Method for positioning service calling problem in power grid resource business based on cloud platform

Abstract

The invention provides a cloud platform-based power grid resource business platform service calling problem positioning method, which comprises the following steps of: for each calling abnormal service, acquiring a first service calling log of each service center of a power grid resource business platform at a calling abnormal moment, a second service calling log in a preset time period before the abnormal time is called; according to the first service calling log, determining the association degree between the service called at the calling abnormal moment and the calling abnormal service, and according to the second service calling log, determining the association degree between each service called at a preset time period before the calling abnormal moment and the calling abnormal service; according to the association degree between each service and the calling abnormal service, determining a suspected abnormal service causing the service calling abnormity; and according to the suspected abnormal service and a preset service calling problem positioning model, determining a target service causing the service calling abnormity. According to the method, the target service causing the service calling abnormity can be quickly and accurately positioned.

Description

Technical Field

[0001] The present invention relates to the technical field of service call problem locating technology, and in particular to a method for locating service call problems of a power grid resource business middle station based on a cloud platform. Background Art

[0002] The power grid resource business middle platform is built on a cloud platform and can provide open and shared service-enabled applications. Currently, typical application scenarios have been built, such as intelligent fault analysis, power outage analysis, image-model integration, active monitoring of distribution network operation status, a new generation of emergency command, and distribution network repair APP. However, for the wide variety of application scenarios in the power grid resource business middle platform, when calling services, there may be problems such as services being called incorrectly and frequently, which in turn affects the efficient and stable operation of the power grid resource business middle platform. Therefore, it is necessary to quickly and accurately locate the problems of abnormal services in order to improve the service support capabilities of the middle platform. Summary of the invention

[0003] The embodiment of the present invention provides a method for locating service call problems of a power grid resource business middle station based on a cloud platform to solve the problem that it is currently difficult to quickly and accurately locate service call problems of a power grid resource business middle station.

[0004] In a first aspect, an embodiment of the present invention provides a method for locating a service call problem of a power grid resource business middle station based on a cloud platform, comprising:

[0005] For each abnormal service call, obtain the first service call log of each service center of the power grid resource business center at the abnormal call time, and the second service call log of each service center in a preset period before the abnormal call time;

[0006] Determine the correlation between the service called by each service center at the abnormal call moment and the abnormal call service according to the first service call log, and determine the correlation between each service called by each service center in a preset period before the abnormal call moment and the abnormal call service according to the second service call log;

[0007] Determine the suspected abnormal service causing the service call abnormality according to the correlation between each service and the abnormal service call;

[0008] According to the suspected abnormal service and the preset service call problem location model, the target service that causes the service call abnormality is determined.

[0009] In a possible implementation, determining, according to the first service call log, the correlation between the service called by each service center at the time of the abnormal call and the abnormal call service includes:

[0010] Determine, according to the first service call log, the application scenario and business request to which the service called by each service center at the time of the abnormal call belongs;

[0011] According to the application scenario and the business request, and the application scenario and the business request for calling the abnormal service, the correlation between the service called by each service center at the time of calling the abnormal service and the calling abnormal service is determined.

[0012] In a possible implementation, determining the correlation between the service called by each service center at the time of calling the abnormal service and the calling abnormal service according to the application scenario and the business request, and the application scenario and business request of calling the abnormal service, includes:

[0013] Record the application scenario and business request of the service called by each service center at the time of abnormal call as the first application scenario and the first business request, and record the application scenario and the business request of calling the abnormal service as the second application scenario and the second business request;

[0014] Determine whether each of the first application scenarios is associated with the second application scenario;

[0015] If the first application scenario is not associated with the second application scenario, determining that the degree of association between the service corresponding to the first application scenario and the abnormal service being called is zero;

[0016] If the first application scenario is associated with the second application scenario, the degree of association between the service corresponding to the first application scenario and the abnormal service call is determined according to the first business request and the second business request corresponding to the first application scenario.

[0017] In a possible implementation, determining, according to the first business request and the second business request corresponding to the first application scenario, a correlation between the service corresponding to the first application scenario and the abnormal service call, includes:

[0018] According to the business logic of the first business request and the business logic of the second business request corresponding to the first application scenario, the correlation between the service corresponding to the first application scenario and the call abnormal service is calculated.

[0019] In a possible implementation, determining the suspected abnormal service causing the service call abnormality according to the correlation between each service and the abnormal service call includes:

[0020] Comparing the correlation between each service and the abnormally called service with a preset correlation threshold;

[0021] If the correlation degree is greater than or equal to the preset correlation degree threshold, the service corresponding to the correlation degree is determined as a suspected abnormal service.

[0022] In a possible implementation, the training process of the preset service call problem location model is:

[0023] Obtain the abnormal service call log and abnormal location results of the historical abnormal service calls of the power grid resource business center;

[0024] The preset neural network model is trained based on the historical abnormal service calls, the abnormal service call logs and the abnormal location results to obtain the preset service call problem location model.

[0025] In a possible implementation, a preset neural network model is trained based on the historical abnormal service calls, the abnormal service call logs, and the abnormal location results to obtain the preset service call problem location model, including:

[0026] According to the abnormal service call log, the application scenario and business request corresponding to each of the historical abnormal service calls are extracted, recorded as the third application scenario and the third business request, and the abnormal time corresponding to each of the historical abnormal service calls is extracted;

[0027] Calculate the distance between each abnormal moment and the abnormal moment of the corresponding abnormal location result;

[0028] Taking the historical call abnormal service, the distance corresponding to the historical call abnormal service, the third application scenario corresponding to the historical call abnormal service and the third business request as input, and taking the abnormal location result corresponding to the historical call abnormal service as output, the preset neural network model is trained to obtain the preset service call problem location model.

[0029] In a possible implementation, calculating the distance between each abnormal moment and the abnormal moment of the corresponding abnormal location result includes:

[0030] The time difference between each abnormal moment and the abnormal moment of the corresponding abnormal location result is calculated as the distance between each abnormal moment and the abnormal moment of the corresponding abnormal location result.

[0031] In a possible implementation, determining the target service causing the service call abnormality according to the suspected abnormal service and the preset service call problem location model includes:

[0032] According to the service call log of the suspected abnormal service, determine the application scenario and business request corresponding to each of the suspected abnormal services, record them as suspected abnormal application scenarios and suspected abnormal business requests, and determine the abnormal time of each of the suspected abnormal services;

[0033] Calculate the distance between the abnormal time of each suspected abnormal service and the abnormal call time, and record it as the first distance;

[0034] Each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests and the first distance are input into a preset service call problem location model to determine the target service that causes the service call abnormality.

[0035] In a possible implementation, each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests, and the first distance are input into a preset service call problem location model to determine the target service that causes the service call abnormality, including:

[0036] Input each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests and the first distance into a preset service call problem location model to determine the suspected target service that causes the service call abnormality;

[0037] Calculate the distance between the abnormal time of each of the suspected abnormal services and the abnormal time of each of the suspected target services, and record it as a second distance;

[0038] Each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests and the second distance are input into a preset service call problem location model to determine the target service that causes the service call abnormality.

[0039] The embodiment of the present invention provides a method for locating service call problems in a power grid resource business middle station based on a cloud platform. For each abnormal service call, the first service call log of each service center in the power grid resource business middle station at the abnormal call time and the second service call log of each service center in a preset period before the abnormal call time are obtained; then, the correlation between the service called by each service center at the abnormal call time and the abnormal service is determined according to the first service call log, and the correlation between each service called by each service center in a preset period before the abnormal call time and the abnormal service is determined according to the second service call log; then, according to the correlation between each service and the abnormal service, the suspected abnormal service that causes the abnormal service call is determined; and then, according to the suspected abnormal service and the preset service call problem location model, the target service that causes the abnormal service call is determined. Therefore, after the abnormal service is called, the target service that causes the abnormal service call can be quickly and accurately located, which is beneficial to the troubleshooting and service optimization of the power grid resource business middle station, and thus improves the service support capability of the middle station. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of the implementation of the cloud platform-based power grid resource business middle station service call problem locating method provided by an embodiment of the present invention;

[0042] Figure 2 It is a structural diagram of a cloud platform-based power grid resource business middle-office service call problem locating device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0044] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0045] Figure 1 The implementation flow chart of the cloud platform-based power grid resource business middle platform service call problem locating method provided in the embodiment of the present invention is detailed as follows:

[0046] Step 101, for each abnormal service call, obtain the first service call log of each service center of the power grid resource business center at the abnormal call time, and the second service call log of each service center in a preset period before the abnormal call time.

[0047] Among them, the power grid resource business middle platform has multiple service centers, including but not limited to the basic service center, power grid asset center, power grid resource center, power grid topology center, power grid graphics center, model management center, real-time measurement center, power grid metering center, power grid analysis center, equipment status center, operation resource center, operation management center, and power grid environment center. It can support marketing 2.0, power supply service command system, four-zone master station system for distribution automation, distributed photovoltaic power quality monitoring system, safe production risk management platform, lean production cost management platform, power transmission and transformation reliability, power transmission panoramic platform, unified video monitoring platform, provincial smart energy service platform, new generation emergency command platform, high-risk customer safety operation system, new generation centralized control system, digital power supply station full business support platform, online power grid, control cloud and other business systems.

[0048] Because when a service call exception occurs, it may be caused by the business request corresponding to the service itself, or it may be caused by the service of the service center where the service is located at the previous moment, or it may be caused by the services of other service centers associated with the service, therefore, obtaining the first service call log of each service center of the power grid resource business center at the time of the abnormal call, as well as the second service call log of each service center in the preset period before the abnormal call, is helpful to analyze the cause of the service call exception.

[0049] Step 102, determining the correlation between the service called by each service center at the abnormal call time and the abnormal call service according to the first service call log, and determining the correlation between each service called by each service center in a preset period before the abnormal call time and the abnormal call service according to the second service call log.

[0050] Optionally, determining the correlation between the service called by each service center at the time of abnormal call and the abnormal call service according to the first service call log may include:

[0051] The application scenario and business request to which the service called by each service center at the time of abnormal call belongs are determined according to the first service call log.

[0052] According to the application scenario and business request, as well as the application scenario and business request for calling the abnormal service, the correlation between the service called by each service center at the time of calling the abnormal service and the calling abnormal service is determined.

[0053] Optionally, according to the application scenario and business request, and the application scenario and business request of calling the abnormal service, determining the correlation between the service called by each service center at the time of calling the abnormal service and the calling abnormal service may include:

[0054] The application scenario and business request of the service called by each service center at the time of abnormal call are recorded as the first application scenario and the first business request, and the application scenario and the business request of calling the abnormal service are recorded as the second application scenario and the second business request.

[0055] It is determined whether each first application scenario is associated with the second application scenario.

[0056] If the first application scenario is not associated with the second application scenario, it is determined that the degree of association between the service corresponding to the first application scenario and the abnormally called service is zero.

[0057] If the first application scenario is associated with the second application scenario, the degree of association between the service corresponding to the first application scenario and the abnormal service call is determined according to the first business request and the second business request corresponding to the first application scenario.

[0058] Optionally, determining the correlation between the service corresponding to the first application scenario and the abnormal service call according to the first business request and the second business request corresponding to the first application scenario may include:

[0059] According to the business logic of the first business request and the business logic of the second business request corresponding to the first application scenario, the correlation between the service corresponding to the first application scenario and the call abnormal service is calculated.

[0060] In this embodiment, considering that the power grid resource business middle platform can support more than 20 typical application scenarios such as intelligent fault analysis, active monitoring of distribution network operation status, new generation emergency command, power outage analysis, image and model integration, distribution network emergency repair APP, equipment failure and abnormal line loss analysis in substations, lean management of high-voltage cables, lightning warning, and active warning of equipment defects, each service of each service center can support multiple application scenarios and business requests under application scenarios, and the business logic of different business requests may cross or overlap. Therefore, the correlation between each service and the calling abnormal service can be evaluated based on the business logic of the business request in the application scenario corresponding to the service at the time of calling the abnormality and the time before the abnormality, and the business logic of the business request in the application scenario corresponding to the calling abnormal service.

[0061] Exemplarily, the service corresponding to the first business request is recorded as the target service. In the process of calculating the correlation between the first business request and the second business request corresponding to the first application scenario according to the business logic of the first business request and the business logic of the second business request, the distance between the target service and the called exception service in the business logic of the first business request can be calculated, and the distance between the called exception service and the target service in the business logic of the second business request can be calculated. The correlation between the service corresponding to the first application scenario and the called exception service is obtained based on the two distances.

[0062] For example, target service 1 is A, and the business logic of the first business request corresponding to target service 1 is: BCADE; target service 2 is C, and the business logic of the first business request corresponding to target service 2 is: BKDCEF; the call exception service is B, and the business logic corresponding to the call exception service is: CDABFK. For target service 1, the distance between target service 1 and the call exception service in the business logic of the first business request corresponding to target service 1 is 2, and the distance between the call exception service and target service 1 in the business logic of the second business request is 1. According to the total distance 3, the correlation between target service 1 and the call exception service can be determined as 1 / 3. For target service 2, the distance between target service 2 and the call exception service in the business logic of the first business request corresponding to target service 2 is 3, and the distance between the call exception service and target service 2 in the business logic of the second business request is 3. According to the total distance 6, the correlation between target service 2 and the call exception service can be determined as 1 / 6.

[0063] Step 103: Determine the suspected abnormal service that causes the service call abnormality according to the correlation between each service and the abnormal service call.

[0064] Exemplarily, determining the suspected abnormal service causing the service call abnormality according to the correlation between each service and the abnormal service call may include:

[0065] The relevance of each service to the abnormally called service is compared with a preset relevance threshold.

[0066] If the correlation degree is greater than or equal to a preset correlation degree threshold, the service corresponding to the correlation degree is determined as a suspected abnormal service.

[0067] Step 104: determine the target service causing the service call abnormality based on the suspected abnormal service and the preset service call problem location model.

[0068] Optionally, the training process of the preset service call problem location model can be:

[0069] Obtain the abnormal service call log and abnormal location results of the historical abnormal service calls of the power grid resource business center.

[0070] The preset neural network model is trained based on the historical abnormal service calls, abnormal service call logs and abnormal location results to obtain the preset service call problem location model.

[0071] In this embodiment, in order to more accurately determine the problem service that ultimately causes the service call exception, the historical service call log of the middle station can be used to obtain a business middle station service status statistics table and a business middle station application status statistics table, and then obtain the abnormal service call log and abnormal location result of the historical abnormal service call of the power grid resource business middle station, so as to obtain the cause of the historical abnormal service call in each business request in each application scenario, and obtain the preset service call problem location model based on this training.

[0072] Optionally, a preset neural network model is trained based on historical abnormal service calls, abnormal service call logs, and abnormal location results to obtain a preset service call problem location model, which may include:

[0073] According to the abnormal service call log, the application scenario and business request corresponding to each historical abnormal service call are extracted and recorded as the third application scenario and the third business request, and the abnormal time corresponding to each historical abnormal service call is extracted.

[0074] Calculate the distance between each abnormal moment and the abnormal moment of the corresponding abnormal location result.

[0075] Taking the historical calls to abnormal services, the distances corresponding to the historical calls to abnormal services, the third application scenarios and the third business requests corresponding to the historical calls to abnormal services as inputs, and the abnormal location results corresponding to the historical calls to abnormal services as outputs, the preset neural network model is trained to obtain a preset service call problem location model.

[0076] Exemplarily, calculating the distance between each abnormal moment and the abnormal moment of the corresponding abnormal positioning result includes: calculating the time difference between each abnormal moment and the abnormal moment of the corresponding abnormal positioning result as the distance between each abnormal moment and the abnormal moment of the corresponding abnormal positioning result.

[0077] Optionally, according to the suspected abnormal service and the preset service call problem location model, determining the target service that causes the service call abnormality may include:

[0078] According to the service call log of the suspected abnormal service, determine the application scenario and business request corresponding to each suspected abnormal service, record them as suspected abnormal application scenario and suspected abnormal business request, and determine the abnormal time of each suspected abnormal service.

[0079] Calculate the distance between the abnormal time of each suspected abnormal service and the abnormal call time, and record it as the first distance.

[0080] Each suspected abnormal service, the suspected abnormal application scenario corresponding to each suspected abnormal service, the suspected abnormal business request and the first distance are input into a preset service call problem location model to determine the target service that causes the service call abnormality.

[0081] Optionally, inputting each suspected abnormal service, the suspected abnormal application scenario corresponding to each suspected abnormal service, the suspected abnormal business request, and the first distance into a preset service call problem location model to determine the target service causing the service call abnormality may include:

[0082] Each suspected abnormal service, the suspected abnormal application scenario corresponding to each suspected abnormal service, the suspected abnormal business request and the first distance are input into a preset service call problem location model to determine the suspected target service that causes the service call abnormality.

[0083] The distance between the abnormal time of each suspected abnormal service and the abnormal time of each suspected target service is calculated and recorded as the second distance.

[0084] Each suspected abnormal service, the suspected abnormal application scenario corresponding to each suspected abnormal service, the suspected abnormal business request and the second distance are input into the preset service call problem location model to determine the target service that causes the service call abnormality.

[0085] This embodiment first takes the call of the abnormal service itself as the cause of the service call abnormality, and then uses the preset service call problem location model to determine at least one suspected target service, and then takes each suspected target service as the cause of the service call abnormality, and then uses the preset service call problem model to perform a screening, and finally more accurately determines the target service that causes the service call abnormality.

[0086] The embodiment of the present invention obtains the first service call log of each service center of the power grid resource business middle station at the time of abnormal call, and the second service call log of each service center in the preset time period before the abnormal call, for each abnormal call service; then firstly determines the correlation between the service called by each service center at the abnormal call time and the abnormal call service according to the first service call log, and determines the correlation between each service called by each service center in the preset time period before the abnormal call and the abnormal call service according to the second service call log; then, according to the correlation between each service and the abnormal call service, determines the suspected abnormal service that causes the abnormal service call; and then determines the target service that causes the abnormal service call according to the suspected abnormal service and the preset service call problem location model. Therefore, after the abnormal service is called, the target service that causes the abnormal service call can be quickly and accurately located, which is beneficial to the troubleshooting and service optimization of the power grid resource business middle station, and thus improves the service support capability of the middle station.

[0087] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0088] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0089] Figure 2 The following is a schematic diagram of the structure of a cloud platform-based power grid resource business middle station service call problem location device provided in an embodiment of the present invention. For ease of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0090] like Figure 2 As shown, the cloud platform-based power grid resource business middle-end service call problem locating device includes: an acquisition module 21, a first processing module 22, a second processing module 23 and a locating module 24.

[0091] The acquisition module 21 is used to acquire, for each abnormal service call, a first service call log of each service center of the power grid resource business middle station at the abnormal call time, and a second service call log of each service center in a preset period before the abnormal call time;

[0092] A first processing module 22 is used to determine the correlation between the service called by each service center at the abnormal call moment and the abnormal call service according to the first service call log, and to determine the correlation between each service called by each service center in a preset period before the abnormal call moment and the abnormal call service according to the second service call log;

[0093] The second processing module 23 is used to determine the suspected abnormal service that causes the service call abnormality according to the correlation between each service and the abnormal service call;

[0094] The positioning module 24 is used to determine the target service that causes the service call abnormality according to the suspected abnormal service and the preset service call problem positioning model.

[0095] The embodiment of the present invention obtains the first service call log of each service center of the power grid resource business middle station at the time of abnormal call, and the second service call log of each service center in the preset time period before the abnormal call, for each abnormal call service; then firstly determines the correlation between the service called by each service center at the abnormal call time and the abnormal call service according to the first service call log, and determines the correlation between each service called by each service center in the preset time period before the abnormal call and the abnormal call service according to the second service call log; then, according to the correlation between each service and the abnormal call service, determines the suspected abnormal service that causes the abnormal service call; and then determines the target service that causes the abnormal service call according to the suspected abnormal service and the preset service call problem location model. Therefore, after the abnormal service is called, the target service that causes the abnormal service call can be quickly and accurately located, which is beneficial to the troubleshooting and service optimization of the power grid resource business middle station, and thus improves the service support capability of the middle station.

[0096] In one possible implementation, the first processing module 22 can be used to determine the application scenario and business request to which the service called by each service center at the time of the abnormal call belongs based on the first service call log; and determine the correlation between the service called by each service center at the time of the abnormal call and the abnormal service based on the application scenario and the business request, as well as the application scenario and business request of the abnormal service.

[0097] In one possible implementation, the first processing module 22 can be used to record the application scenario and business request to which the service called by each service center at the time of the abnormal call as the first application scenario and the first business request, and record the application scenario and the business request for calling the abnormal service as the second application scenario and the second business request; determine whether each of the first application scenarios is associated with the second application scenario; if the first application scenario is not associated with the second application scenario, determine that the correlation between the service corresponding to the first application scenario and the calling abnormal service is zero; if the first application scenario is associated with the second application scenario, determine the correlation between the service corresponding to the first application scenario and the calling abnormal service based on the first business request and the second business request corresponding to the first application scenario.

[0098] In a possible implementation, the first processing module 22 may be configured to calculate the correlation between the service corresponding to the first application scenario and the abnormal service call according to the business logic of the first business request and the business logic of the second business request corresponding to the first application scenario.

[0099] In a possible implementation, the second processing module 23 can be used to compare the correlation between each service and the calling abnormal service with a preset correlation threshold; if the correlation is greater than or equal to the preset correlation threshold, the service corresponding to the correlation is determined as a suspected abnormal service.

[0100] In one possible implementation, the model training module 25 can be used to obtain the abnormal service call log and abnormal location results of the historical abnormal service calls of the power grid resource business station; based on the historical abnormal service calls, the abnormal service call log and the abnormal location results, the preset neural network model is trained to obtain the preset service call problem location model.

[0101] In one possible implementation, the model training module 25 can be used to extract the application scenarios and business requests corresponding to each of the historical abnormal service calls based on the abnormal service call log, recorded as the third application scenario and the third business request, and extract the abnormal moment corresponding to each of the historical abnormal service calls; calculate the distance between each abnormal moment and the abnormal moment of the corresponding abnormal location result; use the historical abnormal service calls, the distance corresponding to the historical abnormal service calls, the third application scenario and the third business request corresponding to the historical abnormal service calls as input, and use the abnormal location result corresponding to the historical abnormal service calls as output to train the preset neural network model to obtain the preset service call problem location model.

[0102] In a possible implementation, the model training module 25 can be used to calculate the time difference between each of the abnormal moments and the abnormal moment of the corresponding abnormal positioning result as the distance between each of the abnormal moments and the abnormal moment of the corresponding abnormal positioning result.

[0103] In one possible implementation, the positioning module 24 can be used to determine the application scenarios and business requests corresponding to each suspected abnormal service based on the service call log of the suspected abnormal service, recorded as suspected abnormal application scenarios and suspected abnormal business requests, and determine the abnormal time of each suspected abnormal service; calculate the distance between the abnormal time of each suspected abnormal service and the abnormal call time, recorded as the first distance; each suspected abnormal service, the suspected abnormal application scenario corresponding to each suspected abnormal service, the suspected abnormal business request and the first distance are input into a preset service call problem positioning model to determine the target service that causes the service call abnormality.

[0104] In one possible implementation, the positioning module 24 can be used to input each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests and the first distance into a preset service call problem location model to determine the suspected target service that causes the service call exception; calculate the distance between the abnormal moment of each of the suspected abnormal services and the abnormal moment of each of the suspected target services, recorded as the second distance; input each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests and the second distance into a preset service call problem location model to determine the target service that causes the service call exception.

[0105] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] Those of ordinary skill in the art will appreciate that the templates, units, and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0107] If the module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned embodiments of the method for locating the problem of calling the service of the middle platform of the power grid resource business based on the cloud platform. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium, etc.

[0108] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for locating service call problems in a power grid resource business middle platform based on a cloud platform, characterized in that: include: For each abnormal service call, obtain the first service call log of each service center of the power grid resource business center at the abnormal call time, and the second service call log of each service center in a preset period before the abnormal call time; Determine the correlation between the service called by each service center at the abnormal call moment and the abnormal call service according to the first service call log, and determine the correlation between each service called by each service center in a preset period before the abnormal call moment and the abnormal call service according to the second service call log; Determine the suspected abnormal service causing the service call abnormality according to the correlation between each service and the abnormal service call; According to the suspected abnormal service and the preset service call problem location model, the target service that causes the service call abnormality is determined.

2. According to the cloud platform-based power grid resource business middle-end service call problem location method according to claim 1, it is characterized in that: Determining the correlation between the service called by each service center at the time of abnormal call and the abnormal call service according to the first service call log includes: Determine, according to the first service call log, the application scenario and business request to which the service called by each service center at the time of the abnormal call belongs; According to the application scenario and the business request, and the application scenario and the business request for calling the abnormal service, the correlation between the service called by each service center at the time of calling the abnormal service and the calling abnormal service is determined.

3. The method for locating service call problems of power grid resource business middle platform based on cloud platform according to claim 2 is characterized in that: According to the application scenario and the business request, and the application scenario and the business request for calling the abnormal service, determining the correlation between the service called by each service center at the time of calling the abnormal service and the calling abnormal service, including: Record the application scenario and business request of the service called by each service center at the time of abnormal call as the first application scenario and the first business request, and record the application scenario and the business request of calling the abnormal service as the second application scenario and the second business request; Determine whether each of the first application scenarios is associated with the second application scenario; If the first application scenario is not associated with the second application scenario, determining that the degree of association between the service corresponding to the first application scenario and the abnormal service being called is zero; If the first application scenario is associated with the second application scenario, the degree of association between the service corresponding to the first application scenario and the abnormal service call is determined according to the first business request and the second business request corresponding to the first application scenario.

4. The method for locating service call problems of power grid resource business middle platform based on cloud platform according to claim 3 is characterized in that: The determining, according to the first business request and the second business request corresponding to the first application scenario, a correlation between the service corresponding to the first application scenario and the abnormal service call, includes: According to the business logic of the first business request and the business logic of the second business request corresponding to the first application scenario, the correlation between the service corresponding to the first application scenario and the call abnormal service is calculated.

5. The method for locating service call problems of power grid resource business middle platform based on cloud platform according to claim 1 is characterized in that: According to the correlation between each service and the abnormal service, the suspected abnormal service causing the abnormal service call is determined, including: Comparing the correlation between each service and the abnormally called service with a preset correlation threshold; If the correlation degree is greater than or equal to the preset correlation degree threshold, the service corresponding to the correlation degree is determined as a suspected abnormal service.

6. The method for locating service call problems of power grid resource business middle platform based on cloud platform according to claim 1 is characterized in that: The training process of the preset service call problem location model is: Obtain the abnormal service call log and abnormal location results of the historical abnormal service calls of the power grid resource business center; The preset neural network model is trained based on the historical abnormal service calls, the abnormal service call logs and the abnormal location results to obtain the preset service call problem location model.

7. The method for locating service call problems of power grid resource business middle platform based on cloud platform according to claim 6 is characterized in that: The preset neural network model is trained based on the historical abnormal service calls, the abnormal service call logs and the abnormal location results to obtain the preset service call problem location model, including: According to the abnormal service call log, the application scenario and business request corresponding to each of the historical abnormal service calls are extracted, recorded as the third application scenario and the third business request, and the abnormal time corresponding to each of the historical abnormal service calls is extracted; Calculate the distance between each abnormal moment and the abnormal moment of the corresponding abnormal location result; Taking the historical call abnormal service, the distance corresponding to the historical call abnormal service, the third application scenario corresponding to the historical call abnormal service and the third business request as input, and taking the abnormal location result corresponding to the historical call abnormal service as output, the preset neural network model is trained to obtain the preset service call problem location model.

8. The method for locating service call problems of power grid resource business middle platform based on cloud platform according to claim 7 is characterized in that: Calculating the distance between each abnormal moment and the abnormal moment of the corresponding abnormal location result includes: The time difference between each abnormal moment and the abnormal moment of the corresponding abnormal location result is calculated as the distance between each abnormal moment and the abnormal moment of the corresponding abnormal location result.

9. The method for locating service call problems of power grid resource business middle platform based on cloud platform according to claim 1, characterized in that: According to the suspected abnormal service and the preset service call problem location model, the target service causing the service call abnormality is determined, including: According to the service call log of the suspected abnormal service, determine the application scenario and business request corresponding to each of the suspected abnormal services, record them as suspected abnormal application scenarios and suspected abnormal business requests, and determine the abnormal time of each of the suspected abnormal services; Calculate the distance between the abnormal time of each suspected abnormal service and the abnormal call time, and record it as the first distance; Each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests and the first distance are input into a preset service call problem location model to determine the target service that causes the service call abnormality.

10. The method for locating service call problems of power grid resource business middle platform based on cloud platform according to claim 9, characterized in that: Inputting each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests, and the first distance into a preset service call problem location model to determine the target service that causes the service call abnormality, including: Input each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests and the first distance into a preset service call problem location model to determine the suspected target service that causes the service call abnormality; Calculate the distance between the abnormal time of each of the suspected abnormal services and the abnormal time of each of the suspected target services, and record it as a second distance; Each of the suspected abnormal services, the suspected abnormal application scenarios corresponding to each of the suspected abnormal services, the suspected abnormal business requests and the second distance are input into a preset service call problem location model to determine the target service that causes the service call abnormality.

Images