A power service work order processing method, device, equipment and storage medium

Abstract

The application discloses a power supply service work order processing method, device and equipment and a storage medium. Power fluctuation parameters, power outage awareness parameters, service handling experience parameters and customer telephone incoming parameters, as well as annual power growth rates, annual capacity change parameters, electricity recovery rates and overdue fees are obtained according to user information corresponding to a work order, which are used to calculate a current annual emotion index and a potential emotion index of a user, and then a target emotion index is calculated. According to the target emotion index, a target service type is allocated to the user to perform order distribution. The embodiment of the application can calculate the target emotion index by obtaining the power consumption related data of the user, determine the corresponding target service type for order distribution according to the target emotion index, improve the user experience, reduce the risk of adverse effects caused by the emotionalization of the user, reduce the burden of the staff, and improve the work efficiency.

Description

Technical Field

[0001] This invention relates to the field of digital twin technology, and in particular to a method, apparatus, equipment and storage medium for processing power supply service work orders. Background Technology

[0002] With the continuous improvement of my country's economic level, enterprises and users have higher requirements for power supply services. Power supply service is an important part of the electricity market and a link between power grid companies and households. Currently, most power grid companies' business personnel use manual inquiry to determine the service type and export power supply service work orders. This work order processing method is limited by the responsibility of business personnel and is easily affected by external factors, which greatly affects the user experience, easily leads to user emotions, and causes adverse effects. Moreover, with the increasing volume of work orders, the manual work order processing process greatly increases the burden on staff and reduces work efficiency. Summary of the Invention

[0003] The purpose of this invention is to provide a power supply service work order processing method, device, equipment, and storage medium that can calculate a target sentiment index by acquiring users' electricity consumption-related data, determine the corresponding target service type based on the target sentiment index, and dispatch orders. This improves user experience, reduces the risk of adverse effects caused by user emotions, reduces the burden on staff, and improves work efficiency.

[0004] To achieve the above objectives, embodiments of the present invention provide a method for processing power supply service work orders, including:

[0005] Obtain the power supply service work order and confirm user information;

[0006] Based on user information, obtain the current year's and the previous year's electricity fluctuation parameters, power outage perception parameters, business processing experience parameters, and customer call parameters, and calculate the user's current year's sentiment index;

[0007] Based on user information, the annual electricity consumption growth rate, annual capacity change parameters, electricity bill collection rate, and amount of outstanding fees are obtained, and the user's potential sentiment index is calculated.

[0008] By combining the current year's sentiment index and the potential sentiment index, the user's target sentiment index is calculated.

[0009] Based on the preset correspondence between sentiment index and service type, a target service type is assigned to the user according to the target sentiment index for order dispatch.

[0010] As an improvement to the above scheme, the current year's sentiment index is calculated using the following formula:

[0011] I y=1-|Q y -Q1| / Q1;

[0012]

[0013] Among them, I y Q represents the current year's sentiment index. y Q1 represents the current year's mood score, while Q1 represents the previous year's mood score. and D is the preset emotion rating weight. b.j Let T be the electricity fluctuation parameter for the j-th month of the current year. g.j Y represents the power outage sensing parameters for the j-th month of the current year. t.j K represents the business processing experience parameters for the j-th month of the current year. d.j This refers to the incoming call parameters for the customer in month j of the current year.

[0014] The potential sentiment index is calculated using the following formula:

[0015] F y =1-|X y -X1| / X1;

[0016] X y =r1D z +r2R b +r3D h +r4Q j ;

[0017] Among them, F y X represents the potential sentiment index for the current year. y R represents the potential score for the current year, X1 represents the potential score for the previous year, r1, r2, r3, and r4 are the preset potential score weights, and D... z R represents the annual electricity consumption growth rate for the current year. b D represents the annual capacity change parameter for the current year. h Q represents the electricity bill collection rate for the current year. j This indicates the amount of outstanding fees for the current year.

[0018] As an improvement to the above scheme, the target sentiment index is calculated using the following formula:

[0019] G y =ω1I y +ω2F y ;

[0020] Among them, I y F represents the current year's sentiment index. y This represents the potential sentiment index, where ω1 is the first weighting coefficient and ω2 is the second weighting coefficient.

[0021] As an improvement to the above solution, the step of obtaining electricity fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer call parameters for the current and previous years based on user information includes:

[0022] Based on user information, obtain the current year's internal and external user data, as well as the previous year's internal and external user data;

[0023] The user's internal data and external data are preprocessed to construct the user behavior feature set for the current year and the user behavior features for the previous year;

[0024] Input the user behavior characteristics of the current year and the user behavior characteristics of the previous year into the pre-trained parameter calculation model to obtain the current year's power consumption fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer telephone call parameters, as well as the previous year's power consumption fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer telephone call parameters.

[0025] As an improvement to the above solution, the user tag includes the power fluctuation parameter, the power outage perception parameter, the service processing experience parameter, and the customer telephone call parameter;

[0026] The parameter calculation model is constructed in the following way:

[0027] Acquire historical internal and external data from several test users to build a customer data information database;

[0028] The customer data information database is cleaned and processed to extract historical user behavior features to construct a user behavior feature set;

[0029] Based on the user's historical behavioral characteristics, cluster analysis is performed on a number of test users. A Fraser distance is added to the Euclidean distance to construct a composite distance that considers the similarity of curve shapes. The formula is defined as follows:

[0030] dis(A,B)=k1ED(A,B)+k2βFD n (A,B);

[0031]

[0032]

[0033] Where A = {a1, a2, ..., a} n}, B={b1,b2,...,b nLet A and B be the historical behavioral features of different test users, α be the reparameterized function of A for a unit interval, β be the reparameterized function of B for a unit interval, k1, k2 (k1+k2=1) be the distance weighting coefficients, β be the balance coefficient, ED(A,B) be the Euclidean distance, and FD be the distance between A and B. n (A,B) is the Frescher distance;

[0034] The test users are clustered based on their historical behavioral characteristics to obtain several user classes, and each user class is assigned a corresponding user label to construct a parameter calculation model.

[0035] As an improvement to the above scheme, the correspondence between the emotion index and the service type includes: the correspondence between the emotion index and the user level, and the correspondence between the user level and the service type;

[0036] The method of assigning a target service type to a user based on the preset correspondence between emotion indices and service types includes:

[0037] Based on the preset correspondence between emotion index and user level, the target user level is determined according to the target emotion index;

[0038] Based on the preset correspondence between user level and service type, a target service type is assigned to the user according to the target user level.

[0039] As an improvement to the above scheme, the user levels include Level 1 premium users, Level 2 users who receive ongoing care, and Level 3 users who receive priority care.

[0040] For the first-level high-quality users, a file is established for each user and a professional is assigned to connect with them; for the second-level users who require ongoing care, a method of constant monitoring is adopted and relevant business personnel are given enhanced training; for the third-level key care users, orders are directly assigned and relevant business personnel are evaluated for excellence.

[0041] After the work order is processed, the authenticity of the work order content is verified. If the verification is successful, the responsibility is determined. When the responsibility is determined to be the responsibility of the power supply company, the work order is filled back using the auxiliary form filling system. The work order filling information includes at least the processing time, the processor, the processing basis, and the processing result. The work order filling method includes at least one of manual filling and voice filling.

[0042] After the work order is filled in, it is reviewed and analyzed to extract user information, electricity usage verification, electricity demand, and appointment service information. Corresponding measures are then developed to link the energy internet and achieve supply and demand interaction. After the review and analysis are deemed satisfactory, a work order index is established and uploaded.

[0043] To achieve the above objectives, embodiments of the present invention provide a power supply service work order processing device, comprising:

[0044] The work order acquisition module is used to acquire power supply service work orders and determine user information;

[0045] The current year sentiment index calculation module is used to obtain the current year and previous year's power consumption fluctuation parameters, power outage perception parameters, business processing experience parameters and customer call parameters based on user information, and to calculate the user's current year sentiment index.

[0046] The potential sentiment index calculation module is used to obtain the annual electricity consumption growth rate, annual capacity change parameters, electricity bill collection rate and arrears amount based on user information, and to calculate the user's potential sentiment index.

[0047] The target emotion index calculation module is used to calculate the user's target emotion index by combining the current year's emotion index and the potential emotion index.

[0048] The service type confirmation module is used to assign a target service type to a user based on a preset sentiment index and the correspondence between service types, and to dispatch orders according to the target sentiment index.

[0049] To achieve the above objectives, embodiments of the present invention provide a power supply service work order processing device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the power supply service work order processing method as described in any of the above embodiments.

[0050] To achieve the above objectives, embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the power supply service work order processing method as described in any of the above embodiments.

[0051] Compared with existing technologies, the power supply service work order processing method, apparatus, equipment, and computer-readable storage medium disclosed in this invention first acquire the power supply service work order and determine user information; then, based on the user information, acquire the current year's and the previous year's electricity fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer telephone call parameters, and calculate the user's current year's emotional index; based on the user information, acquire the annual electricity growth rate, annual capacity change parameters, electricity bill collection rate, and outstanding amount, and calculate the user's potential emotional index; next, combine the current year's emotional index and the potential emotional index to calculate the user's target emotional index; finally, based on a preset correspondence between emotional indices and service types, assign a target service type to the user for work order dispatch according to the target emotional index. This invention can calculate the target emotional index by acquiring the user's electricity consumption-related data, and determine the corresponding target service type for work order dispatch based on the target emotional index, thereby improving user experience, reducing the risk of adverse effects caused by user emotionality, reducing the burden on staff, and improving work efficiency. Attached Figure Description

[0052] Figure 1 This is a flowchart of a power supply service work order processing method provided in an embodiment of the present invention;

[0053] Figure 2 This is another flowchart of a power supply service work order processing method provided in an embodiment of the present invention;

[0054] Figure 3 This is a flowchart of a user tagging system construction method provided in an embodiment of the present invention;

[0055] Figure 4 This is a framework diagram of an improved k-means algorithm provided in an embodiment of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] See Figure 1 This is a flowchart of a power supply service work order processing method provided by an embodiment of the present invention, the power supply service work order processing method including steps S1 to S5:

[0058] S1. Obtain the power supply service work order and confirm user information;

[0059] S2. Obtain the current year's and the previous year's electricity fluctuation parameters, power outage perception parameters, business processing experience parameters, and customer call parameters based on user information, and calculate the user's current year's sentiment index.

[0060] S3. Obtain the annual electricity consumption growth rate, annual capacity change parameters, electricity bill collection rate and arrears amount based on user information, and calculate the user's potential sentiment index.

[0061] S4. Calculate the user's target emotion index by combining the current year's emotion index and the potential emotion index;

[0062] S5. Based on the preset correspondence between emotion index and service type, assign a target service type to the user according to the target emotion index to dispatch orders.

[0063] Specifically, considering that existing work order dispatch methods may suffer from incomplete consideration of indicator variables and imprecise classification, in order to better adapt to high-standard electricity demand, effectively avoid customer complaints, eliminate the adverse effects caused by emotional customer incidents, and optimize the 95598 work order classification method of the State Grid Corporation, thereby improving work order processing efficiency and user satisfaction, and in order to adapt to the needs of the times, the State Grid Corporation needs to provide higher-quality and more considerate services based on user needs to meet the higher-standard electricity demands of users and enterprises, this invention comprehensively analyzes users by considering parameters such as electricity fluctuations, power outage perception, business processing experience, customer call parameters, annual electricity growth rate, annual capacity change parameters, electricity bill collection rate, and arrears amount in the current and previous years, to calculate the user's target sentiment index. Based on the target sentiment index, the target service type is determined for work order dispatch. This not only improves the service efficiency of the power grid and reduces the workload of personnel, but also has important significance for improving the safety of power grid operation, enhancing user experience, and reducing the risk of adverse effects caused by user emotions.

[0064] In one implementation, the current year's sentiment index is calculated using the following formula:

[0065] I y =1-|Q y -Q1| / Q1;

[0066]

[0067] Among them, I y Q represents the current year's sentiment index. y Q1 represents the current year's mood score, while Q1 represents the previous year's mood score. and D is the preset emotion rating weight. b.jLet T be the electricity fluctuation parameter for the j-th month of the current year. g.j Y represents the power outage sensing parameters for the j-th month of the current year. t.j K represents the business processing experience parameters for the j-th month of the current year. d.j This refers to the incoming call parameters for the customer in month j of the current year.

[0068] The potential sentiment index is calculated using the following formula:

[0069] F y =1-|X y -X1| / X1;

[0070] X y =r1D z +r2R b +r3D h +r4Q q ;

[0071] Among them, E y X represents the potential sentiment index. y R represents the potential score for the current year, X1 represents the potential score for the previous year, r1, r2, r3, and r4 are the preset potential score weights, and D... z R represents the annual electricity consumption growth rate for the current year. b D represents the annual capacity change parameter for the current year. h Q represents the electricity bill collection rate for the current year. q This indicates the amount of outstanding fees for the current year.

[0072] In one implementation, the target sentiment index is calculated using the following formula:

[0073] G y =ω1I y +ω2F y ;

[0074] Among them, I y F represents the current year's sentiment index. y This represents the potential sentiment index, where ω1 is the first weighting coefficient and ω2 is the second weighting coefficient.

[0075] Specifically, the user's target sentiment index is mainly divided into two parts: the current year sentiment index, which reflects the user's sentiment regarding maintaining their current electricity consumption behavior; and the potential sentiment index, which reflects the user's sentiment regarding loyalty and trustworthiness in relation to their electricity consumption behavior. The expression is:

[0076] G y =ω1I y +ω2F y ;

[0077] Iy =1-|Q y -Q1| / Q1;

[0078]

[0079] F y =1-|X y -X1| / X1;

[0080] X y =r1D z +r2R b +r3D h +r4Q q ;

[0081] In the formula, G y For the target sentiment index, I y Let F be the current year's sentiment index, ω1 be the weight of the current year's sentiment index, and F be the weight of the current year's sentiment index. y Q represents the potential sentiment index, and ω2 is the weight of the potential sentiment index. y This represents the user's emotional score for the current year, Q1 represents the emotional score for the previous year, and D represents the emotional score for the current year. b.j For power fluctuations, T g.j For power outage sensing, Y t.j To improve the service experience, K d.j Incoming customer calls. and These represent the weights of each variable in the current year's sentiment index. F n D is a potential sentiment index. z R represents the annual electricity consumption growth rate. b For annual capacity changes, D h Q represents the electricity bill recovery rate. j For the amount of unpaid fees, r1, r2, r3, and r4 represent the weights of each variable in the potential sentiment index. After the user sentiment index is established, it is matched with a tagging system to assign tags to different electricity users, thus completing the classification of different users.

[0082] In one implementation, the step of obtaining electricity fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer call parameters for the current and previous years based on user information includes:

[0083] Based on user information, obtain the current year's internal and external user data, as well as the previous year's internal and external user data;

[0084] The user's internal data and external data are preprocessed to construct the user behavior feature set for the current year and the user behavior features for the previous year;

[0085] Input the user behavior characteristics of the current year and the user behavior characteristics of the previous year into the pre-trained parameter calculation model to obtain the current year's power consumption fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer telephone call parameters, as well as the previous year's power consumption fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer telephone call parameters.

[0086] In one implementation, the user tag includes the power fluctuation parameter, the power outage perception parameter, the service processing experience parameter, and the customer telephone call parameter;

[0087] The parameter calculation model is constructed in the following way:

[0088] Acquire historical internal and external data from several test users to build a customer data information database;

[0089] The customer data information database is cleaned and processed to extract historical user behavior features to construct a user behavior feature set;

[0090] Based on the user's historical behavioral characteristics, cluster analysis is performed on a number of test users. A Fraser distance is added to the Euclidean distance to construct a composite distance that considers the similarity of curve shapes. The formula is defined as follows:

[0091] dis(A,B)=k1ED(A,B)+k2βFD n (A,B);

[0092]

[0093]

[0094] Where A = {a1, a2, ..., a} n}, B={b1,b2,...,b n Let A and B be the historical behavioral features of different test users, α be the reparameterized function of A for a unit interval, β be the reparameterized function of B for a unit interval, k1, k2 (k1+k2=1) be the distance weighting coefficients, β be the balance coefficient, ED(A,B) be the Euclidean distance, and FD be the distance between A and B. n (A,B) is the Frescher distance;

[0095] The test users are clustered based on their historical behavioral characteristics to obtain several user classes, and each user class is assigned a corresponding user label to construct a parameter calculation model.

[0096] Specifically, the model construction method of this invention consists of two steps: first, the construction of a label system; and second, the construction of a sentiment index. The entire process can be found in [reference needed]. Figure 2The process of constructing the tag system can be found in [link to documentation]. Figure 3 First, a customer tagging system is constructed based on data analysis. Internal data such as historical user electricity consumption fluctuations, customer power outage perception, business transactions, and customer inbound calls, along with external data such as weather data and the 12345 government hotline, are integrated into a complete customer data information database. This database undergoes data cleaning and processing to extract user behavioral characteristics such as power supply area, transaction method, business transactions, and customer service, constructing a user behavior feature set. This set includes information such as power outage complaints, fault repairs, and business transactions. Simultaneously, the user feature set is updated as information is continuously input. Based on the user feature set, corresponding tagging rules are formulated. Model calculations are performed using these rules to analyze different attributes and establish the final tagging system. The entire user tagging system includes several dimensions: electricity consumption fluctuations, power outage perception, business transaction difficulty, and inbound calls. Next, the entire tagging system is evaluated, and the rules are adjusted appropriately to better meet user needs. An improved k-means clustering algorithm is used for analysis, performing cluster analysis on users. The improved k-means algorithm process is as follows: Figure 4 As shown, it mainly includes three parts: initial cluster center selection, composite distance calculation, and cluster body.

[0097] A composite distance is constructed by adding Fraser distance to the Euclidean distance, taking into account the similarity of curve shapes. Its formula is defined as follows:

[0098] dis(A,B)=k1ED(A,B)+kβFD n (A,B);

[0099]

[0100]

[0101] Where A = {a1, a2, ..., a} n}, B={b1,b2,...,b n Let} represent two curves, k1, k2 (k1+k2=1) be distance weighting coefficients, α be the reparameterized function for the unit interval A, β be the reparameterized function for the unit interval B, ED(A,B) be the Euclidean distance, and FD be the distance between them. n (A, B) represents the Friesian distance. The main process of the clustering is as follows: randomly select object X from the set. i As the initial center c i Find the shortest distance J(X) from each object to the cluster center. i ), that is, J(X i ) = min{dls(X i ,c i)}, calculate the probability that each object in the sample will become the next cluster center, and select the one with the highest probability as the cluster center. The formula is:

[0102]

[0103] The above steps are repeated until the desired number of cluster centers are selected. Simultaneously, the DBI (Distributed Indicator Biometrics) evaluation index is used to assess the clustering results and verify their effectiveness. A label evaluation system is constructed using the clustering algorithm, resulting in a parameter calculation model.

[0104] In one implementation, the correspondence between the emotion index and the service type includes: the correspondence between the emotion index and the user level, and the correspondence between the user level and the service type;

[0105] The method of assigning a target service type to a user based on the preset correspondence between emotion indices and service types includes:

[0106] Based on the preset correspondence between emotion index and user level, the target user level is determined according to the target emotion index;

[0107] Based on the preset correspondence between user level and service type, a target service type is assigned to the user according to the target user level.

[0108] Specifically, users are first categorized into different levels based on their emotional index, and then the corresponding service type is determined based on the user level.

[0109] In one implementation, the user levels include Level 1 premium users, Level 2 users who receive ongoing care, and Level 3 users who receive priority care.

[0110] For the first-level high-quality users, a file is established for each user and a professional is assigned to connect with them; for the second-level users who require ongoing care, a method of constant monitoring is adopted and relevant business personnel are given enhanced training; for the third-level key care users, orders are directly assigned and relevant business personnel are evaluated for excellence.

[0111] After the work order is processed, the authenticity of the work order content is verified. If the verification is successful, the responsibility is determined. When the responsibility is determined to be the responsibility of the power supply company, the work order is filled back using the auxiliary form filling system. The work order filling information includes at least the processing time, the processor, the processing basis, and the processing result. The work order filling method includes at least one of manual filling and voice filling.

[0112] After the work order is filled in, the work order is reviewed and analyzed to extract user information, electricity consumption verification, electricity demand and appointment service information, and corresponding countermeasures are formulated to link the energy internet to realize supply and demand interaction. After the review and analysis are qualified, the work order index is established and uploaded.

[0113] For example, in combination Figure 3 As shown, a work order processing method based on RPA technology and related algorithms has been constructed to address the characteristics and needs of traditional power supply services. This method enables intelligent form filling, response review, and data analysis for non-faulty work orders (95958). It allows for real-time interaction between the power grid and customers, providing precise customer service, reducing labor costs, and improving business efficiency. Firstly, a user sentiment database reflecting customer sentiment indices is built, categorizing customer sentiment indices into levels to warn of potential emotional risks and achieve public opinion detection and protection, thereby improving the business skills of operators. Leveraging the user sentiment database, it is also possible to warn of potential customer emotions and analyze the quality of employee response indices, forming a new "digital intelligent customer service" power supply service model that is customer-demand oriented, intelligently interactive, and high-quality.

[0114] By integrating a user sentiment database, the system can quantify customer sentiment values ​​during work order dispatch to enable targeted work order assignment and issue warnings for high-risk work orders. When submitting work orders, it assists staff in completing the task through logical judgment and template matching, ensuring the work order is correctly filled out before submission. After the work order is reviewed and approved, its quality value is quantified, and units and individuals with high work order acceptance rates and high error rates are given advance warnings before the next work order dispatch. Simultaneously, the user sentiment database can be continuously updated to optimize the handling process and provide optimal feedback when encountering sensitive work orders and customer issues.

[0115] To better illustrate the advantages of the embodiments of the present invention, a specific example is briefly introduced below: Pilot use was implemented at the State Grid Ruian Power Supply Company at the end of April 2021, establishing an energy internet platform. Initially, the platform was piloted in repetitive and error-prone tasks. Operation is safe and stable, demonstrating reliable operational capabilities that meet the company's requirements. A digital assessment of the power supply service experience of 197,000 customers in four areas of Ruian has been completed, improving the quality of order entry for frontline staff, reducing the number of orders reviewed by service personnel, and enabling the timely detection and warning of risky work orders. This has resulted in a reduction in the number of work orders and the working hours of frontline staff, decreasing the number of work orders by over 30% and effectively reducing costs. Simultaneously, by combining user sentiment indexes, precise customer classification services have been achieved. For Tier 1 users, the company has established a "one customer, one file" system, providing training to relevant personnel and assigning relevant business personnel to continuously monitor user electricity usage. For Tier 2 users, user needs information is collected promptly, and communication with relevant users is strengthened. For Tier 3 users, high-quality service will continue to be maintained, and relevant personnel will be evaluated for excellence, providing users with a better and more considerate service experience.

[0116] This invention enables intelligent dispatching and work order backfilling for non-faulty work orders (95598), improving business efficiency and standardized operation levels. Simultaneously, by constructing a user sentiment index and establishing a user sentiment database, it achieves precise user classification, enabling a comprehensive and accurate understanding of customers, correctly grasping customer psychology and expectations, and providing differentiated care, thus optimizing enterprise services and enhancing customer experience. Furthermore, the sentiment index can be used to assess public satisfaction with power supply companies, assisting the government in evaluating industry conduct, objectively assessing the power supply service levels of power companies in various regions, optimizing the business environment, and establishing a competitive electricity market.

[0117] This invention also provides a power supply service work order processing device, comprising:

[0118] The work order acquisition module is used to acquire power supply service work orders and determine user information;

[0119] The current year sentiment index calculation module is used to obtain the current year and previous year's power consumption fluctuation parameters, power outage perception parameters, business processing experience parameters and customer call parameters based on user information, and to calculate the user's current year sentiment index.

[0120] The potential sentiment index calculation module is used to obtain the annual electricity consumption growth rate, annual capacity change parameters, electricity bill collection rate and arrears amount based on user information, and to calculate the user's potential sentiment index.

[0121] The target emotion index calculation module is used to calculate the user's target emotion index by combining the current year's emotion index and the potential emotion index.

[0122] The service type confirmation module is used to assign a target service type to a user based on a preset sentiment index and the correspondence between service types, and to dispatch orders according to the target sentiment index.

[0123] It is worth noting that the specific working process of the power supply service work order processing device can be referred to the working process of the power supply service work order processing method described in the above embodiments, and will not be repeated here.

[0124] Compared with existing technologies, the power supply service work order processing method and apparatus disclosed in this invention first acquires the power supply service work order and determines the user information; then, based on the user information, it acquires the current year's and the previous year's electricity fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer telephone call parameters, and calculates the user's current year's emotional index; based on the user information, it acquires the annual electricity growth rate, annual capacity change parameters, electricity bill collection rate, and outstanding amount, and calculates the user's potential emotional index; next, it combines the current year's emotional index and the potential emotional index to calculate the user's target emotional index; finally, based on a preset correspondence between emotional indices and service types, it assigns a target service type to the user for work order dispatch based on the target emotional index. This invention can calculate the target emotional index by acquiring the user's electricity-related data, and determine the corresponding target service type for work order dispatch based on the target emotional index, thereby improving user experience, reducing the risk of adverse effects caused by user emotionality, reducing the burden on staff, and improving work efficiency.

[0125] This invention also provides a power supply service order processing device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps described in the above-described power supply service order processing method embodiment, for example... Figure 1 The steps S1 to S5 described above; or, when the processor executes the computer program, it implements the functions of each module in the above-described device embodiments, such as the work order acquisition module.

[0126] For example, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the power supply service work order processing device. For example, the computer program can be divided into multiple modules, each with the following specific functions:

[0127] The work order acquisition module is used to acquire power supply service work orders and determine user information;

[0128] The current year sentiment index calculation module is used to obtain the current year and previous year's power consumption fluctuation parameters, power outage perception parameters, business processing experience parameters and customer call parameters based on user information, and to calculate the user's current year sentiment index.

[0129] The potential sentiment index calculation module is used to obtain the annual electricity consumption growth rate, annual capacity change parameters, electricity bill collection rate and arrears amount based on user information, and to calculate the user's potential sentiment index.

[0130] The target emotion index calculation module is used to calculate the user's target emotion index by combining the current year's emotion index and the potential emotion index.

[0131] The service type confirmation module is used to assign a target service type to a user based on a preset sentiment index and the correspondence between service types, and to dispatch orders according to the target sentiment index.

[0132] The specific working process of each module can be referred to the working process of the power supply service work order processing device described in the above embodiments, and will not be repeated here.

[0133] The power supply service order processing device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The power supply service order processing device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the schematic diagram is merely an example of a power supply service order processing device and does not constitute a limitation on the device. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the power supply service order processing device may also include input / output devices, network access devices, buses, etc.

[0134] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the power supply service order processing equipment, connecting all parts of the equipment via various interfaces and lines.

[0135] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the power supply service work order processing device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0136] If the modules integrated into the power supply service work order processing equipment are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0137] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for processing power supply service work orders, characterized in that, include: Obtain the power supply service work order and confirm user information; Based on user information, obtain the current year's and the previous year's electricity fluctuation parameters, power outage perception parameters, business processing experience parameters, and customer call parameters, and calculate the user's current year's sentiment index; Based on user information, the annual electricity consumption growth rate, annual capacity change parameters, electricity bill collection rate, and amount of outstanding fees are obtained, and the user's potential sentiment index is calculated. By combining the current year's sentiment index and the potential sentiment index, the user's target sentiment index is calculated. Based on the preset correspondence between sentiment index and service type, the system assigns target service type to users according to the target sentiment index for order dispatch. The process of obtaining electricity fluctuation parameters, power outage perception parameters, service processing experience parameters, and customer call parameters for the current and previous years based on user information includes: Based on user information, obtain the current year's internal and external user data, as well as the previous year's internal and external user data; The user's internal data and external data are preprocessed to construct user behavior characteristics for the current year and user behavior characteristics for the previous year; Input the user behavior characteristics of the current year and the user behavior characteristics of the previous year into the pre-trained parameter calculation model to obtain the current year's power fluctuation parameters, power outage perception parameters, business processing experience parameters and customer telephone call parameters, as well as the previous year's power fluctuation parameters, power outage perception parameters, business processing experience parameters and customer telephone call parameters. User tags include the power fluctuation parameters, the power outage perception parameters, the service processing experience parameters, and the customer telephone call parameters; The parameter calculation model is constructed in the following way: Acquire historical internal and external data from several test users to build a customer data information database; The customer data database is cleaned and processed to extract users' historical behavioral characteristics; Based on the user's historical behavioral characteristics, cluster analysis is performed on a number of test users. A Fraser distance is added to the Euclidean distance to construct a composite distance that considers the similarity of curve shapes. The formula is defined as follows: ； ； ； in, , A and B represent the historical behavioral characteristics of different test users, respectively. Let A be a reparameterized function for the unit interval A. For a reparameterized function over a B-unit interval, and This is the distance weighting coefficient. , Euclidean distance. For the Frege distance; It is the balance coefficient; The test users are clustered based on their historical behavioral characteristics to obtain several user classes, and each user class is assigned a corresponding user label to construct a parameter calculation model.

2. The power supply service work order processing method as described in claim 1, characterized in that, The current year's sentiment index is calculated using the following formula: ； ； in, This indicates the current year's sentiment index. This represents the current year's mood score. This indicates the mood score for the previous year; , , and The preset emotion rating weights, Let j be the electricity fluctuation parameter for the current year's month j. The power outage sensing parameters for month j of the current year. For the business processing experience parameters of month j of the current year, For the customer's incoming call parameters in month j of the current year; The potential sentiment index is calculated using the following formula: ； ； in, Indicates the potential sentiment index. Indicates the potential score for the current year. This indicates the potential score for the previous year. , , and As preset potential rating weights, This represents the annual electricity consumption growth rate for the current year. This indicates the annual capacity change parameters for the current year. This indicates the electricity bill collection rate for the current year. This indicates the amount of outstanding fees for the current year.

3. The power supply service work order processing method as described in claim 1, characterized in that, The target sentiment index is calculated using the following formula: ； in, This indicates the current year's sentiment index. Indicates the potential sentiment index, As the first weighting coefficient, This is the second weighting coefficient.

4. The power supply service work order processing method as described in claim 1, characterized in that, The correspondence between the emotion index and service type includes: the correspondence between the emotion index and user level, and the correspondence between user level and service type; The method of assigning a target service type to a user based on the preset correspondence between emotion indices and service types includes: Based on the preset correspondence between emotion index and user level, the target user level is determined according to the target emotion index; Based on the preset correspondence between user level and service type, a target service type is assigned to the user according to the target user level.

5. The power supply service work order processing method as described in claim 4, characterized in that, The user levels include Level 1 Premium Users, Level 2 Users Who Receive Regular Care, and Level 3 Users Who Receive Special Care. For the first-level high-quality users, a file is established for each user and a professional is assigned to connect with them; for the second-level users who require continued care, a real-time monitoring approach is adopted and relevant business personnel are given enhanced training; for the third-level key care users, orders are directly assigned and relevant business personnel are evaluated for excellence. After the work order is processed, the authenticity of the work order content is verified. If the verification is successful, the responsibility is determined. When the responsibility is determined to be the responsibility of the power supply company, the work order is filled back using the auxiliary form filling system. The work order filling information includes at least the processing time, the processor, the processing basis, and the processing result. The work order filling method includes at least one of manual filling and voice filling. After the work order is filled in, the work order is reviewed and analyzed to extract user information, electricity consumption verification, electricity demand and appointment service information, and corresponding countermeasures are formulated to link the energy internet to realize supply and demand interaction. After the review and analysis are qualified, the work order index is established and uploaded.

6. A power supply service work order processing device, characterized in that, include: The work order acquisition module is used to acquire power supply service work orders and determine user information; The current year sentiment index calculation module is used to obtain the current year and previous year's power consumption fluctuation parameters, power outage perception parameters, business processing experience parameters and customer call parameters based on user information, and to calculate the user's current year sentiment index. The potential sentiment index calculation module is used to obtain the annual electricity consumption growth rate, annual capacity change parameters, electricity bill collection rate and arrears amount based on user information, and to calculate the user's potential sentiment index. The target emotion index calculation module is used to calculate the user's target emotion index by combining the current year's emotion index and the potential emotion index. The service type confirmation module is used to assign a target service type to the user based on the preset emotion index and the correspondence between service types, and to dispatch orders according to the target emotion index. The current year sentiment index calculation module is used to obtain the current year and the previous year's electricity fluctuation parameters, power outage perception parameters, business processing experience parameters, and customer call parameters through the following methods: Based on user information, obtain the current year's internal and external user data, as well as the previous year's internal and external user data; The user's internal data and external data are preprocessed to construct user behavior characteristics for the current year and user behavior characteristics for the previous year; Input the user behavior characteristics of the current year and the user behavior characteristics of the previous year into the pre-trained parameter calculation model to obtain the current year's power fluctuation parameters, power outage perception parameters, business processing experience parameters and customer telephone call parameters, as well as the previous year's power fluctuation parameters, power outage perception parameters, business processing experience parameters and customer telephone call parameters. User tags include the power fluctuation parameters, the power outage perception parameters, the service processing experience parameters, and the customer telephone call parameters; The parameter calculation model is constructed in the following way: Acquire historical internal and external data from several test users to build a customer data information database; The customer data database is cleaned and processed to extract users' historical behavioral characteristics; Based on the user's historical behavioral characteristics, cluster analysis is performed on a number of test users. A Fraser distance is added to the Euclidean distance to construct a composite distance that considers the similarity of curve shapes. The formula is defined as follows: ； ； ； in, , A and B represent the historical behavioral characteristics of different test users, respectively. Let A be a reparameterized function for the unit interval A. For a reparameterized function over a B-unit interval, and This is the distance weighting coefficient. , Euclidean distance. For the Frege distance; It is the balance coefficient; The test users are clustered based on their historical behavioral characteristics to obtain several user classes, and each user class is assigned a corresponding user label to construct a parameter calculation model.

7. A power supply service work order processing device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the power supply service work order processing method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the power supply service work order processing method as described in any one of claims 1 to 5.

Images