Power grid mobile application platform abnormity alarm method, device, equipment, storage medium and program product

By detecting abnormal events and evaluating the operating data of the power grid mobile application platform, and displaying target alarm information to the management terminal, the problem of users in the power grid mobile application platform waiting for maintenance is solved, and abnormalities are detected earlier and resolved in a timely manner. Improves operational stability and user experience.

CN118940173APending Publication Date: 2024-11-12SHENZHEN COMTOP INFORMATION TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410984183.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Due to the vertical, single and closed technical architecture, the power grid mobile application platform has inconsistent business barriers and service quality, which affects normal use. When users find abnormalities, they need to wait for the management to dispatch technicians to repair, resulting in limited user experience.

Method used

By obtaining the operating data of the power grid mobile application platform, detecting abnormal events and evaluating health indicators, determining the target alarm method, displaying abnormal alarm information to the management terminal, realizing active detection and timely alarm, and improving the timely resolution of abnormal events.

Benefits of technology

It improves the timeliness and accuracy of abnormal alarms, detects abnormalities early, solves problems in a timely manner, and improves the operating stability and user experience of the power grid mobile application platform.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940173A_ABST
    Figure CN118940173A_ABST
Patent Text Reader

Abstract

The invention relates to a power grid mobile application platform abnormity alarm method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring operation data of a power grid mobile application platform; when it is detected that an abnormal event exists in the power grid mobile application platform based on the operation data, health degree index detection is carried out on the abnormal event based on the operation data, and a health degree index value is obtained; and determining a target alarm mode based on the health degree index value, and displaying abnormal alarm information to a management terminal corresponding to the power grid mobile application platform by adopting the target alarm mode. By adopting the method, the timeliness of abnormal alarm can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of power grid mobile application platforms, and in particular to a power grid mobile application platform abnormal alarm method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] With the development of the power grid field and the introduction of various new energy technologies, the power grid system is becoming more and more complex, and the power grid dispatch is becoming more and more complex. The power grid mobile application platform has emerged. The power grid mobile application platform can provide a series of functions related to power grid management and power services for power company employees and power customers. However, the vertical, single, and closed technical architecture adopted by the power grid mobile application platform has gradually generated business barriers and uneven service quality over a long period of time, affecting the normal use of the power grid mobile application platform.

[0003] In traditional technology, users of the power grid mobile application platform usually report the abnormality to the management side after discovering obvious usage obstacles, and the management side will then send technical personnel to carry out inspection and maintenance.

[0004] However, traditional technology relies on the way users of the power grid mobile application platform discover anomalies, which has a certain lag and thus affects the user experience. Summary of the invention

[0005] Based on this, it is necessary to provide a power grid mobile application platform abnormal alarm method, device, computer equipment, computer readable storage medium and computer program product that can improve the timeliness of abnormal alarms in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for abnormal alarm of a power grid mobile application platform, comprising:

[0007] Obtain operation data of the power grid mobile application platform;

[0008] In the case where an abnormal event is detected on the power grid mobile application platform based on the operation data, a health index of the abnormal event is detected based on the operation data to obtain a health index value;

[0009] The target alarm method is determined based on the health index value, and the abnormal alarm information is displayed to the management terminal corresponding to the power grid mobile application platform using the target alarm method.

[0010] In one embodiment, the health index includes an impact range, and the health index value includes an impact range classification result; the health index is detected for the abnormal event based on the operation data to obtain the health index value, including:

[0011] Extract abnormal object information corresponding to the abnormal event from the operation data, and query abnormal radiation object information corresponding to the abnormal object information from the preset platform object relationship table;

[0012] Based on the abnormal object information and the abnormal radiation object information, the impact scope of the abnormal event is classified to obtain an impact scope classification result, wherein the impact scope classification result includes one of a system scope, a platform scope, a function scope, a performance scope, and a recommended scope;

[0013] In one embodiment, the health index includes urgency, and the health index value includes an urgency classification result; the health index is detected for the abnormal event based on the operation data to obtain the health index value, including:

[0014] Extracting trigger time information corresponding to abnormal events from operation data;

[0015] Based on the trigger time information, the urgency of the abnormal event is classified to obtain an urgency classification result, wherein the urgency classification result includes one of an immediate demand, a scheduled demand, a delayed demand and a long-term demand.

[0016] In one embodiment, there are multiple health indicators; determining a target alarm mode based on the health indicator value includes:

[0017] Abnormal events are classified according to the values ​​of each health index, and the target abnormal level of the abnormal event is determined;

[0018] According to the preset correspondence between abnormal level and alarm mode, query the target alarm mode corresponding to the target abnormal level.

[0019] In one embodiment, abnormal events are classified according to the health index values ​​to determine the target abnormal level of the abnormal event, including:

[0020] The abnormality classification model is used to classify the abnormality levels based on the health index values ​​to obtain the target abnormality level of the abnormal event, wherein the abnormality classification model is optimized by the Bayesian optimizer.

[0021] In one embodiment, the abnormal alarm information is displayed to the management terminal corresponding to the power grid mobile application platform in a target alarm manner, including:

[0022] Extract the abnormal object information corresponding to the abnormal event from the operation data, and query the target management terminal corresponding to the abnormal object information from the preset platform management authority table;

[0023] The target alarm method is used to display abnormal alarm information to the target management terminal.

[0024] In a second aspect, the present application also provides an abnormal alarm device for a power grid mobile application platform, comprising:

[0025] An acquisition module is used to acquire the operation data of the power grid mobile application platform;

[0026] A detection module, for detecting a health index of the abnormal event based on the operation data to obtain a health index value when an abnormal event is detected on the power grid mobile application platform based on the operation data;

[0027] The alarm module is used to determine the target alarm method based on the health index value, and use the target alarm method to display abnormal alarm information to the management terminal corresponding to the power grid mobile application platform.

[0028] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0029] Obtain operation data of the power grid mobile application platform;

[0030] In the case where an abnormal event is detected on the power grid mobile application platform based on the operation data, a health index of the abnormal event is detected based on the operation data to obtain a health index value;

[0031] The target alarm method is determined based on the health index value, and the abnormal alarm information is displayed to the management terminal corresponding to the power grid mobile application platform using the target alarm method.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0033] Obtain operation data of the power grid mobile application platform;

[0034] In the case where an abnormal event is detected on the power grid mobile application platform based on the operation data, a health index of the abnormal event is detected based on the operation data to obtain a health index value;

[0035] The target alarm method is determined based on the health index value, and the abnormal alarm information is displayed to the management terminal corresponding to the power grid mobile application platform using the target alarm method.

[0036] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0037] Obtain operation data of the power grid mobile application platform;

[0038] In the case where an abnormal event is detected on the power grid mobile application platform based on the operation data, a health index of the abnormal event is detected based on the operation data to obtain a health index value;

[0039] The target alarm method is determined based on the health index value, and the abnormal alarm information is displayed to the management terminal corresponding to the power grid mobile application platform using the target alarm method.

[0040] The above-mentioned abnormal alarm method, device, computer equipment, computer-readable storage medium and computer program product of the power grid mobile application platform first obtain the operation data of the power grid mobile application platform, and then detect abnormal events based on the operation data. When the power grid mobile application platform detects abnormal events based on the operation data, the health index of the abnormal event is detected based on the operation data to obtain the health index value, and then the target alarm method is determined based on the health index value. The target alarm method is used to display the abnormal alarm information to the management terminal corresponding to the power grid mobile application platform, so that the abnormal event detection and health index evaluation are actively performed during the operation of the power grid mobile application platform, and the abnormal alarm is performed to the management terminal according to the current health of the power grid mobile application platform. On the one hand, compared with the user's abnormal reporting, the operation data can reflect the abnormal event earlier, so the abnormality can be discovered earlier, which helps to solve the abnormal event in time before it causes a usage obstacle. On the other hand, by determining the target alarm method based on the health index value, not only the accuracy of the abnormal alarm can be improved, but also the abnormal event can be solved more timely and effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 A schematic diagram of a flow chart of an abnormal alarm method of a power grid mobile application platform in one embodiment;

[0043] Figure 2 This is an application environment diagram of an abnormal alarm method for a power grid mobile application platform in one embodiment;

[0044] Figure 3 It is a flowchart of an abnormal alarm method of a power grid mobile application platform in another embodiment;

[0045] Figure 4 It is a structural block diagram of an abnormal alarm device for a power grid mobile application platform in one embodiment;

[0046] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] In an exemplary embodiment, Figure 1 As shown, a method for abnormal alarm of a power grid mobile application platform is provided. This embodiment takes the method applied to a server of a power grid mobile application platform as an example. Figure 2 , the server 102 can be respectively connected to multiple user terminals 104 and multiple management terminals 106 in communication, so that the operation data of the power grid mobile application platform can be obtained from each user terminal 104, and abnormal alarm information can be displayed to each management terminal 106 when an abnormal event is detected. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal may include a user terminal or a management terminal, and the terminal may be, but not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc.

[0049] In this embodiment, the method includes the following steps S10-S30. Among them:

[0050] Step S10, obtaining operation data of the power grid mobile application platform.

[0051] Among them, the power grid mobile application platform refers to a mobile application that can provide a series of functions related to power grid management and power services for power grid employees and power grid customers. Operation data refers to various data generated during the operation of the power grid mobile application platform, including at least one of user behavior data, manager behavior data, performance data, technical operation and maintenance data, etc. Among them, performance data refers to data related to the operation performance of the power grid mobile application platform, including at least one of page loading time, resource consumption, whether the network request is successful, network request response time, etc. Technical operation and maintenance data refers to data generated by technical operation and maintenance operations such as automatic or manual inspection and maintenance of the power grid mobile application platform, including at least one of server load and response time, system logs, security events, etc.

[0052] Exemplarily, the operation data generated by the operation of the power grid mobile application platform in each user terminal may be acquired from each user terminal of the power grid mobile application platform.

[0053] Step S20, when an abnormal event is detected in the power grid mobile application platform based on the operation data, a health index of the abnormal event is detected based on the operation data to obtain a health index value.

[0054] Among them, abnormal events refer to unexpected conditions or error states encountered during the operation of the power grid mobile application platform. The power grid mobile application platform usually has a certain ability to identify abnormal events, and when an abnormal event is identified, the operating environment or operating system of the power grid mobile application platform will record or identify the abnormal event, thereby retaining the record or identification information of the abnormal event in the operation data.

[0055] The health index refers to an index used to evaluate the health of the power grid mobile application platform, which may include at least one of the scope of influence, urgency, influence, etc. The detection method of the health index includes at least one of calculation, statistical analysis, model reasoning, classification, etc. The health index value obtained by detection may be in the form of a numerical value or a classification result.

[0056] Exemplarily, after the operation data is acquired, it is possible to detect whether there are records or identification information of abnormal events in the operation data. If records or identification information of abnormal events are detected, it can be determined that there are abnormal events in the power grid mobile application platform, and it is necessary to detect health indicators. The health indicators can be detected based on the operation data by at least one method of calculation, statistical analysis, model reasoning, classification, etc. If no records or identification information of abnormal events are detected, it can be considered that there are currently no abnormal events in the power grid mobile application platform, and no abnormal alarm is required, but the operation data can continue to be monitored.

[0057] As an example, the health index value can be a health index score; detecting the health index of an abnormal event based on the operation data to obtain the health index value can include: using a preset health score algorithm, based on the operation data, to calculate the health index score of the abnormal event, the health score algorithm can be selected and trained according to the actual situation, and this embodiment does not limit this. It can be understood that if there are multiple health indicators, for each health indicator, the above steps can be used to determine the corresponding health index score.

[0058] As an example, the health index value can be a health index classification result; detecting the health index of an abnormal event based on the operating data to obtain the health index value can include: using a preset health classification model, classifying the health index of the abnormal event based on the operating data to obtain the health index classification result, and the health classification model can be selected and trained according to actual conditions, which is not limited in this embodiment. It can be understood that if there are multiple health indicators, for each health indicator, the above steps can be used to determine the corresponding health index classification result.

[0059] Step S30, determining a target alarm mode based on the health index value, and using the target alarm mode to display abnormal alarm information to a management terminal corresponding to the power grid mobile application platform.

[0060] Among them, the alarm method includes at least one of the alarm time, alarm channel, alarm object, etc. For example, if it is determined that the alarm time is an immediate alarm, the alarm method can be to immediately use any channel to alarm any object; if the alarm time is determined to be within 24 hours, the alarm channel is text messages and applications, then the alarm method can be to alarm any object once or multiple times through the two channels of text messages and applications within 24 hours; if the alarm time is determined to be 9 o'clock in the morning, the alarm channel is a call, and the alarm object is operation and maintenance personnel A, then the alarm method can be to make a voice call or Internet call to operation and maintenance personnel A at 9 o'clock in the morning, and after the call is connected, play an abnormal alarm voice.

[0061] Abnormal alarm information refers to information used to remind the administrator of the power grid mobile application platform that there is an abnormal event on the power grid mobile application platform. The abnormal alarm information may include at least one of abnormal event identification information, health index value, and warning information. Among them, the abnormal event identification information may include at least one of the name and number of the abnormal event; the warning information may include at least one of the warning sentence and warning image.

[0062] Exemplarily, after determining the health index value, a suitable target alarm method can be determined based on the health index value, and then the target alarm method is used to display abnormal alarm information to the management terminal corresponding to the power grid mobile application platform.

[0063] As an example, determining the target alarm method based on the health index value may include: based on the correspondence between the preset health index detection results and the alarm method, querying the target alarm method corresponding to the health index value. For example, if the health index value is within the functional range, the target alarm method is to alert the management terminal corresponding to the target abnormal function, wherein the target abnormal function can be determined based on the operating data.

[0064] As an example, when there are multiple health indicators and the health indicator values ​​are health indicator scores, determining the target alarm method based on the health indicator values ​​may include: aggregating the health indicator scores to obtain a health score, based on the target score range to which the health score belongs, and then according to the correspondence between the preset score range and the alarm method, determining the target alarm method corresponding to the target score range.

[0065] As an example, when there are multiple health indicators and the health indicator values ​​are health indicator classification results, determining the target alarm method based on the health indicator values ​​may include: selecting one from each health indicator classification result as a health classification result according to a preset grading rule; for example, if the impact range classification result is level one and the urgency classification result is level three, and the preset grading rule is to select the highest level, then level one may be determined as the health classification result; and then, based on the correspondence between the preset classification results and the alarm method, the target alarm method corresponding to the health classification result may be determined.

[0066] As an example, when there are multiple health indicators and the health indicator values ​​are health indicator classification results, determining the target alarm method based on the health indicator values ​​may include: normalizing the classification results of each health indicator, and then aggregating the normalized health indicator classification results to obtain a health classification result, wherein the aggregation method may be at least one of summation, averaging, weighted summation or weighted averaging; and then the target alarm method corresponding to the health classification result may be determined based on the correspondence between the preset classification result and the alarm method.

[0067] In the above-mentioned abnormal alarm method of the power grid mobile application platform, the operation data of the power grid mobile application platform is first obtained, and then the abnormal event detection can be performed based on the operation data. When the power grid mobile application platform has an abnormal event based on the operation data, the health index of the abnormal event is detected based on the operation data to obtain the health index value, and then the target alarm method is determined based on the health index value, and the abnormal alarm information is displayed to the management terminal corresponding to the power grid mobile application platform using the target alarm method, so that the abnormal event detection and health index evaluation are actively performed during the operation of the power grid mobile application platform, and the abnormal alarm is performed to the management terminal according to the current health of the power grid mobile application platform. On the one hand, compared with the user's abnormal reporting, the operation data can reflect the abnormal event earlier, so the abnormality can be discovered earlier, which is helpful to solve the abnormal event in time before it causes the use of obstacles. On the other hand, by determining the target alarm method based on the health index value, not only the accuracy of the abnormal alarm can be improved, but also the abnormal event can be solved more timely and effectively.

[0068] In an exemplary embodiment, the health index includes an impact range, and the health index value includes an impact range classification result; detecting the health index of an abnormal event based on the operation data to obtain the health index value includes steps S211 to S212. Among them:

[0069] Step S211, extracting abnormal object information corresponding to the abnormal event from the operation data, and querying abnormal radiation object information corresponding to the abnormal object information from the preset platform object relationship table.

[0070] Among them, the impact scope refers to the scope affected by the abnormal event, including one of the system scope, platform scope, functional scope, performance scope and recommended scope, among which the system scope means that the impact scope of the abnormal event covers at least two of the server, user terminal and management terminal of the power grid mobile application platform; the platform scope means that the impact scope of the abnormal event only involves the user terminal of the power grid mobile application platform. It can be understood that when the impact scope of the abnormal event exceeds the user terminal of the power grid mobile application platform, the impact scope of the abnormal event belongs to the system scope; the functional scope means that the impact scope of the abnormal event only involves a certain function in the power grid mobile application platform. It can be understood that when the impact scope of the abnormal event involves multiple functions, the impact scope of the abnormal event belongs to the platform scope; the performance scope means that the impact scope of the abnormal event only involves the performance of the power grid mobile application platform; the recommended scope means that the impact scope of the abnormal event only involves the optimization of the power grid mobile application platform.

[0071] Abnormal objects refer to the functional modules of the power grid mobile application platform involved in the process of abnormal events. Abnormal radiation objects refer to the functional modules that are not involved in the process of abnormal events, but have functional associations with abnormal objects, where the functional association refers to the association between functional modules caused by at least one of the various functions of the power grid mobile application platform being triggered. There are certain functional associations between the various functional modules in the power grid mobile application platform. Abnormal objects will be affected by abnormal events and produce abnormalities in the current scenario, while abnormal radiation objects may be affected by abnormal objects and produce abnormalities in other scenarios. It’s just that because other scenarios have not yet occurred, the abnormal radiation objects have not detected abnormalities. Once other scenarios occur, the abnormal radiation objects will also be abnormal. The platform object relationship table refers to a table that records the functional associations between the various functional modules in the power grid mobile application platform.

[0072] Exemplarily, after the operation data is acquired, it is possible to detect whether there is a record or identification information of an abnormal event in the operation data. If a record or identification information of an abnormal event is detected, it can be determined that an abnormal event exists in the power grid mobile application platform, and a health indicator detection is required. Furthermore, the relevant operation data related to the abnormal event can be first extracted from the operation data, and then the functional module identification information can be identified from the relevant operation data, and the abnormal object information corresponding to the abnormal event can be determined based on the functional module identification information; then, the abnormal radiation object information corresponding to the abnormal object information can be queried from the preset platform object relationship table. Among them, the functional module identification information can be a code, an identifier, etc.

[0073] Step S212, based on the abnormal object information and the abnormal radiation object information, classify the impact scope of the abnormal event to obtain an impact scope classification result, wherein the impact scope classification result includes one of a system scope, a platform scope, a function scope, a performance scope and a recommended scope.

[0074] Exemplarily, the abnormal object information is matched with the preset influence range division rule to determine the coverage range of the abnormal object, and the abnormal radiation object information is matched with the preset influence range division rule to determine the coverage range of the abnormal radiation object, and the larger coverage range is taken from the coverage range of the abnormal object and the coverage range of the abnormal radiation object as the influence range classification result corresponding to the abnormal event. For example, if the coverage range of the abnormal object is the function range, and the coverage range of the abnormal radiation object is the platform range, since the platform range is larger than the function range, the platform range can be determined as the influence range classification result corresponding to the abnormal event.

[0075] As an example, different alarm objects can be determined for different impact range classification results, that is, the target alarm method is determined based on the health index value, and the target alarm method is used to display the abnormal alarm information to the management terminal corresponding to the power grid mobile application platform. It can include: determining the target alarm object based on the impact range classification result, and then displaying the abnormal alarm information to the target management terminal corresponding to the target alarm object.

[0076] In this embodiment, by classifying the impact scope of abnormal events, on the one hand, it can help to accurately judge the severity of abnormal events, and on the other hand, it can also help to clarify the alarm objects, improve the effectiveness of abnormal alarm information, avoid unnecessary panic that may be caused by displaying abnormal alarm information to all management terminals, and avoid managers who frequently receive abnormal alarm information that is not related to themselves, and thus reduce the degree of attention they pay to abnormal alarm information. When they receive abnormal alarm information that is closely related to themselves, they are likely to ignore the abnormal alarm information, resulting in the abnormality cannot be promptly and effectively resolved, thereby improving the user experience of managers.

[0077] In an exemplary embodiment, the health index includes urgency, and the health index value includes the urgency classification result; detecting the health index of the abnormal event based on the operation data to obtain the health index value includes steps S221 to S222. Among them:

[0078] Step S221, extracting trigger time information corresponding to the abnormal event from the operation data.

[0079] Among them, urgency refers to the time requirement for resolving abnormal events, including immediate demand, scheduled demand, delayed demand and long-term demand. Among them, immediate demand refers to abnormal events that need to be handled or responded to immediately, which are usually highly urgent, such as equipment failure alarms, power grid safety incidents, user emergency complaints, etc.; scheduled demand means that abnormal events are automatically triggered according to a predetermined time or cycle, such as electricity bill generation, regular inspection tasks, system maintenance windows, etc.; delayed demand means that abnormal events need to occur in the future, but the time of occurrence is controllable, such as planned power outage notifications, user electricity application approval, equipment replacement appointments, etc.; long-term demand refers to abnormal events that last for a long time and have a wide range of impact, which require long-term tracking and management, such as power grid planning projects, user electricity usage habit analysis, and system performance optimization.

[0080] The trigger time information refers to information related to the occurrence time of the abnormal event, including the set trigger time, the setting method of the trigger time, etc. The setting method of the trigger time includes custom, scheduled, immediate, etc.

[0081] Exemplarily, after the operation data is acquired, it is possible to detect whether there is a record or identification information of an abnormal event in the operation data. If a record or identification information of an abnormal event is detected, it can be determined that an abnormal event exists in the power grid mobile application platform, and a health indicator detection is required. Furthermore, relevant operation data related to the abnormal event can be extracted from the operation data, and then the trigger time identification information can be identified from the relevant operation data, and the trigger time information corresponding to the abnormal event can be determined based on the trigger time identification information. Among them, the trigger time identification information can be a code, an identifier, etc.

[0082] Step S222, based on the trigger time information, classify the urgency of the abnormal event to obtain an urgency classification result, wherein the urgency classification result includes one of immediate demand, scheduled demand, delayed demand and long-term demand.

[0083] As an example, based on the trigger time information, the probability that the abnormal object belongs to each urgency classification can be calculated through statistical analysis, model reasoning, etc., and then the urgency classification with the highest probability is selected as the urgency classification result.

[0084] As an example, the trigger time information may be accurately matched or fuzzily matched with the feature words corresponding to the preset urgency classifications, and the urgency classification with the most matching feature words may be determined as the urgency classification result.

[0085] As an example, for different urgency classification results, different alarm times, different alarm channels, and different alarm objects can be determined, that is, the target alarm method is determined based on the health index value, and the target alarm method is used to display the abnormal alarm information to the management terminal corresponding to the power grid mobile application platform. It can include: determining the target alarm object, target alarm time and target alarm channel based on the urgency classification result, and then at the target alarm time, through the target alarm channel, displaying the abnormal alarm information to the target management terminal corresponding to the target alarm object. For example, the number of target alarm objects can be decreased according to immediate demand, scheduled demand and delayed demand; the time difference between the target alarm time and the current time can be increased according to immediate demand, scheduled demand and delayed demand; the number of target alarm channels can be decreased according to immediate demand, scheduled demand and delayed demand; the alarm intensity of the target alarm channel can be decreased according to immediate demand, scheduled demand and delayed demand. For example, the target alarm channel corresponding to the demand can be a call alarm, the target alarm channel corresponding to the scheduled demand can be an email alarm and a SMS alarm, and the target alarm channel corresponding to the delayed demand can be an application pop-up alarm.

[0086] As an example, if the urgency classification result is a timing demand or a delay demand, the earliest time point in the overlapping time period between the first time period between the current time and the trigger time of the abnormal time and the preset maintenance time period can be determined as the target alarm time. If there is no overlapping time period between the first time period between the current time and the trigger time of the abnormal time and the preset maintenance time period, the time point closest to the preset maintenance time period in the first time period between the current time and the trigger time of the abnormal time can be determined as the target alarm time, or the current time can be determined as the target alarm time, and an alarm is issued immediately. Among them, the preset maintenance time period can be set in advance by the management personnel according to their own working hours, rest time, etc.

[0087] As an example, if the urgency classification result is a delayed demand, the abnormal event can be suspended until the abnormality is resolved.

[0088] In this embodiment, by classifying the urgency of abnormal events, on the one hand, it can help to accurately judge the severity of abnormal events, and on the other hand, it can also help to clarify the alarm object, alarm time and alarm channel, improve the effectiveness and freedom of abnormal alarm information, and improve the user experience of managers.

[0089] In an exemplary embodiment, Figure 3 As shown, there are multiple health indicators; determining the target alarm mode based on the health indicator value includes steps S311 to S312. Among them:

[0090] Step S311, classify the abnormal events according to the health index values, and determine the target abnormal level of the abnormal events.

[0091] It should be noted that evaluating abnormal events based only on a single health indicator has certain limitations, which may lead to lower accuracy in reporting to the police.

[0092] For example, when there are multiple health indicators, the values ​​of each health indicator may be combined to classify the abnormal event and determine the target abnormal level to which the abnormal event belongs.

[0093] As an example, various health indicator values ​​may be aggregated to obtain a health value, and abnormal events may be classified based on the health value to determine a target abnormal level to which the abnormal event belongs.

[0094] As an example, each health indicator value may also be input into a preset abnormality classification model to classify the abnormality level, and the output is the target abnormality level corresponding to the abnormal event.

[0095] Step S312: query the target alarm mode corresponding to the target abnormal level according to the preset correspondence between the abnormal level and the alarm mode.

[0096] Exemplarily, the target alarm mode corresponding to the target abnormal level is queried from the correspondence between the preset abnormal level and the alarm mode.

[0097] In this embodiment, by comprehensively classifying the abnormality based on the health index values, abnormal events can be classified from multiple aspects, thereby improving the accuracy of abnormality classification and thus improving the accuracy of the police alert method.

[0098] In an exemplary embodiment, abnormal events are classified according to the health index values ​​to determine the target abnormal level of the abnormal event, including:

[0099] The abnormality classification model is used to classify the abnormality levels based on the health index values ​​to obtain the target abnormality level of the abnormal event, wherein the abnormality classification model is optimized by the Bayesian optimizer.

[0100] Among them, the anomaly classification model is a classification model. The anomaly classification model can perform reasoning based on the input health indicator values, analyze the probability of abnormal events belonging to each abnormal level, and determine the target abnormal level with the highest probability. The Bayesian optimizer is a global optimization algorithm that can find near-optimal parameter settings with relatively few function evaluations.

[0101] For example, before the abnormal classification model is applied, the Bayesian optimizer can be used to optimize the model based on the health index training data to obtain the optimized abnormal classification model. Furthermore, in the actual application process, after determining the values ​​of each health index, each health index value is input into the optimized abnormal classification model for reasoning, and the probability of abnormal events belonging to each abnormal level is analyzed, and the highest probability is determined as the target abnormal level.

[0102] In this embodiment, the abnormality classification model can effectively integrate the health index values ​​to make accurate abnormality classification judgments.

[0103] In an exemplary embodiment, the abnormal alarm information is displayed to the management terminal corresponding to the power grid mobile application platform in a target alarm manner, including steps S321 to S322. Among them:

[0104] Step S321: extract abnormal object information corresponding to the abnormal event from the operation data, and query the target management terminal corresponding to the abnormal object information from the preset platform management authority table.

[0105] It should be noted that the power grid mobile application platform has many functions and involves a lot of data. On the one hand, some functions may require professional managers to maintain, and on the other hand, some data may need to be kept confidential. Therefore, although the more managers the abnormal alarm is sent to, the higher the efficiency of abnormal handling will be, the effectiveness and confidentiality of the abnormal alarm will be worse.

[0106] The abnormal object refers to the functional module of the power grid mobile application platform involved in the abnormal event. The platform management authority table contains the management authority corresponding to each functional module in the power grid mobile application platform, which can be set in advance according to the confidentiality requirements.

[0107] Exemplarily, relevant operating data related to the abnormal event can be extracted from the operating data, and then the functional module identification information can be identified from the relevant operating data, and the abnormal object information corresponding to the abnormal event can be determined based on the functional module identification information; then, the target management terminal corresponding to the abnormal object information is queried from the preset platform management authority table.

[0108] As an example, a trained permission allocation model can be used to allocate management permissions of at least one functional module to managers based on their user portrait data, user behavior data generated for the power grid mobile application platform, user identity information, etc. Before performing permission allocation, user portrait data of training managers, user behavior data generated for the power grid mobile application platform, user identity information, etc. can be collected in advance as training sample data, and permission labels of training managers can be obtained. Then, the permission allocation model is trained based on the training sample data to obtain permission allocation training results, and the difference between the permission allocation training results and the permission labels is compared to determine whether the training is completed. If the training is completed, a trained permission allocation model is obtained. If the training is not completed, the permission allocation model is iteratively optimized based on the difference between the permission allocation training results and the permission labels until the training is completed. Among them, whether the training is completed can be determined by at least one of whether the model converges, whether the maximum number of iterations is reached, and whether the maximum iteration time is reached.

[0109] Step S322: Display abnormal alarm information to the target management terminal in a target alarm manner.

[0110] Exemplarily, after the target management terminal and the target alarm method are determined, the target alarm method can be used to display abnormal alarm information to the target management terminal.

[0111] In this embodiment, by extracting the abnormal object information, the functional modules related to the abnormal event can be determined, and then combined with the preset platform management authority table, the target management terminal that has a strong correlation with the abnormal event and meets the confidentiality requirements can be determined, thereby effectively improving the efficiency and confidentiality of abnormal alarms.

[0112] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0113] Based on the same inventive concept, the embodiment of the present application also provides a power grid mobile application platform abnormal alarm device for implementing the power grid mobile application platform abnormal alarm method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power grid mobile application platform abnormal alarm device embodiments provided below can refer to the limitations of the power grid mobile application platform abnormal alarm method above, and will not be repeated here.

[0114] In an exemplary embodiment, Figure 4 As shown, a power grid mobile application platform abnormal alarm device is provided, including: an acquisition module 402, a detection module 404 and an alarm module 406, wherein:

[0115] An acquisition module 402 is used to acquire operation data of the power grid mobile application platform;

[0116] The detection module 404 is used to detect the health index of the abnormal event based on the operation data to obtain the health index value when an abnormal event is detected in the power grid mobile application platform based on the operation data;

[0117] The alarm module 406 is used to determine a target alarm method based on the health index value, and use the target alarm method to display abnormal alarm information to the management terminal corresponding to the power grid mobile application platform.

[0118] In an exemplary embodiment, the health index includes an impact range, and the health index value includes an impact range classification result; the detection module 404 is further used to:

[0119] Extract abnormal object information corresponding to the abnormal event from the operation data, and query abnormal radiation object information corresponding to the abnormal object information from the preset platform object relationship table;

[0120] Based on the abnormal object information and the abnormal radiation object information, the impact scope of the abnormal event is classified to obtain an impact scope classification result, wherein the impact scope classification result includes one of a system scope, a platform scope, a function scope, a performance scope and a recommended scope.

[0121] In an exemplary embodiment, the health index includes urgency, and the health index value includes an urgency classification result; the detection module 404 is further used to:

[0122] Extracting trigger time information corresponding to abnormal events from operation data;

[0123] Based on the trigger time information, the urgency of the abnormal event is classified to obtain an urgency classification result, wherein the urgency classification result includes one of an immediate demand, a scheduled demand, a delayed demand and a long-term demand.

[0124] In an exemplary embodiment, there are multiple health indicators; the alarm module 406 is also used to:

[0125] Abnormal events are classified according to the values ​​of each health index, and the target abnormal level of the abnormal event is determined;

[0126] According to the preset correspondence between abnormal level and alarm mode, query the target alarm mode corresponding to the target abnormal level.

[0127] In an exemplary embodiment, the alarm module 406 is further configured to:

[0128] The abnormality classification model is used to classify the abnormality levels based on the health index values ​​to obtain the target abnormality level of the abnormal event, wherein the abnormality classification model is optimized by the Bayesian optimizer.

[0129] In an exemplary embodiment, the alarm module 406 is further configured to:

[0130] Extract the abnormal object information corresponding to the abnormal event from the operation data, and query the target management terminal corresponding to the abnormal object information from the preset platform management authority table;

[0131] The target alarm method is used to display abnormal alarm information to the target management terminal.

[0132] Each module in the abnormal alarm device of the above-mentioned power grid mobile application platform can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0133] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, a method for abnormal alarm of a power grid mobile application platform is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0134] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0135] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0136] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0137] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0138] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0139] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0140] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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 application.

[0141] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for abnormal alarm of a power grid mobile application platform, characterized in that: The method comprises: Obtain operation data of the power grid mobile application platform; In the case where an abnormal event is detected on the power grid mobile application platform based on the operation data, a health index is detected for the abnormal event based on the operation data to obtain a health index value; A target alarm method is determined based on the health index value, and the target alarm method is used to display abnormal alarm information to a management terminal corresponding to the power grid mobile application platform.

2. The method according to claim 1, characterized in that The health index includes an impact range, and the health index value includes an impact range classification result; the health index detection of the abnormal event based on the operation data to obtain the health index value includes: Extracting abnormal object information corresponding to the abnormal event from the operation data, and querying abnormal radiation object information corresponding to the abnormal object information from a preset platform object relationship table; Based on the abnormal object information and the abnormal radiation object information, the impact scope of the abnormal event is classified to obtain an impact scope classification result, wherein the impact scope classification result includes one of a system scope, a platform scope, a function scope, a performance scope and a recommended scope.

3. The method according to claim 1, characterized in that The health index includes urgency, and the health index value includes an urgency classification result; the health index detection of the abnormal event based on the operation data to obtain the health index value includes: Extracting trigger time information corresponding to the abnormal event from the operation data; Based on the trigger time information, the urgency of the abnormal event is classified to obtain an urgency classification result, wherein the urgency classification result includes one of an immediate demand, a scheduled demand, a delayed demand and a long-term demand.

4. The method according to claim 1, characterized in that: The number of the health indicators is multiple; and the determining of the target alarm mode based on the health indicator value includes: Classifying the abnormal events according to the health index values ​​to determine the target abnormal level of the abnormal events; According to the preset correspondence between the abnormal level and the alarm mode, the target alarm mode corresponding to the target abnormal level is queried.

5. The method according to claim 4, characterized in that The abnormality classification of the abnormal event according to each of the health index values ​​to determine the target abnormality level of the abnormal event includes: The abnormality level is classified based on each of the health index values ​​through an abnormality classification model to obtain a target abnormality level of the abnormal event, wherein the abnormality classification model is optimized by a Bayesian optimizer.

6. The method according to any one of claims 1 to 4, characterized in that: The method of displaying abnormal alarm information to the management terminal corresponding to the power grid mobile application platform by using the target alarm method includes: Extracting abnormal object information corresponding to the abnormal event from the operation data, and querying the target management terminal corresponding to the abnormal object information from the preset platform management authority table; The target alarm method is used to display abnormal alarm information to the target management terminal.

7. An abnormal alarm device for a power grid mobile application platform, characterized in that: The device comprises: An acquisition module is used to acquire the operation data of the power grid mobile application platform; A detection module, configured to detect a health index of the abnormal event based on the operation data to obtain a health index value when an abnormal event is detected on the power grid mobile application platform based on the operation data; An alarm module is used to determine a target alarm method based on the health index value, and use the target alarm method to display abnormal alarm information to a management terminal corresponding to the power grid mobile application platform.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.