Detection method and system for multi-objective optimization of power marketing business scheme

Abstract

The invention provides a detection method for a multi-objective optimization electricity marketing business scheme. The detection method comprises the following steps: acquiring a plurality of enforceable schemes of an electricity marketing business; in each enforceable scheme, scores of preset evaluation indexes of the strategic risk control layer, the compliance examination layer and the customer experience layer are obtained; and constructing a multi-objective optimization function, solving a Pareto optimal solution of the multi-objective optimization function corresponding to each enforceable scheme in combination with scores of all evaluation indexes in each enforceable scheme, and selecting a scheme meeting a predetermined condition from the plurality of enforceable schemes according to the Pareto optimal solution and outputting the scheme. Wherein the multi-objective optimization function is obtained by constructing an objective function from evaluation indexes of a strategic risk control layer, a compliance review layer and a customer experience layer. By implementing the method and the device, quality detection can be performed on the business scheme from the aspect of enterprise internal risk prevention, so that the enterprise is helped to better manage and cope with strategic risks, and the stability and the safety of the business are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a detection method and system for a multi-objective optimization power marketing business plan. Background Art

[0002] As the market-oriented reform of the power industry continues to deepen, power companies are facing increasingly complex internal and external risks in their marketing business, including changes in the market environment and policies and regulations, rapid changes in customer needs, and the complexity of internal management. However, these internal and external risks work together to increase the risk exposure of power companies in marketing, which may have an adverse impact on their operating results and market position.

[0003] At present, most of the detection methods for power market marketing business solutions on the market focus on external performance, but lack business solution detection methods from the perspective of internal risk prevention of the enterprise, which makes it difficult for enterprises to effectively identify and prevent potential risks, affecting the robustness and sustainability of marketing business, as well as service quality and user satisfaction.

[0004] Therefore, there is an urgent need to build a sustainable improvement mechanism to conduct quality inspections on business plans from the perspective of internal risk prevention in the enterprise, so as to help enterprises better manage and respond to strategic risks and improve the stability and security of their business. Summary of the invention

[0005] The technical problem to be solved by the embodiments of the present invention is to provide a detection method and system for a multi-objective optimization power marketing business plan, which can perform quality detection on the business plan from the perspective of internal risk prevention of the enterprise, so as to help the enterprise better manage and respond to strategic risks and improve the stability and security of the business.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a detection method for a multi-objective optimization power marketing business plan, the method comprising the following steps:

[0007] Obtain multiple feasible implementation plans for power marketing business;

[0008] In each feasible implementation plan, the scores of the preset evaluation indicators of the strategic risk control layer, the preset evaluation indicators of the compliance review layer and the preset evaluation indicators of the customer experience layer are obtained;

[0009] A multi-objective optimization function is constructed, and the Pareto optimal solution of the multi-objective optimization function corresponding to each feasible implementation plan is obtained by combining the scores of all evaluation indicators obtained in each feasible implementation plan, and further, according to the Pareto optimal solution obtained for each feasible implementation plan, a plan that meets predetermined conditions is selected from the multiple feasible implementation plans for output; wherein, the multi-objective optimization function is obtained by an objective function constructed based on the preset evaluation indicators of the strategic risk control layer, a second objective function constructed based on the preset evaluation indicators of the compliance review layer, and an objective function constructed based on the preset evaluation indicators of the customer experience layer.

[0010] Wherein, the multi-objective optimization function is in,

[0011] fstrategy(Sj) is the objective function constructed based on the preset evaluation indicators of the strategic risk control layer; fcompliance(Sj) is the objective function constructed based on the preset evaluation indicators of the compliance review layer; fexperience(Sj) is the objective function constructed based on the preset evaluation indicators of the customer experience layer; Sj is the score of the jth evaluation indicator.

[0012] The score of each evaluation indicator is calculated by its efficacy score and dynamic weight;

[0013] The efficacy score D of each evaluation index is obtained by the formula D=A1+(100-A1)*B1; A1 is the basic score, which is a positive integer less than 100; B1 is the efficacy coefficient, S is the actual value of the indicator, which is between (0, 1]; T is the unacceptable value of the indicator, which is between (0, 1]; M is the satisfactory value of the indicator. If the unacceptable value T of the indicator is the maximum abnormal rate, the value is 0; otherwise, if the unacceptable value T of the indicator is the minimum qualified rate, the value is 1;

[0014] Through the formula w i (t) = w i (0)+α*f(t), and obtain the dynamic weight w of each evaluation index i (t); w i (0) is the initial weight of the i-th evaluation index, and α is the parameter adjustment coefficient, and its value is between (0, 1]; f(t) is the trend function based on historical data, and its value is determined by the maximum score and the minimum score at time 0 to t.

[0015] Among them, the preset evaluation indicators of the strategic risk control layer include safety hazard management, important user file management, electricity fee recovery rate and electricity fee refund rate; the preset evaluation indicators of the compliance review layer include business process standardization, contract execution compliance and business operation risk warning; the preset evaluation indicators of the customer experience layer include customer complaint service quality and efficiency abnormality rate, group customer concentrated appeal abnormality rate, customer appeal work order processing timeliness rate, customer appeal problem solving abnormality rate, customer appeal follow-up satisfaction abnormality and customer problem escalation complaint abnormality rate.

[0016] Wherein, the method further comprises:

[0017] A heuristic algorithm is used to optimize the output solution.

[0018] The embodiment of the present invention also provides a detection system for a multi-objective optimization power marketing business plan, including:

[0019] A business solution acquisition unit, used to acquire multiple feasible implementation plans for power marketing business;

[0020] A business indicator scoring unit is used to obtain the scores of the preset evaluation indicators of the strategic risk control layer, the preset evaluation indicators of the compliance review layer, and the preset evaluation indicators of the customer experience layer in each feasible implementation plan;

[0021] A business solution screening unit is used to construct a multi-objective optimization function, and combine the scores of all evaluation indicators obtained in each feasible implementation plan to obtain the Pareto optimal solution of the multi-objective optimization function corresponding to each feasible implementation plan, and further select a solution that meets predetermined conditions from the multiple feasible implementation plans according to the Pareto optimal solution obtained for each feasible implementation plan; wherein the multi-objective optimization function is obtained by an objective function constructed based on the preset evaluation indicators of the strategic risk control layer, a second objective function constructed based on the preset evaluation indicators of the compliance review layer, and an objective function constructed based on the preset evaluation indicators of the customer experience layer.

[0022] Wherein, the multi-objective optimization function is in,

[0023] fstrategy(Sj) is the objective function constructed based on the preset evaluation indicators of the strategic risk control layer; fcompliance(Sj) is the objective function constructed based on the preset evaluation indicators of the compliance review layer; fexperience(Sj) is the objective function constructed based on the preset evaluation indicators of the customer experience layer; Sj is the score of the jth evaluation indicator.

[0024] The score of each evaluation indicator is calculated by its efficacy score and dynamic weight;

[0025] The efficacy score D of each evaluation index is obtained by the formula D=A1+(100-A1)*B1; A1 is the basic score, which is a positive integer less than 100; B1 is the efficacy coefficient, S is the actual value of the indicator, which is between (0, 1]; T is the unacceptable value of the indicator, which is between (0, 1]; M is the satisfactory value of the indicator. If the unacceptable value T of the indicator is the maximum abnormal rate, the value is 0; otherwise, if the unacceptable value T of the indicator is the minimum qualified rate, the value is 1;

[0026] Through the formula w i (t) = w i (0)+α*f(t), and obtain the dynamic weight w of each evaluation index i (t); w i (0) is the initial weight of the i-th evaluation index, α is the parameter adjustment coefficient, and its value is between (0, 1]; f(t) is the trend function based on historical data, and its value is determined by the maximum score and the minimum score at time 0 to t.

[0027] Among them, the preset evaluation indicators of the strategic risk control layer include safety hazard management, important user file management, electricity fee recovery rate and electricity fee refund rate; the preset evaluation indicators of the compliance review layer include business process standardization, contract execution compliance and business operation risk warning; the preset evaluation indicators of the customer experience layer include customer complaint service quality and efficiency abnormality rate, group customer concentrated appeal abnormality rate, customer appeal work order processing timeliness rate, customer appeal problem solving abnormality rate, customer appeal follow-up satisfaction abnormality and customer problem escalation complaint abnormality rate.

[0028] Among them, it also includes:

[0029] The output solution optimization unit is used to optimize the output solution by using a heuristic algorithm.

[0030] Implementing the embodiments of the present invention has the following beneficial effects:

[0031] The present invention constructs a multi-objective optimization function associated with the preset evaluation indicators of the strategic risk control layer, the compliance review layer and the customer experience layer, and combines the scores of all the above-mentioned associated evaluation indicators in multiple feasible implementation plans to obtain the Pareto optimal solution of the multi-objective optimization function, and uses the obtained Pareto optimal solution to select feasible implementation plans that meet the predetermined conditions, thereby being able to perform quality inspections on business plans from the perspective of internal risk prevention in the enterprise, so as to help enterprises better manage and respond to strategic risks and improve the stability and security of their businesses. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0033] Figure 1 A flowchart of a detection method for a multi-objective optimization power marketing business plan provided by an embodiment of the present invention;

[0034] Figure 2 A schematic diagram of the structure of a detection system for a multi-objective optimization power marketing business solution provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings.

[0036] like Figure 1 As shown, a detection method for a multi-objective optimization power marketing business plan is provided in an embodiment of the present invention, and the method comprises the following steps:

[0037] Step S1, obtaining multiple feasible implementation plans for power marketing business;

[0038] Step S2: In each feasible implementation plan, the scores of the preset evaluation indicators of the strategic risk control layer, the scores of the preset evaluation indicators of the compliance review layer, and the scores of the preset evaluation indicators of the customer experience layer are obtained;

[0039] Step S3, construct a multi-objective optimization function, and combine the scores of all evaluation indicators obtained in each feasible implementation plan to find the Pareto optimal solution of the multi-objective optimization function corresponding to each feasible implementation plan, and further select the plan that meets the predetermined conditions from the multiple feasible implementation plans according to the Pareto optimal solution obtained for each feasible implementation plan; wherein the multi-objective optimization function is obtained by an objective function constructed based on the preset evaluation indicators of the strategic risk control layer, a second objective function constructed based on the preset evaluation indicators of the compliance review layer, and an objective function constructed based on the preset evaluation indicators of the customer experience layer.

[0040] The specific process is that in step S1, a plurality of implementable solutions for the power marketing business formulated by the staff are automatically obtained.

[0041] In step S2, first, based on relevant information such as external market changes and policy adjustments, the evaluation indicators of the strategic risk control layer are determined and regularly updated, including but not limited to safety hazard management, important user file management, electricity fee recovery rate and electricity fee refund rate.

[0042] Secondly, based on relevant information such as the update or optimization of business processes, determine and promptly adjust the evaluation indicators of the compliance review layer, including but not limited to business process standardization, contract execution compliance and business operation risk warning.

[0043] Next, based on relevant information such as customer feedback and service quality monitoring results, determine and dynamically optimize the evaluation indicators of the customer experience layer, including but not limited to the customer complaint service quality and efficiency abnormality rate, the group customer concentrated appeal abnormality rate, the customer appeal work order processing timeliness rate, the customer appeal problem solving abnormality rate, the customer appeal follow-up satisfaction abnormality and the customer problem escalation complaint abnormality rate.

[0044] Finally, relevant business data is extracted from relevant systems such as the marketing management system, customer comprehensive system, and metering master station system, and the efficacy coefficients of various indicators of the evaluation object are calculated and converted into corresponding efficacy score values, which are further combined with dynamic weights to obtain the scores of each evaluation indicator.

[0045] For example, the efficacy score D of each evaluation index is obtained by the formula D=A1+(100-A1)*B1; A1 is the basic score, which is a positive integer less than 100; B1 is the efficacy coefficient, and S is the actual value of the indicator, which is between (0, 1]; T is the unacceptable value of the indicator, which is between (0, 1]; M is the satisfactory value of the indicator. If the unacceptable value T of the indicator is the maximum abnormal rate, the value is 0; otherwise, if the unacceptable value T of the indicator is the minimum qualified rate, the value is 1.

[0046] Through the formula w i (t) = w i (0)+α*f(t), and obtain the dynamic weight w of each evaluation index i (t); w i (0) is the initial weight of the i-th evaluation index, and α is the parameter adjustment coefficient, and its value is between (0, 1]; f(t) is the trend function based on historical data, and its value is determined by the maximum score and the minimum score at time 0 to t.

[0047] Through the formula M = D * w i (t), and obtain the score M of each evaluation index.

[0048] By analogy, in each feasible implementation plan, we can obtain the scores of the preset evaluation indicators of the strategic risk control layer, the scores of the preset evaluation indicators of the compliance review layer, and the scores of the preset evaluation indicators of the customer experience layer.

[0049] In one example, the initial weight w i (0) As shown in Table 1 below:

[0050] Table 1

[0051] index <![CDATA[w i (0)]]> Safety hazard management 0.15 Important user profile management 0.15 Electricity recovery rate 0.1 Electricity fee refund rate 0.1 Business process standardization 0.1 Contract execution compliance 0.1 Business operation risk warning 0.1 Abnormal rate of customer complaints about service quality and efficiency 0.05 Abnormal rate of concentrated demands from group customers 0.05 Timely processing rate of customer request work orders 0.05 Abnormal rate of solving customer complaints 0.05 Customer satisfaction rate is abnormal 0.05 Abnormal rate of customer escalation complaints 0.05

[0052] Set the parameter integer coefficient α = 0.1 and use simple average as the trend function Thus, we get the dynamic weight w i (t) as shown in Table 2 below:

[0053] Table 2

[0054]

[0055]

[0056] In Table 2, assuming that the scores of safety hazard management in the past quarter are: 75%, 78%, 80% → average value f(t) = (75% + 78% + 80%) / 3 = 77.67%, after dynamic adjustment w 1 (1) = w 1 (0)+α*(80-75) / 100=0.15+0.005=0.155.

[0057] In step S3, first, a multi-objective optimization function is constructed as Among them, fstrategy(Sj) is the objective function constructed based on the preset evaluation indicators of the strategic risk control layer; fcompliance(Sj) is the objective function constructed based on the preset evaluation indicators of the compliance review layer; fexperience(Sj) is the objective function constructed based on the preset evaluation indicators of the customer experience layer; Sj is the score of the jth evaluation indicator. It should be noted that the objective functions corresponding to the strategic risk control layer, compliance review layer and customer experience layer are all the sum of the dynamic weights * the scores of each evaluation indicator.

[0058] Secondly, according to the scores of all evaluation indicators obtained in each feasible implementation plan, the Pareto optimal solution of the multi-objective optimization function corresponding to each feasible implementation plan is obtained.

[0059] Finally, based on the Pareto optimal solution obtained for each feasible implementation plan, a plan that meets the predetermined conditions is selected from multiple feasible implementation plans and outputted.

[0060] In one example, the feasible solutions include solution A, solution B and solution C. Using the multi-objective optimization function, a set of Pareto optimal solutions are obtained to represent the best balance achieved among multiple objectives.

[0061] Taking the case where the Pareto optimal solutions of Scheme A, Scheme B and Scheme C are the same as an example, the application scenario of the present invention is further described as follows:

[0062] At this time, considering Plan A: the strategic risk control level is increased to 80%, the compliance review level is increased to 75%, and the customer complaint service quality and efficiency abnormality rate is reduced to 8%.

[0063] Therefore, according to the Pareto optimal solution (0.155, 0.105, 0.045), the fitness of scheme A is calculated to be 0.155*0.80+0.105*0.75+0.045*0.92=0.124+0.079+0.0414=0.244.

[0064] Similarly, considering that Plan B: the strategic risk control layer remains at 75%, the compliance review layer is increased to 80%, and the abnormal rate of customer complaint service quality and efficiency is reduced to 7%. Therefore, according to the Pareto optimal solution (0.155, 0.105, 0.045), the fitness of Plan B is calculated to be 0.242.

[0065] Similarly, considering that Plan C: the strategic risk control layer is increased to 77%, the compliance review layer is increased to 77%, and the abnormal rate of customer complaint service quality and efficiency is reduced to 6%. Therefore, according to the Pareto optimal solution (0.155, 0.105, 0.045), the fitness of Plan C is calculated to be 0.242.

[0066] In summary, by comparing the fitness values, plan A with the highest fitness value is selected for implementation.

[0067] In the embodiment of the present invention, a heuristic algorithm (including a genetic algorithm for crossover and mutation operations) can be used to generate a new solution for the selected solution, and fitness sorting and non-dominated solution selection are performed until the number of iterations is completed or the fitness change threshold is reached. Therefore, the method further includes: using a heuristic algorithm to optimize the output solution.

[0068] like Figure 2 As shown in the figure, a detection system for a multi-objective optimization power marketing business plan is provided in an embodiment of the present invention, comprising:

[0069] A business solution acquisition unit 110 is used to acquire multiple feasible implementation plans for power marketing business;

[0070] The business indicator scoring unit 120 is used to obtain the score of the preset evaluation indicator of the strategic risk control layer, the score of the preset evaluation indicator of the compliance review layer, and the score of the preset evaluation indicator of the customer experience layer in each feasible implementation scheme;

[0071] The business solution screening unit 130 is used to construct a multi-objective optimization function, and combine the scores of all evaluation indicators obtained in each feasible implementation plan to obtain the Pareto optimal solution of the multi-objective optimization function corresponding to each feasible implementation plan, and further select a solution that meets predetermined conditions from the multiple feasible implementation plans according to the Pareto optimal solution obtained for each feasible implementation plan; wherein the multi-objective optimization function is obtained by an objective function constructed based on the preset evaluation indicators of the strategic risk control layer, a second objective function constructed based on the preset evaluation indicators of the compliance review layer, and an objective function constructed based on the preset evaluation indicators of the customer experience layer.

[0072] Wherein, the multi-objective optimization function is in,

[0073] fstrategy(Sj) is the objective function constructed based on the preset evaluation indicators of the strategic risk control layer; fcompliance(Sj) is the objective function constructed based on the preset evaluation indicators of the compliance review layer; fexperience(Sj) is the objective function constructed based on the preset evaluation indicators of the customer experience layer; Sj is the score of the jth evaluation indicator.

[0074] The score of each evaluation indicator is calculated by its efficacy score and dynamic weight;

[0075] The efficacy score D of each evaluation index is obtained by the formula D=A1+(100-A1)*B1; A1 is the basic score, which is a positive integer less than 100; B1 is the efficacy coefficient, S is the actual value of the indicator, which is between (0, 1]; T is the unacceptable value of the indicator, which is between (0, 1]; M is the satisfactory value of the indicator. If the unacceptable value T of the indicator is the maximum abnormal rate, the value is 0; otherwise, if the unacceptable value T of the indicator is the minimum qualified rate, the value is 1;

[0076] Through the formula w i (t) = w i (0)+α*f(t), and obtain the dynamic weight w of each evaluation index i (t); w i (0) is the initial weight of the i-th evaluation index, and α is the parameter adjustment coefficient, and its value is between (0, 1]; f(t) is the trend function based on historical data, and its value is determined by the maximum score and the minimum score at time 0 to t.

[0077] Among them, the preset evaluation indicators of the strategic risk control layer include safety hazard management, important user file management, electricity fee recovery rate and electricity fee refund rate; the preset evaluation indicators of the compliance review layer include business process standardization, contract execution compliance and business operation risk warning; the preset evaluation indicators of the customer experience layer include customer complaint service quality and efficiency abnormality rate, group customer concentrated appeal abnormality rate, customer appeal work order processing timeliness rate, customer appeal problem solving abnormality rate, customer appeal follow-up satisfaction abnormality and customer problem escalation complaint abnormality rate.

[0078] Among them, it also includes:

[0079] The output solution optimization unit is used to optimize the output solution by using a heuristic algorithm.

[0080] Implementing the embodiments of the present invention has the following beneficial effects:

[0081] The present invention constructs a multi-objective optimization function associated with the preset evaluation indicators of the strategic risk control layer, the compliance review layer and the customer experience layer, and combines the scores of all the above-mentioned associated evaluation indicators in multiple feasible implementation plans to obtain the Pareto optimal solution of the multi-objective optimization function, and uses the obtained Pareto optimal solution to select feasible implementation plans that meet the predetermined conditions, thereby being able to perform quality inspections on business plans from the perspective of internal risk prevention in the enterprise, so as to help enterprises better manage and respond to strategic risks and improve the stability and security of their businesses.

[0082] It is worth noting that in the above system embodiment, the various system modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the various functional modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0083] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as ROM / RAM, disk, CD-ROM, etc.

[0084] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A detection method for a multi-objective optimization power marketing business plan, characterized in that: The method comprises the following steps: Obtain multiple feasible implementation plans for power marketing business; In each feasible implementation plan, the scores of the preset evaluation indicators of the strategic risk control layer, the preset evaluation indicators of the compliance review layer and the preset evaluation indicators of the customer experience layer are obtained; A multi-objective optimization function is constructed, and the Pareto optimal solution of the multi-objective optimization function corresponding to each feasible implementation plan is obtained by combining the scores of all evaluation indicators obtained in each feasible implementation plan, and further, according to the Pareto optimal solution obtained for each feasible implementation plan, a plan that meets predetermined conditions is selected from the multiple feasible implementation plans for output; wherein, the multi-objective optimization function is obtained by an objective function constructed based on the preset evaluation indicators of the strategic risk control layer, a second objective function constructed based on the preset evaluation indicators of the compliance review layer, and an objective function constructed based on the preset evaluation indicators of the customer experience layer.

2. The detection method of the multi-objective optimization power marketing business plan according to claim 1, characterized in that: The multi-objective optimization function is in, fstrategy(Sj) is the objective function constructed based on the preset evaluation indicators of the strategic risk control layer; fcompliance(Sj) is the objective function constructed based on the preset evaluation indicators of the compliance review layer; fexperience(Sj) is the objective function constructed based on the preset evaluation indicators of the customer experience layer; Sj is the score of the jth evaluation indicator.

3. The detection method of the multi-objective optimization power marketing business plan according to claim 2, characterized in that: The score of each evaluation indicator is calculated by its efficacy score and dynamic weight; The efficacy score D of each evaluation index is obtained by the formula D=A1+(100-A1)*B1; A1 is the basic score, which is a positive integer less than 100; B1 is the efficacy coefficient, S is the actual value of the indicator, which is between (0, 1]; T is the unacceptable value of the indicator, which is between (0, 1]; M is the satisfactory value of the indicator. If the unacceptable value T of the indicator is the maximum abnormal rate, the value is 0; otherwise, if the unacceptable value T of the indicator is the minimum qualified rate, the value is 1; Through the formula w i (t) = w i (0)+α*f(t), and obtain the dynamic weight w of each evaluation index i (t); w i (0) is the initial weight of the i-th evaluation index, and α is the parameter adjustment coefficient, and its value is between (0, 1]; f(t) is the trend function based on historical data, and its value is determined by the maximum score and the minimum score at time 0 to t.

4. The detection method of the multi-objective optimization power marketing business plan according to claim 3 is characterized in that: The preset evaluation indicators of the strategic risk control layer include safety hazard management, important user file management, electricity fee recovery rate and electricity fee refund rate; the preset evaluation indicators of the compliance review layer include business process standardization, contract execution compliance and business operation risk warning; The preset evaluation indicators of the customer experience layer include the abnormal rate of customer complaint service quality and efficiency, the abnormal rate of concentrated demands from group customers, the timely processing rate of customer demand work orders, the abnormal rate of customer demand problem resolution, the abnormal rate of customer demand follow-up satisfaction and the abnormal rate of customer problem escalation complaints.

5. The detection method of the multi-objective optimization power marketing business plan according to claim 1, characterized in that: The method further comprises: A heuristic algorithm is used to optimize the output solution.

6. A detection system for multi-objective optimization of power marketing business plan, characterized in that: include: A business plan acquisition unit, used to acquire multiple feasible implementation plans for power marketing business; A business indicator scoring unit is used to obtain the scores of the preset evaluation indicators of the strategic risk control layer, the preset evaluation indicators of the compliance review layer, and the preset evaluation indicators of the customer experience layer in each feasible implementation plan; A business solution screening unit is used to construct a multi-objective optimization function, and combine the scores of all evaluation indicators obtained in each feasible implementation plan to obtain the Pareto optimal solution of the multi-objective optimization function corresponding to each feasible implementation plan, and further select a solution that meets predetermined conditions from the multiple feasible implementation plans according to the Pareto optimal solution obtained for each feasible implementation plan; wherein the multi-objective optimization function is obtained by an objective function constructed based on the preset evaluation indicators of the strategic risk control layer, a second objective function constructed based on the preset evaluation indicators of the compliance review layer, and an objective function constructed based on the preset evaluation indicators of the customer experience layer.

7. The detection system for multi-objective optimization of power marketing business plan according to claim 6, characterized in that: The multi-objective optimization function is in, fstrategy(Sj) is the objective function constructed based on the preset evaluation indicators of the strategic risk control layer; fcompliance(Sj) is the objective function constructed based on the preset evaluation indicators of the compliance review layer; fexperience(Sj) is the objective function constructed based on the preset evaluation indicators of the customer experience layer; Sj is the score of the jth evaluation indicator.

8. The detection system for multi-objective optimization of power marketing business plan according to claim 7, characterized in that: The score of each evaluation indicator is calculated by its efficacy score and dynamic weight; The efficacy score D of each evaluation index is obtained by the formula D=A1+(100-A1)*B1; A1 is the basic score, which is a positive integer less than 100; B1 is the efficacy coefficient, S is the actual value of the indicator, which is between (0, 1]; T is the unacceptable value of the indicator, which is between (0, 1]; M is the satisfactory value of the indicator. If the unacceptable value T of the indicator is the maximum abnormal rate, the value is 0; otherwise, if the unacceptable value T of the indicator is the minimum qualified rate, the value is 1; Through the formula w i (t) = w i (0)+α*f(t), and obtain the dynamic weight w of each evaluation index i (t); w i (0) is the initial weight of the i-th evaluation index, and α is the parameter adjustment coefficient, and its value is between (0, 1]; f(t) is the trend function based on historical data, and its value is determined by the maximum score and the minimum score at time 0 to t.

9. The detection system for multi-objective optimization of power marketing business plan according to claim 8, characterized in that: The preset evaluation indicators of the strategic risk control layer include safety hazard management, important user file management, electricity fee recovery rate and electricity fee refund rate; the preset evaluation indicators of the compliance review layer include business process standardization, contract execution compliance and business operation risk warning; The preset evaluation indicators of the customer experience layer include the abnormal rate of customer complaint service quality and efficiency, the abnormal rate of concentrated demands from group customers, the timely processing rate of customer demand work orders, the abnormal rate of customer demand problem resolution, the abnormal rate of customer demand follow-up satisfaction and the abnormal rate of customer problem escalation complaints.

10. The detection system for multi-objective optimization of power marketing business plan according to claim 6, characterized in that: Also includes: The output solution optimization unit is used to optimize the output solution by using a heuristic algorithm.

Images