A multi-scene service data calling requirement analysis method
By conducting correlation analysis on four categories of vehicle service data, the shortcomings of traditional technologies in data retrieval demand analysis have been addressed, enabling more scientific service plan development and marketing effectiveness, thereby improving customer satisfaction and corporate competitiveness.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- QINGMIN DIGITAL TECHNOLOGY (QINGDAO) TECHNOLOGY SERVICE CO LTD
- Filing Date
- 2026-02-27
- Publication Date
- 2026-06-02
AI Technical Summary
Traditional technologies lack analysis of the interrelationships and the strength of the correlation between data scope requirements in different scenarios, resulting in a low degree of personalization in service solutions and reduced customer service satisfaction.
By classifying the data requirements for vehicle services into four categories, analyzing the correlation and changing trends between different categories of information, and comprehensively obtaining the correlation decision weight value and weight influence coefficient, personalized service plans and promotion strategies are formulated.
This improved the scientific nature of our service solutions and enhanced customer satisfaction, allowing us to accurately understand market demands, strengthen our competitiveness, and meet the diverse needs of different customers.
Smart Images
Figure CN122134008A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of service data invocation technology, and in particular to a method for analyzing service data invocation requirements in multiple scenarios. Background Technology
[0002] By analyzing data retrieval requirements in different scenarios, we can identify each stage of vehicle services. For example, in a vehicle repair scenario, we can understand what data support is needed for each step, from scheduling repairs, vehicle inspection upon arrival at the workshop, fault diagnosis, parts replacement, to delivery after repair completion. This clarifies the data inputs and outputs for each stage, allowing for the redesign or optimization of the service process, reducing unnecessary steps, and improving service efficiency.
[0003] In traditional technologies, data retrieval requirements for different scenarios are often analyzed by directly matching and combining the required data for each scenario. However, no further analysis is done on the interrelationships between the required data ranges or the impact of changes in different scenarios on the strength of the correlation between the various related data ranges. This can easily lead to a lack of personalization in the service solutions developed based on the final data retrieval analysis, resulting in a lower degree of optimization and reduced customer satisfaction. Summary of the Invention
[0004] To overcome the shortcomings of the existing technology, this application provides a method for analyzing service data call requirements in multiple scenarios.
[0005] This application provides a method for analyzing service data invocation requirements across multiple scenarios, the method comprising: S1. Statistically analyze the three categories of data requirements for vehicle services: basic information of vehicle owners, vehicle information, and service record information. Obtain the first category information 1, the first category information 2, and the first category information 3. Based on the service decision correlation trend characteristics among the first category information 1 and the first category information 2, the first category information 1 and the first category information 3, and the first category information 2 and the first category information 3 in the historical service demand data, comprehensively obtain the correlation decision weight value that affects the formulation of vehicle service plans. S2, classify the scenario-wide demand information into market research, customer service, marketing promotion and after-sales service information categories to obtain second category information one, second category information two, second category information three and second category information four. Based on the trend characteristics of the correlation influence between second category information one and the associated decision weight value in the historical scenario statistical demand data, obtain the first category weight influence coefficient. Based on the first category weight influence coefficient and the associated decision weight value, determine the positioning and promotion area of the new model and output the first demand analysis result. S3. Based on the trend characteristics of the correlation influence between the second category information three and the associated decision weight value in the historical scenario statistical demand data, the second category weight influence coefficient is obtained. Based on the second category weight influence coefficient and the associated decision weight value, a service promotion plan is formulated, and the second demand analysis result is output. Based on the first category information three, the personalized service plan belonging to the second category information two and the customer vehicle repair demand information belonging to the second category information four are formulated, and the third demand analysis result and the fourth demand analysis result are obtained.
[0006] Preferably, the data scope requirements for vehicle services are categorized into vehicle owner basic information, vehicle information, and service record information to obtain first category information one, first category information two, and first category information three; Obtain historical demand service data, and based on the correlation and change trend characteristics between the first category information one and the first category information two in the historical demand service data, calculate the synchronous change amplitude ratio between the first category information one and the first category information two to obtain the correlation reference value one. Based on historical demand service data and the first associated reference value, we obtain the second associated reference value to which the first category information 1 and the first category information 3 belong, and the third associated reference value to which the first category information 2 and the first category information 3 belong.
[0007] Preferably, the first, second, and third associated reference values are summed to obtain the comprehensive reference value to be measured; The correlation reference value 1, correlation reference value 2, and correlation reference value 3 are compared with the comprehensive reference value to be measured to obtain the correlation decision weight value that affects the formulation of vehicle service plan.
[0008] Preferably, the information on the demand for vehicle services in different scenarios is categorized into market research, customer service, marketing promotion, and after-sales service information to obtain second category information one, second category information two, second category information three, and second category information four. Acquire historical scene statistical requirement data, and statistically analyze the changes in customer age range and geographical distribution area in the second category of information one in the historical scene statistical requirement data during different adjacent historical periods to obtain the first feature variation data to be tested. The changes in decision weight values of each category of information in the second category of information in the scenario requirement are statistically analyzed in different adjacent historical periods to obtain the data one of the changes in the decision weight influence of the target decision. Based on the correlation and change trend characteristics between the measured feature amplitude data one and the measured decision weight influence amplitude data one, the first type of weight influence coefficient is obtained.
[0009] Preferably, based on the variable amplitude data of the feature to be measured, the variable amplitude data of the current feature to which the second category information belongs in the current period is statistically analyzed; Based on the first type of weight influence coefficient, the current feature amplitude data one, and the associated decision weight value, the associated decision weight value is compensated for the weight amplitude to obtain the actual decision weight value one. Based on the actual decision weight value, the market preference demand information of the second category of information is obtained. Based on the market preference and demand information, determine the positioning and promotion area of the new model, and output the first demand analysis results.
[0010] Preferably, the changes in customer consumption preference items and purchase data in the second category of information three in the historical scenario statistical demand data are statistically analyzed in different adjacent historical periods to obtain the second feature variation data to be tested. Based on the measured feature amplitude data 2 and the first type of weight influence coefficient, the second type of weight influence coefficient to which the second type of information 2 belongs is obtained; Based on the second feature amplitude data to be measured, the second category of information three is statistically analyzed to determine the current feature amplitude data to which the current feature amplitude data belongs in the current period; Based on the second type of weight influence coefficient, the current feature amplitude data 2, and the associated decision weight value, the associated decision weight value is compensated for the weight amplitude to obtain the actual decision weight value 2. Based on the actual decision weight value two, the customer demand information one to which the second category information three belongs is obtained. Customer demand information one refers to the demand information of customers' preference for high-consumption or low-consumption behavior. Based on the first customer demand information, a service promotion plan is developed, and the second demand analysis result is output.
[0011] Preferably, based on the first category of information three, the second category of information two, which belongs to the customer demand information two, refers to the customer preference consultation or feedback experience demand information; Based on the second customer demand information, a personalized service plan is developed, resulting in the third demand analysis result. Based on information in category 3, compile statistics on customer vehicle repair needs belonging to information in category 4 of category 2; Based on the customer's vehicle repair needs information, a repair reminder service plan is developed, resulting in the fourth demand analysis result.
[0012] Compared with the prior art, the present invention has the following characteristics and beneficial effects: By categorizing vehicle service demand data into four types, subsequent analysis of the correlation characteristics between these categories is facilitated. Specifically, based on the changing trends in service decision-making correlations across different categories of historical demand data, a comprehensive weight value for the correlation decision influencing vehicle service plan formulation is derived. This allows for a more accurate grasp of the importance of each factor when developing vehicle service plans, avoiding the one-sided influence of a single factor, thus leading to more scientific and reasonable service plans that better align with customer satisfaction. Through the classification of scenario-based demand information and the analysis of historical scenario statistical demand data, a first-category weight influence coefficient is obtained. This, combined with the correlation decision weight value, determines the positioning and promotion area of new vehicle models. This data-driven approach enables companies to more accurately understand market demand, promote new models to the most likely acceptance areas, and improve marketing effectiveness. Based on different customer demand information, such as customer preferences for high- or low-consumption behavior (related to the second-category weight influence coefficient), customer preferences for consultation or feedback experience (related to the first-category information), and customer vehicle maintenance needs, service promotion plans, personalized service plans, and maintenance reminder service plans are formulated respectively. This can meet the diverse needs of different customers, improve customer satisfaction, and enhance the company's competitiveness. Attached Figure Description
[0013] Figure 1 This is a flowchart illustrating the steps of a multi-scenario service data call requirement analysis method, which is the main feature of this embodiment. Detailed Implementation
[0014] The present invention will be further described in detail below with reference to the following embodiments.
[0015] Reference Figure 1 A method for analyzing service data invocation requirements across multiple scenarios, comprising the following steps: S1. Statistically analyze the three categories of data requirements for vehicle services: basic information of vehicle owners, vehicle information, and service record information, to obtain Category 1 Information 1, Category 2 Information 2, and Category 3 Information 3. Based on the changing trend characteristics of service decision associations between Category 1 Information 1 and Category 2 Information 2, Category 1 Information 1 and Category 3 Information 3, and Category 2 Information 1 and Category 3 Information 3 in historical service demand data, comprehensively obtain the association decision weight values that influence the formulation of vehicle service plans.
[0016] S2 categorizes the scenario-wide demand information into market research, customer service, marketing promotion, and after-sales service information categories, resulting in second category information one, second category information two, second category information three, and second category information four. Based on the trend characteristics of the correlation influence between second category information one and the associated decision weight value in historical scenario statistical demand data, the first category weight influence coefficient is obtained. Based on the first category weight influence coefficient and the associated decision weight value, the positioning and promotion area of the new model is determined, and the first demand analysis result is output.
[0017] S3. Based on the trend characteristics of the correlation influence between the second category of information three and the associated decision weight value in the historical scenario statistical demand data, the second category weight influence coefficient is obtained. Based on the second category weight influence coefficient and the associated decision weight value, a service promotion plan is formulated, and the second demand analysis result is output. Based on the first category of information three, the personalized service plan belonging to the second category of information two and the customer vehicle repair demand information belonging to the second category of information four are formulated, and the third demand analysis result and the fourth demand analysis result are obtained.
[0018] Specifically, by categorizing vehicle service demand data into four types, subsequent analysis of the correlation characteristics between these categories can be conducted. This involves comprehensively determining the correlation weights influencing vehicle service plan development based on the changing trends of service decision-making relationships between different categories of historical demand data. This allows for a more accurate grasp of the importance of each factor when developing vehicle service plans, avoiding the one-sided influence of a single factor, thus leading to more scientific and reasonable service plans that better align with customer satisfaction. By classifying scenario-based demand information and analyzing historical scenario statistical demand data, a first-category weight influence coefficient is obtained. This, combined with the correlation decision weight values, determines the positioning and promotion areas for new vehicle models. This data-driven approach enables companies to more accurately understand market demand, push new models to the most likely acceptance areas, and improve marketing effectiveness. Based on different customer demand information, such as customer preferences for high- or low-consumption behavior (related to the second-category weight influence coefficient), customer preferences for consultation or feedback experience (related to the first-category information), and customer vehicle maintenance needs, service promotion plans, personalized service plans, and maintenance reminder service plans can be developed respectively. This can meet the diverse needs of different customers, improve customer satisfaction, and enhance the company's competitiveness.
[0019] The specific step S1 includes the following sub-steps: The data scope requirements for vehicle services are categorized into vehicle owner basic information, vehicle information, and service record information, resulting in Category I Information 1, Category II Information 2, and Category III Information 3.
[0020] Obtain historical demand service data, and based on the correlation and change trend characteristics between the first category information 1 and the first category information 2 in the historical demand service data, calculate the synchronous change ratio between the first category information 1 and the first category information 2 to obtain the correlation reference value 1.
[0021] Based on historical demand service data and the first associated reference value, we obtain the second associated reference value to which the first category information 1 and the first category information 3 belong, and the third associated reference value to which the first category information 2 and the first category information 3 belong.
[0022] The summation of the first, second, and third related reference values yields the comprehensive reference value to be measured.
[0023] The correlation reference value 1, correlation reference value 2, and correlation reference value 3 are compared with the comprehensive reference value to be measured to obtain the correlation decision weight value that affects the formulation of vehicle service plan.
[0024] Specifically, data storage processing is required before data retrieval requirements analysis. This includes data anonymization (which involves modifying sensitive information while preserving its format and structure to prevent leakage of personal privacy or trade secrets in non-production environments or when shared externally. Common anonymization methods include replacement, masking, encryption, and randomization). Multiple data anonymization algorithms (such as hash function families, symmetric encryption algorithms, and asymmetric encryption algorithms) can be used to employ appropriate anonymization methods for different types of data (such as names, ID numbers, and license plate numbers). This ensures that the anonymized data is irreversible and retains business relevance. The anonymization rules and degree can be flexibly adjusted according to business scenarios and security levels. For example, in market research scenarios, some key information can be appropriately retained for analysis; when sharing data externally, deep anonymization should be performed. For instance, in a market research analysis scenario, the goal is to support trend analysis without exposing individuals, and the anonymization level is moderate. An example would be retaining gender, age group, and spending level, but hiding ID numbers and precise addresses; data storage: build a secure and reliable distributed data storage architecture with high availability and disaster recovery capabilities to ensure that data is not lost or damaged (e.g., client layer - API gateway - application server cluster - distributed file system - NoSQL database - relational database - backup and recovery system). The anonymized data should be categorized and stored for easy subsequent querying and management. For example, data can be categorized according to owner information, vehicle information, and service records; Data retrieval (the following section describes the analysis and processing of data retrieval): Multiple data retrieval interfaces are provided to support different business systems of B-end enterprises (such as CRM systems, marketing systems, after-sales service systems, etc.) to retrieve anonymized data on demand. Access control for data retrieval is implemented, allocating different data access permissions based on user roles and business needs to ensure data security. Data retrieval can respond quickly to meet business needs in high-concurrency scenarios; Security audit: All data anonymization, storage, and retrieval operations are recorded, including operation time, operator, and operation content. Regular security audit reports are generated to facilitate security monitoring and compliance review for enterprises.Basic vehicle owner information, such as name, contact information (phone, email, etc.), and ID number; vehicle information, such as license plate number, vehicle identification number (VIN), vehicle model, vehicle color, purchase price, and purchase date; service records, such as maintenance and repair records (time, items, and costs); insurance records (insurance type, coverage amount, and claims status); traffic violation records; historical service demand data (including the vehicle owner's age, gender, occupation, and other basic information, as well as the vehicle's brand, model, purchase date, and maintenance history); and a first correlation reference value (e.g., calculated using Pearson correlation coefficient, Spearman rank correlation coefficient, or regression analysis; for example, focusing on two variables: vehicle owner age and vehicle purchase price, with vehicle owners A, B, C, D, and E, and ages 30, 45, 60, and 40 respectively). 0, 50; vehicle purchase price: 20, 35, 15, 30, 40 (in ten thousand yuan). Calculate the correlation coefficient between these two variables. If using the Pearson correlation coefficient, a value between -1 and 1 will be obtained, representing the degree of linear correlation between the two variables. A positive value close to 1 indicates a strong positive correlation, a negative value close to -1 indicates a strong negative correlation, and a value close to 0 indicates almost no linear relationship. The obtained correlation coefficient is the first correlation reference value. The second correlation reference value belongs to the first category of information one and the first category of information three, and the third correlation reference value belongs to the first category of information two and the first category of information three (based on the first correlation reference value, and so on). The correlation decision weight value affecting the vehicle service plan formulation (used to measure the relative importance of each factor in the final decision).
[0025] The specific step S2 includes the following sub-steps: The information on the demand for vehicle services is categorized into market research, customer service, marketing promotion, and after-sales service, resulting in two categories: Category 1, Category 2, Category 3, and Category 4.
[0026] Obtain historical scene statistical requirement data, and statistically analyze the changes in customer age range and geographical distribution area in the second category of information in the historical scene statistical requirement data during different adjacent historical periods to obtain the first feature variation data to be tested.
[0027] The changes in decision weight values of each category of information in the second category of information requirement scenario are statistically analyzed in different adjacent historical periods to obtain the data one of the changes in the influence of the decision weight to be measured.
[0028] Based on the correlation and change trend characteristics between the variable amplitude data of the feature to be measured and the variable amplitude data of the decision weight to be measured, the first type of weight influence coefficient is obtained.
[0029] Based on the variable amplitude data of the feature to be measured, the variable amplitude data of the current feature to which the second category information belongs in the current period is statistically analyzed.
[0030] Based on the first type of weight influence coefficient, the current feature amplitude data one, and the associated decision weight value, the associated decision weight value is compensated for the weight amplitude to obtain the actual decision weight value one.
[0031] Based on the actual decision weight value, the market preference demand information of the second category of information is obtained.
[0032] Based on market preference and demand information, determine the positioning and promotion area of the new model, and output the first demand analysis results.
[0033] Specifically, this could include historical scenario statistical demand data (including data on age, geographic distribution, historical service records, consumption habits, purchasing power, vehicle maintenance records, etc.), and the variation data of the features to be measured (e.g., in historical period t1, age segments are divided into n1 and n2, the number of customers is r1 and r2, and the regional coverage area is m1 and m2; in the adjacent historical period t2, age segments are divided into n3 and n4, the number of customers is r3 and r4, and the regional coverage area is m3 and m4; the increase or decrease in customer age segments = (number of customers in t2 - number of customers in t1) / number of customers in t1; the increase or decrease in geographic distribution area = (area in t2 - area in t1) / area in t1; n1: if the increase in the number of customers = (r3 - r1) / r1, n2 and so on). Following this logic, if the area increase = (m3-m1) / m1, and so on, we can average the customer increase and area increase for n1 and n2 respectively to obtain z1 and z2. Averaging z1 and z2 gives us the first variable data of the feature to be tested. The decision weight value refers to the importance or influence of each category of information on the decision in a specific period. The first variable data of the influence of the decision weight to be tested is (for example, in period q1, the weight of "car owner age" on the car purchase decision may be 0.3, while the weight of "repair frequency" may be 0.5; in period q2, the weight of "car owner age" on the car purchase decision may be 0.4, while the weight of "repair frequency" may be 0.4. Therefore, the variable data of the influence of the decision weight of car owner age is 0.4-0.1=0).1. Following this pattern, we obtain the following: (1) the influence amplitude data of the decision weight to be tested; (2) the first type of weight influence coefficient (e.g., by plotting the trend curve of the correlation influence of the influence amplitude data of the decision weight to be tested and the first type of feature amplitude data of the decision weight to be tested), (3) the current feature amplitude data of the decision weight to be tested (i.e., obtained by comparing and statistically analyzing the data with the most recent historical period, and so on), (4) the actual decision weight value of the decision weight of the decision weight to be tested (e.g., actual decision weight value of the decision weight of the decision weight of the decision weight to be tested = (current feature amplitude data of the decision weight to be tested / first type of weight influence coefficient) + correlation decision weight value), and (5) market preference demand information. For example, Category 1 information directly impacts purchasing power and vehicle usage scenarios (weighted at 30%); Category 1 information reflects current user consumption upgrade or downgrade trends (weighted at 40%); and Category 1 information reveals user sensitivity to features (e.g., reliability is more important than configuration). For instance, a survey found that among men aged 30-40, 70% currently drive joint-venture brand gasoline vehicles, but they have frequently inquired about the range and charging infrastructure of plug-in hybrid vehicles in the past six months; simultaneously, their vehicles have had an average of twice the industry average number of repairs in the past year (mainly engine failures). The high proportion of "males aged 30-40" in "Basic Owner Information" indicates that this group's needs are amplified. "Switching from gasoline vehicles to plug-in hybrids" falls under the "Vehicle Information" category for replacement needs, with a weight of 40%. "Reliability concerns due to high repair rates" corresponds to a pain point in "Service Records," with a weight of 30%. Therefore, the core needs of this group are "gasoline and electric compatibility without range anxiety + low failure rate for peace of mind," meaning the mainstream demand is "reliable long-range new energy vehicles." This demand is then grounded in "people" and "places": age group (monetization characteristics: primarily 30-40 years old (first-time or additional purchase decision-makers in families)), leading to the following promotional strategies (emphasizing practicality and space). (Child seat interface), intelligent configuration (voice control for convenient childcare), geographical distribution (variable characteristics: 65% in third-tier cities and below), derived promotion strategies (low charging pile coverage in these areas - primarily promoting plug-in hybrids rather than pure electric vehicles; low average local wages - pricing below 200,000 RMB; battery insulation technology a selling point in cold winters)), primary demand analysis results (e.g., the four-quadrant rule for vehicle positioning: horizontal axis = price range (150,000-200,000 RMB), vertical axis = product strength emphasis (family comfort over performance and handling), promotion areas: key cities - Weifang, Linyi, Handan (third- and fourth-tier cities with high per capita GDP + substantial new energy vehicle policy subsidies)).
[0034] The specific step S3 includes the following sub-steps: The changes in customer consumption preferences and purchase data in the second category of information three in the historical scenario statistical data are statistically analyzed in different adjacent historical periods to obtain the second feature variation data.
[0035] Based on the second variable data of the feature to be tested and the first type of weight influence coefficient, the second type of weight influence coefficient of the second type of information is obtained.
[0036] Based on the variable amplitude data of the feature to be measured, the variable amplitude data of the current feature to which the second category of information three belongs in the current period is statistically analyzed.
[0037] Based on the second type of weight influence coefficient, the current feature amplitude data 2, and the associated decision weight value, the associated decision weight value is compensated for the weight amplitude to obtain the actual decision weight value 2.
[0038] Based on the actual decision weight value two, we obtain the customer demand information one belonging to the second category information three. Customer demand information one refers to the demand information regarding customer preferences for high-consumption or low-consumption behavior.
[0039] Based on the first customer requirement, develop a service promotion plan and output the second requirement analysis results.
[0040] Based on the first category of information three, the second category of information two, which belongs to the customer demand information two, refers to the customer preference information regarding consultation or feedback experience.
[0041] Based on the second set of customer needs information, a personalized service plan was developed, resulting in the third set of needs analysis results.
[0042] Based on information in category 3 of the first category, the customer vehicle repair needs information belonging to information in category 4 of the second category is statistically analyzed.
[0043] Based on the customer's vehicle repair needs, a repair reminder service plan is developed, resulting in the fourth requirement analysis.
[0044] Specifically, consider the following: Data on the variation of the feature to be measured (e.g., two time points T1 and T2; assuming the consumption (or purchase amount) of a certain item is C1 at T1 and C2 at T2, with a change in amplitude of (C2-C1) / C1; performing the above calculation on all relevant items, then synthesizing an overall variation data, and finally averaging to obtain the second data on the variation of the feature to be measured), the second type of weight influence coefficient, the second data on the variation of the current feature, the second actual decision weight value (based on the first type of weight influence coefficient, the first data on the variation of the feature to be measured, and the first actual decision weight value, and so on), and customer demand information (the second actual decision weight value reflects the impact of different data dimensions on the judgment of "customer consumption"). The importance of "preferences" can be assessed, for example, by weighting vehicle brand or model (30%), average past maintenance / repair costs (25%), estimated owner occupation / income level (20%), high-end service history (15%), and other factors (e.g., vehicle age, mileage) (10%). This indicates whether the customer is a "high-spending preference" or a "low-spending preference" customer. For example, a high-spending preference might be characterized by: driving a new car from a BBA (Mercedes-Benz, BMW, Audi) or higher brand; consistently choosing the highest-priced maintenance package from the 4S dealership; frequently upgrading to high-end audio systems or making modifications; being insensitive to price; and prioritizing quality and service experience. This suggests the customer's needs may include higher demands for vehicle performance, comfort, and technological features. The first requirement is a desire for a personalized and premium service experience, an interest in the latest automotive technology and high-end maintenance products, and a potential need to upgrade to a higher-end vehicle. The second requirement analysis result (the service promotion plan could include: high-end customized maintenance packages, seasonal or themed high-end accessories or upgrade recommendations, exclusive member activities or experience invitations, used car trade-in or new car pre-purchase discounts, and one-on-one dedicated consultant services). The third requirement is customer demand information (such as extracting information related to "preferences" or "experiences" from service records like customer reviews, complaints, praise, and follow-up recordings, categorizing it as "demand information two"). For example, if a car owner previously reported uncomfortable seats, information could be extracted based on the specific needs of different customers. Features and customized service actions: For example, customer service representatives can proactively inquire about relevant situations during subsequent communications. Customer vehicle repair needs information (such as repair and maintenance records in Category 1, Information 3: repair records (repair date, fault description, repair items, replaced parts, etc.), maintenance records (maintenance cycle, maintenance content, etc.). Repair records are categorized according to fault type, such as engine faults, braking system faults, electrical system faults, etc.; they can also be differentiated based on repair frequency and urgency, such as routine maintenance needs and emergency fault repair needs. This categorization allows for a clearer understanding of the customer's vehicle repair needs. Statistical methods are used to analyze various types of repair need information.For example, calculating the frequency of different fault types to determine which faults are more common; analyzing the distribution of repair costs to understand the approximate cost of different repair items; and also calculating the length of repair time to evaluate repair efficiency, etc. The fourth requirement analysis result (based on vehicle usage and past maintenance records, developing personalized maintenance reminder plans. For example, for vehicles frequently driven in harsh road conditions (such as gravel roads, muddy roads, etc.), because their chassis components wear relatively quickly, the reminder interval for chassis inspection and related component replacement can be appropriately shortened based on the normal maintenance cycle. When the vehicle's mileage approaches the set reminder threshold, the owner is promptly notified via SMS, telephone, or mobile application that chassis maintenance is required, including checking the suspension system, brake pad thickness, tire wear, etc., and cleaning and rustproofing the chassis to ensure safe vehicle operation).
[0045] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.
Claims
1. A method for analyzing service data invocation requirements across multiple scenarios, characterized in that, Includes the following steps: S1. Statistically analyze the three categories of data requirements for vehicle services: basic information of vehicle owners, vehicle information, and service record information. Obtain the first category information 1, the first category information 2, and the first category information 3. Based on the service decision correlation trend characteristics among the first category information 1 and the first category information 2, the first category information 1 and the first category information 3, and the first category information 2 and the first category information 3 in the historical service demand data, comprehensively obtain the correlation decision weight value that affects the formulation of vehicle service plans. S2, classify the scenario-wide demand information into market research, customer service, marketing promotion and after-sales service information categories to obtain second category information one, second category information two, second category information three and second category information four. Based on the trend characteristics of the correlation influence between second category information one and the associated decision weight value in the historical scenario statistical demand data, obtain the first category weight influence coefficient. Based on the first category weight influence coefficient and the associated decision weight value, determine the positioning and promotion area of the new model and output the first demand analysis result. S3. Based on the trend characteristics of the correlation influence between the second category information three and the associated decision weight value in the historical scenario statistical demand data, the second category weight influence coefficient is obtained. Based on the second category weight influence coefficient and the associated decision weight value, a service promotion plan is formulated, and the second demand analysis result is output. Based on the first category information three, the personalized service plan belonging to the second category information two and the customer vehicle repair demand information belonging to the second category information four are formulated, and the third demand analysis result and the fourth demand analysis result are obtained.
2. The multi-scenario service data call demand analysis method according to claim 1, characterized in that, Step S1 includes: The data scope requirements for vehicle services are categorized into vehicle owner basic information, vehicle information, and service record information, resulting in Category 1 Information 1, Category 2 Information 2, and Category 3 Information 3. Obtain historical demand service data, and based on the correlation and change trend characteristics between the first category information one and the first category information two in the historical demand service data, calculate the synchronous change amplitude ratio between the first category information one and the first category information two to obtain the correlation reference value one. Based on historical demand service data and the first associated reference value, we obtain the second associated reference value to which the first category information 1 and the first category information 3 belong, and the third associated reference value to which the first category information 2 and the first category information 3 belong.
3. The multi-scenario service data call demand analysis method according to claim 2, characterized in that, Step S1 also includes: The first, second, and third associated reference values are summed to obtain the comprehensive reference value to be measured. The correlation reference value 1, correlation reference value 2, and correlation reference value 3 are compared with the comprehensive reference value to be measured to obtain the correlation decision weight value that affects the formulation of vehicle service plan.
4. The multi-scenario service data call demand analysis method according to claim 3, characterized in that, Step S2 includes: The information on the demand for vehicle services is categorized into market research, customer service, marketing promotion, and after-sales service, resulting in two categories: Category 1, Category 2, Category 3, and Category 4. Acquire historical scene statistical requirement data, and statistically analyze the changes in customer age range and geographical distribution area in the second category of information one in the historical scene statistical requirement data during different adjacent historical periods to obtain the first feature variation data to be tested. The changes in decision weight values of each category of information in the second category of information in the scenario requirement are statistically analyzed in different adjacent historical periods to obtain the data one of the changes in the decision weight influence of the target decision. Based on the correlation and change trend characteristics between the measured feature amplitude data one and the measured decision weight influence amplitude data one, the first type of weight influence coefficient is obtained.
5. The multi-scenario service data call demand analysis method according to claim 4, characterized in that, Step S2 also includes: Based on the variable amplitude data of the feature to be measured, the variable amplitude data of the current feature to which the second category information belongs in the current period is statistically analyzed. Based on the first type of weight influence coefficient, the current feature amplitude data one, and the associated decision weight value, the associated decision weight value is compensated for the weight amplitude to obtain the actual decision weight value one. Based on the actual decision weight value, the market preference demand information of the second category of information is obtained. Based on the market preference and demand information, determine the positioning and promotion area of the new model, and output the first demand analysis results.
6. The multi-scenario service data call demand analysis method according to claim 5, characterized in that, Step S3 includes: The statistical data of the second category of information three in the historical scenario statistical requirements data is statistically analyzed to obtain the amplitude of the change in customer consumption preference items and purchase data in different adjacent historical periods, and the combined data is used to obtain the second feature amplitude data to be tested. Based on the measured feature amplitude data 2 and the first type of weight influence coefficient, the second type of weight influence coefficient to which the second type of information 2 belongs is obtained; Based on the second feature amplitude data to be measured, the second category of information three is statistically analyzed to determine the current feature amplitude data to which the current feature amplitude data belongs in the current period; Based on the second type of weight influence coefficient, the current feature amplitude data 2, and the associated decision weight value, the associated decision weight value is compensated for the weight amplitude to obtain the actual decision weight value 2. Based on the actual decision weight value two, the customer demand information one to which the second category information three belongs is obtained. Customer demand information one refers to the demand information of customers' preference for high-consumption or low-consumption behavior. Based on the first customer demand information, a service promotion plan is developed, and the second demand analysis result is output.
7. The multi-scenario service data call demand analysis method according to claim 6, characterized in that, Step S3 also includes: Based on the first category of information three, the second category of information two, which belongs to the second category of customer demand information two, refers to customer preference information regarding consultation or feedback experience. Based on the second customer demand information, a personalized service plan is developed, resulting in the third demand analysis result. Based on information in category 3, compile statistics on customer vehicle repair needs belonging to information in category 4 of category 2; Based on the customer's vehicle repair needs information, a repair reminder service plan is developed, resulting in the fourth demand analysis result.