A method for realizing fee clearing and power restoration timeout warning using big data technology

Abstract

The present invention discloses a method for realizing timeout warning of fee settlement and power restoration by using big data technology, including setting up an information acquisition module connected to the power system, for obtaining user payment information and searching for user specific information; constructing an information processing module, for dividing users into primary, secondary, and tertiary power restoration according to the power outage time; setting up a field staff management module, for managing the status of field staff, and for supporting the dispatch of field staff with three-level power restoration needs; and a dispatch module, for predicting the time for field staff to arrive at the site. In addition, an inspection time prediction module is also provided, for predicting the inspection time according to historical power equipment maintenance information, and generating a maintenance report and sending it to the field staff. The warning module integrates the dispatching and inspection time prediction results, and sends a power restoration time warning to the user. This method realizes efficient and automated management of the fee settlement and power restoration process, and improves power service efficiency and user satisfaction.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method for realizing fee clearing and power restoration timeout warning using big data technology. Background Art

[0002] Fee settlement and power restoration refers to the process in which the power system restores power supply to users based on their payment information after the users have paid their electricity bills. This process is an important part of power services and is directly related to the user's electricity experience and the power company's operating efficiency. In actual operations, fee settlement and power restoration involves multiple links, including receiving user payment information, searching and verifying user information, classifying power restoration levels, dispatching field staff and on-site inspections, etc. This process requires power companies to respond quickly and accurately to users' payment requests to ensure timely restoration of power supply.

[0003] There are some obvious shortcomings in the current fee clearance and power restoration process. First, the processing of payment information and the search for user information often rely on manual operations, which is not only inefficient but also prone to errors. Secondly, there is a lack of a scientific hierarchical processing mechanism for the user's power restoration needs, resulting in a cumbersome and inflexible processing process. Furthermore, the management and scheduling of field personnel also lack intelligent means, and it is impossible to grasp the work status and location information of field personnel in real time, which affects the efficiency of power restoration. In addition, the existing technology also lacks an accurate prediction and early warning mechanism for the power restoration time, and users often cannot understand the progress of power restoration in a timely manner, which brings inconvenience to the user's electricity usage arrangements. Therefore, there is an urgent need for an efficient, accurate, and intelligent fee clearance and power restoration method to solve these problems in the existing technology.

[0004] To this end, we propose a big data technology to achieve Feiqing Fudian timeout warning method Summary of the invention

[0005] The purpose of the present invention is to provide a method for realizing fee clearing and power restoration timeout warning by using big data technology to solve the above-mentioned deficiencies in the prior art.

[0006] In order to achieve the above-mentioned purpose, the present invention provides the following technical solution: A method for realizing a timeout warning of fee clearing and power restoration using big data technology, comprising the following steps:

[0007] A: Establish an information acquisition module connected to the power system through an interface. When the power system receives payment information from the user, the information acquisition module obtains the payment information through the interface, and searches for the user's specific information in the power system based on the payment information, including but not limited to the power outage time and power equipment maintenance records;

[0008] B: Construct an information processing module to interface with the information acquisition module. After the information acquisition module obtains the power outage time of the user, the user is divided into level one, level two and level three according to the power outage time. Level one means directly restoring the power supply through the power system, level two means restoring the power supply after manual review, and level three means restoring the power supply after field staff have checked on site.

[0009] C: Set up a field staff management module, which is used to manage the field status of field staff, provide field staff work status information when the third-level power restoration needs to be met, and provide support for selecting appropriate field staff to handle the third-level power restoration needs;

[0010] D: a scheduling module, which is used to send scheduling information to the field staff who are in an idle state, and predict the time to rush to the field work location according to the distance between the field staff and the users who need to restore power at the third level;

[0011] E: Inspection time prediction module, which is connected to the information acquisition module, and generates the current maintenance report according to the equipment maintenance record provided by the information acquisition module and sends it to the field inspection personnel, and predicts the time required for the current equipment inspection according to the maintenance report;

[0012] F: Early warning module: The sum of the predicted times in step D and step E is the predicted power restoration time for the user with the third-level power restoration demand, and a power restoration time warning is sent to the user.

[0013] As a further description of the above technical solution: the information acquisition module in step A is connected to the power system through the API interface and transmits data using the HTTPS protocol. When the power system receives the user's payment notice, the notice is automatically forwarded to the API interface. The information acquisition module receives the payment notice through the API interface and parses key information such as the user ID, payment amount, and payment time. Then, the information acquisition module uses the user ID to search for the corresponding user information in the power system, including the power outage time and the power equipment maintenance record.

[0014] As a further description of the above technical solution: the specific steps of classifying the users in step B are:

[0015] B1: Use the integrated development environment IntelliJ IDEA and corresponding programming languages ​​such as Java to build a framework for the information processing module, where the framework must include a data input interface (for receiving user payment and power data from the information acquisition module), data processing logic (for cleaning and verifying data), a level classification algorithm (for classifying users into level 1, level 2, and level 3 power restoration according to preset rules such as power outage time thresholds) and a data output interface (for sending the classification results to subsequent modules);

[0016] B2: Based on the constructed framework, the database management system MySQL is used to store and process the received user data, and key information such as power outage time is extracted through SQL query technology;

[0017] B3: Based on the queried power outage time information of the paying user, the user's power restoration level is automatically divided into level one, level two and level three through the power restoration level classification algorithm.

[0018] As a further description of the above technical solution: the specific construction method of the field staff management module in step C is:

[0019] C1: Set up a front-end unit and a back-end unit. The front-end unit is used by field staff to submit field applications and reports, while the back-end unit is responsible for processing these applications and updating the status information of field staff.

[0020] C2: Use MySQL to store the basic information of field staff, current status (idle, out), field application and field report data;

[0021] C3: Field employees submit field work applications through the front-end unit, including but not limited to field work purpose, location, estimated time and other information. After receiving the field work application, the back-end unit updates the field employee's status to "out of office". After the field work is completed, the employee needs to submit a field work report in the front-end unit, including but not limited to the completion time of the field work. After receiving the report, the back-end unit updates the field employee's status to "available".

[0022] As a further description of the above technical solution: the scheduling module obtains the employee's work location based on the employee information in the field employee management module and obtains the location of the third-level power restoration user through the information acquisition module, and then uses the map service API to calculate the distance between the two locations, and obtains the recommended route between the two locations through the interface of the map service API, and at the same time obtains the estimated driving time of the route.

[0023] As a further description of the above technical solution: the specific method of the inspection time prediction module to predict the inspection time is:

[0024] E1: The information acquisition module is used to obtain the historical power equipment maintenance information of the third-level power restoration demand users, and a checklist is generated based on the historical maintenance information and sent to the field staff;

[0025] E2: The inspection time prediction module searches for the maintenance records of the same equipment in the historical power equipment maintenance information, and then predicts the time required for this maintenance based on the equipment maintenance time in the maintenance records.

[0026] As a further description of the above technical solution, the method for selecting field employees by the scheduling module is divided into the following steps:

[0027] D1: For each three-level power restoration task D n , the maintenance report generated by the inspection time prediction module lists all the equipment that needs to be inspected;

[0028] D2: For each field employee k, calculate the average time T they spend checking each device i based on historical data ki If an employee has not checked a device, a default value is used for estimation. When the total number of devices is M, for each device i, i = 1, 2, 3, ..., M, employee K has checked n i Inspections, each inspection time is T ki1 , T ki2 , ..., T kini Then the average inspection time of employee K for equipment i is T ki It can be calculated by the following formula;

[0029]

[0030] Among them, n i is the number of times employee K checks equipment i, T kij is the time when employee K checks the device i for the jth time, where j is an index variable used to traverse all the times when employee K checks the device i;

[0031] D3: Checklist D for each Level 3 power restoration task n , the total inspection time K required for each field employee K to complete the task is calculated by the following formula: 总 :

[0032] K 总 =∑ i∈Dn C ni ×T ki

[0033] Among them, K 总 Indicates the total inspection time, C ni Is the device i in the check list D n The number of times it appears in

[0034] D4: Traverse the K of all idle employees 总 Then, find K 总 The field employee K with the smallest value is the best dispatched employee for this third-level power restoration task.

[0035] In the above technical solution, the big data technology provided by the present invention realizes the fee clearing and power restoration timeout warning method, which has the following beneficial effects:

[0036] Efficient and automated management: By setting up multiple modules such as information acquisition module and information processing module, efficient and automated management of fee settlement and power restoration process is achieved. From user payment to the sending of power restoration warning, the whole process is seamlessly connected, reducing manual intervention and improving work efficiency.

[0037] Accurate hierarchical processing: Based on the user's power outage time, the information processing module is used to accurately divide the user into primary, secondary, and tertiary power restoration levels. Different power restoration measures are taken for users of different levels to ensure the rational allocation and utilization of resources.

[0038] Optimized dispatch of field employees: Through the field employee management module and dispatch module, the system can grasp the status and location of field employees in real time, and perform intelligent dispatch according to the three-level power restoration needs, ensuring that field employees can arrive at the site in time and shorten the power restoration time.

[0039] Accurate inspection time prediction: The inspection time prediction module can accurately predict the time required for the equipment inspection based on historical power equipment maintenance information, provide reliable data support for the early warning module, and improve the accuracy of the power restoration time warning.

[0040] Improved user satisfaction: By sending power restoration time warnings to users, users can clearly understand the power restoration progress and possible problems, which enhances their understanding and trust in the power service process and improves user satisfaction. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below.

[0042] The embodiment of the present invention provides a technical solution: a method for realizing fee clearing and power restoration timeout warning by using big data technology, comprising the following steps:

[0043] A: Establish an information acquisition module connected to the power system through an interface. When the power system receives payment information from the user, the information acquisition module obtains the payment information through the interface, and searches for the user's specific information in the power system based on the payment information, including but not limited to the power outage time and power equipment maintenance records;

[0044] The information acquisition module is connected to the power system through the API interface and uses the HTTPS protocol for data transmission. When the power system receives the user's payment notice, the notice is automatically forwarded to the API interface. The information acquisition module receives the payment notice through the API interface and parses the key information such as the user ID, payment amount, and payment time. Then, the information acquisition module uses the user ID to search for the corresponding user information in the power system, including the power outage time and the power equipment maintenance record.

[0045] It should be noted that HTTPS uses the SSL / TLS protocol to encrypt data transmitted by the interface to ensure that sensitive information (such as user ID, payment amount, etc.) is not stolen during transmission;

[0046] B: Construct an information processing module to interface with the information acquisition module. After the information acquisition module obtains the power outage time of the user, the user is divided into level one, level two and level three according to the power outage time. Level one means directly restoring the power supply through the power system, level two means restoring the power supply after manual review, and level three means restoring the power supply after field staff have checked on site.

[0047] It should be noted that the specific steps for classifying users are as follows:

[0048] B1: Use the integrated development environment IntelliJ IDEA and corresponding programming languages ​​such as Java to build a framework for the information processing module, where the framework must include a data input interface (for receiving user payment and power data from the information acquisition module), data processing logic (for cleaning and verifying data), a level classification algorithm (for classifying users into level 1, level 2, and level 3 power restoration according to preset rules such as power outage time thresholds) and a data output interface (for sending the classification results to subsequent modules);

[0049] B2: Based on the constructed framework, the database management system MySQL is used to store and process the received user data, and key information such as power outage time is extracted through SQL query technology;

[0050] B3: Based on the power outage time information of the bill paying user, the user's power restoration level is automatically divided into level one, level two and level three through the power restoration level classification algorithm;

[0051] It should be noted here that the first-level power restoration is for users with a very short power outage time, such as users who have been out of power for one day. After paying again, the power supply will be restored to them immediately through the power system. Compared with the first-level power restoration, the second-level power restoration is for users with a longer power outage time, such as half a month or a month. Such users need to undergo manual review. After the manual review is passed, the power supply can be restored through the power system. The manual review time here is usually faster. According to the work arrangement, the power supply can be restored on the day of payment or the next day. The manual review here needs to verify the payment information provided by the user, including the payment amount, payment time, payment method, etc., to ensure that the user has completed the payment as required. After confirming that the payment information is correct, the auditor will further check the user's electricity usage record, power outage reason, power equipment status and other information to determine whether the user meets the power restoration conditions. For users with problems in the power equipment status, the user will be upgraded to a third-level power restoration user, and the power supply can only be restored after the field staff has checked it on site.

[0052] C: Set up a field staff management module, which is used to manage the field status of field staff, provide field staff work status information when the third-level power restoration needs to be met, and provide support for selecting appropriate field staff to handle the third-level power restoration needs;

[0053] The specific construction method of the field staff management module is as follows:

[0054] C1: Set up a front-end unit and a back-end unit. The front-end unit is used by field staff to submit field applications and reports, while the back-end unit is responsible for processing these applications and updating the status information of field staff.

[0055] C2: Use MySQL to store the basic information of field staff, current status (idle, out), field application and field report data;

[0056] C3: Field employees submit field work applications through the front-end unit, including but not limited to field work purpose, location, estimated time and other information. After receiving the field work application, the back-end unit updates the field employee's status to "out of office". After the field work is completed, the employee needs to submit a field work report through the front-end unit, including but not limited to the completion time of the field work. After receiving the report, the back-end unit updates the field employee's status to "available".

[0057] The front-end interface can be developed using the React front-end framework to provide the user interface of the front-end unit. The back-end service can use the Python back-end technology stack and combine it with the Spring Boot or Django framework to build a RESTful API interface for receiving and processing requests sent by the front-end.

[0058] D: a scheduling module, which is used to send scheduling information to the field staff who are in an idle state, and predict the time to rush to the field work location according to the distance between the field staff and the users who need to restore power at the third level;

[0059] The scheduling module obtains the employee's work location based on the employee information in the field employee management module and obtains the location of the third-level power restoration demand user through the information acquisition module, and then uses the map service API to calculate the distance between the two locations, and obtains the recommended route between the two locations through the interface of the map service API, and obtains the estimated travel time of the route;

[0060] E: Inspection time prediction module, which is connected to the information acquisition module, and generates the current maintenance report according to the equipment maintenance record provided by the information acquisition module and sends it to the field inspection personnel, and predicts the time required for the current equipment inspection according to the maintenance report;

[0061] The specific method of the inspection time prediction module to predict the inspection time is:

[0062] E1: The information acquisition module is used to obtain the historical power equipment maintenance information of the third-level power restoration demand users, and a checklist is generated based on the historical maintenance information and sent to the field staff;

[0063] E2: The inspection time prediction module searches for the maintenance records of the same equipment in the historical power equipment maintenance information, and then predicts the time required for this maintenance based on the equipment maintenance time in the maintenance record;

[0064] In order to improve the inspection time prediction module's prediction accuracy and effectiveness, the inspection time prediction module can use machine learning models to intelligently analyze historical maintenance information to identify common failure modes, maintenance cycles, and maintenance priorities of equipment. Based on the analysis results, the module generates a checklist for this maintenance. The checklist must list in detail the equipment to be inspected, inspection content, possible failure points, required tools and materials, and other information. The module sends the checklist and related information to the field personnel's devices through SMS, email, or mobile application notifications to ensure that they can receive task information in a timely manner and be prepared.

[0065] It should also be noted that when generating the inspection form, the module will also search for inspection records similar to the equipment type and failure mode of the current inspection in the historical power equipment inspection information in the information acquisition module. By comparing and analyzing the inspection time in these similar inspection records, the module uses statistical methods to predict the time required for this inspection. Then, the module can not only send the predicted inspection time to the early warning module, but also send the predicted inspection time to the field staff so that they can better plan the work progress and arrange the time.

[0066] When field inspectors discover new problems or abnormal conditions in electrical equipment during on-site inspections, the early warning module will communicate the situation to users via wireless networks / 5G, and an explanation will be attached to explain why the power restoration time has changed. This not only improves the transparency of the service, but also enhances users' understanding and trust in the power service process. Users can clearly understand the specific problems encountered during the maintenance process and how these problems affect the time schedule for power restoration, so as to make more reasonable arrangements and preparations.

[0067] F: Early warning module: The sum of the predicted times in step D and step E is the predicted power restoration time for the user with the third-level power restoration demand, and a power restoration time warning is sent to the user.

[0068] 8. In another embodiment of the present invention, the method for the scheduling module to select field staff is divided into the following steps:

[0069] D1: For each three-level power restoration task D n , the maintenance report generated by the inspection time prediction module lists all the equipment that needs to be inspected;

[0070] D2: For each field employee k, calculate the average time T they spend checking each device i based on historical data ki If an employee has not checked a device, a default value is used for estimation. When the total number of devices is M, for each device i, i = 1, 2, 3, ..., M, employee K has checked n i Inspections, each inspection time is T ki1 , T ki2 ...T kini Then the average inspection time of employee K for equipment i is T ki It can be calculated by the following formula;

[0071]

[0072] Among them, n i is the number of times employee K checks equipment i, T kij is the time when employee K checks the device i for the jth time, where j is an index variable used to traverse all the times when employee K checks the device i;

[0073] D3: Checklist D for each Level 3 power restoration task n , the total inspection time K required for each field employee K to complete the task is calculated by the following formula: 总 :

[0074] K 总 =∑ i∈Dn Cni ×T ki

[0075] Among them, K 总 Indicates the total inspection time, C ni Is the device i in the check list D n The number of times it appears in

[0076] D4: Traverse the K of all idle employees 总 Then, find K 总 The field worker K with the minimum value is the best dispatched worker for this level 3 power restoration task, where C ni In normal cases, it is set to 1 because a device only needs to be checked once. In some special cases, when a device needs to be checked multiple times, C ni For the specific number of inspections required, through the above calculation, the best personnel that can be dispatched from the idle field staff can be found according to the inspection items in this inspection list; however, in order to solve the problem that less experienced employees cannot be dispatched or are rarely dispatched according to this type of dispatch method, and experienced employees are often dispatched, field staff can be dispatched in the following way:

[0077] Step 1: Calculate the work capacity weight of field staff through the field staff management module. First, collect the raw data of the time it takes for all employees to complete the inspection of a certain equipment, and calculate the median M. Based on the median M, set a weight range; for example, 90% to 110% of M is a standard range;

[0078] Step 2: Within this standard range, refine the weight level. If the inspection time is between 0.9M and 1.1M, the work capacity weight is W. 能力 =5, which is the basic weight; if the inspection time is less than 0.9M, the weight increases by 1 for every 10% lower; if the inspection time is higher than 1.1M, the weight decreases by 1 for every 10% higher, calculated according to the following formula:

[0079]

[0080] Where T is the inspection time of a certain employee on a piece of equipment;

[0081] Step 3: Set the allowable deviation percentage α of the total inspection time of the best dispatched employee, and then calculate the maximum dispatchable time interval according to the following formula, which is 120% of the predicted inspection time of the best dispatched employee:

[0082] T 最大 =T b ×(1+α),

[0083] Among them, Tb The inspection time predicted for dispatching the best employee, and then from the inspection time [T b , T 最大 ], select W 能力 The youngest employees are the ones to be dispatched. In this way, without greatly affecting the efficiency of inspecting users' electrical equipment, employees with less experience and longer field work hours can be dispatched to increase their practical experience.

[0084] The specific process is as follows: When the third-level power restoration occurs, after the user completes the payment, the power system sends the payment information to the information acquisition module through the API interface. The information acquisition module obtains information such as the user ID, and searches the power system for the user's power outage time and power equipment maintenance records. According to the power outage duration, the information processing module automatically classifies the user as a third-level power restoration, which means that field staff are required to conduct on-site inspections before power can be restored. At this time, through the set field staff management module, the field staff management module records the current status of all field staff. The system sends field dispatch information to all idle field staff through the back-end unit, and selects the first field staff member who replies to the information through the front-end unit. At the same time, the dispatch module uses the map service API to calculate the distance between the field staff and the third-level power restoration user, and plans the best route, predicting the approximate time to arrive at the scene.

[0085] The inspection time prediction module generates a detailed inspection report based on the equipment inspection records provided by the information acquisition module and sends it to the field staff who are about to go. By searching the inspection records of the same equipment in the historical inspection information, the module predicts the time that may be required for this equipment inspection.

[0086] Finally, the early warning module combines the time to arrive at the site predicted by the dispatch module and the maintenance time given by the inspection time prediction module to derive the total predicted time required to restore power to this third-level power restoration demand user. The system then sends a power restoration time warning to the user, informing him of the expected power restoration time so that the user can make corresponding preparations. The entire process, from user payment to the sending of power restoration warnings, achieves efficient and automated management, greatly improving the efficiency of power services and user satisfaction.

[0087] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that, for those skilled in the art, the described embodiments can be modified in various ways without departing from the spirit and scope of the present invention. Therefore, the above description is illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for realizing timeout warning of fee clearing and power restoration using big data technology, characterized in that: The steps include: A: Establish an information acquisition module connected to the power system through an interface. When the power system receives payment information from a user, the information acquisition module acquires the payment information through the interface, and searches for the user's specific information in the power system based on the payment information, including but not limited to the power outage time and power equipment maintenance records; B: Construct an information processing module to interface with the information acquisition module. After the information acquisition module obtains the power outage time of the user, the user is divided into level one, level two and level three according to the power outage time. Level one means directly restoring the power supply through the power system, level two means restoring the power supply after manual review, and level three means restoring the power supply after on-site inspection by field staff. C: Set up a field staff management module, which is used to manage the field status of field staff, provide field staff work status information when the third-level power restoration needs to be met, and provide support for selecting appropriate field staff to handle the third-level power restoration needs; D: Scheduling module, which is used to send scheduling information to the field staff who are in an idle state, and predict the time to arrive at the field work location based on the distance between the field staff and the location of the user who needs third-level power restoration; E: Inspection time prediction module, which is connected to the information acquisition module, and generates the current maintenance report according to the equipment maintenance record provided by the information acquisition module and sends it to the field inspection personnel, and predicts the time required for the current equipment inspection according to the maintenance report; F: Early warning module: The sum of the predicted times in step D and step E is the predicted power restoration time for the user with the third-level power restoration demand, and a power restoration time warning is sent to the user.

2. According to the big data technology of claim 1, the method for realizing fee clearing and power restoration timeout warning is characterized in that: In step A, the information acquisition module is connected to the power system through the API interface and transmits data using the HTTPS protocol. When the power system receives a payment notice from a user, the notice is automatically forwarded to the API interface. The information acquisition module receives the payment notice through the API interface and parses key information such as the user ID, payment amount, and payment time. The information acquisition module then uses the user ID to search for corresponding user information in the power system, including power outage time and power equipment maintenance records.

3. According to claim 2, a method for realizing fee clearing and power restoration timeout warning by big data technology, characterized in that: The specific steps of classifying the users in step B are as follows: B1: Use the integrated development environment IntelliJIDEA and corresponding programming languages ​​such as Java to build a framework for the information processing module, which must include: A data input interface, used to receive user payment and power data from the information acquisition module; Data processing logic to clean and validate data; The power restoration level classification algorithm divides users into level one, level two, and level three power restoration levels according to preset rules such as power outage time thresholds; Data output interface, used to send the division results to subsequent modules; B2: Based on the constructed framework, the database management system MySQL is used to store and process the received user data, and key information such as power outage time is extracted through SQL query technology; B3: Based on the queried power outage time information of the paying user, the user's power restoration level is automatically divided into level one, level two and level three through the power restoration level classification algorithm.

4. According to claim 3, a method for realizing fee clearing and power restoration timeout warning by big data technology is characterized in that: The specific construction method of the field staff management module in step C is: C1: Set up a front-end unit and a back-end unit. The front-end unit is used by field staff to submit field applications and reports, while the back-end unit is responsible for processing these applications and updating the status information of field staff. C2: Use MySQL to store the basic information, current status, field application and field report data of field staff; the current status includes idle and out; C3: The field employee submits a field application through the front-end unit, including but not limited to the field purpose, location, estimated time and other information. After the back-end unit receives the field application, it updates the field employee's status to out of office. After the field work is completed, the employee needs to submit a field report in the front-end unit, including but not limited to the completion time of the field work. After receiving the report, the back-end unit updates the field employee's status to free.

5. According to claim 4, a method for realizing fee clearing and power restoration timeout warning by big data technology is characterized in that: The scheduling module obtains the employee's work location based on the employee information in the field employee management module and obtains the location of the third-level power restoration user through the information acquisition module, and then uses the map service API to calculate the distance between the two locations, and obtains the recommended route between the two locations through the interface of the map service API, and at the same time obtains the estimated driving time of the route.

6. The method for realizing fee clearing and power restoration timeout warning by big data technology according to claim 5 is characterized in that: The specific method for the inspection time prediction module to predict the inspection time is: E1: The information acquisition module is used to obtain the historical power equipment maintenance information of the third-level power restoration demand users, and a checklist is generated based on the historical maintenance information and sent to the field staff; E2: The inspection time prediction module searches for the maintenance records of the same equipment in the historical power equipment maintenance information, and then predicts the time required for this maintenance based on the equipment maintenance time in the maintenance records.

7. The method for realizing fee clearing and power restoration timeout warning by big data technology according to claim 6 is characterized in that: The method for selecting field staff by the scheduling module is divided into the following steps: D1: For each three-level power restoration task D n , the maintenance report generated by the inspection time prediction module lists all the equipment that needs to be inspected; D2: For each field employee k, calculate the average time T they spend checking each device i based on historical data ki If an employee has not checked a device, a default value is used for estimation. When the total number of devices is M, for each device i, i = 1, 2, 3, ..., M, employee K has checked n i Inspections, each inspection time is T ki1 , T ki2 ,...,T kini Then the average inspection time of employee K for equipment i is T ki It can be calculated by the following formula; Among them, n i is the number of times employee KK checks equipment i, T kij is the time when employee K checks the device i for the jth time, where j is an index variable used to traverse all the times when employee K checks the device i; D3: Checklist D for each Level 3 power restoration task n , the total inspection time K required for each field employee K to complete the task is calculated by the following formula: 总 : K 总 =∑ i∈Dn C ni ×T ki Among them, K 总 Indicates the total inspection time, C ni Is the device i in the check list D n The number of times it appears in D4: Traverse the K of all idle employees 总 Then, find K 总 The field employee K with the smallest value is the best dispatched employee for this third-level power restoration task.

Images