Distribution network maintenance decision management system based on priority level

Abstract

The invention discloses a distribution network maintenance decision management system based on priority levels, relates to the technical field of fault maintenance, and solves the problem that maintenance task sorting cannot meet user requirements and operation requirements due to the fact that user levels, historical complaint conditions and other multi-dimensional factors are not considered in the prior art. According to the method, the user sorting coefficient is calculated based on the user level, the complaint frequency, namely the complaint level and the complaint frequency of the user, and then the user queuing decision is output by combining the user sorting coefficient and the queuing time and taking the influence minimization of the user sorting coefficient and the minimization of the queuing time as targets. In the process, influence factors such as the user grade and the complaint frequency of the user, namely the complaint grade and the complaint frequency, are considered, so that the user with the higher user grade, the more complaint frequency, the higher complaint grade and the longer queuing time can obtain a more previous sequence, and the satisfaction degree of the user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault maintenance, and in particular to a distribution network maintenance decision management system based on priority levels. Background Art

[0002] In the current power customer service, fault repair is an important link. Usually, power companies collect customer fault reports through customer service hotlines, online platforms or automatic monitoring systems. Once the fault information is received, the maintenance team will quickly start the maintenance operation to restore power supply as soon as possible. During peak hours when faults are frequent, maintenance tasks may accumulate quickly, and at this time, it is necessary to effectively sort the maintenance tasks. Reasonable sorting can ensure that those faults that have the greatest impact on customers are handled first, thereby improving service efficiency and customer satisfaction.

[0003] However, the current maintenance task sorting system has some shortcomings. The main problem is that many sorting mechanisms are based solely on the time when the fault information is received, that is, the principle of first come first served. Although this method is simple, it does not take into account user level, historical complaints, and other multi-dimensional factors. This leads to some high-level users or those who complain frequently not getting faster responses and more priority services, resulting in serious consequences.

[0004] In view of this, a distribution network maintenance decision management system based on priority is needed. Summary of the invention

[0005] In view of the problem that the prior art does not take into account user level, historical complaints and other multi-dimensional factors, resulting in maintenance task sorting that is insufficient to meet user needs and operational needs, the present invention provides a distribution network maintenance decision management system based on priority levels, which can dynamically adjust the priority of maintenance tasks based on multiple factors, such as user level, complaint history, fault type and impact range. The specific technical solution is as follows:

[0006] A distribution network maintenance decision management system based on priority level, comprising:

[0007] The user influence degree determination unit calculates the user ranking coefficient based on the user level, the number of complaints (i.e., complaint level), and the complaint frequency. The calculation of the user ranking coefficient is specifically as follows:

[0008]

[0009] Where y(L) is the user level coefficient, l i is the complaint level coefficient of the ith complaint, N 投诉 is the total number of user complaints during the statistical period, P d is the frequency of complaints;

[0010] The maintenance demand acquisition and decision output unit is connected to the user impact degree determination unit, and outputs the user queuing decision based on the user ranking coefficient and queuing time.

[0011] Preferably, the calculation formula for complaint frequency is as follows:

[0012]

[0013] Where N 投诉 is the number of complaints within the statistical period, T 统计 The total duration of the statistical period.

[0014] Preferably, the process of obtaining the complaint level coefficient is as follows: firstly, the power users are classified into several levels; then, a value is assigned to each level, and the assigned value is the user level coefficient.

[0015] Preferably, the maintenance demand acquisition and decision output unit includes a demand acquisition module, a maintenance resource storage module and a decision output module;

[0016] The demand acquisition module is connected to the user terminal and is used to receive a fault repair signal from the user terminal, and does not record the reception time of the fault repair signal. The fault repair signal includes a fault type and a detailed address;

[0017] The maintenance resource storage module stores specific information of personnel, vehicles and tools, as well as available resources of personnel, vehicles and tools updated in real time, and stores a fault-resource correspondence table, which is used to reflect the personnel qualifications, vehicle models and tool lists required for the maintenance of the fault type;

[0018] The decision output module is used to output the user's fault repair strategy, and the decision output module outputs the fault repair strategy in a manner of solving an objective function.

[0019] Preferably, the objective function is as follows:

[0020]

[0021] Where M is the total number of users participating in the sorting, X j is the ranking of the jth user, X j =[1,2,…,j,…,M],W j is the user ranking coefficient of the jth user, T 排队_j is the cumulative sorting time of the jth user.

[0022] Preferably, there are also constraints, which are as follows:

[0023] Staff availability constraints:

[0024] Q 人 ≠0

[0025] In the formula, Q 人 is the personnel idleness coefficient, which is 1 if the personnel is idle and 0 if the personnel is not idle;

[0026] Vehicle Idle Condition Constraints:

[0027] Q 车 ≠0

[0028] In the formula, Q 车 is the vehicle idle condition coefficient, which is 1 if the vehicle is idle and 0 if the vehicle is not idle;

[0029] Tool Idle Condition Constraints:

[0030] Q 物 ≠0

[0031] In the formula, Q 物 is the tool idle condition coefficient, which is 1 if the tool is idle and 0 if the tool is not idle.

[0032] Preferably, the decision output module uses a gradient ascent algorithm to solve the objective function, as follows:

[0033] Step 1: Get the data set for decision making and randomly select an initial point as the starting point;

[0034] Step 2: Calculate the gradient of the objective function Z at the current point;

[0035] Step 3: Update the parameters along the direction of the gradient, define the learning rate, and control the step size;

[0036] Step 4: Check whether the magnitude of the gradient is less than a preset threshold, or check whether the value of the objective function changes very little in several consecutive iterations. If so, the algorithm is considered to have converged.

[0037] Step 5: If there is no convergence, return to step 2 and continue iterating;

[0038] Step 6: When the algorithm converges, output the value of the current decision.

[0039] Preferably, it also includes an alarm and execution unit, which includes an alarm module and an execution module. The alarm module makes a judgment based on the user fault repair situation obtained by the demand acquisition module and the available resources stored in the maintenance resource storage module to determine whether it is necessary to start queuing; the judgment basis is: when the available resources are insufficient to provide maintenance services for user fault repairs, an alarm signal is issued; the execution unit is used to send an execution instruction to the execution personnel, and when the available resources are sufficient to provide maintenance services for user fault repairs, the personnel, vehicles and tools arranged for the corresponding fault repairs are generated, and the information is sent to the execution terminal for processing. When the available resources are insufficient to provide maintenance services for user fault repairs, the decision output module is started, and the ranking between the users to be queued is output by solving the objective function, and the maintenance personnel, vehicles and tools are arranged at one time according to the ranking.

[0040] A computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the priority-based distribution network maintenance decision management system as described above.

[0041] A processor is used to run a program, wherein when the program is run, the priority-based distribution network maintenance decision management system as described above is executed.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention calculates the user ranking coefficient based on the user's user level, number of complaints, i.e., complaint level, and complaint frequency, and then combines the user ranking coefficient and queuing time to output the user queuing decision with the goal of minimizing the influence of the user ranking coefficient and the queuing time. The user ranking coefficient influence minimization is specifically: the larger the user ranking coefficient, the higher the ranking should be. In this process, the user's user level, number of complaints, i.e., complaint level, complaint frequency and other influencing factors are taken into account, so that users with higher user levels, more complaints, higher complaint levels and longer queuing time can get higher rankings, thereby improving user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0045] Figure 1 It is a schematic diagram of the overall framework of the system of the present invention;

[0046] Figure 2 Schematic diagram of the specific steps of the gradient ascent method. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0049] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0050] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0051] In one embodiment of the present invention, a maintenance decision management system based on priority is provided, such as Figure 1 As shown, including:

[0052] 1. User Impact Determination Unit

[0053] A user impact determination unit calculates a user ranking coefficient based on the user's user level, number of complaints, complaint level, and complaint frequency. The user ranking coefficient is used for management and decision-making during subsequent maintenance operations.

[0054] The calculation of the user ranking coefficient is specifically as follows:

[0055]

[0056] Where y(L) is the user level coefficient, l i is the complaint level coefficient of the i-th complaint, N 投诉 is the total number of user complaints during the statistical period, P d The frequency of complaints.

[0057] The calculation formula for complaint frequency is as follows:

[0058]

[0059] Where N 投诉 is the number of complaints within the statistical period, T 统计 The total duration of the statistical period.

[0060] The process of obtaining the user level coefficient is as follows:

[0061] S1: First, the power users are classified into different levels. The present embodiment provides an example as follows:

[0062] Special important users: These are users who are particularly important in the management of national affairs and whose power supply interruption will endanger national security. The detailed scope includes important national radio stations, television stations, communication centers, aerospace, national airports, etc.

[0063] First-level important users: These refer to users whose power outages may have serious consequences, including direct personal injury, serious environmental pollution, poisoning, explosion or fire, major political impact, major economic losses, and serious disorder of social public order on a large scale. The detailed scope includes national information centers, financial centers, and securities trading centers; national earthquake, meteorological, and flood control monitoring and command centers; airports, rail transit hubs, railway hubs, and railway dispatching centers; important water conservancy hub dams; coal mines and non-coal mines; hazardous chemical production enterprises; petroleum, petrochemical, chemical, and other enterprises where power outages may cause explosions, fires, or toxic gas emissions.

[0064] Secondary important users: These refer to users whose power supply interruption may cause serious environmental pollution, political impact, economic losses, and serious disruption of social public order on a large scale.

[0065] Ordinary users: users other than the above levels.

[0066] Four common user level classification methods are listed above. In practical applications, classification can be based on other standards or adjustments can be made based on the above classifications, which are not specifically limited in this embodiment.

[0067] S2: Based on the above user classification, each user classification is assigned a value, which is the user level coefficient. Industry experts or other staff assign values ​​to each classification so that the assigned value can reflect the importance of each user.

[0068] 2. Maintenance demand acquisition and decision output unit

[0069] The maintenance demand acquisition and decision output unit includes a demand acquisition module, a maintenance resource storage module and a decision output module. The demand acquisition module is connected to the user terminal and is used to receive the fault repair signal from the user terminal, but does not record the reception time of the fault repair signal. The fault repair signal includes the fault type and detailed address.

[0070] The maintenance resource storage module stores the specific information of personnel, vehicles and tools, as well as the available resources of personnel, vehicles and tools (idle personnel, idle vehicles and idle tools) updated in real time. It also stores a fault-resource correspondence table, which is used to reflect the personnel qualifications, vehicle models and tool details required for the fault type maintenance, as shown in Table 1 below:

[0071] Table 1 Fault-resource correspondence table

[0072]

[0073] The decision output module is used to output the user's fault repair strategy. The decision output module outputs the fault repair strategy for reference in a manner of solving an objective function.

[0074] The objective function is as follows:

[0075]

[0076] Where M is the total number of users participating in the sorting, X j is the ranking of the jth user, X j =[1,2,…,j,…,M],W j is the user ranking coefficient of the jth user, T 排队_j is the cumulative sorting time of the jth user.

[0077] Constraints:

[0078] 1. Staff availability constraints:

[0079] Q 人 ≠0

[0080] In the formula, Q 人 is the personnel idleness coefficient, which is 1 if the personnel is idle and 0 if the personnel is not idle;

[0081] 2. Vehicle Idle Condition Constraints:

[0082] Q 车 ≠0

[0083] In the formula, Q 车 is the vehicle idle condition coefficient, which is 1 if the vehicle is idle and 0 if the vehicle is not idle;

[0084] 3. Tool Idle Condition Constraints:

[0085] Q 物 ≠0

[0086] In the formula, Q 物 is the tool idle condition coefficient, which is 1 if the tool is idle and 0 if the tool is not idle.

[0087] The decision output module of this embodiment adopts the gradient ascent algorithm (Gradient Ascent). The gradient ascent method is an iterative method that gradually adjusts the parameters along the direction of the objective function gradient to find the minimum value of the function. Figure 2 As shown, the following are the specific steps of the gradient ascent method:

[0088] Step 1: Get the data set for decision making and randomly select an initial point as the starting point;

[0089] Step 2: Calculate the gradient of the objective function Z at the current point;

[0090] Step 3: Update the parameters along the direction of the gradient, define the learning rate, and control the step size;

[0091] Step 4: Check whether the magnitude of the gradient is less than a preset threshold, or check whether the value of the objective function changes very little in several consecutive iterations. If so, the algorithm is considered to have converged.

[0092] Step 5: If there is no convergence, return to step 2 and continue iterating;

[0093] Step 6: When the algorithm converges, output the value of the current decision.

[0094] 3. Alarm and Execution Unit

[0095] The alarm and execution unit includes an alarm module and an execution module. The alarm module determines whether to start queuing based on the user fault repair situation obtained by the demand acquisition module and the available resources (idle personnel, idle vehicles and idle tools) stored in the maintenance resource storage module. The judgment basis is: when the available resources are insufficient to provide maintenance services for the user's fault repair, an alarm signal is issued, and the alarm signal can be in the form of sound and light alarm or sending information to a specific terminal.

[0096] The execution unit is used to send execution instructions to the execution personnel, including outputting work tickets, etc. When the available resources are sufficient to provide maintenance services for user fault reports, the personnel, vehicles and tools arranged for the corresponding fault repair are generated, and the information is sent to the execution terminal for processing. When the available resources are insufficient to provide maintenance services for user fault repairs, the decision output module is started, and the ranking of the waiting users is output by solving the objective function, and the maintenance personnel, vehicles and tools are arranged at once according to the ranking.

[0097] In summary, the present invention calculates the user ranking coefficient based on the user's user level, number of complaints, i.e., complaint level, and complaint frequency, and then combines the user ranking coefficient and queuing time to output the user queuing decision with the goal of minimizing the influence of the user ranking coefficient and minimizing the queuing time. The minimization of the influence of the user ranking coefficient is specifically: the larger the user ranking coefficient, the higher the ranking should be. In this process, the user's user level, number of complaints, i.e., complaint level, complaint frequency and other influencing factors are taken into account, so that users with higher user levels, more complaints, higher complaint levels and longer queuing time can get higher rankings, thereby improving user satisfaction and facilitating user maintenance and management.

[0098] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0099] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0100] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A distribution network maintenance decision management system based on priority, characterized in that: include: The user influence degree determination unit calculates the user ranking coefficient based on the user level, the number of complaints (i.e., complaint level), and the complaint frequency. The calculation of the user ranking coefficient is specifically as follows: Where y(L) is the user level coefficient, l i is the complaint level coefficient of the i-th complaint, N 投诉 is the total number of user complaints during the statistical period, P d is the frequency of complaints; The maintenance demand acquisition and decision output unit is connected to the user impact determination unit, and combines the user ranking coefficient and the queuing time to output the user queuing decision with the goal of minimizing the impact of the user ranking coefficient and the queuing time. The minimization of the impact of the user ranking coefficient is specifically: the larger the user ranking coefficient, the higher the ranking should be.

2. A distribution network maintenance decision management system based on priority according to claim 1, characterized in that: The calculation formula for complaint frequency is as follows: Where N 投诉 is the number of complaints within the statistical period, T 统计 The total duration of the statistical period.

3. A distribution network maintenance decision management system based on priority according to claim 1, characterized in that: The process of obtaining the complaint level coefficient is specifically as follows: firstly, the power users are divided into several levels; then, a value is assigned to each level, and the assigned value is the user level coefficient.

4. A distribution network maintenance decision management system based on priority level according to claim 1, characterized in that: The maintenance demand acquisition and decision output unit includes a demand acquisition module, a maintenance resource storage module and a decision output module; The demand acquisition module is connected to the user terminal and is used to receive a fault repair signal from the user terminal, and does not record the reception time of the fault repair signal. The fault repair signal includes a fault type and a detailed address; The maintenance resource storage module stores specific information of personnel, vehicles and tools, as well as available resources of personnel, vehicles and tools updated in real time, and stores a fault-resource correspondence table, which is used to reflect the personnel qualifications, vehicle models and tool lists required for the maintenance of the fault type; The decision output module is used to output the user's fault repair strategy, and the decision output module outputs the fault repair strategy in a manner of solving an objective function.

5. A distribution network maintenance decision management system based on priority level according to claim 4, characterized in that: The objective function is as follows: Where M is the total number of users participating in the sorting, X j is the ranking of the jth user, X j =[1,2,…,j,…,M],W j is the user ranking coefficient of the jth user, T 排队_j is the cumulative sorting time of the jth user.

6. A distribution network maintenance decision management system based on priority level according to claim 5, characterized in that: There are also constraints, as follows: Staff availability constraints: Q 人 ≠0 In the formula, Q 人 is the personnel idleness coefficient, which is 1 if the personnel is idle and 0 if the personnel is not idle; Vehicle Idle Condition Constraints: Q 车 ≠0 In the formula, Q 车 is the vehicle idle condition coefficient, which is 1 if the vehicle is idle and 0 if the vehicle is not idle; Tool Idle Condition Constraints: Q 物 ≠0 In the formula, Q 物 is the tool idle condition coefficient, which is 1 if the tool is idle and 0 if the tool is not idle.

7. A priority-based distribution network maintenance decision management system according to claim 6, characterized in that: The decision output module uses the gradient ascent algorithm to solve the objective function, as follows: Step 1: Get the data set for decision making and randomly select an initial point as the starting point; Step 2: Calculate the gradient of the objective function Z at the current point; Step 3: Update the parameters along the direction of the gradient, define the learning rate, and control the step size; Step 4: Check whether the magnitude of the gradient is less than a preset threshold, or check whether the value of the objective function changes very little in several consecutive iterations. If so, the algorithm is considered to have converged. Step 5: If there is no convergence, return to step 2 and continue iterating; Step 6: When the algorithm converges, output the value of the current decision.

8. A priority-based distribution network maintenance decision management system according to claim 4, characterized in that: It also includes an alarm and execution unit, which includes an alarm module and an execution module. The alarm module makes a judgment based on the user fault report situation obtained by the demand acquisition module and the available resources stored in the maintenance resource storage module to determine whether it is necessary to start queuing; the judgment basis is: when the available resources are insufficient to provide maintenance services for the user's fault report, an alarm signal is issued; the execution unit is used to send an execution instruction to the execution personnel, and when the available resources are sufficient to provide maintenance services for the user's fault report, the personnel, vehicles and tools information arranged for the corresponding fault repair is generated, and the information is sent to the execution terminal for processing; when the available resources are insufficient to provide maintenance services for the user's fault report, the decision output module is started, and the ranking between the users to be queued is output by solving the objective function, and the maintenance personnel, vehicles and tools are arranged at one time according to the ranking situation.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the priority-based distribution network maintenance decision-making management system according to any one of claims 1 to 7.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the priority-based distribution network maintenance decision-making management system described in any one of claims 1 to 7.

Images