and the first work order information of the first service work order contained in the candidate problem pool, select the target problem pool corresponding to the initial service work order from the candidate problem pool;

[0220] Based on the main service work order associated with the target issue pool, determine the main service work order associated with the initial service work order.

[0221] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: standardizing the original work order information of the initial service work order to obtain the standard work order information of the initial service work order, including:

[0222] Based on the mapping rule knowledge base, the initial fields contained in the original work order information of the initial service work order are standardized to obtain the target fields;

[0223] Based on the business ontology dictionary and standardization rules, the initial values ​​of the target fields are standardized to obtain the standard values ​​of the target fields;

[0224] The standard values ​​of the target field are optimized to obtain the optimized values ​​of the target field.

[0225] Based on the target field and the optimized value corresponding to the target field, the standard work order information of the initial service work order is obtained.

[0226] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: selecting a target problem pool corresponding to the initial service work order from the candidate problem pool based on standard work order information and the first work order information of the first service work order contained in the candidate problem pool, including:

[0227] Based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool; wherein, the cluster center information is determined based on the first work order information of the first service work order contained in the candidate problem pool.

[0228] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: selecting the target problem pool corresponding to the initial service work order from the candidate problem pool based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, including:

[0229] Semantic analysis is performed on the problem description in the service description field of standard work order information to obtain a text semantic vector;

[0230] Determine the customer's geographic coordinates based on the geographic location field in the standard work order information;

[0231] Determine the event timestamp based on the time field in the standard work order information;

[0232] Based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service work order is selected from the candidate issue pool.

[0233] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the cluster center information includes the center location coordinates, center time, and center semantic vector; based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service order is selected from the candidate issue pool, including:

[0234] For each candidate question pool, a text similarity score is determined based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool.

[0235] The spatial similarity score is determined based on the customer's geospatial coordinates and the coordinates of the center location of the question clusters associated with the candidate question pool;

[0236] The time similarity score is determined based on the event timestamp and the center time of the question cluster associated with the candidate question pool;

[0237] Based on text similarity score, spatial similarity score, and event similarity score, the comprehensive similarity score between the initial service order and the candidate issue pool is determined;

[0238] Based on the comprehensive similarity score between the initial service order and each candidate problem pool, the target problem pool corresponding to the initial service order is selected from the candidate problem pools.

[0239] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0240] For each first service link in the service chain, the risk index of the first service link is determined based on the actual time consumed by the first service link and the standard time consumed by the first service link.

[0241] Based on the risk index and weighting coefficient of the first service link that is currently active, determine the current total risk index of the service link;

[0242] If the current total risk index exceeds the index threshold, a risk alarm message will be sent to the operations and maintenance team.

[0243] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0244] Upon receiving an initial service order initiated by a client terminal, determine the primary service order associated with the initial service order;

[0245] Get the current service stage of the service chain associated with the main service order;

[0246] Based on the current service stage, provide feedback on the business service results to the customer terminal.

[0247] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the master service order associated with the initial service order, including:

[0248] The original work order information of the initial service work order is standardized to obtain the standard work order information of the initial service work order.

[0249] Based on the standard work order information and the first work order information of the first service work order contained in the candidate problem pool, select the target problem pool corresponding to the initial service work order from the candidate problem pool;

[0250] Based on the main service work order associated with the target issue pool, determine the main service work order associated with the initial service work order.

[0251] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: standardizing the original work order information of the initial service work order to obtain the standard work order information of the initial service work order, including:

[0252] Based on the mapping rule knowledge base, the initial fields contained in the original work order information of the initial service work order are standardized to obtain the target fields;

[0253] Based on the business ontology dictionary and standardization rules, the initial values ​​of the target fields are standardized to obtain the standard values ​​of the target fields;

[0254] The standard values ​​of the target field are optimized to obtain the optimized values ​​of the target field.

[0255] Based on the target field and the optimized value corresponding to the target field, the standard work order information of the initial service work order is obtained.

[0256] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: selecting a target problem pool corresponding to the initial service work order from the candidate problem pool based on standard work order information and the first work order information of the first service work order contained in the candidate problem pool, including:

[0257] Based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool; wherein, the cluster center information is determined based on the first work order information of the first service work order contained in the candidate problem pool.

[0258] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: selecting the target problem pool corresponding to the initial service work order from the candidate problem pool based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, including:

[0259] Semantic analysis is performed on the problem description in the service description field of standard work order information to obtain a text semantic vector;

[0260] Determine the customer's geographic coordinates based on the geographic location field in the standard work order information;

[0261] Determine the event timestamp based on the time field in the standard work order information;

[0262] Based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service work order is selected from the candidate issue pool.

[0263] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the cluster center information includes the center location coordinates, center time, and center semantic vector; based on the text semantic vector, customer geospatial coordinates, event timestamp, and cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service order is selected from the candidate issue pool, including:

[0264] For each candidate question pool, a text similarity score is determined based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool.

[0265] The spatial similarity score is determined based on the customer's geospatial coordinates and the coordinates of the center location of the question clusters associated with the candidate question pool;

[0266] The time similarity score is determined based on the event timestamp and the center time of the question cluster associated with the candidate question pool;

[0267] Based on text similarity score, spatial similarity score, and event similarity score, the comprehensive similarity score between the initial service order and the candidate issue pool is determined;

[0268] Based on the comprehensive similarity score between the initial service order and each candidate problem pool, the target problem pool corresponding to the initial service order is selected from the candidate problem pools.

[0269] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0270] For each first service link in the service chain, the risk index of the first service link is determined based on the actual time consumed by the first service link and the standard time consumed by the first service link.

[0271] Based on the risk index and weighting coefficient of the first service link that is currently active, determine the current total risk index of the service link;

[0272] If the current total risk index exceeds the index threshold, a risk alarm message will be sent to the operations and maintenance team.

[0273] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchain. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to these.

[0274] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0275] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for providing power grid business services, characterized in that, The method includes: Upon receiving an initial service order initiated by a client terminal, determine the primary service order associated with the initial service order; Obtain the current service stage of the service link associated with the main service work order; Based on the current service stage, the service results are fed back to the customer terminal.

2. The method according to claim 1, characterized in that, The step of determining the primary service order associated with the initial service order includes: The original work order information of the initial service work order is standardized to obtain the standard work order information of the initial service work order. Based on the standard work order information and the first work order information of the first service work order contained in the candidate problem pool, select the target problem pool corresponding to the initial service work order from the candidate problem pool; Based on the main service work order associated with the target problem pool, determine the main service work order associated with the initial service work order.

3. The method according to claim 2, characterized in that, The standardization process of the original work order information of the initial service work order to obtain the standard work order information of the initial service work order includes: Based on the mapping rule knowledge base, the initial fields contained in the original work order information of the initial service work order are standardized to obtain the target fields; Based on the business ontology dictionary and standardization rules, the initial values ​​of the target field are standardized to obtain the standard values ​​of the target field; The standard values ​​of the target field are optimized to obtain the optimized values ​​of the target field; Based on the target field and the optimized value corresponding to the target field, the standard work order information of the initial service work order is obtained.

4. The method according to claim 2, characterized in that, The step of selecting the target problem pool corresponding to the initial service work order from the candidate problem pool based on the standard work order information and the first work order information of the first service work order included in the candidate problem pool includes: Based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool, the target problem pool corresponding to the initial service work order is selected from the candidate problem pool; wherein, the cluster center information is determined based on the first work order information of the first service work order contained in the candidate problem pool.

5. The method according to claim 4, characterized in that, The step of selecting the target problem pool corresponding to the initial service work order from the candidate problem pool based on the standard work order information and the cluster center information of the problem clusters associated with the candidate problem pool includes: Semantic analysis is performed on the problem description in the service description field of the standard work order information to obtain a text semantic vector; The customer's geographic coordinates are determined based on the geographic location field in the standard work order information. The event timestamp is determined based on the time field in the standard work order information; Based on the text semantic vector, the customer's geospatial coordinates, the event timestamp, and the cluster center information of the issue clusters associated with the candidate issue pool, the target issue pool corresponding to the initial service work order is selected from the candidate issue pool.

6. The method according to claim 5, characterized in that, The cluster center information includes the center location coordinates, center time, and center semantic vector; the step of selecting the target problem pool corresponding to the initial service order from the candidate problem pool based on the text semantic vector, the customer's geospatial coordinates, the event timestamp, and the cluster center information of the problem clusters associated with the candidate problem pool includes: For each candidate question pool, a text similarity score is determined based on the text semantic vector and the central semantic vector of the question cluster associated with the candidate question pool; The spatial similarity score is determined based on the customer's geospatial coordinates and the center coordinates of the question clusters associated with the candidate question pool. The time similarity score is determined based on the event timestamp and the center time of the question cluster associated with the candidate question pool; Based on the text similarity score, the spatial similarity score, and the event similarity score, the comprehensive similarity score between the initial service order and the candidate problem pool is determined; Based on the comprehensive similarity score between the initial service order and each candidate problem pool, the target problem pool corresponding to the initial service order is selected from the candidate problem pools.

7. The method according to claim 5, characterized in that, The method further includes: For each first service link in the service chain, the risk index of the first service link is determined based on the actual time consumed by the first service link and the standard time consumed by the first service link. The current total risk index of the service link is determined based on the risk index and weighting coefficient of the first service link that is currently active. If the current total risk index is greater than the index threshold, a risk alarm message is sent to the operations and maintenance department.

8. A power grid service device, characterized in that, The device includes: The first determining module is used to determine the main service order associated with the initial service order when it receives an initial service order initiated by the client terminal. The acquisition module is used to acquire the current service link of the service link associated with the main service work order; The first sending module is used to send the service result back to the client terminal based on the current service stage.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the power grid business service method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the power grid business service method according to any one of claims 1 to 7.

Images