Data analysis method and system equipment for electric power service win-order amount and medium

Abstract

The invention discloses a data analysis method and system equipment for electric power service win-order amount and a medium, and the method comprises the steps: collecting and analyzing the data of electricity customers, and obtaining the comprehensive score of the electricity customers; performing qualification evaluation on the comprehensive scores of the electricity customers, and screening out a first electricity customer; and carrying out risk assessment on the screened first electricity customers, and carrying out secondary screening to obtain second electricity customers. According to the data analysis method and system for the electric power service order winning amount, the accuracy and efficiency of value-added electric power service demand identification are remarkably improved, the correlation degree between the electricity customer characteristics and the value-added electric power service is accurately matched, and the success rate of electric power service popularization is improved. And resource waste and investment risks are effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power service demand analysis, and in particular to a data analysis method, system equipment and medium for the number of electric power service wins. Background Art

[0002] With the continuous development and opening up of the electricity market, value-added power services are gradually becoming a new profit growth point for power companies. However, power companies currently face many challenges in implementing value-added power services. Electricity customers' demands for value-added power services are becoming increasingly diverse and personalized, making it difficult for companies to accurately grasp these needs. Traditional value-added power service decisions often rely on experience and simple data statistics, lacking in-depth data analysis support. This approach makes it difficult to fully and accurately understand customer needs, resulting in weakly targeted power service strategies and limited results in increased wins. Therefore, there is an urgent need for a method and system that can accurately analyze data and increase the number of wins for value-added power services. Summary of the Invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is that the existing methods are insufficient in the accuracy and efficiency of electricity customer data analysis and demand forecasting, and the problem of how to quickly and accurately identify the potential demand of different electricity customers for specific value-added electricity services needs to be solved urgently.

[0005] To solve the above technical problems, the present invention provides the following technical solution: a data analysis method for the number of electricity service wins, comprising the following steps:

[0006] Collect and analyze electricity customer data to obtain comprehensive scores of electricity customers; conduct qualification assessments on the comprehensive scores of electricity customers to screen out the first electricity customers; conduct risk assessments on the screened out first electricity customers, conduct secondary screening, and obtain the second electricity customers.

[0007] The beneficial effects of this preferred technical solution are: through multi-level screening steps, it can accurately locate truly potential and low-risk electricity users, help concentrate resources on marketing and services for high-quality customers, increase the number of wins and success rate of value-added power services, and enhance the company's market competitiveness and economic benefits.

[0008] As a preferred solution of the data analysis method for the number of electricity service wins described in the present invention, the step of analyzing electricity customer data includes calculating a comprehensive score of the electricity customer based on the collected electricity customer data.

[0009] As a preferred solution of the data analysis method for the number of electricity service wins described in the present invention, the step of the qualification assessment includes:

[0010] Based on the comprehensive score of the electricity user, the value-added electricity service product required by the electricity user is selected; based on the historical information data of the value-added electricity service product required by the electricity user, a threshold probability is calculated through the historical information data; if the comprehensive score is greater than the threshold probability, the electricity user is identified as an electricity user customer group associated with the value-added electricity service.

[0011] The beneficial effects of this preferred technical solution are: by comparing the comprehensive score with the threshold probability and combining historical information data to select the target customer group, the accuracy and rationality of the assessment of customers' value-added power service needs are enhanced, which helps to screen out customer groups with real and high demand for value-added power services, providing strong support for precision marketing, and better meeting customers' personalized needs.

[0012] As a preferred solution of the data analysis method for the number of electricity service wins described in the present invention, the method for evaluating the electricity customer group associated with the value-added electricity service also includes:

[0013] Calculate the fitness score of each electricity customer for each electricity service, where the fitness score reflects the degree of match between the characteristics of the electricity customer and the characteristics of the electricity service; calculate the group of electricity customers associated with the value-added electricity service based on the fitness score of each electricity customer for each electricity service; the electricity customer characteristics include electricity load parameters, customer attribute parameters, and historical compliance parameters; the electricity service characteristic parameters include technical adaptation indicators, functional matching indicators, and cost adaptation indicators.

[0014] The beneficial effects of this preferred technical solution are: introducing a calculation method for fitness scoring, evaluating customers from the perspective of business adaptability, and being able to more comprehensively measure the matching relationship between customer characteristics and power service characteristics, helping to further screen out customer groups that are highly matched with value-added power services, optimize customer selection and resource allocation, and improve customer acceptance and satisfaction with services.

[0015] As a preferred solution of the data analysis method for the number of electricity service wins described in the present invention, screening the first electricity customer includes the following steps:

[0016] Conduct a comprehensive evaluation of the characteristics of all electricity users; perform calculations based on the comprehensive evaluation of the characteristics of all electricity users, and screen electricity users through the calculation structure;

[0017] Among them, the step of comprehensive characteristic evaluation includes: performing multi-dimensional comprehensive scoring by combining electricity customer characteristics with weighted scoring method, principal component analysis method or hierarchical analysis method, and outputting a comprehensive evaluation of the characteristics of electricity customers that are adapted to value-added power services.

[0018] The beneficial effects of this preferred technical solution are: the use of multiple comprehensive evaluation methods, such as weighted scoring method, principal component analysis method or hierarchical analysis method, can fully consider the multi-dimensional factors of customer characteristics, making the comprehensive evaluation of customer characteristics more comprehensive and reasonable, and providing a more accurate basis for subsequent customer screening, which is conducive to discovering more potential high-quality customers, improving the quality and value of the customer base, and also enhancing the comprehensive service capabilities for the customer base.

[0019] As a preferred solution of the data analysis method for the number of electricity service wins described in the present invention, wherein: risk assessment and secondary screening are performed on the screened electricity customers;

[0020] The secondary screening steps include:

[0021] The final electricity customers are obtained by combining the electricity customer risk assessment weights and index variables.

[0022] As a preferred solution of the data analysis method for the number of electricity service wins described in the present invention, the electricity customer data includes the electricity consumption of the electricity customer, the type of value-added electricity service product of the electricity customer's historical electricity consumption, the industry category of the electricity customer, and the comprehensive score of the electricity customer.

[0023] A data analysis system for the number of orders won for power services, characterized by:

[0024] The module for analyzing the characteristics of electricity users collects data information of electricity users and analyzes the characteristics of electricity users.

[0025] The module for screening potential electricity users evaluates the groups of electricity users who have a need for value-added electricity services, and selects electricity users who have the potential to increase the number of orders for value-added electricity services.

[0026] The secondary screening module conducts risk assessment on the screened electricity users, performs secondary screening, and obtains the final electricity users.

[0027] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0028] A computer-readable storage medium stores a computer program, which implements the steps of the method described above when executed by a processor.

[0029] The beneficial effects of this invention include significantly improving the accuracy and efficiency of identifying demand for value-added power services, accurately matching the correlation between electricity user characteristics and value-added power services, and improving the success rate of power service promotion. It also effectively reduces resource waste and investment risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 This is an overall flow chart of a data analysis method for the number of electricity service wins provided by the first embodiment of the present invention. DETAILED DESCRIPTION

[0032] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0033] Example 1, with reference to Figure 1 , as one embodiment of the present invention, provides a data analysis method for the number of win orders for power services, comprising:

[0034] S1: Collect and analyze electricity customer data to obtain a comprehensive score for electricity users.

[0035] Electricity customer data includes but is not limited to electricity consumption of electricity customers, historical electricity consumption of electricity customers, types of value-added electricity service products, industry categories of electricity customers, development of the region where electricity customers are located, and financial credit scores of electricity customers.

[0036] Data related to power value-added services are collected from multiple data sources in the power system, including but not limited to customer information databases, historical service order databases, market research data platforms, and power equipment operation monitoring systems. The collected data covers basic customer information, past value-added service demand records, order transaction status, market competitor service information, and power equipment operation status data.

[0037] Integrate the collected multi-source data and unify the data format; clean the data to remove noise data, duplicate data and invalid data; fill in missing data using interpolation, regression filling or machine learning-based filling algorithms, and normalize and standardize the data to make it comparable.

[0038] In an optional embodiment, based on the pre-processed data, text analysis, association rule mining and other technologies are used to deeply analyze the customer's value-added service demand pattern, including the customer's demand tendency, demand frequency, demand time characteristics, etc. for different types of value-added services (such as energy-saving transformation, power equipment hosting, customized electricity use plans, etc.), establish a customer demand model, analyze the collected market competitor service information, including the types of value-added services provided by competitors, service pricing strategies, market share, customer evaluations, etc., build a competitive situation model, and identify the company's own advantages, disadvantages, opportunities and threats in market competition.

[0039] In an optional embodiment, analyzing the characteristics of electricity users includes calculating the comprehensive score C of electricity users based on the collected electricity user data information. cust :

[0040]

[0041] Among them, α represents the influencing parameter of electricity consumption of electricity customers, P represents the electricity consumption of electricity customers, β represents the influencing parameter of the type of value-added electricity service products of electricity customers' historical electricity consumption, H represents the type of value-added electricity service products of electricity customers' historical electricity consumption, γ represents the index influencing parameter of the industry category of electricity customers, I ind represents the index of the industry category of the electricity customer, κ represents the influencing parameter of the financial credit score of the electricity customer, Q represents the financial credit score of the electricity customer, ξ represents the influencing parameter of the development index of the region where the electricity customer is located, D represents the development index of the region where the electricity customer is located, τ represents the scaling coefficient of the development index of the region where the electricity customer is located, λ represents the power coefficient of the electricity customer's electricity consumption, σ represents the power coefficient of the financial credit score of the electricity customer, η represents the power coefficient of the development index of the region where the electricity customer is located, δ represents the adjustment parameter used to balance the degree of influence of the type of value-added power service product on the electricity customer's historical electricity consumption, and k represents the influencing parameter of the financial credit score of the electricity customer.

[0042] In specific use, it is set to electricity consumption P = 1000 degrees, electricity consumption impact parameter α = 0.3, power coefficient λ = 50, and historical electricity consumption value-added power service product type H = 5, impact parameter is 0.2, industry category index is 8, impact parameter is 0.4, financial credit score = 70, impact parameter = 0.5, regional development index = 6, scaling factor = 0.2, power coefficient = 4.

[0043] Therefore, through calculation, it can be concluded that the comprehensive score of this electricity customer is approximately 0.3544. This process demonstrates how the formula is applied in actual scenarios.

[0044] This method breaks down data silos by integrating multi-source data such as customer information databases, historical orders, equipment monitoring, and market research. It covers basic customer information (industry, region), behavioral data (electricity consumption, historical service records), credit qualifications (financial scores), and equipment status to form a three-dimensional customer portrait and avoid the one-sidedness of single-dimensional analysis.

[0045] S2: Conduct a qualified assessment on the comprehensive scores of electricity users and select the first electricity users.

[0046] The steps of the qualification assessment include: selecting the value-added power service products required by the power user based on the comprehensive score of the power user; calculating the threshold probability based on the historical information data of the value-added power service products required by the power user; if the comprehensive score is greater than the threshold probability, the power user is identified as a power user group associated with the value-added power service.

[0047] In an optional embodiment, evaluating the group of electricity users who need value-added electricity services includes selecting value-added electricity service products that are likely to be needed by electricity users in the region based on the comprehensive scores of the electricity users, as expressed as:

[0048]

[0049] In this formula, n represents the total number of electricity customer attributes, j represents the index variable, and w ij Represents the weight coefficient of the electricity customer's nature on the demand probability, α j represents the attribute power function, λ k represents the smoothing coefficient, k represents the index variable, l represents the index variable, δ l represents the exponential power coefficient, p l represents the exponential decay coefficient, C cust Indicates the comprehensive score of electricity customers, (S i ) represents the value-added electricity service product, which is the object of evaluating demand probability, and p represents the demand probability.

[0050] It should be noted that the above formula comprehensively considers multiple different electricity customer attributes, and evaluates the demand probability of different value-added electricity services for specific electricity customer groups through the adjustment of weights and powers and the application of logarithmic and exponential functions.

[0051] The threshold probability P is calculated based on the customer's historical electricity consumption, the number of years the value-added electricity service product has been used, the customer's total annual consumption, the average customer's judgment score, and the market economic growth rate. y:

[0052]

[0053] in, H represents the weight of the number of years of use of the value-added electricity service product of the i-th electricity customer’s historical electricity consumption, i represents the number of years of historical electricity consumption value-added electricity service products used by the i-th electricity customer, ρ y represents the total annual consumption weight of the i-th electricity customer, C i represents the total annual consumption of the i-th electricity customer, τ represents the weight of the average electricity customer satisfaction score, A represents the average electricity customer satisfaction score, λ represents the weight of the market economic growth rate, and E represents the market economic growth rate.

[0054] In the calculation, the judgment score of the average electricity user may be the satisfaction score of the average electricity user, which may be obtained through an actual survey and averaging the survey results.

[0055] If P(S i ) is greater than P y , then the electricity customers in this region are identified as the electricity customer group with high demand for value-added electricity services.

[0056] The method for evaluating the group of electricity users associated with value-added power services also includes calculating the fitness score of each electricity user for each power service, wherein the fitness score reflects the degree of match between the characteristics of the electricity user and the characteristics of the power service; and calculating the group of electricity users associated with the value-added power service based on the fitness score of each electricity user for each power service; the characteristics of the electricity user include electricity load parameters, customer attribute parameters, and historical compliance parameters; and the characteristic parameters of the power service include technical adaptation indicators, functional matching indicators, and cost adaptation indicators.

[0057] Calculate the adaptability score B(S) of each electricity customer to each electricity service i ,C), reflects the matching degree between the characteristics of electricity customers and the characteristics of electricity services, which is expressed as:

[0058]

[0059] Among them, t ij Represents the fitness coefficient.

[0060] Based on each electricity customer's adaptability score for various electricity services and the demand probability of value-added electricity service products, the electricity customer group with high demand for value-added electricity services is calculated, which is expressed as:

[0061]

[0062] Where m represents the number of power service types, α i represents the importance coefficient of the i-th electricity service, Ω represents the adjustment constant of the overall demand score, and κ j represents the slope adjustment coefficient, P(S j ) represents the demand probability of the jth electricity service, G(C) represents the overall demand score of the electricity customer group with high demand for value-added electricity services, B(S i , C) represents the fitness scoring function between the i-th power service and the comprehensive score C of the electricity customer, which measures the matching degree between the power service and the customer score, Ω represents the adjustment constant of the overall demand score, θ j represents the jth adjustment parameter, κ j Represents the slope adjustment coefficient.

[0063] It should be noted that the above formula combines the demand probability of each electricity service, the importance of the electricity service, and the electricity user's fitness score for the electricity service to calculate the electricity user's overall demand score for all electricity services. The formula also includes a logistic function processing of the electricity service demand probability to account for the mutual influence and balance between different electricity services.

[0064] Screening the first electricity customer includes the following steps: conducting a comprehensive evaluation of the characteristics of all electricity customers; performing calculations based on the comprehensive evaluation of the characteristics of all electricity customers, and screening electricity customers using a calculation structure. The comprehensive evaluation step includes performing a multi-dimensional comprehensive scoring based on the characteristics of the electricity customers combined with a weighted scoring method, principal component analysis, or hierarchical analysis method, and outputting a comprehensive evaluation of the characteristics of the electricity customers that are compatible with the value-added power service.

[0065] Screening out electricity users with high potential demand involves conducting a comprehensive evaluation of the characteristics of all electricity users:

[0066]

[0067] Among them, H represents the electricity consumption weight of electricity users, γ M represents the weight of the electricity customer satisfaction index, M represents the electricity customer satisfaction index, Y represents the number of years of cooperation with the electricity customer, μ represents the market influence index parameter of the electricity customer, E C represents the market influence index of electricity users, and F represents the complaint rate of electricity users.

[0068] It should be noted that the above formula comprehensively considers multiple key characteristics of electricity users, fully reflects the overall situation of electricity users, and provides an accurate basis for subsequent calculations.

[0069] Calculate the potential demand of electricity customers based on the characteristics of all electricity customers:

[0070]

[0071] In this formula, γ k represents the comprehensive evaluation weight coefficient, p represents the total number of different electricity customer characteristics considered, t represents, t represents the integral variable, k represents the index variable, δ L represents the product term coefficient of the Lth characteristic, η L Represents the sensitivity of the Lth feature in the logistic function.

[0072] In another optional embodiment, a three-dimensional matrix method is used to divide customers into four categories:

[0073] High-potential customers (Class A): Comprehensive score ≥ 80 points, and meet any of the following conditions: historically purchased two or more value-added services; belongs to the high-energy-consuming manufacturing industry (industry classification code Class C) and the average monthly electricity consumption is > 500,000 kWh.

[0074] Medium-potential customers (Class B): 60 points ≤ Comprehensive score < 80 points, and meet any of the following conditions: Regional development index is 20% higher than the city average; Financial credit score ≥ 70 points and electricity consumption increase in the past 6 months is > 10%

[0075] Low-potential customers (Category C): 40 points ≤ comprehensive score < 60 points, and not included in the negative list.

[0076] Customers without potential (Category D): The overall score is less than 40 points, or they belong to restricted industries (such as small thermal power companies).

[0077] The missing financial credit scores were filled using the K nearest neighbor interpolation method (K=5), and duplicate customers were eliminated. The unified social credit code was used to remove duplicates, and a total of 120 duplicate data were cleaned. The "unit energy consumption service expenditure" was calculated as the historical value-added service consumption amount / total electricity consumption in the past year. Generate a "policy sensitivity label": If the regional policy dividend (P o )>industry average, marked as policy sensitive.

[0078] The business rule engine performs three-level screening: excludes customers on the negative list, customers with a financial credit score of Q < 50 points and no policy subsidies (P o =0), there have been more than three service complaints in the past two years and no rectification has been completed. The comprehensive score is then calculated, and finally the service tendency is matched according to the potential level.

[0079] Through the above embodiments, standardized implementation from customer characteristics to potential customer screening is achieved, providing a high-quality target customer pool for subsequent risk assessment, and effectively improving the precision marketing efficiency of value-added power services.

[0080] S3: Conduct risk assessment on the screened first electricity users, conduct secondary screening, and obtain second electricity users.

[0081] It should be noted that when conducting screening, not only the electricity customer groups with high demand for value-added power services should be considered, but also whether the risks of these electricity customers exceed the company's ability to bear. Therefore, it is necessary to assess the risks of electricity customers.

[0082] The risk assessment of the screened electricity customers is expressed as:

[0083]

[0084] Among them, ω represents the adjustment coefficient of the electricity customer's arrears, G represents the electricity customer's arrears, r1 represents the power parameter of the electricity customer's arrears, κ HT H represents the product parameter of the number of complaints from electricity users, T represents the number of complaints from electricity users, λ HT Represents the number of customer complaints, μ I represents the adjustment coefficient of the electricity customer order delay rate, I represents the electricity customer order delay rate, π represents the electricity customer market share change rate adjustment coefficient, K represents the electricity customer market share change rate, L Y represents the business growth rate of electricity customers, and r2 represents the power parameter of the business growth rate of electricity customers.

[0085] The final electricity customers are obtained by combining the electricity customer risk assessment weights and index variables for calculation.

[0086] In another optional embodiment, performing secondary screening is expressed as:

[0087]

[0088] Among them, η m represents the risk assessment weight of electricity customers, r represents the total number of secondary screening items, m represents the index variable, Represents the slope adjustment coefficient.

[0089] It should be noted that the above formula calculates the final customer score by combining multiple evaluation indicators, using a weighted summation and a hyperbolic sine function. This effectively assesses the comprehensive risk and potential value of each customer, helping to determine the final list of eligible customers.

[0090] Furthermore, all variable parameters such as adjustment parameters, weight coefficients, power coefficients, etc. in the present invention are adjusted by analyzing historical data and according to actual conditions, and can be changed in actual use.

[0091] In another optional embodiment, the secondary screening step may also be: obtaining the overdue payment records of the past two years from the financial system, and accurate to the number of overdue days and amount; extracting equipment parameters such as customer transformers and distribution rooms from the equipment monitoring system, and calculating the equipment compatibility index; capturing industry carbon emission data from the official website of the Ministry of Ecology and Environment, and quantifying regional carbon emission reduction pressure.

[0092] Missing contract fulfillment rates are filled with the industry average. For example, the default fulfillment rate for small and micro enterprises is 85%. Text-based regulatory levels are numerically coded, with encouragement = 0, restriction = 1, and elimination = 2.

[0093] Clearly high-risk customers are excluded. The triggering exclusion rules are: the industry they belong to is obsolete, such as small thermal power plants and steel mills with backward production capacity; they have been in arrears for more than three times in the past year and the single arrears lasted for more than 30 days; the equipment compatibility index is less than 50 points and they are technically unable to adapt to the target service.

[0094] Through model calculation and manual review, low-risk customers with R<40 points are directly included in the final list, medium-risk customers are included after the risk control measures are approved, and high-risk customers enter the observation pool and are re-evaluated every quarter.

[0095] By integrating multi-dimensional indicators such as outstanding balance history, number of complaints, device compatibility, and policy risk, a quantitative risk assessment model has been constructed, increasing the accuracy of identifying high-risk customers from 60% in manual assessments to 85%. This effectively eliminates customers with technical mismatches, device compatibility scores below 50, poor credit (i.e., over three outstanding balances), and policy restrictions, thereby reducing post-service performance and compliance risks. By setting a risk threshold below 40 points, customers are included in the shortlist, focusing on low-risk, high-potential customers and reducing ineffective resource investment. With additional risk control measures, medium-risk customers are expected to see a 40% reduction in bad debt losses. This also avoids overly cautious exclusion of potential customers, balancing risk and business growth.

[0096] Example 2 is the second embodiment of the present invention, which is different from the previous embodiment in that:

[0097] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0098] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0099] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0100] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0101] Example 3 is the third embodiment of the present invention, which provides a system for analyzing data on the number of win orders for electric power services, including:

[0102] Module for analyzing the characteristics of electricity users, collecting data and information of electricity users, and analyzing the characteristics of electricity users;

[0103] Screening potential electricity customers module, evaluate the electricity customer groups that need value-added electricity services, and screen out electricity customers who are relevant to increasing the number of value-added electricity service orders;

[0104] The secondary screening module conducts risk assessment on the screened electricity users, performs secondary screening, and obtains the final electricity users.

[0105] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A data analysis method for the number of win orders for power services, characterized in that: The following steps are involved: Collect and analyze electricity customer data to obtain comprehensive scores for electricity users; Conduct a qualified assessment of the comprehensive scores of electricity users and select the first-class electricity users; Conduct risk assessment on the screened first electricity users, conduct secondary screening, and obtain the second electricity users.

2. The data analysis method for the number of electricity service wins according to claim 1, characterized in that: The step of analyzing the electricity customer data includes calculating a comprehensive score of the electricity customer based on the collected electricity customer data.

3. The data analysis method for the number of electricity service wins according to claim 2, characterized in that: The steps of the conformity assessment include: Selecting value-added electricity service products that meet the electricity user's needs based on the comprehensive score of the electricity user; Based on historical information data of value-added power service products required by electricity users, and calculating threshold probability through historical information data; If the comprehensive score is greater than the threshold probability, the electricity customer is identified as an electricity customer group associated with the value-added power service.

4. The data analysis method for the number of electricity service wins according to claim 3, characterized in that: The evaluation methods for electricity customer groups associated with value-added electricity services also include: Calculating the fitness score of each electricity customer for each electricity service, where the fitness score reflects the degree of match between the characteristics of the electricity customer and the characteristics of the electricity service; Calculating the electricity customer group associated with the value-added electricity service based on the adaptability score of each electricity customer to each electricity service; The electricity customer characteristics include electricity load parameters, customer attribute parameters, and historical compliance parameters; The power service characteristic parameters include technical adaptation indicators, functional matching indicators, and cost adaptation indicators.

5. The data analysis method for the number of electricity service wins according to claim 4, characterized in that: Screening the first electricity customer includes the following steps: Conduct comprehensive characteristic evaluation of all electricity customers; Calculate based on comprehensive evaluation of the characteristics of all electricity customers and screen electricity customers through calculation structure; The step of comprehensive evaluation of characteristics includes: By combining the characteristics of electricity users with weighted scoring method, principal component analysis method or hierarchical analysis method, a multi-dimensional comprehensive scoring is performed to output a comprehensive evaluation of the characteristics of electricity users that are compatible with value-added power services.

6. The data analysis method for the number of electricity service wins according to claim 5, characterized in that: The aforementioned risk assessment and secondary screening of the screened electricity customers; The secondary screening steps include: The final electricity customers are obtained by combining the electricity customer risk assessment weights and index variables.

7. The data analysis method for the number of electricity service wins according to claim 6, characterized in that: The electricity customer data includes the electricity customer's electricity consumption, the electricity customer's historical electricity consumption, the type of value-added electricity service product, the electricity customer's industry category, and the electricity customer's comprehensive score.

8. A system for analyzing data on the number of wins in electric power services, using a method for analyzing data on the number of wins in electric power services according to any one of claims 1 to 7, characterized in that: It includes a data analysis module, a first screening module, and a second screening module; The data analysis module analyzes the collected electricity customer data to obtain a comprehensive score of the electricity customer; The first screening module is used to perform a qualification assessment on the comprehensive scores of the electricity users and screen out the first electricity users; The second screening module is used to perform risk assessment on the screened first electricity users, perform secondary screening, and obtain second electricity users.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the data analysis method for the number of electric service wins according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the data analysis method for the number of electric service wins according to any one of claims 1 to 7 are implemented.

Images