New energy charging operation platform analysis method and system, electronic equipment and storage medium

Abstract

The invention discloses a new energy charging operation platform analysis method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining new energy charging related data, and building a marketing activity analysis model according to the new energy charging related data; analyzing and evaluating the risk condition of the marketing activity by using the marketing activity analysis model, including: constructing risk indexes, and performing risk merging and calculation on the risk indexes; and according to a total assessment judgment rule, the merging and calculation result of the risk indexes is judged, and an assessment report containing all the risk indexes and the total risk rating is generated. According to the invention, an effective marketing activity analysis model is constructed, a potential risk identification module is developed at the same time, marketing risks are early warned in real time, comprehensive assessment from three dimensions of fund loss risk, new drawing capability and profitability is realized, and finally an assessment report comprehensively including all indexes and overall risk rating is generated. And a scientific basis and decision support are provided for a marketing strategy of a new energy charging operation platform.

Description

Technical Field

[0001] The present invention relates to the field of marketing risk assessment and new energy charging platform operation technology, and in particular to a new energy charging operation platform analysis method, system, electronic equipment and storage medium. Background Art

[0002] As climate warming, energy crisis and environmental pollution intensify, electric vehicles (EVs) have become an important solution to alleviate energy pressure and reduce environmental pollution with their environmentally friendly, energy-saving and economical characteristics. Countries around the world are actively promoting electric vehicles as a key link in the transformation of their transportation systems. Charging stations, as the interface between electric vehicles and the power grid, are the infrastructure supporting the popularization of electric vehicles. Technological progress, especially the innovation of battery technology and charging technology, has provided charging platforms with efficient and fast charging solutions. At the same time, the application of intelligent and digital technologies, such as the Internet of Things (IoT), big data analysis and artificial intelligence (AI), has made charging station management more intelligent and services more personalized. Policy support is also a powerful driving force for the development of new energy charging platforms, including financial subsidies, tax incentives and construction standards, which have reduced operator costs and increased consumer acceptance. Market competition and cooperation have promoted the improvement of service quality and operational efficiency, and the establishment of cross-operator charging networks has provided users with more convenience. In the face of diversified user needs, charging platforms need to continuously innovate service models to meet the needs of fast, convenient, reasonably priced, intelligent and personalized charging. The development of the electric vehicle charging service industry is crucial to the successful promotion of electric vehicles.

[0003] Although new energy charging platforms are developing rapidly, the intensified market competition has also brought unprecedented challenges. There are many risks hidden behind the endless marketing methods, so risk assessment has become a core link in operations. By identifying, analyzing and evaluating the risk factors that may be encountered during operations, risk assessment helps operators to discover and respond to potential problems in advance. To deal with these operational risks, charging platforms need to build a complete risk management system, including identifying and evaluating all potential risks, and formulating preventive measures and emergency plans. This is not only related to the daily operation stability of the charging platform, but also an important guarantee for its sustainable development. In a rapidly changing market environment, how to effectively manage risks has become an important issue facing new energy charging platforms. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a new energy charging operation platform analysis method to solve the problem that the new energy charging operation platform lacks a scientific analysis model and risk warning mechanism in the formulation of marketing strategies.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a new energy charging operation platform analysis method, comprising:

[0008] Acquire new energy charging related data, and establish a marketing activity analysis model based on the new energy charging related data;

[0009] The marketing activity analysis model is used to analyze and evaluate the risk situation of the marketing activity, including: constructing risk indicators, and performing risk aggregation and calculation on the risk indicators; judging the aggregation and calculation results of the risk indicators based on the overall assessment judgment rules, and generating an assessment report containing all risk indicators and overall risk ratings.

[0010] As a preferred scheme of the new energy charging operation platform analysis method described in the present invention, the risk indicators include excessive risk of activity discount superposition, risk of activity budget overspending, risk of capital loss, excessively high proportion of discount amount, decreased proportion of new customers, negative growth of ROI, abnormal changes in marketing payment amount, low conversion rate and high fluctuations in average customer price.

[0011] As a preferred solution of the new energy charging operation platform analysis method of the present invention, wherein: risk merging of the risk indicators includes:

[0012] The risks of marketing activities are aggregated and evaluated according to the prescribed risk assessment rules, forming a comprehensive assessment of the three dimensions of capital loss risk, new customer acquisition ability and profitability;

[0013] The risk of capital loss includes excessive superposition of promotional offers, overspending of promotional budgets, risk of capital loss, and excessively high promotional ratios;

[0014] The ability to attract new customers, including the proportion of new customers, has decreased;

[0015] Profitability includes negative ROI growth, abnormal fluctuations in marketing payment amounts, low conversion rates and high fluctuations in average order value.

[0016] As a preferred solution of the new energy charging operation platform analysis method of the present invention, wherein: the risk calculation of the risk index includes:

[0017] Based on the risk indicator merging result, corresponding weights are set, and the risk indicator value is calculated using a fuzzy comprehensive evaluation method. Whether the risk indicator is abnormal is determined based on the risk indicator value.

[0018] As a preferred solution of the new energy charging operation platform analysis method described in the present invention, wherein: according to the overall assessment judgment rule, the risk indicators are merged and the calculation results are judged, and an assessment report containing all risk indicators and overall risk ratings is generated, including:

[0019] The abnormal number of risk indicators of the overall assessment determination rule is divided into four levels, including normal, low risk, medium risk and high risk;

[0020] When all indicators are within the normal range and there are no abnormalities, it is judged as normal;

[0021] When no more than 2 risk indicators show abnormalities, it is judged as low risk;

[0022] When no more than 5 risk indicators show abnormalities, it is judged as medium risk;

[0023] When more than 5 risk indicators show abnormalities, it is judged as high risk.

[0024] As a preferred solution of the new energy charging operation platform analysis method described in the present invention, the risk indicators include:

[0025] A risk identification module and real-time early warning mechanism are established based on risk indicators to provide real-time early warning for various risks arising from marketing activities.

[0026] As a preferred solution of the new energy charging operation platform analysis method described in the present invention, the new energy charging related data includes:

[0027] After obtaining the data related to new energy charging, the data is preprocessed and feature screened, and the correlation analysis method is used to identify the feature data set required for the prediction of the marketing activity analysis model.

[0028] In a second aspect, the present invention provides a system for analyzing a new energy charging operation platform, comprising:

[0029] Data acquisition module, used to obtain new energy charging related data;

[0030] A model building module, used to build a marketing activity analysis model based on the new energy charging related data;

[0031] An indicator determination and analysis module is used to construct risk indicators and perform risk aggregation and calculation on the risk indicators;

[0032] The risk assessment module is used to determine the aggregation and calculation results of risk indicators based on the overall assessment judgment rules, and generate an assessment report containing all risk indicators and overall risk ratings.

[0033] In a third aspect, the present invention provides a computing device, comprising:

[0034] Memory and processor;

[0035] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the new energy charging operation platform analysis method are implemented.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the new energy charging operation platform analysis method.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention establishes a marketing analysis and diagnosis method and system for a new energy charging operation platform based on big data, which can accurately obtain and analyze the marketing activities, costs and user behavior data of the charging platform, build an effective marketing activity analysis model, and develop a potential risk identification module at the same time, to warn of marketing risks in real time, and realize a comprehensive evaluation from three dimensions: capital loss risk, new customer acquisition ability and profitability. Finally, an evaluation report that comprehensively includes all indicators and overall risk ratings is generated, which provides a scientific basis and decision-making support for the marketing strategy of the new energy charging operation platform, and significantly improves the risk prevention and control capabilities of marketing activities and the accuracy of effect evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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 creative labor. Among them:

[0039] Figure 1 This is a schematic diagram of the overall process of a new energy charging operation platform analysis method according to an embodiment of the present invention;

[0040] Figure 2 It is a schematic diagram of simulation results of a new energy charging operation platform analysis method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0045] At the same time, in the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0046] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0047] Example 1

[0048] Reference Figure 1, which is an embodiment of the present invention, provides a new energy charging operation platform analysis method, including:

[0049] S100: Acquire data related to new energy charging, and establish a marketing activity analysis model based on the data related to new energy charging;

[0050] In the embodiment of the present application, the new energy charging related data includes marketing activity data, cost data and user behavior data of the new energy charging platform;

[0051] The channels for obtaining new energy charging-related data can be collected from marketing automation tools, social media platforms, internal sales reports, etc., including but not limited to: marketing activity data such as activity date, activity type, number of participants, conversion rate, etc.; cost data such as activity budget, cost-benefit analysis, etc. are collected from financial reports, purchase invoices, etc.; user behavior data such as the proportion of new users, fluctuations in high customer unit prices, etc. are collected from charging platform databases, online behavior tracking, etc.

[0052] Preferably, after obtaining the new energy charging related data, the new energy charging related data is preprocessed and feature screened, and a correlation analysis method is used to identify the feature data set required for the marketing activity analysis model prediction;

[0053] In the embodiment of the present application, the preprocessing may include but is not limited to: removing duplicate values, processing missing values, and encoding non-numeric data into numerically standardized or normalized numerical data;

[0054] In another possible embodiment, a statistical test method may be used to identify and obtain the most critical feature set for model prediction;

[0055] The specific process of identifying the feature data set required for the prediction of the marketing activity analysis model by using the correlation analysis method includes: calculating the correlation coefficient between each feature variable, such as activity date, activity type, number of participants, conversion rate, activity budget, cost-benefit analysis, new user ratio, high customer unit price fluctuation, etc. and the target variable, such as marketing activity effect, user participation or cost-effectiveness; the present invention selects the Pearson correlation coefficient, sorts and screens according to the calculated correlation coefficient, retains those features that are correlated with the target variable, and sets a statistical significance threshold, such as a p-value less than 0.05 or the absolute value of the correlation coefficient is greater than a certain threshold; based on the multicollinearity problem between features, further feature optimization is performed through the variance inflation factor method to ensure that the final selected feature data set contains variables that have a substantial contribution to the model prediction, avoiding the increase in model complexity and performance degradation caused by redundant information.

[0056] In the embodiments of the present application, after preprocessing and correlation analysis, a clustering model is introduced to explore the intrinsic structure and potential patterns of the data. The natural groupings in the data are understood through cluster analysis, which provides data support for market segmentation, user behavior analysis, etc.

[0057] S102: Use the marketing activity analysis model to analyze and assess the risk of marketing activities, including:

[0058] S102-1: Construct risk indicators, and perform risk aggregation and calculation on risk indicators;

[0059] Preferably, risk indicators include the risk of excessive superposition of activity discounts, the risk of activity budget overspending, the risk of capital loss, an excessively high proportion of discount amounts, a decrease in the proportion of new customers, negative growth in ROI, abnormal changes in marketing payment amounts, low conversion rates, and high fluctuations in average order value.

[0060] Preferably, the risk aggregation of risk indicators includes aggregating and evaluating the risks of marketing activities according to prescribed risk assessment rules to form a comprehensive assessment of the three dimensions of capital loss risk, new customer acquisition capability and profitability;

[0061] Preferably, the risk of capital loss includes excessive superposition of activity discounts, activity budget overruns, risk of capital loss, and excessively high discount ratios;

[0062] Preferably, the ability to attract new customers includes a decrease in the proportion of new customers;

[0063] Preferably, profitability includes negative ROI growth, abnormal fluctuations in marketing payment amounts, low conversion rates, and high fluctuations in average order value.

[0064] Preferably, the risk calculation of the risk indicator includes setting corresponding weights based on the risk indicator merging results, calculating the risk indicator value by using a fuzzy comprehensive evaluation method, and judging whether the risk indicator is abnormal according to the risk indicator value;

[0065] In the embodiment of the present application, the risk indicators are analyzed according to the big data analysis technology, and the fuzzy comprehensive evaluation method is adopted to conduct an in-depth risk analysis of the above risk indicators. This method effectively solves the uncertainty problem existing in traditional risk assessment by integrating qualitative analysis and quantitative calculation; the fuzzy comprehensive evaluation method can not only conduct a detailed quantitative evaluation of risk factors, but also can reasonably classify the size of risks according to the evaluation results. This process not only improves the accuracy of risk assessment, but also provides a more accurate reference basis for risk management;

[0066] Specifically, the risk indicator calculation and judgment rules can be expressed as:

[0067] ① Risk of excessive superposition of promotional offers:

[0068] DPR>Dis.max

[0069] Among them, DPR is the actual discount rate, Dis.max is the maximum discount rate threshold;

[0070] ②Risk of activity budget overspending:

[0071] EMP>MB

[0072] Among them, EMP is the expected marketing payment amount, and MB is the activity budget;

[0073] ③Risk of capital loss:

[0074] EMP>MB*(1+POP)

[0075] Among them, POP is the preset tolerance overspending percentage;

[0076] ④Risk of excessively high preferential amount ratio:

[0077] (MPD / MPA)>DPT

[0078] Among them, MPD is the marketing discount amount, MPA is the marketing payment amount, and DPT is the set discount ratio threshold;

[0079] ⑤Risk of decline in the proportion of new customers:

[0080] NCN / TC<NCPT

[0081] Among them, NCN is the number of new customer transactions, TC is the total number of transactions, and NCPT is the set new customer ratio threshold;

[0082] ⑥ Negative ROI growth:

[0083] ROI-current<ROI-average-(2*ROI-SD)

[0084] Among them, ROI-current is the current value of ROI, ROI-average is the historical average value of ROI, and ROI-SD is the historical standard deviation of ROI;

[0085] ⑦Risk of abnormal changes in marketing payment amount:

[0086] AMP-HAMP>2*DPT

[0087] Among them, AMP is the current value of the marketing payment amount, HAMP is the historical average of the marketing payment amount, and HSDAMP is the historical standard deviation of the marketing payment amount;

[0088] ⑧Low conversion rate risk:

[0089] CR=(MPN / UV)<CVR

[0090] Among them, CR is the conversion rate, MPN is the number of marketing payment, UV is the number of customers browsing activities, and CVR is the set conversion rate threshold;

[0091] ⑨High customer price fluctuation:

[0092] |ACU-HACU|>2*HSDACU

[0093] Among them, ACU is the current average customer price, HACU is the average historical customer price, and HSDACU is the standard deviation of the historical customer price;

[0094] Preferably, a risk identification module and a real-time early warning mechanism are established based on risk indicators to provide real-time early warnings for various risks arising in marketing activities.

[0095] It should be noted that the process of risk aggregation and calculation of risk indicators and forming a comprehensive assessment of the three dimensions of capital loss risk, new customer acquisition ability and profitability can achieve comprehensive identification and quantitative assessment of marketing activity risks. By setting corresponding weights and using fuzzy comprehensive evaluation or other methods to calculate risks, it is possible to determine whether risk indicators are abnormal, thereby timely warning of potential marketing risks, which helps platform operators to take timely measures to reduce risk losses and ensure the stable operation of the platform; in addition, the risk identification module and real-time warning mechanism established based on risk indicators can achieve real-time monitoring and warning of marketing activity risks, which helps platform operators to promptly discover and respond to potential marketing risks and improve the initiative and timeliness of risk management.

[0096] S102-2: Based on the overall assessment judgment rules, the risk indicators are combined and the calculation results are judged to generate an assessment report containing all risk indicators and overall risk ratings;

[0097] Preferably, the number of abnormalities of the risk indicator of the overall assessment determination rule is divided into four levels, including normal, low risk, medium risk and high risk;

[0098] Preferably, when all indicators are within the normal range and there is no abnormality, it is determined to be normal;

[0099] Preferably, when no more than 2 risk indicators show abnormality, it is determined to be low risk;

[0100] Preferably, when no more than 5 risk indicators show abnormalities, it is determined to be medium risk;

[0101] Preferably, when more than 5 risk indicators show abnormalities, it is determined to be high risk.

[0102] It should be noted that according to the overall assessment judgment rules, a detailed assessment report can be generated by combining the risk indicators and making a comprehensive judgment on the calculation results. The report not only contains detailed data of all risk indicators, but also gives an overall risk rating. This assessment method can intuitively reflect the risk status faced by marketing activities and provide operators with a scientific basis for decision-making;

[0103] Specifically, according to the abnormal number of risk indicators, the risks are divided into four levels: normal, low risk, medium risk and high risk. This helps operators to quickly identify and respond to potential risks, so that they can take timely measures to reduce risk losses and ensure the smooth progress of marketing activities. The assessment report based on big data and precise risk assessment not only improves the efficiency and accuracy of risk management, but also provides a strong guarantee for the stable operation and sustainable development of the new energy charging operation platform.

[0104] The above is a schematic scheme of a new energy charging operation platform analysis method of this embodiment. It should be noted that the technical scheme of the new energy charging operation platform analysis system and the technical scheme of the above-mentioned new energy charging operation platform analysis method belong to the same concept. For details not described in detail in the technical scheme of the new energy charging operation platform analysis system in this embodiment, please refer to the description of the technical scheme of the above-mentioned new energy charging operation platform analysis method.

[0105] The new energy charging operation platform analysis system in this embodiment includes:

[0106] Data acquisition module, used to obtain new energy charging related data;

[0107] Model building module, used to build marketing activity analysis models based on new energy charging related data;

[0108] The indicator determination and analysis module is used to construct risk indicators and to aggregate and calculate risk indicators;

[0109] The risk assessment module is used to determine the aggregation and calculation results of risk indicators based on the overall assessment judgment rules, and generate an assessment report containing all risk indicators and overall risk ratings.

[0110] This embodiment also provides a computing device suitable for analyzing the new energy charging operation platform, including:

[0111] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the new energy charging operation platform analysis method proposed in the above embodiment.

[0112] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for analyzing the new energy charging operation platform proposed in the above embodiment is implemented.

[0113] The storage medium proposed in this embodiment and the method for realizing the analysis of the new energy charging operation platform proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0114] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0115] Example 2

[0116] Reference Figure 2 Tables 1-7 are an embodiment of the present invention, which provides a new energy charging operation platform analysis method. In order to verify its beneficial effects, experimental simulation results of the method test of the present invention are provided.

[0117] The method of obtaining the marketing activity data, cost data and user behavior data of the new energy charging platform and building a marketing activity analysis model for the charging operation platform is as follows:

[0118] New energy charging platform, the new generation of charging facility operation and management platform adopts microservice architecture, built on SpringCloud and Spring Boot, uses Apache Kafka to process high-throughput data streams, combines MySQL and MongoDB to process structured and unstructured data, uses Redis to improve performance, and uses MinIO for large-scale file storage. Spring Boot is an open source Java framework developed by the Pivotal team (now part of VMware). It is a module of the Spring framework with features such as automatic configuration, independent operation, and deployment-friendly, designed to simplify the initial construction and development process of Spring applications. Spring Cloud is a collection of frameworks to simplify the development of distributed systems. It extends the functionality of Spring Boot and provides tools and libraries for building microservices in a cloud environment. It includes a variety of components such as service discovery, configuration management, message bus, load balancing, circuit breakers, etc. Spring Cloud has good integration capabilities, allowing developers to quickly embed various functions of cloud services into their own applications and build more flexible and scalable cloud-native applications.

[0119] New energy charging platform marketing data acquisition, the new generation charging facility operation management platform uploads charging pile data to the platform in real time through two data collection methods (NBT33007 protocol and MQTT protocol), and users can also manually enter or import and export data. The platform uses Apache Flink for real-time data processing and stores real-time data in Redis to support fast access and display. Historical data is stored in MongoDB for long-term storage and in-depth analysis.

[0120] Marketing activity analysis model: Data quantification of marketing activities is achieved by analyzing user data, charging data, marketing activity data, coupon data, and vehicle-network interaction data. This involves using methods such as questionnaires, data mining, data visualization, and data analysis tools to collect and analyze data.

[0121] Marketing campaign strategy: By using big AI models, we can analyze large amounts of marketing campaign data, build models, optimize marketing strategies, and evaluate campaign effectiveness.

[0122] Specifically, based on big data analysis technology, we construct risk indicators, develop potential risk identification modules, and provide real-time warnings for various risks that may arise in marketing activities. The specific rules for constructing nine risk indicators are as follows:

[0123] Risk of excessive discount stacking: A calculation rule is set, that is, when the actual discount rate exceeds the set maximum discount rate threshold, the system will automatically identify and issue an alert.

[0124] Risk of activity budget overspending: By comparing the expected marketing payment amount with the established activity budget, the system will issue an early warning if the former exceeds the latter.

[0125] Risk of capital loss: This article introduces a preset tolerance overspending percentage. When the expected marketing payment amount exceeds the product of the activity budget and the overspending percentage, the system will prompt the potential risk of capital loss.

[0126] Negative ROI growth: The decline in return on investment (ROI) is the focus of the model. If the current ROI value is lower than the historical average minus two standard deviations, the system will mark it as a negative growth risk.

[0127] Abnormal changes in marketing payment amounts: By monitoring the deviation between the current value of the marketing payment amount and its historical average, if the deviation exceeds twice the historical standard deviation, the system will alert you to abnormal changes.

[0128] Discount ratio is too high: The model sets a discount ratio threshold, such as 30%. When the ratio of marketing discount amount to marketing payment amount exceeds this threshold, the system will identify the risk of excessive discount ratio.

[0129] Low conversion rate: Conversion rate is a key indicator to measure marketing effectiveness. If the conversion rate, which is the ratio of the number of marketing payment customers to the number of browsing customers, is lower than the set threshold, the system will prompt a low conversion rate risk.

[0130] Decline in the proportion of new customers: The introduction of new customers is crucial to business growth. If the proportion of new customer transactions to total transactions is lower than the set threshold, the system will warn of the risk of a decline in the proportion of new customers.

[0131] High average order value fluctuation: The stability of average order value is another important indicator that the model focuses on. If the current average order value deviates from the historical average by more than two standard deviations, the system will warn of the risk of high average order value fluctuation.

[0132] Through these precise calculation rules, the model can comprehensively analyze all aspects of marketing activities and identify potential risks in a timely manner. It also provides solid data support for operational decisions, making the decision-making process more scientific and reasonable, and effectively improving the accuracy and success rate of marketing strategies.

[0133] According to the prescribed calculation rules, the data collected are stipulated in the English abbreviations as shown in Table 1:

[0134] Table 1 English abbreviations of collected data

[0135] Data indicators Abbreviations Actual discount rate DPR Maximum discount rate threshold Dis.max Expected marketing payment amount EMP Activity Budget MB Preset tolerance overspending percentage POP Current value of marketing payment amount AMP Historical average of marketing payment amount HAMP Historical standard deviation of marketing payment amount HSDAMP Marketing discount amount MPD Marketing payment amount MPA Conversion rate CR Marketing payment number MPN Number of customers browsing activities UV Set conversion rate threshold CVR Set the discount ratio threshold DPT Number of new customer transactions NCN Total transaction quantity TC The set new customer ratio threshold NCPT Current average order value ACU Historical average customer price HACU Historical average order value standard deviation HSDACU

[0136] Based on the above data indicators and abbreviations, nine risk assessment calculation rules are analyzed and formulated. According to the calculation results of each indicator, risks are merged and evaluated to form a comprehensive evaluation of the three main dimensions of capital loss risk, new customer acquisition ability and profitability. When analyzing and evaluating the risks of marketing activities, the fuzzy comprehensive evaluation method is used to conduct risk assessment of the analyzed marketing activities.

[0137] By dividing the nine indicators into three dimensions, namely, "capital loss risk", "new customer acquisition capability" and "profitability", the weights of the three dimensions in risk assessment are determined according to the actual situation. The present invention adopts the analytic hierarchy process (AHP) to determine the weights of the three dimensions.

[0138] The analytic hierarchy process (AHP) was first proposed by Professor Satti and put into practice in various industry issues. This method is an effective analytical method for weighted decision-making. It is a means of decision-making when the influencing factors are difficult to quantify, there are many influencing factors and the structure is complex. This model will decompose the target problem into multiple factors at different levels, analyze them layer by layer, quantify the uncertain factors, and use them to solve complex decision-making problems with multiple options.

[0139] ⑴ Establish a hierarchical model

[0140] First, determine the goal of the decision, identify and define the decision criteria, break down the complex decision problem into several smaller and more manageable parts, analyze the relationship between the elements, organize them into a clear hierarchy, and draw it into a clear hierarchy diagram;

[0141] ⑵Construct judgment matrix

[0142] Refer to the impact value selection standard to construct a pairwise comparison matrix and calculate the weight of the risk indicator under each dimension. The value selection standard is shown in Table 2:

[0143] Table 2 Impact value standards

[0144] Scale meaning 1 Both factors are equally important 3 One factor is slightly more important than the other 5 One factor is significantly more important than the other 7 One factor is more important than another 9 One factor is more important than another 2,4,6,8 Importance between odd numbers The reciprocal of the above numbers The values ​​obtained by reverse comparison

[0145] ⑶Consistency test

[0146] The pairwise comparison matrix is ​​the core of the entire analysis method. The elements in it are obtained by comparing two factors. In the process of pairwise comparison, since the evaluators have different knowledge backgrounds and experience reserves, their judgments cannot be completely consistent and there are evaluation errors. Therefore, before using this judgment to make a decision, it is necessary to perform a consistency test on the comparison judgment matrix. The specific steps are as follows.

[0147] First, the pairwise comparison matrices to be tested are listed, and then multiplied by their eigenvectors. The resulting matrix vector is called the weighted sum vector, and the indicators are calculated one by one according to the method.

[0148] Divide each weighted sum vector by the corresponding eigenvector component, and then find the maximum eigenroot λ max

[0149] Calculate the consistency index CI

[0150]

[0151] Find the corresponding average random consistency index RI, and the RI (degree of freedom index) values ​​are shown in Table 3.

[0152] Table 3 Random consistency index RI value

[0153] n 1 2 3 4 5 6 7 8 9 RI 0 0 0.58 0.9 1.12 1.24 1.32 1.41 1.45

[0154] The consistency ratio CR was calculated.

[0155]

[0156] When CR < 0.10, the consistency of the judgment matrix is ​​considered acceptable, then λ max The corresponding feature vector can be used as the weight vector for sorting.

[0157] ⑷ Find the weight of each standard

[0158] The weights are calculated using the square root method or the sum method. The square root method is to calculate the product of the elements in each row of the judgment matrix, then take the square root and normalize to get the weights; while the sum method is to first normalize each column of the judgment matrix, then sum the normalized matrix by row, and finally normalize the row sum to get the weights.

[0159] ⑸Calculate the score and make a decision

[0160] The calculated weights can be used in decision analysis to assist in risk assessment.

[0161] In real conditions, the specific weight ratios should be determined according to the actual situation of the marketing activities, and the weight ratios of the three dimensions should be determined.

[0162] The root-finding method was used to calculate the weight value and the maximum characteristic root of each indicator in the matrix, and the Delphi method was used to score, resulting in a judgment matrix as shown in Table 4.

[0163] Table 4 Target layer judgment matrix

[0164]

[0165] According to this method, the weight ratios of the three dimensions in risk judgment can be calculated, thereby achieving better judgment results in risk assessment.

[0166] Fuzzy comprehensive evaluation method is an evaluation method based on fuzzy mathematics theory, which can effectively deal with uncertainty and ambiguity problems in the evaluation process. This method transforms qualitative evaluation into quantitative analysis by constructing fuzzy sets and membership functions, so that the evaluation results are more in line with the actual situation. When conducting fuzzy comprehensive evaluation, it is first necessary to determine the evaluation factor set, which are the key indicators affecting the evaluation object. The evaluation factors can be multi-level, for example, a primary factor can contain multiple secondary factors, and so on. Then, according to the characteristics of the evaluation objectives and factors, the corresponding evaluation set is constructed, which represents the various levels or states of the evaluation results.

[0167] The determination of weights is one of the key steps in the fuzzy comprehensive evaluation method. The weights reflect the importance of each evaluation factor in the overall evaluation. The allocation of weights is usually determined based on expert experience, historical data analysis or related methods.

[0168] Then, it is necessary to construct a membership function, which describes the relationship between the evaluation factor value and the evaluation set. The membership function can be based on different mathematical forms or determined according to expert evaluation to express the degree to which the evaluation factor value reaches a certain evaluation level.

[0169] The specific general steps of the fuzzy comprehensive evaluation method are as follows:

[0170] Determine the evaluation factors: First, determine the various factors or indicators that need to be considered for the evaluation object. These factors may include quantitative indicators and qualitative indicators.

[0171] Constructing factor sets: Construct the determined evaluation factors into factor sets and express them in mathematical symbols, e.g.

[0172] U={u1,u2,...,u n}

[0173] where u i represents the i-th evaluation factor.

[0174] Determine the evaluation set: The evaluation set is the set of evaluation results, V = {v1,v2,...,v n} means, v j Indicates the level or category of the evaluation result.

[0175] Construct an evaluation matrix: Based on expert experience or actual data, construct a membership matrix R of each factor to each evaluation level, where r ij Indicator u i Evaluation level v j The degree of membership.

[0176] Determine the weight set: Determine the weight of each evaluation factor to form a weight set W = {w1, w2, ..., w n}, where w i Indicator u i The weight of .

[0177] Fuzzy synthesis: Through fuzzy comprehensive operation, the weight set and the evaluation matrix are synthesized to obtain the comprehensive membership of each evaluation level, that is, B = W × R.

[0178] Result analysis: According to the size of the comprehensive membership, the evaluation objects are sorted or classified to obtain the evaluation results.

[0179] Sensitivity analysis: Analyze the sensitivity of weights to test the stability and reliability of evaluation results

[0180] After completing the above steps, the weights are combined with the membership function through the fuzzy synthesis method to calculate the contribution of each factor to the comprehensive evaluation value, thereby obtaining a comprehensive evaluation result. The fuzzy comprehensive evaluation method not only provides a comprehensive evaluation value, but also gives the membership distribution of the evaluation results, which helps to deeply analyze the performance of the evaluation object at different levels.

[0181] Fuzzy comprehensive evaluation method is an effective tool for evaluation under uncertainty and fuzziness. Through the application of fuzzy mathematics, it allows qualitative evaluation criteria to be converted into quantitative analysis, so as to better deal with the uncertainty in the evaluation factors. This method can consider multiple influencing factors at the same time and comprehensively weight them to obtain a more comprehensive evaluation result. The membership function of the fuzzy comprehensive evaluation method can be customized according to different evaluation objectives, providing a flexible setting of factor weights in the evaluation process, so that the evaluation results are more in line with the actual situation. It not only provides a comprehensive evaluation value, but also provides the membership distribution of the evaluation results, which helps to deeply analyze the performance of the evaluation object at different levels. In addition, the fuzzy comprehensive evaluation method is easy to understand and apply, so that non-professionals can also better grasp the evaluation results. At the same time, it provides a scientific quantitative basis for decision makers when facing complex problems, helping them to make more reasonable decisions. The method has strong adaptability and can be widely used in many fields such as project management, risk assessment, policy analysis, etc., and can be easily adjusted and optimized when the evaluation model or conditions change. Especially in risk assessment, the fuzzy comprehensive evaluation method can identify and warn potential risk factors early, providing strong support for risk management.

[0182] According to the actual operation of the new energy charging operation platform, based on the processes of data collection, model building, and evaluation target decomposition, a marketing activity risk evaluation index system for the new energy charging operation platform is constructed, as shown in Table 5:

[0183] Table 5 Marketing activity risk assessment indicator system

[0184]

[0185]

[0186] In the present invention, the factor set is:

[0187] U={X 11 ,X 12 ,...,X 34}

[0188] The evaluation set is: V = {V1, V2, V3, V4} = {9, 5, 2, 0}

[0189] Among them: V1-normal, V2-low risk, V3-medium risk, V4-high risk, the specific judgment criteria are shown in Table 6:

[0190] Table 6 Risk Assessment Table

[0191] Risk Assessment Abnormal number of indicators normal 0 Low risk 1-2 Medium risk 2-5 High risk 5-9

[0192] The evaluation matrix is ​​constructed, and the membership matrix R of each factor to each evaluation level is artificially specified based on expert experience and actual data. Taking the present invention as an example, it is assumed that we have the following input values, as shown in Table 7:

[0193] Table 7 Variable input values

[0194]

[0195]

[0196] According to the calculation formula, the membership matrix can be calculated as:

[0197]

[0198] Each row in the matrix represents an indicator, each column represents an evaluation level, and each element represents the degree of membership of the corresponding indicator to the corresponding evaluation level. For example, 0.875 in the first row and first column means that the degree of membership of the first indicator to the "normal" evaluation level is 0.875.

[0199] Determine the weight of each factor to form a weight set W. Through fuzzy comprehensive operation, synthesize the weight set W and the evaluation matrix to obtain the comprehensive membership of each evaluation level, that is, B = W × R. According to the size of the final calculated comprehensive membership, the evaluation object, that is, the risk of the marketing activity, is evaluated.

[0200] Specifically, based on the overall assessment judgment rules, the overall risk of the marketing activities is judged and an assessment report containing all indicators and overall risk ratings is generated.

[0201] Based on in-depth analysis of market data and extensive consultation with experts, a series of comprehensive evaluation and judgment rules have been formulated to more accurately grasp the current situation and make corresponding decisions. The rules are summarized as follows:

[0202] Normal: When all monitoring indicators are stable within the established normal range and there are no abnormal fluctuations, they are characterized as normal, which means that all current operating indicators are performing well and no additional intervention is required;

[0203] Low risk: If no more than 2 indicators are found to be abnormal, but these abnormalities do not constitute any significant risk signs, it will be classified as a low risk state. Although the risk is low, it is recommended to continuously monitor these indicators to detect and deal with potential problems in a timely manner.

[0204] Medium risk: When 5 or fewer indicators are abnormal, it is marked as a medium risk state. This indicates that some problems have occurred that require close attention and appropriate actions must be taken to investigate the cause and develop a solution.

[0205] High risk: If more than 5 indicators show serious abnormalities at the same time, it will be immediately characterized as a high-risk state. This requires immediate emergency measures to respond quickly and mitigate potential negative impacts.

[0206] According to the above method, the simulation results are obtained, such as Figure 2 As shown, Figure 2 The simulation results of the risk assessment model constructed by the patent are presented. The simulation results show that the model proposed in this paper exhibits high adaptability and accuracy in simulating various risk scenarios.

[0207] 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 the 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 new energy charging operation platform analysis method, characterized in that: include: Acquire new energy charging related data, and establish a marketing activity analysis model based on the new energy charging related data; Analyzing and evaluating the risk of marketing activities using the marketing activity analysis model, including: constructing risk indicators, and performing risk aggregation and calculation on the risk indicators; Based on the overall assessment judgment rules, the risk indicators are merged and the calculation results are judged to generate an assessment report containing all risk indicators and overall risk ratings.

2. The new energy charging operation platform analysis method according to claim 1, characterized in that: The risk indicators include the risk of excessive superposition of activity discounts, the risk of activity budget overspending, the risk of capital loss, an excessively high proportion of discount amounts, a decrease in the proportion of new customers, negative growth in ROI, abnormal changes in marketing payment amounts, low conversion rates and high fluctuations in average order value.

3. The new energy charging operation platform analysis method according to claim 1 or 2, characterized in that: The risk aggregation of the risk indicators includes: The risks of marketing activities are aggregated and evaluated according to the prescribed risk assessment rules, forming a comprehensive assessment of the three dimensions of capital loss risk, new customer acquisition ability and profitability; The risk of capital loss includes excessive superposition of promotional offers, overspending of promotional budgets, risk of capital loss, and excessively high promotional ratios; The ability to attract new customers, including the proportion of new customers, has decreased; Profitability includes negative ROI growth, abnormal fluctuations in marketing payment amounts, low conversion rates and high fluctuations in average order value.

4. The new energy charging operation platform analysis method according to claim 3, characterized in that: The risk calculation for the risk indicator includes: Based on the risk indicator merging result, corresponding weights are set, and the risk indicator value is calculated using a fuzzy comprehensive evaluation method. Whether the risk indicator is abnormal is determined based on the risk indicator value.

5. The new energy charging operation platform analysis method according to claim 4, characterized in that: According to the overall assessment judgment rules, the risk indicators are combined and the calculation results are judged to generate an assessment report containing all risk indicators and overall risk ratings, including: The abnormal number of risk indicators of the overall assessment determination rule is divided into four levels, including normal, low risk, medium risk and high risk; When all indicators are within the normal range and there are no abnormalities, it is judged as normal; When no more than 2 risk indicators show abnormalities, it is judged as low risk; When no more than 5 risk indicators show abnormalities, it is judged as medium risk; When more than 5 risk indicators show abnormalities, it is judged as high risk.

6. The new energy charging operation platform analysis method according to claim 5, characterized in that: Risk indicators include: A risk identification module and real-time early warning mechanism are established based on risk indicators to provide real-time early warning for various risks arising from marketing activities.

7. The new energy charging operation platform analysis method according to claim 1, characterized in that: New energy charging related data include: After obtaining the data related to new energy charging, the data is preprocessed and feature screened, and the correlation analysis method is used to identify the feature data set required for the prediction of the marketing activity analysis model.

8. A system for analyzing a new energy charging operation platform, characterized in that: include, Data acquisition module, used to obtain new energy charging related data; A model building module, used to build a marketing activity analysis model based on the new energy charging related data; An indicator determination and analysis module is used to construct risk indicators and perform risk aggregation and calculation on the risk indicators; The risk assessment module is used to determine the aggregation and calculation results of risk indicators based on the overall assessment judgment rules, and generate an assessment report containing all risk indicators and overall risk ratings.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the new energy charging operation platform analysis method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the new energy charging operation platform analysis method described in any one of claims 1 to 7.

Images