Vehicle-mounted service recommendation method, device and equipment

Abstract

The application relates to the technical field of Internet of Vehicles services, in particular to a vehicle-mounted service recommendation method, device and equipment, wherein the method comprises the following steps: obtaining user behavior data, vehicle state data and battery degradation data; predicting a battery degradation trajectory according to the user behavior data, the vehicle state data and the battery degradation data; calculating a service cost trajectory of the vehicle according to the battery degradation trajectory, calculating consumption degradation feedback data of a vehicle-mounted service according to an influence vector of the battery degradation trajectory on the vehicle-mounted service and a service effect attenuation value; calculating a service pricing sequence according to the vehicle degradation trajectory, the service cost trajectory and the consumption degradation feedback data; and generating a recommendation list of the vehicle-mounted service according to the battery degradation trajectory and the service pricing sequence. Therefore, the problems in the related art, such as pricing of value-added services based on user data, vehicle state data or market information, price adjustment only according to existing data and mismatch between pricing results and actual user demand, are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle networking service technology, specifically to a method, apparatus, and device for recommending in-vehicle services. Background Technology

[0002] Precise pricing and intelligent recommendations for in-vehicle value-added services can enhance user experience and user stickiness, thereby increasing the commercial value of automakers' service ecosystem. Therefore, researching dynamic pricing and recommendation technologies for in-vehicle value-added services throughout the entire vehicle lifecycle is of great significance. Currently, related technologies mainly adjust value-added service prices based on user data, vehicle status data, or market information. However, this method only adjusts prices based on existing data at the current state, resulting in insufficient matching between the pricing results and actual user needs. Summary of the Invention

[0003] This application provides a method, apparatus, and device for recommending in-vehicle services, in order to solve the problems of poor accuracy in in-vehicle service recommendations caused by price adjustments based on existing data, which result in pricing that does not match the actual needs of users.

[0004] The first aspect of this application provides a method for recommending in-vehicle services, the method comprising the following steps: acquiring user behavior data, vehicle status data, and battery degradation data; predicting a battery degradation trajectory based on the user behavior data, vehicle status data, and battery degradation data; calculating a service cost trajectory for the vehicle based on the battery degradation trajectory; calculating consumption degradation feedback data for the in-vehicle services based on the influence vector of the in-vehicle services on the battery degradation trajectory and the service effect attenuation value; calculating a service pricing sequence based on the vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data; and generating a recommended list of in-vehicle services based on the battery degradation trajectory and the service pricing sequence.

[0005] Based on the aforementioned technical means, this application acquires user behavior data, vehicle status data, and battery degradation data, and predicts battery degradation trajectories based on multi-source data, enabling dynamic perception of future vehicle performance trends. Furthermore, it calculates service cost trajectories based on battery degradation trajectories and combines the impact vector of in-vehicle services on battery degradation trajectories and service effect attenuation values ​​to calculate consumer degradation feedback data. This establishes a correlation between in-vehicle service consumption behavior and vehicle degradation changes, enabling quantitative analysis of service effects and subsequent cost changes. On this basis, it calculates service pricing sequences based on vehicle degradation trajectories, service cost trajectories, and consumer degradation feedback data, and generates an in-vehicle service recommendation list based on battery degradation status. This comprehensively considers changes in the vehicle lifecycle, service cost evolution, and user service needs, achieving dynamic pricing and accurate recommendations for future states. Compared to related technologies that adjust prices and recommend services based on current vehicle status or user preferences in a single transaction, this application achieves a closed-loop correlation between vehicle status prediction, service value assessment, price optimization, and recommendation decisions, improving the rationality and accuracy of in-vehicle value-added service decisions and enhancing the user experience.

[0006] Optionally, the battery degradation trajectory can be predicted based on user behavior data, vehicle status data, and battery degradation data, including: determining user profiles and degradation impact coefficients based on user behavior data; calculating battery degradation amounts at multiple future time points based on vehicle status data and battery degradation data; and generating a battery degradation trajectory based on user profiles, degradation impact coefficients, and battery degradation amounts at multiple future time points.

[0007] Based on the aforementioned technical means, this application determines user profiles and degradation impact coefficients based on user behavior data, and calculates the amount of battery degradation at multiple future moments by combining vehicle status data and battery degradation data, further generating a battery degradation trajectory. This enables the correlation analysis between user behavior factors and the battery's own degradation characteristics, achieving personalized degradation trend prediction for different user habits.

[0008] Optionally, user profiles and degradation impact coefficients are determined based on user behavior data, including: extracting user driving behavior data, in-vehicle service usage data, payment history data, and user information from user behavior data; determining multiple degradation impact factors based on user driving behavior data, and calculating the degradation impact coefficient based on the weighted average of multiple degradation impact factors; determining user category labels based on user driving behavior data, in-vehicle service usage data, and payment history data, and constructing user profiles based on user category labels and user information.

[0009] Based on the aforementioned technical means, this application extracts user driving behavior data, in-vehicle service usage data, payment history data, and user information. It then determines degradation influencing factors based on user driving behavior data to calculate degradation impact coefficients. Simultaneously, it constructs user profiles by combining user category tags. This allows for the characterization of user features from multiple dimensions, including driving habits, service needs, and consumption characteristics, enabling correlation analysis between user behavior and the battery degradation process. On one hand, the degradation impact coefficient quantifies the impact of different user behaviors on battery degradation speed, improving the personalization of battery degradation trajectory prediction. On the other hand, user profiles identify the service demand characteristics of different users, providing more accurate data for subsequent in-vehicle service pricing and recommendations, thus improving the accuracy of service matching.

[0010] Optionally, a battery degradation trajectory is generated based on the user profile, degradation impact coefficient, and battery degradation amount at multiple future time points, including: predicting the user's future behavior pattern based on the user profile and extracting the current battery state parameters from the battery degradation data; predicting the health value and internal resistance value at multiple future time points based on the current battery state parameters, the user's future behavior pattern, degradation impact coefficient, and battery degradation amount at multiple future time points; generating a health trajectory sequence based on the health value at multiple future time points, generating an internal resistance trajectory sequence based on the internal resistance value at multiple future time points, and generating a battery degradation trajectory based on the health trajectory sequence and the internal resistance trajectory sequence.

[0011] Based on the aforementioned technical means, this application predicts future user behavior patterns according to user profiles, and combines current battery state parameters, degradation impact coefficients, and battery degradation amounts at multiple future moments to predict health and internal resistance values. This further generates health trajectory sequences and internal resistance trajectory sequences, enabling dynamic prediction of the battery degradation process. By simultaneously considering changes in future user behavior and changes in battery performance, it can more accurately reflect the evolution trend of battery state under different usage scenarios, improving the accuracy of battery degradation trajectory prediction.

[0012] Optionally, before generating the battery degradation trajectory based on user profiles, degradation impact coefficients, and battery degradation amounts at multiple future time points, the method further includes: extracting charging data from the battery degradation data; calculating the vehicle's degradation increment based on the charging data; and correcting the vehicle's battery degradation amount based on the degradation increment.

[0013] Based on the aforementioned technical means, this application extracts charging data from battery degradation data and calculates the vehicle's degradation increment based on the charging data. It further uses this degradation increment to correct the vehicle's battery degradation amount, thus incorporating the impact of actual user charging behavior on battery performance degradation into the battery degradation prediction process. This makes the calculated battery degradation amount more closely reflect real-world vehicle usage. This application further considers the differentiated degradation effects caused by different charging modes, charging frequencies, and charging depths, avoiding deviations in degradation trend prediction due to ignoring charging behavior. Simultaneously, by dynamically correcting the battery degradation amount, the accuracy of subsequent battery degradation trajectory generation can be improved, making service cost calculations, dynamic pricing, and service recommendations based on the degradation trajectory more consistent with the actual lifecycle changes of the vehicle.

[0014] Optionally, the service cost trajectory of the vehicle is calculated based on the battery degradation trajectory, including: extracting the health trajectory sequence and internal resistance trajectory sequence from the battery degradation trajectory; identifying the battery degradation stage based on the health trajectory sequence; determining the service cost structure of the vehicle based on the degradation stage; and calculating the service cost trajectory of the vehicle based on the service cost structure, the health trajectory sequence, and the internal resistance trajectory sequence.

[0015] Based on the aforementioned technical means, this application extracts the health trajectory sequence and internal resistance trajectory sequence from the battery degradation trajectory, identifies the battery degradation stage based on the health trajectory sequence, determines the corresponding service cost structure based on different degradation stages, and further calculates the vehicle service cost trajectory by combining the health trajectory sequence and internal resistance trajectory sequence. This enables the correlation between battery performance change trends and vehicle service cost changes, achieving dynamic prediction of service costs for different future periods. It fully considers the impact of battery degradation on maintenance needs, energy consumption levels, and failure risks, thereby improving the accuracy of service cost calculation.

[0016] Optionally, the service cost trajectory of the vehicle is calculated based on the service cost structure, the health trajectory sequence, and the internal resistance trajectory sequence, including: calculating the maintenance service cost of the vehicle based on the health trajectory sequence; calculating the energy consumption service cost of the vehicle based on the internal resistance trajectory sequence; calculating the failure risk cost of the vehicle based on the health trajectory sequence and the internal resistance trajectory sequence; and identifying the target cost corresponding to each period in the service cost structure to calculate the service cost trajectory of the vehicle, wherein the target cost corresponding to each period includes at least one of the maintenance service cost, the energy consumption service cost, and the failure risk cost.

[0017] Based on the aforementioned technical means, this application calculates the vehicle's maintenance service cost based on the health trajectory sequence, the vehicle's energy consumption service cost based on the internal resistance trajectory sequence, and calculates the fault risk cost by combining the health trajectory sequence and the internal resistance trajectory sequence. Furthermore, it generates vehicle service cost trajectories based on target costs corresponding to different time periods. This allows for the establishment of a correlation between the battery performance degradation process and changes in subsequent vehicle service needs, enabling the prediction of service cost trends throughout the vehicle's entire lifecycle. Compared to methods that assess service costs solely based on the current vehicle status or a single cost factor, this application comprehensively considers the impact of factors such as declining battery health, changes in energy consumption, and increased fault risk on service costs, making the service costs corresponding to different degradation stages more consistent with the actual vehicle operating conditions. Simultaneously, by generating service cost trajectories corresponding to multiple periods, it provides dynamic cost references for subsequent cross-period service pricing and service recommendations, improving the matching degree between service pricing strategies and the actual vehicle usage status.

[0018] Optionally, the service pricing sequence is calculated based on vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data, including: reading a pre-set objective function, which includes service revenue, vehicle health, and total vehicle value; inputting the vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data into the objective function; determining the service price data of at least one in-vehicle service through the solution of the objective function; and generating a service pricing sequence based on the service price data of at least one in-vehicle service.

[0019] Based on the aforementioned technical means, this application inputs vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data into an objective function that includes service revenue, vehicle health, and vehicle value. Based on the solution of the objective function, a service pricing sequence is generated, enabling service prices to be dynamically adjusted according to vehicle degradation status, changes in service costs, and the impact of service consumption. This achieves a shift from pricing at a single time point to multi-cycle joint optimization pricing, thereby avoiding the pricing lag problem caused by only considering the current vehicle status and improving the matching degree between the in-vehicle service pricing strategy and the entire life cycle of vehicle changes.

[0020] Optionally, a recommended list of in-vehicle services is generated based on the battery degradation trajectory and service pricing sequence, including: extracting the health trajectory sequence from the battery degradation trajectory; identifying the battery degradation stage based on the health trajectory sequence; determining the target recommendation strategy for the in-vehicle services based on the battery degradation stage; and generating the recommended list of in-vehicle services based on the target recommendation strategy and service pricing sequence.

[0021] Based on the aforementioned technical means, this application extracts the health trajectory sequence from the battery degradation trajectory and identifies the battery degradation stage based on the health change trend. Furthermore, it combines different degradation stages to determine target recommendation strategies and corresponding service pricing sequences to generate an in-vehicle service recommendation list. This enables the service recommendation process to match the vehicle's performance changes. Compared to methods that only recommend services based on user preferences or the current vehicle status, this application can dynamically adjust the recommended content according to the vehicle's future degradation trend, making the recommended services more suitable for the vehicle's current and future usage needs, and improving the adaptability and effectiveness of in-vehicle service recommendations.

[0022] Optionally, after generating the recommended list of in-vehicle services based on the target recommendation strategy and service pricing sequence, the method further includes: determining the preference matching weight of the in-vehicle services based on user behavior data; determining the pricing rationality weight of the in-vehicle services based on the service pricing sequence; determining the service degradation improvement index and degradation stage weight of the in-vehicle services based on the battery degradation trajectory; calculating the recommendation priority of the in-vehicle services based on the user preference matching weight, pricing rationality weight, service degradation improvement index, and degradation stage weight; and sorting the in-vehicle services in the recommended list according to the recommendation priority.

[0023] Based on the aforementioned technical means, this application determines preference matching weights based on user behavior data, pricing rationality weights based on service pricing sequences, and service degradation improvement indices and degradation stage weights by combining battery degradation trajectories. It further calculates the recommendation priority of in-vehicle services and sorts the recommendation list. This approach, based on user demand matching, further considers the vehicle degradation improvement effect and service price suitability, achieving multi-factor integrated service ranking. Therefore, this application can prioritize services with higher adaptability to the current degradation state of the vehicle, improving the matching degree between recommendation results and vehicle health management needs, and enhancing the effectiveness of in-vehicle service recommendations.

[0024] A second aspect of this application provides an in-vehicle service recommendation device, comprising: an acquisition module for acquiring user behavior data, vehicle status data, and battery degradation data; a prediction module for predicting a battery degradation trajectory based on the user behavior data, vehicle status data, and battery degradation data; a calculation module for calculating the vehicle's service cost trajectory based on the battery degradation trajectory, and calculating the consumption degradation feedback data of the in-vehicle service based on the influence vector of the in-vehicle service on the battery degradation trajectory and the service effect attenuation value; and a generation module for calculating a service pricing sequence based on the vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data, and generating a recommendation list of in-vehicle services based on the battery degradation trajectory and the service pricing sequence.

[0025] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the in-vehicle service recommendation method as described in the above embodiments.

[0026] Therefore, this application has at least the following beneficial effects: (1) This application obtains user behavior data, vehicle status data and battery degradation data, and performs fusion analysis on multi-source data to achieve a comprehensive representation of user usage characteristics, vehicle operating status and battery health status, which can provide a more comprehensive data foundation for pricing and recommendation of in-vehicle value-added services.

[0027] (2) This application predicts the battery degradation trajectory based on user behavior data, vehicle status data and battery degradation data, and can obtain the future status change trend of the vehicle. Compared with the method of making service decisions based on the current vehicle status, it can improve the foresight and adaptability of service pricing.

[0028] (3) This application calculates the vehicle service cost trajectory based on the battery degradation trajectory and calculates the consumption degradation feedback data by combining the influence vector of the vehicle service on the battery degradation trajectory and the service effect decay value. This enables a quantitative analysis of the impact of vehicle services and provides an effective basis for service pricing optimization.

[0029] (4) This application calculates the service pricing sequence by combining vehicle degradation trajectory, service cost trajectory and consumption degradation feedback data, which can comprehensively consider the impact of changes in vehicle status and service costs on price adjustment, realize dynamic pricing of in-vehicle value-added services, and improve the rationality of pricing results.

[0030] (5) This application generates a list of recommended in-vehicle services based on battery degradation trajectory and service pricing sequence, which can match appropriate in-vehicle services with changes in vehicle status, thereby improving the accuracy of service recommendations and user experience.

[0031] (6) This application optimizes services across cycles by comprehensively considering vehicle degradation status, service cost changes and service consumption feedback information, so that the decision-making of in-vehicle value-added services is transformed from passive adjustment based on a single moment of status to active optimization based on the trend of status change, thereby improving the level of intelligence in the operation of in-vehicle services. Attached Figure Description

[0032] Figure 1 This is a flowchart of an in-vehicle service recommendation method according to an embodiment of this application; Figure 2 This is a schematic diagram of the overall architecture of the in-vehicle service recommendation method according to an embodiment of this application; Figure 3This is a flowchart illustrating the specific steps of the in-vehicle service recommendation method according to an embodiment of this application; Figure 4 A flowchart illustrating the core technology of the in-vehicle service recommendation method according to embodiments of this application; Figure 5 This is an example diagram of an in-vehicle service recommendation device according to an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0033] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.

[0034] The following description, with reference to the accompanying drawings, describes a method, apparatus, and device for recommending in-vehicle services according to embodiments of this application. Addressing the issues mentioned in the background art regarding price adjustments for value-added services based on user data, vehicle status data, or market information, where price adjustments are made solely based on existing data, resulting in pricing outcomes that do not match actual user needs, this application provides an in-vehicle service recommendation method. This method first acquires user behavior data, vehicle status data, and battery degradation data, and then fuses these data to construct a multidimensional dataset reflecting user usage characteristics, vehicle operating status, and battery health status. By fusing multi-source data, a data foundation is provided for subsequent battery degradation trend prediction. Second, based on the user behavior data, vehicle status data, and battery degradation data, the future battery degradation process is predicted to obtain the battery degradation trajectory. By establishing a dynamic battery degradation prediction model, the battery degradation trajectory within the vehicle's future operating cycle is obtained. The system analyzes the changing health status of vehicles to avoid making service decisions solely based on the current state, thus improving the foresight of service pricing. Then, it calculates the service cost trajectory corresponding to the vehicle based on the battery degradation trajectory. Combining the impact vector of in-vehicle services on the battery degradation trajectory and the service effect decay value, it calculates the consumption degradation feedback data of in-vehicle services. By establishing the correlation between service cost changes and service consumption impact, it quantifies the impact of different in-vehicle services on vehicle status changes. Finally, it calculates the pricing sequence of in-vehicle services based on the vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data. Combining the battery degradation trajectory and service pricing sequence, it generates an in-vehicle service recommendation list. By comprehensively considering the impact of vehicle status changes, service cost changes, and service feedback, it achieves dynamic pricing and accurate recommendations for in-vehicle value-added services, improving service matching and user experience. This solves the problems of related technologies that adjust value-added service prices based on user data, vehicle status data, or market information, making price adjustments solely based on existing data, and resulting in pricing results that do not match actual user needs.

[0035] Specifically, Figure 1 This is a flowchart illustrating a vehicle service recommendation method provided in an embodiment of this application, wherein the method includes the following steps: In step S101, user behavior data, vehicle status data, and battery degradation data are acquired.

[0036] The user behavior data includes data used to characterize user driving habits, in-vehicle service usage, and consumption behavior, representing user behavior characteristics during vehicle use in this application; the vehicle status data includes data used to characterize vehicle operating status and health status, such as vehicle operating parameters, energy consumption status, fault status, and health monitoring information; the battery degradation data includes data used to characterize the performance degradation process of the power battery, such as battery capacity degradation, internal resistance changes, and degradation characteristics related to the charging and discharging process.

[0037] It is understood that the embodiments of this application can comprehensively characterize the vehicle status from multiple dimensions such as user habits, vehicle operating status, and battery performance changes by acquiring user behavior data, vehicle status data, and battery degradation data. By making full use of the correlation information between multi-source data, it can provide a more comprehensive data foundation for subsequent battery degradation trajectory prediction, service cost analysis, and dynamic pricing and recommendation of in-vehicle services.

[0038] This application communicates with the in-vehicle terminal, user terminal, and cloud server respectively to collect user behavior data and vehicle status data in real time or at regular intervals, providing a foundation for subsequent processing and modeling. User behavior data includes: user driving behavior (acceleration frequency, braking frequency, driving speed, driving duration, driving conditions), in-vehicle service usage data (service click count, usage duration, exit time, preference type), payment history data (payment amount, payment frequency, payment type, willingness to pay), scenario preference data (commuting, long-distance, outdoor, late-night, etc.), and basic user information (age, gender, occupation). Vehicle status data includes: three-electric system operation data (battery voltage, current, battery degradation rate, motor operating efficiency, electronic control system stability), vehicle energy consumption data (energy consumption per 100 kilometers, energy consumption coefficient), fault warning data (fault type, number of warnings, fault level), mileage data, vehicle health monitoring data, tire pressure, and remaining battery power. Battery degradation data includes: battery charge-discharge voltage curves (recording the voltage-time curves of each charge-discharge process, used to calculate the battery internal resistance and capacity decay trend), charging mode data (proportion of fast charging and slow charging, distribution of charging depth, distribution of charging initial state of charge), temperature condition data (distribution of battery operating temperature, proportion of extreme temperature conditions), and cycle condition data (power demand curves for each trip, used to calculate stress degradation factor), etc.

[0039] Furthermore, the collected user behavior data, vehicle status data, and battery degradation data are cleaned, desensitized, normalized, and subjected to degradation feature engineering processing to extract degradation-related features such as battery health value, internal resistance growth rate, and peak shift of capacity increment curve (dQ / dV) to generate structured data.

[0040] First, abnormal data (such as abnormal driving data such as sudden acceleration and braking, and invalid payment records) is removed, and redundant data (repeatedly collected vehicle status data) is filtered out. Sensitive data such as user ID numbers, mobile phone numbers, and vehicle identification numbers are encrypted to ensure data compliance. Data of different formats and scales (such as energy consumption data and payment amounts) are converted into a unified standard (0-1 range), and electrochemical parameters (voltage, internal resistance, and capacity) are nominalized based on the battery specifications.

[0041] The degradation characteristic engineering processing includes: battery health value, which is the ratio of the current maximum capacity to the nominal capacity, and is the core indicator of battery health status; internal resistance growth rate, which is the ratio of the current internal resistance to the initial internal resistance, reflects the change in the battery's internal impedance and directly affects the energy consumption level; constant voltage charging time ratio, which is the proportion of constant voltage charging time to the total charging time, reflects the change in lithium-ion diffusion impedance; and peak position offset of the capacity increment curve, which is the amount of drift of the peak position of the capacity increment curve (dQ / dV) with degradation, and is a key feature for identifying battery degradation stages.

[0042] In step S102, the battery degradation trajectory is predicted based on user behavior data, vehicle status data, and battery degradation data.

[0043] Among them, the battery degradation trajectory is a data sequence used to describe the changing trend of power battery performance parameters over time or usage cycle. In this application, it represents the change process of degradation parameters such as battery health status and internal resistance at multiple future moments. Predicting the battery degradation trajectory is the process of predicting the future state changes of the battery based on historical operating data and degradation characteristics. In this application, it represents the process of determining the changing trend of battery health status within future cycles based on user behavior data, vehicle status data, and battery degradation data.

[0044] Understandably, this application predicts battery degradation trajectory by using user behavior data, vehicle status data, and battery degradation data. It can comprehensively consider user habits, vehicle operating status, and the battery's own performance degradation characteristics to obtain the future trend of battery status changes. Compared with the method of making service decisions based solely on the current vehicle status, it can improve the accuracy of vehicle status assessment and provide more reliable data basis for subsequent service cost calculation, dynamic pricing, and service recommendations.

[0045] In step S103, the service cost trajectory of the vehicle is calculated based on the battery degradation trajectory, and the consumption degradation feedback data of the vehicle service is calculated based on the influence vector of the vehicle service on the battery degradation trajectory and the service effect decay value.

[0046] Among them, the service cost trajectory is a data sequence used to describe the trend of service cost changes for vehicles in different time periods. In this application, it represents the process of change in service costs such as future maintenance costs, energy consumption costs, and failure risk costs determined based on changes in battery degradation status. The influence vector is data used to characterize the degree of influence of in-vehicle services on battery degradation status. In this application, it represents the improvement or influence of different in-vehicle services on changes in battery health status. The service effect decay value is a parameter used to characterize the degree of change in the effect of in-vehicle services over time. In this application, it represents the characteristic of the gradual decrease in the improvement effect of in-vehicle services on battery degradation over the usage period. The consumption degradation feedback data is data used to describe the impact of users purchasing in-vehicle services on the battery degradation process. In this application, it represents information on the impact of in-vehicle service consumption behavior on subsequent battery degradation trajectory and service cost changes.

[0047] Understandably, this application calculates the vehicle's service cost trajectory based on the battery degradation trajectory, and combines the influence vector of in-vehicle services on the battery degradation trajectory with the service effect attenuation value to calculate consumption degradation feedback data. This enables the correlation analysis between changes in vehicle degradation status and changes in service costs, while quantifying the impact of in-vehicle service consumption behavior on the battery degradation process, thus achieving dynamic evaluation of service effectiveness.

[0048] Specifically, this application first extracts degradation state parameters such as health value and internal resistance value corresponding to each future time period in the battery degradation trajectory. Based on the vehicle's maintenance needs, energy consumption level and failure risk under different degradation stages, it calculates the maintenance service cost, energy consumption service cost and failure risk cost corresponding to each time period, and comprehensively obtains the service cost trajectory of the vehicle in multiple future time periods. Secondly, an impact vector on the vehicle degradation state of different in-vehicle services is pre-established to characterize the degree of improvement of battery health, internal resistance growth rate or degradation rate by the corresponding in-vehicle services; at the same time, the service effect decay value is determined according to the continuous effective time of the corresponding in-vehicle services to reflect the changing pattern of the improvement effect of in-vehicle services gradually weakening over time. Furthermore, the influence vector and service effect decay value are fused together to obtain the consumption degradation feedback data corresponding to the in-vehicle service. This data is used to characterize the dynamic impact of users purchasing in-vehicle services on the future degradation trajectory of the vehicle. This provides feedback for the calculation of the subsequent service pricing sequence, so that service pricing not only considers the current degradation state of the vehicle, but also comprehensively considers the impact of service consumption on the future degradation trend of the vehicle and changes in service costs, thus achieving forward-looking dynamic pricing for the entire life cycle of the vehicle.

[0049] In step S104, a service pricing sequence is calculated based on the vehicle degradation trajectory, service cost trajectory, and consumer degradation feedback data, and a recommended list of in-vehicle services is generated based on the battery degradation trajectory and service pricing sequence.

[0050] The service pricing sequence is a data sequence used to describe the changes in in-vehicle service prices over different time periods. In this application, it represents the service pricing scheme for multiple future periods determined based on vehicle degradation status, changes in service costs, and the impact of service feedback. The recommendation list is a set of in-vehicle services recommended to users. In this application, it represents the service recommendation results adapted to the user and vehicle status, determined based on battery degradation status and service pricing results.

[0051] Understandably, this application calculates a service pricing sequence based on vehicle degradation trajectory, service cost trajectory, and consumer degradation feedback data, and generates an in-vehicle service recommendation list based on battery degradation trajectory and service pricing sequence. It comprehensively considers future changes in vehicle status, changes in service costs, and the impact of service consumption on vehicle status, thereby achieving dynamic matching between in-vehicle service prices and changes in vehicle status. At the same time, it recommends suitable services to users based on different degradation stages, improving the rationality of service pricing and the accuracy of service recommendations.

[0052] Therefore, this application embodiment can dynamically perceive the future performance change trend of the vehicle by acquiring user behavior data, vehicle status data, and battery degradation data, and predicting the battery degradation trajectory based on multi-source data. Furthermore, it can calculate the service cost trajectory based on the battery degradation trajectory, and combine the influence vector of in-vehicle services on the battery degradation trajectory and the service effect attenuation value to calculate consumption degradation feedback data. This establishes a correlation between in-vehicle service consumption behavior and vehicle degradation changes, enabling quantitative analysis of service effects and subsequent cost changes. Based on this, it calculates a service pricing sequence based on the vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data, and generates an in-vehicle service recommendation list based on the battery degradation status. This comprehensively considers changes in the vehicle lifecycle, service cost evolution, and user service needs, achieving dynamic pricing and accurate recommendations for future states. Compared to related technologies that adjust prices and recommend services based on the current vehicle status or user preferences in a single transaction, this application achieves a closed-loop correlation between vehicle status prediction, service value assessment, price optimization, and recommendation decisions, improving the rationality and accuracy of in-vehicle value-added service decisions and enhancing the user experience.

[0053] Based on the above embodiments, the following will describe the relevant embodiments of predicting the battery degradation trajectory based on user behavior data, vehicle status data, and battery degradation data in step S102, as follows: In one embodiment of this application, predicting a battery degradation trajectory based on user behavior data, vehicle status data, and battery degradation data includes: determining a user profile and degradation impact coefficient based on user behavior data; calculating the amount of battery degradation at multiple future time points based on vehicle status data and battery degradation data; and generating a battery degradation trajectory based on the user profile, degradation impact coefficient, and the amount of battery degradation at multiple future time points.

[0054] Among them, the user profile is a data model used to describe the characteristics of user behavior and service needs. In this application, it represents a set of user features constructed based on information such as user driving behavior, in-vehicle service usage behavior, and consumption behavior. The degradation impact coefficient is a parameter used to characterize the degree of influence of user behavior on the rate of battery degradation. In this application, it represents the degree of acceleration or deceleration of battery degradation determined based on the user's driving and charging habits. The battery degradation amount is data used to represent the degree of degradation of battery performance during use. In this application, it represents the amount of change in parameters such as battery capacity, health status, or internal resistance over multiple future time periods.

[0055] It is understood that the embodiments of this application can determine user profiles and degradation impact coefficients based on user behavior data, and calculate the amount of battery degradation at multiple future moments by combining vehicle status data and battery degradation data, generate battery degradation trajectory, and perform correlation analysis between user behavior factors and the battery's own degradation characteristics through battery degradation trajectory, so as to realize personalized degradation trend prediction for different user habits.

[0056] In this embodiment, the joint degradation kinetics model establishes a degradation prediction model that integrates electrochemical degradation mechanisms and user behavior influences based on vehicle state data, battery degradation data, and degradation impact coefficients corresponding to user behavior. This model predicts the degradation state of the vehicle over multiple future time periods and further calculates the corresponding service cost trajectory based on the predicted degradation trajectory, providing a data foundation for subsequent dynamic pricing and service recommendations. The joint degradation kinetics model first establishes a basic degradation model based on the battery electrochemical degradation mechanism, calculating the basic degradation amount based on the vehicle's current state and historical degradation data. Then, it introduces user behavior degradation impact coefficients to correct the basic degradation amount, reflecting the impact of different user driving and charging habits on the vehicle degradation process. Furthermore, it predicts the vehicle's capacity retention rate and internal resistance change trends over multiple future time periods, generating a battery degradation trajectory. Based on this trajectory, it calculates the maintenance service cost, energy consumption service cost, and failure risk cost for future periods, forming a service cost trajectory.

[0057] Specifically, in this embodiment of the application, when predicting battery degradation trajectory based on user behavior data, vehicle status data, and battery degradation data, the vehicle degradation trajectory under a specific user driving behavior pattern is jointly predicted based on the electrochemical degradation fundamental model and the user behavior degradation coupling function. The expression for the user behavior degradation coupling function is as follows:

[0058] in, The first calculation for the basic model of electrochemical degradation Periodic basal degradation; The coefficient representing the impact of user behavior degradation; Additional degradation increments for extreme operating conditions.

[0059] The expression for the internal resistance degradation coupling function is as follows:

[0060] in, This is the increase in basic internal resistance; This refers to the additional increase in internal resistance caused by extreme operating conditions.

[0061] Battery capacity degradation is primarily influenced by internal chemical reactions within the battery. As battery usage time increases, the solid electrolyte interfacial film on the negative electrode surface continues to grow, consuming active lithium ions and gradually reducing the battery's usable capacity. Simultaneously, the growth of the solid electrolyte interfacial film leads to increased internal impedance, thereby affecting battery charging and discharging efficiency and vehicle energy consumption. Based on this electrochemical degradation mechanism, battery operating parameters from vehicle state data and historical degradation characteristic data from battery degradation data are used as inputs to the electrochemical degradation basic model submodule. The battery degradation data includes degradation kinetics data characterizing the battery degradation process, calculating the amount of battery degradation at multiple future time points.

[0062] Furthermore, to account for the impact of different user driving and charging habits on the battery degradation process, a degradation impact coefficient corresponding to the user profile is introduced into the battery degradation model to correct the amount of battery degradation. For example, for behavioral patterns such as frequent fast charging and deep discharging, the degradation amount within the corresponding time period can be increased by increasing the degradation impact coefficient; for users with a high proportion of slow charging and relatively stable driving behavior, the degradation amount within the corresponding time period can be slowed down by decreasing the degradation impact coefficient. Based on the corrected battery degradation amount at multiple future moments, combined with the user profile and the degradation impact coefficient, a battery degradation trajectory under the corresponding user behavior pattern is generated.

[0063] In one embodiment of this application, determining a user profile and degradation impact coefficient based on user behavior data includes: extracting user driving behavior data, in-vehicle service usage data, payment history data, and user information from the user behavior data; determining multiple degradation impact factors based on the user driving behavior data; calculating the degradation impact coefficient by weighting the multiple degradation impact factors; determining user category tags based on the user driving behavior data, in-vehicle service usage data, and payment history data; and constructing a user profile based on the user category tags and user information.

[0064] Among them, user driving behavior data describes the user's operating habits and driving characteristics during driving, and in this application represents information affecting changes in vehicle state such as acceleration frequency, braking frequency, driving speed, driving duration, and driving conditions; in-vehicle service usage data describes the user's use of in-vehicle services, and in this application represents the user's frequency of use, usage duration, and service preference information for in-vehicle entertainment, office, and maintenance services; payment history data describes the user's historical service consumption behavior, and in this application represents consumption characteristics such as the amount, frequency, and type of in-vehicle services purchased by the user; degradation influencing factors are characteristic parameters used to characterize the degree of influence of user behavior on the battery degradation process, and in this application represent influencing factors determined based on fast charging dependence, deep discharge degree, high temperature usage ratio, and high rate discharge ratio; user category tags are classification identifiers used to distinguish different user behaviors and consumption characteristics, and in this application represent user type information determined based on user driving behavior, service usage behavior, and payment behavior.

[0065] Understandably, this application extracts user driving behavior data, in-vehicle service usage data, payment history data, and user information. It then determines degradation influencing factors based on user driving behavior data to calculate degradation impact coefficients. Simultaneously, it constructs user profiles by combining user category tags. This allows for the characterization of user traits from multiple dimensions, including driving habits, service needs, and consumption patterns, enabling correlation analysis between user behavior and the battery degradation process. On one hand, the degradation impact coefficient quantifies the impact of different user behaviors on battery degradation speed, improving the personalization of battery degradation trajectory prediction. On the other hand, user profiles identify the service demand characteristics of different users, providing more accurate data for subsequent in-vehicle service pricing and recommendations, thus improving the accuracy of service matching.

[0066] Specifically, this application determines user profiles and degradation impact coefficients based on user behavior data, extracting user driving behavior data, in-vehicle service usage data, payment history data, and user information from the user behavior data. Based on the processed user behavior data, user profiles are constructed to predict user willingness to pay, and the degradation impact coefficient of user driving behavior is calculated to quantify the degree to which user driving habits and charging habits accelerate or slow down battery degradation. The process of constructing user profiles is as follows: This application first extracts features from processed user behavior data, including but not limited to user driving behavior data, in-vehicle service usage data, payment history data, and user information; determines multiple degradation influencing factors based on user driving behavior data, and determines user category labels based on user driving behavior data, in-vehicle service usage data, and payment history data; constructs user profiles based on user category labels and user information; and further predicts user willingness to pay based on payment history data and user profiles.

[0067] Clustering algorithms are used for user classification and tagging, including behavioral tags (commuting driving, long-distance driving, night driving), payment preference tags (high willingness to pay, low willingness to pay, preference for package services), scenario demand tags (commuting entertainment, outdoor camping, long-distance maintenance), lifecycle value tags (high lifecycle value users, low lifecycle value users), and driving habit tags (conservative, aggressive). Based on degradation dynamics-related data in user behavior data, including charging mode data, temperature condition data, and cycle condition data, multiple degradation influencing factors are extracted to characterize the degree of impact of user behavior on battery degradation. Specifically, fast charging dependence and deep discharge habits are determined based on charging mode data, the proportion of high-temperature conditions is determined based on temperature condition data, and the proportion of high-rate discharge is determined based on cycle condition data. Furthermore, a weighted calculation is performed based on multiple degradation influencing factors to obtain the user behavior degradation impact coefficient.

[0068] The behavioral degradation impact coefficient is obtained by weighted summation and normalization of multiple degradation influencing factors. .when A value greater than 1 indicates that the user's driving and charging habits accelerate battery degradation; when... When the value is less than 1, it indicates that the user's driving and charging habits slow down battery degradation. The weights of each degradation influencing factor are calibrated based on experimental data.

[0069] This application determines user category tags based on user driving behavior data, in-vehicle service usage data, and payment history data, and constructs user profiles by combining user information. The degradation impact coefficient can be used as an input parameter for subsequent joint degradation dynamics models to correct battery degradation trajectory predictions and improve the matching degree between degradation trajectory prediction results and actual user behavior.

[0070] In one embodiment of this application, before generating the battery degradation trajectory based on the user profile, degradation impact coefficient, and battery degradation amount at multiple future time points, the method further includes: extracting charging data from the battery degradation data; calculating the vehicle's degradation increment based on the charging data; and correcting the vehicle's battery degradation amount based on the degradation increment.

[0071] Among them, charging data refers to data used to describe the charging process and charging behavior characteristics of the vehicle, and in this application, it represents information such as the number of charging times, charging mode, charging depth, charging time, and voltage and current during the charging process; degradation increment refers to the additional impact of the charging process on battery performance degradation, and in this application, it represents degradation changes such as battery capacity reduction and internal resistance increase determined based on charging behavior characteristics.

[0072] Understandably, this application extracts charging data from battery degradation data, calculates the vehicle's degradation increment based on the charging data, and further uses the degradation increment to correct the vehicle's battery degradation amount. This allows the impact of the user's actual charging behavior on battery performance degradation to be incorporated into the battery degradation prediction process, making the calculated battery degradation amount more consistent with the vehicle's actual usage. This application further considers the differentiated degradation effects caused by different charging modes, charging frequencies, and charging depths, avoiding deviations in degradation trend prediction due to ignoring charging behavior. Simultaneously, by dynamically correcting the battery degradation amount, the accuracy of subsequent battery degradation trajectory generation can be improved, making the service cost calculation, dynamic pricing, and service recommendation results based on the degradation trajectory more consistent with the actual lifecycle changes of the vehicle.

[0073] Specifically, the degradation process of a vehicle battery is affected not only by the battery's own electrochemical characteristics but also by the user's actual usage behavior. To establish a correlation between user behavior and the battery degradation process, this application first calculates the basic degradation amount corresponding to the vehicle in its current state based on a battery electrochemical degradation model. The basic degradation amount is used to characterize the capacity decay and internal resistance increase of the battery over time and cycle count under standard usage conditions.

[0074] Furthermore, the behavioral degradation impact coefficient output by the user profiling module... Introducing the baseline degradation value, a user behavior-coupled correction is applied to it. This includes the behavior degradation impact coefficient. This is used to characterize the impact of user driving and charging behaviors on the battery degradation rate. When users engage in behaviors that accelerate degradation, such as frequent fast charging, deep discharging, and high-rate operation... If the value exceeds the preset baseline, the basic degradation will increase; when users use low-rate charging, shallow charging and discharging, and stable driving methods, The value is less than or close to the preset baseline value, so that the basic degradation amount is maintained or reduced.

[0075] Furthermore, for extreme operating conditions encountered by users during actual use, the additional degradation increment corresponding to these extreme conditions is calculated by analyzing charging data within the battery degradation data. This additional degradation increment is then added to the base degradation amount after correction by the behavioral degradation impact coefficient, resulting in a corrected battery degradation amount that more closely reflects actual usage conditions. The additional degradation increment is calculated by... The degradation kinetics data within the cycle are analyzed and determined. Based on the charging mode data, temperature condition data, and cycle condition data in the degradation kinetics data, extreme fast charging conditions, extreme deep discharge conditions, extreme high temperature conditions, and extreme high rate discharge conditions are identified respectively. The number of triggers of each type of extreme condition is counted, and the degradation impact corresponding to each type of extreme condition is weighted according to the preset weight to obtain the additional degradation increment.

[0076] Specifically, the corrected battery degradation can be expressed as a combination of the base degradation, the user behavior impact term, and the extreme operating condition impact term. That is, the relationship between user behavior and battery degradation is established through the user behavior degradation coupling function.

[0077] By incorporating user behavior factors into the battery degradation model in the above manner, vehicles of the same model and in the same initial state can exhibit different degradation trends based on different users' driving and charging habits, thereby improving the personalization and accuracy of subsequent battery degradation trajectory prediction.

[0078] The trajectory prediction process in this embodiment is as follows:

[0079] First, initialize by inputting the current time. Battery status: , , User future behavior pattern prediction sequence ; Secondly, iterative prediction is performed cycle by cycle, with calculations performed for each cycle: (1) Basic degradation amount: Based on the basic electrochemical degradation model, the input temperature condition. and number of loops ,calculate .

[0080] (2) Calculate the coupling degradation: Substituting the user behavior degradation coupling function, we get:

[0081] (3) Update the status according to the following formula:

[0082]

[0083] (4) Degeneration stage identification: based on health value Determine the stage of degradation.

[0084] Next, the trajectory sequence is output to obtain the future trajectory. Health trajectory sequence of each cycle and internal resistance trajectory sequence ; Finally, service consumption feedback is added (if a user purchases a service). At the time of purchase In all subsequent cycles, the amount of service degradation improvement will be... The original health trajectory sequence is superimposed using an exponential decay function. This decay function describes the gradual decrease in the effectiveness of the in-vehicle service in improving battery degradation over time. Specifically, the remaining proportion of the service effect at different time periods is calculated based on preset decay parameters, and this remaining proportion is used to correct the battery degradation trajectory after service implementation, thus reflecting the service's continued impact on future degradation.

[0085] In one embodiment of this application, generating a battery degradation trajectory based on user profiles, degradation impact coefficients, and battery degradation amounts at multiple future time points includes: predicting future user behavior patterns based on user profiles and extracting current battery state parameters from battery degradation data; predicting health values ​​and internal resistance values ​​at multiple future time points based on current battery state parameters, future user behavior patterns, degradation impact coefficients, and battery degradation amounts at multiple future time points; generating a health trajectory sequence based on the health values ​​at multiple future time points, generating an internal resistance trajectory sequence based on the internal resistance values ​​at multiple future time points, and generating a battery degradation trajectory based on the health trajectory sequence and the internal resistance trajectory sequence.

[0086] Among them, the user future behavior pattern is a data model used to describe the user's possible future driving and service usage behaviors, which in this application represents the future driving habits, charging habits, and service usage trends predicted based on the user's historical behavior characteristics; the current battery state parameters are data used to characterize the current performance state of the battery, which in this application represent parameters reflecting the degree of battery degradation, such as the current battery health, internal resistance value, and capacity state; the health trajectory sequence is a data sequence used to describe the trend of battery health status changes over time, which in this application represents the process of battery health value changes at multiple future moments; and the internal resistance trajectory sequence is a data sequence used to describe the trend of battery internal impedance changes, which in this application represents the process of battery internal resistance value changes at multiple future moments.

[0087] Understandably, this application predicts future user behavior patterns based on user profiles and combines this with current battery state parameters, degradation impact coefficients, and battery degradation amounts at multiple future points to predict health and internal resistance values. This further generates health trajectory sequences and internal resistance trajectory sequences, enabling dynamic prediction of the battery degradation process. By simultaneously considering changes in future user behavior and battery performance, it can more accurately reflect the evolution trend of battery state under different usage scenarios, improving the accuracy of battery degradation trajectory prediction.

[0088] Since the degradation process of vehicle batteries is continuous and cumulative, the current battery status alone cannot accurately reflect the future health trend of the vehicle. Therefore, this application embodiment constructs the user's future behavior pattern based on the user's historical behavior characteristics, and combines the current battery status parameters, the degree of influence of user behavior on the degradation process, and the amount of battery degradation at multiple future times to predict the degradation status of the vehicle in multiple future time periods.

[0089] Specifically, firstly, based on historical data such as driving habits, charging habits, and service usage behavior in user profiles, the system predicts the user's likely behavioral patterns over a future period. This includes predicting future driving frequency, charging methods, and usage rates under different operating conditions. Then, vehicle status data, including current battery health values, current internal resistance values, or internal resistance growth rates, is extracted from battery degradation data as the initial state for degradation trajectory prediction.

[0090] Furthermore, the current battery state parameters, future user behavior patterns, and behavioral degradation impact coefficients will be considered. The battery degradation amounts corresponding to multiple future time points are input into the user behavior degradation coupling function. This function then predicts the battery health and internal resistance values ​​for multiple future time periods. The behavior degradation influence coefficient is also included. This method is used to correct the impact of different user behavior patterns on battery degradation rates, so that different behavior patterns correspond to different degradation prediction results under the same initial vehicle conditions. The prediction process for future user behavior patterns is as follows: First, based on user profiles, behavioral pattern data from multiple historical time periods is obtained. This behavioral pattern data includes driving behavior data, in-vehicle service usage data, and charging behavior data. Then, features are extracted from the behavioral pattern data to generate corresponding behavioral feature vectors. Further, trend analysis is performed on the behavioral feature vectors to identify the changing trends of user behavior patterns. Based on the historical behavioral pattern change patterns, a behavioral prediction model is established to obtain the predicted user behavior pattern sequence for multiple future time periods.

[0091] After obtaining the health and internal resistance values ​​for multiple future time periods, a health trajectory sequence and an internal resistance trajectory sequence are constructed in chronological order. These two sequences are then fused to generate the battery degradation trajectory for the vehicle. The battery degradation trajectory not only reflects the changing trend of battery health status in each future time period but also characterizes the energy consumption change trend caused by the increase in internal resistance.

[0092] Furthermore, this application identifies the battery degradation stages corresponding to each future time period based on the predicted health value in the health trajectory sequence, and the degradation stages can be divided according to the battery health value. For example, when the predicted battery health value is greater than 90%, the vehicle can be considered to be in the early degradation stage. At this time, the battery capacity decay is low, the difference between the usable capacity and the rated capacity is small, the vehicle's range and overall performance are relatively stable, and the user's demand for battery maintenance services is low. The focus is mainly on value-added services such as in-vehicle entertainment and in-vehicle office to improve the user experience. When the predicted battery health value is between 80% and 90%, the vehicle can be considered to be in the mid-degradation stage. At this time, the battery capacity begins to decline to a certain extent, which may lead to a decrease in the vehicle's range and an increase in energy consumption. Therefore, battery health management, energy consumption optimization, and preventive maintenance services can be prioritized. When the predicted battery health value is between 70% and 80%, the vehicle can be considered to be in the late degradation stage. At this time, the battery capacity decreases further, the degradation trend accelerates, and the risk of vehicle failure increases. In-depth maintenance, fault warning, and extended warranty services can be strongly recommended. When the predicted battery health value is below 70%, the vehicle can be considered to be in the late degradation stage. At this time, the battery capacity retention is low, and vehicle safety assurance, repair, replacement, or replacement-related services should be prioritized.

[0093] It should be noted that the degradation stage classification thresholds corresponding to the above battery health values ​​are only an exemplary classification method. In actual applications, different stage classification thresholds can be set according to vehicle type, battery model, historical operating data, and service strategy requirements.

[0094] By combining user behavior factors with the current degradation status of the vehicle in the above manner, personalized degradation trajectory prediction for multiple future time periods can be achieved. Compared with the method of static evaluation based solely on the current vehicle status, this method can predict the future degradation trend of the vehicle in advance and formulate corresponding in-vehicle service strategies according to different degradation stages.

[0095] Based on at least one of the above embodiments, the following will describe the relevant embodiments of service cost trajectory and consumption degradation feedback data in step S103, as follows: In one embodiment of this application, calculating the service cost trajectory of a vehicle based on the battery degradation trajectory includes: extracting the health trajectory sequence and the internal resistance trajectory sequence from the battery degradation trajectory; identifying the battery degradation stage based on the health trajectory sequence; determining the service cost structure of the vehicle based on the degradation stage; and calculating the service cost trajectory of the vehicle based on the service cost structure, the health trajectory sequence, and the internal resistance trajectory sequence.

[0096] Among them, the battery degradation stage is a state interval used to divide the degree of battery performance degradation. In this application, it represents different degradation stages determined according to changes in battery health. The service cost structure is a data model used to describe the composition of service costs corresponding to different degradation stages of the vehicle. In this application, it represents the correspondence between cost types such as maintenance service costs, energy consumption service costs, and failure risk costs and degradation states.

[0097] Understandably, this application extracts the health trajectory sequence and internal resistance trajectory sequence from the battery degradation trajectory, identifies the battery degradation stage based on the health trajectory sequence, determines the corresponding service cost structure based on different degradation stages, and further calculates the vehicle service cost trajectory by combining the health trajectory sequence and internal resistance trajectory sequence. This enables the correlation between battery performance change trends and vehicle service cost changes, achieving dynamic prediction of service costs for different future periods. It fully considers the impact of battery degradation on maintenance needs, energy consumption levels, and failure risks, thereby improving the accuracy of service cost calculation.

[0098] In one embodiment of this application, calculating the service cost trajectory of a vehicle based on a service cost structure, a health trajectory sequence, and an internal resistance trajectory sequence includes: calculating the vehicle's maintenance service cost based on the health trajectory sequence; calculating the vehicle's energy consumption service cost based on the internal resistance trajectory sequence; calculating the vehicle's failure risk cost based on the health trajectory sequence and the internal resistance trajectory sequence; and identifying the target cost corresponding to each period in the service cost structure to calculate the vehicle's service cost trajectory, wherein the target cost corresponding to each period includes at least one of maintenance service cost, energy consumption service cost, and failure risk cost.

[0099] Among them, maintenance service cost is used to represent the cost corresponding to the maintenance needs of the vehicle due to performance degradation. In this application, it represents the service cost of repair, maintenance, and battery maintenance determined based on the trend of battery health changes; energy consumption service cost is used to represent the cost corresponding to the increase in energy consumption of the vehicle due to changes in battery performance. In this application, it represents the service cost of the increase in vehicle energy consumption determined based on the trend of battery internal resistance changes; failure risk cost is used to represent the cost corresponding to the increased probability of failure due to the increased degree of vehicle degradation. In this application, it represents the potential failure handling cost determined based on battery health and internal resistance changes; target cost is used to represent the comprehensive service cost of the vehicle within a certain time period. In this application, it represents at least one of the maintenance service cost, energy consumption service cost, and failure risk cost selected according to different degradation stages.

[0100] Understandably, this application calculates vehicle maintenance service costs based on the vehicle's health trajectory sequence, energy consumption service costs based on the vehicle's internal resistance trajectory sequence, and fault risk costs by combining the health trajectory sequence and internal resistance trajectory sequence. Furthermore, it generates vehicle service cost trajectories based on target costs corresponding to different time periods. This allows for the establishment of a correlation between battery performance degradation and changes in subsequent vehicle service needs, enabling the prediction of service cost trends throughout the vehicle's entire lifecycle. Compared to methods that assess service costs solely based on the current vehicle condition or a single cost factor, this application comprehensively considers the impact of declining battery health, changes in energy consumption, and increased fault risk on service costs, making service costs at different degradation stages more consistent with actual vehicle operation. Simultaneously, by generating service cost trajectories for multiple periods, it provides dynamic cost references for subsequent cross-period service pricing and recommendations, improving the alignment between service pricing strategies and actual vehicle usage.

[0101] Specifically, this application calculates the vehicle's maintenance service cost based on a health trajectory sequence. As the battery's health gradually declines, the degree of battery performance degradation increases, and the vehicle's maintenance needs rise accordingly. Therefore, the corresponding maintenance service cost is determined based on the corresponding health change trend within different time periods. Furthermore, as the degree of degradation deepens, the maintenance demand typically exhibits a non-linear growth trend; that is, the lower the health status, the higher the maintenance frequency within the corresponding period, and the higher the maintenance cost.

[0102] The energy service cost of a vehicle is calculated based on the internal resistance trajectory sequence. Since the battery's internal resistance gradually increases with aging, this increase leads to increased energy loss during charging and discharging, thus raising the energy consumption level during vehicle operation. Therefore, the energy service cost for the corresponding period is determined based on the internal resistance change trend for each future time period.

[0103] The failure risk cost of the vehicle is calculated based on the health status trajectory sequence and the internal resistance trajectory sequence. Specifically, a decline in health status and a continuous increase in internal resistance both reflect the degree of battery degradation. As the degree of battery degradation increases, the probability of the vehicle experiencing abnormal operating conditions also increases. Therefore, the failure risk cost for the corresponding period is determined based on the changes in health status and internal resistance at different time periods.

[0104] After obtaining the maintenance service cost, energy consumption service cost, and failure risk cost, the target cost for each period in the service cost structure is identified, and the vehicle's service cost trajectory is generated based on the target cost for each period. The target cost for each period can include at least one of the maintenance service cost, energy consumption service cost, and failure risk cost. For example, when battery degradation is low, energy consumption service cost can be primarily considered; as degradation increases, maintenance service cost and failure risk cost can be further increased. This is achieved by considering future... The target cost for each time period is calculated to obtain the expected service cost sequence, which is then used as the cost basis for subsequent forward-looking dynamic pricing.

[0105] Based on at least one of the above embodiments, the following will describe the relevant embodiments of the service pricing sequence and the recommended list of in-vehicle services in step S104, as follows: In one embodiment of this application, calculating a service pricing sequence based on vehicle degradation trajectory, service cost trajectory, and consumer degradation feedback data includes: reading a pre-set objective function, which includes service revenue, vehicle health, and total vehicle value; inputting the vehicle degradation trajectory, service cost trajectory, and consumer degradation feedback data into the objective function; determining service price data for at least one in-vehicle service based on the solution result of the objective function; and generating a service pricing sequence based on the service price data for at least one in-vehicle service.

[0106] The objective function is a mathematical model used to comprehensively evaluate multiple optimization objectives and determine the optimal result. In this application, it represents a calculation model that optimizes the pricing scheme for in-vehicle services by combining factors such as service revenue, vehicle health, and vehicle value. Service revenue is a parameter used to represent the economic benefits generated by in-vehicle service prices and user purchasing behavior. In this application, it represents an indicator used to measure service operation revenue during the pricing process of in-vehicle services. Vehicle health is a parameter used to represent the vehicle performance maintenance status. In this application, it represents vehicle health level information determined based on battery degradation status. The total vehicle value is an evaluation parameter used to represent the changes in vehicle value throughout its entire life cycle. In this application, it represents an overall value indicator that comprehensively considers changes in vehicle health status and long-term user value. The service pricing sequence is a data sequence used to describe changes in in-vehicle service prices over multiple time periods. In this application, it represents a dynamic pricing scheme determined based on vehicle degradation status, service costs, and consumer feedback results.

[0107] Understandably, this application inputs vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data into an objective function that includes service revenue, vehicle health, and vehicle value. Based on the solution of the objective function, a service pricing sequence is generated, enabling service prices to be dynamically adjusted according to vehicle degradation status, changes in service costs, and the impact of service consumption. This achieves a shift from pricing at a single time point to multi-cycle joint optimization pricing, thereby avoiding the pricing lag problem caused by only considering the current vehicle status and improving the matching degree between the in-vehicle service pricing strategy and the changes in the entire life cycle of the vehicle.

[0108] Specifically, this application first establishes the correlation between in-vehicle services and vehicle degradation status, and describes the improvement effect of users purchasing different in-vehicle services on vehicle degradation status by defining the influence vector of in-vehicle services on vehicle degradation trajectory.

[0109] For example, for in-depth maintenance services, the degree of improvement in battery health can be determined by comparing vehicle status data collected by the battery management system before and after the service implementation; for battery health management services, the degree of improvement in degradation rate can be determined by analyzing changes in user behavior and internal resistance growth before and after the service implementation; and for energy consumption optimization services, the impact of internal resistance growth on vehicle energy consumption levels can be reduced by optimizing user driving behavior and vehicle energy consumption management strategies.

[0110] Specifically, a corresponding degradation impact vector is established for different in-vehicle services to describe the improvement effect of users purchasing in-vehicle services on the vehicle's degradation trajectory. The improvement in the vehicle's battery health value after purchasing the service can be used as the service degradation impact vector. The calculation method for the degradation impact varies depending on the type of in-vehicle service. For example, for deep maintenance services, the improvement in battery health can be determined based on changes in vehicle status data collected by the battery management system before and after the service implementation; in practice, this improvement can be approximately 2%-3%. For battery health management services, the degree of degradation rate reduction can be determined based on changes in user charging and discharging behavior and internal resistance growth before and after the service implementation; for example, it can reduce the rate by approximately 3%-5%. For energy consumption optimization services, the extent to which the increase in internal resistance reduces energy consumption can be determined based on driving behavior optimization and the effectiveness of vehicle energy consumption management. For example, it can reduce it by about 10%-15%.

[0111] Furthermore, since the improvement effect of in-vehicle services on vehicle degradation is not permanent but gradually weakens with continued vehicle operation, this application embodiment sets corresponding service effect decay parameters for different in-vehicle services to describe the pattern of service improvement effect changes over time. These service effect decay parameters may include decay period parameters, which represent the time required for the service improvement effect to decay to half of its initial improvement effect. For example, the decay period for deep maintenance services can be set to approximately 6 months, and the decay period for battery health management services can be set to approximately 12 months.

[0112] A service effect decay function is established based on the decay period parameter, so that the degradation improvement corresponding to the in-vehicle service gradually decreases over time, and the vehicle degradation trajectory after the user purchases the service is updated according to the degradation improvement corresponding to different time periods. For example, after purchasing the in-vehicle service, the predicted value of the vehicle battery health is improved in the initial stage based on the service improvement. As the service effect gradually decays, the predicted value of the battery health gradually approaches the original degradation trajectory before the service was purchased.

[0113] After obtaining the updated vehicle degradation trajectory, the corresponding service cost trajectory is recalculated based on the updated trajectory, thereby obtaining the future cost changes after a user purchases a certain in-vehicle service. By establishing the above-mentioned service consumption degradation feedback mechanism, this application can assess the impact of a user's purchase of a certain in-vehicle service on the future vehicle status and service costs. For example, a certain in-vehicle service may lead to a decrease in service revenue in the current time period, but because the service can delay vehicle degradation, it reduces maintenance costs, energy costs, or failure risk costs in subsequent time periods. Therefore, from the perspective of overall revenue over multiple time periods, the service may have better long-term value.

[0114] Furthermore, vehicle degradation trajectory, service cost trajectory, and consumer degradation feedback data are input into a pre-established objective function. This objective function aims to maximize the combined revenue of all three parties (service revenue, vehicle health, and vehicle value) and is used to comprehensively evaluate the overall profitability of the in-vehicle service pricing scheme over multiple time periods.

[0115] Service revenue represents the commercial revenue generated after pricing in-vehicle services. Specifically, it can be determined based on the in-vehicle service price, user purchase probability, and service cost within each time period, and the cumulative revenue over multiple time periods can be calculated by combining time discounting factors. Vehicle health represents the degree of improvement in the vehicle's degradation status after in-vehicle service intervention. For example, the amount of improvement in vehicle health status can be determined by comparing the battery health value trajectory after purchasing in-vehicle services with the baseline degradation trajectory before service intervention. Vehicle value represents the changes in the long-term user value. For example, the impact of different pricing strategies on the long-term user value can be assessed based on changes in user lifetime value.

[0116] The objective function is expressed as follows:

[0117] in, The objective function is... For service revenue weighting, As a weight for vehicle health, Assign weights to vehicle value to satisfy The specific value can be configured according to the business strategy (e.g.: =0.5, =0.3, =0.2); For service In the cycle Pricing (decision variable); For service revenue; For vehicle health; Value of the vehicle.

[0118] The service revenue expression is as follows:

[0119] in, The time discount factor is (e.g., 0.95). For service In the cycle Pricing (decision variable); For users For services In price Conversion probability (based on user profile prediction); For service In the cycle Costs (based on the vehicle's service cost trajectory); Indicates service In the cycle Whether it is recommended.

[0120] The vehicle health status expression is as follows:

[0121] in, This represents the final vehicle battery health value under the recommended scheme. This represents the final vehicle battery health value under the baseline scenario without intervention.

[0122] The vehicle's value is expressed as follows:

[0123] in, For period The increase in user lifetime value.

[0124] The process of solving the objective function is as follows: (1) Stage division. The cycle is divided into Each stage corresponds to a pricing decision point.

[0125] (2) State Definition. The state includes the current vehicle battery health value, internal resistance, and cumulative user lifetime value, expressed as follows:

[0126] (3) Decision variables. The expressions for decision variables are as follows:

[0127] That is, the pricing and recommendation decisions for each service.

[0128] (4) State transition equation. The state transition consists of three components that are updated simultaneously: The expression for the SOH component is as follows:

[0129] The expression for the internal resistance component is as follows:

[0130] User lifetime value components, i.e. The component expressions are as follows:

[0131] in For service Effect decay period parameter, Purchase time for services.

[0132] (5) Solve recursively. From the terminal Starting from here, we proceed with reverse recursion, as shown in the following expression:

[0133] The expression for immediate profit is as follows:

[0134] in, This is the optimal value function for subsequent stages.

[0135] (6) Boundary conditions. .

[0136] (7) Forward backtracking. From Depart, depending on the situation Find the optimal decision by looking up the table. Transfer to Repeat until The globally optimal pricing sequence is obtained. .

[0137] (8) Online update. After each cycle, based on the latest observed battery health value, measured internal resistance value and actual user behavior, steps (1)-(7) are re-executed to update the pre-planned pricing for the subsequent cycle.

[0138] This application first establishes a cross-cycle joint optimization pricing model, which will include future... The service pricing process over multiple time periods is optimized as a whole, rather than pricing each time period independently. The joint optimization model sets objective functions that include service revenue, vehicle health, and long-term user value. By comprehensively evaluating the impact of different pricing strategies on these three aspects, the optimal pricing scheme for overall revenue across multiple time periods is determined.

[0139] Service revenue represents the commercial revenue generated after pricing in-vehicle services. It can be calculated based on the in-vehicle service price, user purchase probability, and corresponding service cost in each time period, and the cumulative revenue over multiple periods can be obtained by combining time discounting factors. Vehicle health represents the degree of improvement in the vehicle's degradation status after intervention through in-vehicle services. For example, the amount of improvement in vehicle health status can be determined by comparing the trajectory of the vehicle's battery health value after purchasing services with the baseline degradation trajectory before service intervention. Long-term user value represents the value changes generated by users over multiple time periods. For example, the impact of different pricing strategies on users' continued consumption behavior can be assessed based on the increment of user lifetime value.

[0140] In conducting joint optimization, this application assigns corresponding weights to service revenue, vehicle health, and long-term user value based on actual business needs, and employs dynamic programming to solve the optimization process across multiple time periods. Specifically, it will... The joint optimization problem corresponding to each time period is divided into multiple stage sub-problems. By calculating the revenue changes corresponding to different service price schemes in each time period in each stage, and combining the changes in vehicle degradation status and service costs in subsequent periods, the overall optimal service pricing sequence is determined.

[0141] In the solution process, consumer degradation feedback data is introduced, enabling this application to simulate changes in vehicle status after users purchase different in-vehicle services. For example, after determining that a user has purchased a certain in-vehicle service, the vehicle degradation trajectory can be updated based on the degradation improvement effect corresponding to that service, and the future service cost trajectory can be further updated. This allows for the evaluation of the overall revenue impact of the service on multiple future cycles after the price reduction in the current cycle to attract users to purchase it. Therefore, even if a service experiences a decrease in revenue in the current cycle, it is possible to determine whether it has superior value from a full lifecycle perspective.

[0142] Furthermore, future models are generated based on the solution results of the joint optimization model. The pricing sequence corresponds to a time period. The service price for the current time period can be directly applied to the user service display and purchase process. The pre-planned prices for subsequent time periods can be dynamically adjusted during actual operation based on the re-acquired vehicle degradation trajectory, changes in user behavior, and service feedback results, thereby improving the adaptability of the pricing strategy.

[0143] Furthermore, to prevent increased vehicle degradation risks from preventing users from accessing necessary services in a timely manner, this embodiment further establishes a protective pricing strategy under degradation safety constraints. Specifically, based on the vehicle degradation trajectory prediction results, it is determined whether the vehicle battery health value will fall below a preset safety threshold within a future time period. When a high degradation risk is predicted for the vehicle, price constraints are set for safety-related in-vehicle services such as fault warnings, in-depth maintenance, and roadside assistance. By lowering service prices, the likelihood of user purchases is increased, guiding users to promptly adopt services that can improve the vehicle's degradation status, thereby reducing the risk of further vehicle degradation.

[0144] Through the above methods, this embodiment achieves cross-cycle dynamic pricing that considers service revenue, vehicle health status, and long-term user value based on vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data. This allows in-vehicle service prices to be optimized based on the vehicle's entire lifecycle status rather than being limited to current cycle revenue, thus improving the foresight and rationality of in-vehicle service pricing.

[0145] In one embodiment of this application, generating a recommended list of in-vehicle services based on a battery degradation trajectory and a service pricing sequence includes: extracting a health trajectory sequence from the battery degradation trajectory; identifying a battery degradation stage based on the health trajectory sequence; determining a target recommendation strategy for the in-vehicle services based on the battery degradation stage; and generating a recommended list of in-vehicle services based on the target recommendation strategy and the service pricing sequence.

[0146] The target recommendation strategy is a strategy model used to determine the recommendation method for in-vehicle services. In this application, it represents the service type, recommendation priority, and recommendation method matched according to the battery degradation stage of the vehicle. The recommendation list is a set of in-vehicle services provided to the user. In this application, it represents the in-vehicle service recommendation results that are adapted to the user's needs based on the vehicle degradation status and service pricing scheme.

[0147] Understandably, this application extracts the health trajectory sequence from the battery degradation trajectory, identifies battery degradation stages based on health change trends, and further combines different degradation stages to determine target recommendation strategies and corresponding service pricing sequences to generate an in-vehicle service recommendation list. This enables the service recommendation process to match the vehicle's performance changes. Compared to methods that only recommend services based on user preferences or current vehicle status, this application can dynamically adjust the recommended content according to the vehicle's future degradation trends, making the recommended services more in line with the vehicle's current and future usage needs, and improving the adaptability and effectiveness of in-vehicle service recommendations.

[0148] The degradation stage adaptive strategy of this application is as follows: different degradation stages are divided according to the battery health value. For example, when the battery health value is greater than 90%, the vehicle is determined to be in the early degradation stage; when the battery health value is between 80% and 90%, the vehicle is determined to be in the mid-degradation stage; when the battery health value is between 70% and 80%, the vehicle is determined to be in the late degradation stage; and when the battery health value is less than 70%, the vehicle is determined to be in the final degradation stage. Different degradation stages correspond to different vehicle states, service requirements, and cost structures.

[0149] Furthermore, based on the identified vehicle degradation stage, a corresponding in-vehicle service recommendation strategy is determined. In the early degradation stage, the overall vehicle condition is relatively good, and the decline in battery performance has a smaller impact on the user experience. Therefore, the recommendation strategy focuses on improving user experience and user stickiness, prioritizing experiential in-vehicle services such as in-vehicle entertainment, in-vehicle office, and lifestyle services. At the same time, a pricing method that improves user conversion rate is adopted in conjunction with the service pricing sequence.

[0150] During the mid-term degradation phase, the vehicle's battery health value begins to decline, and changes in battery performance gradually affect the vehicle's energy consumption. Therefore, the recommended strategy includes adding preventative maintenance services and energy consumption optimization services, and providing cross-cycle preferential schemes such as preventative maintenance packages based on service pricing sequences to guide users to perform vehicle maintenance in advance.

[0151] In the later stages of degradation, the rate of vehicle degradation increases further and the risk of failure gradually rises. Therefore, the recommended strategy is to focus on maintenance and support-related in-vehicle services, while prioritizing in-vehicle services that can improve the vehicle degradation trajectory and reduce subsequent service costs.

[0152] In the final degradation stage, vehicles approach the preset degradation threshold, and vehicle safety risks and usage costs further increase. Therefore, the recommended strategy focuses on services such as extended warranty, vehicle trade-in discounts, and vehicle upgrade programs, prioritizing vehicle safety and long-term user value, rather than simply pursuing service benefits in the current cycle.

[0153] Finally, target in-vehicle services are selected from multiple in-vehicle services based on the target recommendation strategy, and the corresponding service prices are determined by combining the service pricing sequence, generating a recommended list of in-vehicle services for display to the user. Through this method, the recommendation results can simultaneously consider the vehicle's current degradation state, future degradation trends, and service price changes, achieving degradation-aware service recommendations based on the vehicle's entire lifecycle status.

[0154] In one embodiment of this application, after generating a recommended list of in-vehicle services based on the target recommendation strategy and service pricing sequence, the method further includes: determining the preference matching weight of the in-vehicle services based on user behavior data; determining the pricing rationality weight of the in-vehicle services based on the service pricing sequence; determining the service degradation improvement index and degradation stage weight of the in-vehicle services based on the battery degradation trajectory; calculating the recommendation priority of the in-vehicle services based on the user preference matching weight, pricing rationality weight, service degradation improvement index, and degradation stage weight; and sorting the in-vehicle services in the recommended list according to the recommendation priority.

[0155] Among them, the preference matching weight is a parameter used to measure the degree of matching between in-vehicle services and user needs. In this application, it represents the degree of user preference for different in-vehicle services determined based on user driving behavior, service usage habits, and historical consumption behavior. The pricing reasonableness weight is a parameter used to evaluate the price suitability of in-vehicle services. In this application, it represents the price reasonableness index determined based on the relationship between service pricing sequence and vehicle status and service value. The service degradation improvement index is an evaluation index used to characterize the effect of in-vehicle services on improving the degradation status of vehicles. In this application, it represents the service value parameter determined based on the degree of improvement of battery health status by in-vehicle services. The degradation stage weight is a parameter used to indicate the importance of services under different battery degradation stages. In this application, it represents the weight coefficient for adjusting the service recommendation priority based on the current and future degradation status of the vehicle. The recommendation priority is an evaluation result used to indicate the recommendation order of different in-vehicle services. In this application, it represents the service ranking basis calculated comprehensively based on user needs, service prices, and vehicle degradation improvement effects.

[0156] Understandably, this application determines preference matching weights based on user behavior data, pricing rationality weights based on service pricing sequences, and service degradation improvement indices and degradation stage weights by combining battery degradation trajectories. It further calculates the recommendation priority of in-vehicle services and sorts the recommendation list. This approach, based on user needs matching, considers both vehicle degradation improvement effects and service price suitability, achieving multi-factor service ranking. Compared to recommendations solely based on user preferences, this application prioritizes services with higher adaptability to the current vehicle degradation state, improving the matching degree between recommendation results and vehicle health management needs, and enhancing the effectiveness of in-vehicle service recommendations.

[0157] Specifically, the interactive display and degradation trajectory correction iterative process of this application includes degradation trajectory error monitoring and online model parameter correction. The specific process is as follows: First, the preference matching weight of in-vehicle services is determined based on user behavior data. This user behavior data includes user driving behavior data, in-vehicle service usage data, payment history data, and scenario demand data. By analyzing users' historical service usage, service preferences, and payment behavior, the user's preference for different in-vehicle services is determined, and corresponding preference matching weights are generated. For example, for users who frequently use in-vehicle entertainment functions, the preference matching weight for entertainment services is increased; for users with long-distance driving needs, the preference matching weight for protection services is increased.

[0158] Secondly, the pricing rationality weight of in-vehicle services is determined based on the service pricing sequence. Specifically, by comparing the actual price of in-vehicle services in the current period with the service pricing sequence generated by forward-looking dynamic pricing, the degree of matching between the current service price and users' willingness to pay and service value is evaluated, and pricing rationality weights are generated based on the evaluation results.

[0159] Furthermore, the service degradation improvement index and degradation stage weights for in-vehicle services are determined based on the battery degradation trajectory. The service degradation improvement index evaluates the vehicle degradation improvement effect per unit price of the in-vehicle service, and can be expressed as the amount of battery health value improvement achieved per unit price. The service degradation improvement index depends on the service degradation impact vector. For example, deep maintenance services can determine the amount of battery health value improvement based on changes in vehicle status before and after maintenance collected by the battery management system; in practical applications, the improvement effect can be approximately 2%-3%. Battery health management services can determine the degree of degradation rate improvement based on changes in user behavior and internal resistance growth, for example, reducing the degradation rate by approximately 3%-5%. Energy consumption optimization services can determine the degree of reduction in the impact of internal resistance growth on energy consumption based on driving behavior optimization and energy consumption management effects, for example, reducing it by approximately 10%-15%.

[0160] Because the improvement effects of in-vehicle services vary at different degradation stages, a weighting system is implemented for each degradation stage. When a vehicle is in the early degradation stage, its overall condition is good, and there is significant room for service improvement, resulting in a lower weighting for the degradation stage. As the vehicle enters the mid-, late-, or final degradation stages, the degree of degradation increases, and the value of services that can improve the degradation state rises. Therefore, the weighting of each degradation stage is gradually increased, allowing services that can slow down vehicle degradation to receive a higher recommendation priority.

[0161] Specifically, this application ranks services based on the degradation improvement index, and calculates the recommendation priority of in-vehicle services according to the weights of user preference matching, pricing rationality, service degradation improvement index, and degradation stage. For example: Recommendation priority = User preference matching weight + Pricing reasonableness weight + Service degradation improvement index × Degradation stage weight.

[0162] Among these factors, a higher service degradation improvement index indicates a more significant improvement in battery health value per unit of service price; a higher degradation stage weight indicates a higher current degradation risk for the vehicle, and this application is more inclined to recommend in-vehicle services that can improve the vehicle's degradation trajectory. Based on the calculated recommendation priority, the in-vehicle services in the recommendation list are sorted, and the recommendation results are displayed to the user according to the sorting results.

[0163] Furthermore, to improve the accuracy of the recommendation results, this embodiment can also perform closed-loop optimization of the recommendation model based on user interaction feedback and the actual operating status of the vehicle. Specifically, at the end of each time period, the predicted vehicle degradation trajectory is compared with the actual collected vehicle degradation data. When the prediction error of the battery health value or the prediction error of the internal resistance exceeds a preset threshold (e.g., 5%), the degradation trajectory correction process is triggered.

[0164] During model calibration, the parameters in the joint degradation kinetics model are adjusted based on the prediction error. For example, when this application consistently overestimates the degree of vehicle degradation, the corresponding weight in the user behavior degradation influence coefficient is reduced; when this application consistently underestimates the degree of vehicle degradation, the corresponding weight is increased. Simultaneously, the parameters of the electrochemical degradation baseline model are revised based on the latest collected vehicle degradation data, enabling the prediction model to more accurately reflect the actual degradation trend of the vehicle.

[0165] After completing the degradation trajectory correction, the forward-looking dynamic pricing process is re-executed to generate an updated service pricing sequence, and the weight parameters in the tripartite joint objective function are adjusted according to the actual business results.

[0166] The present application will be further described in detail below with reference to specific embodiments. The technical solutions in the embodiments of the present application are clearly and completely described. The specific values ​​and implementation methods below are for illustrative purposes only and are not intended to limit the scope of the application.

[0167] This application constructs a correlation between user behavior and vehicle degradation by collecting user behavior data, vehicle status data, and battery degradation data. It uses a degradation impact coefficient to characterize the influence of different user driving and charging habits on the vehicle degradation process, and combines this with the feedback effect of service consumption on the degradation trajectory to achieve dynamic adjustment of in-vehicle service pricing and recommendation strategies. The following sections illustrate the application scenarios under different user behavior characteristics and vehicle degradation states.

[0168] In one embodiment of this application, the user has a daily morning rush hour commute, frequently uses in-car music services, has a strong willingness to pay, and is a user with high user lifetime value.

[0169] Regarding the vehicle's condition, this is a new energy vehicle that has been in use for 18 months. The current battery health value is 94%, which is in the early stage of degradation. The vehicle's energy consumption per 100 kilometers is 12kWh, which is lower than the industry average.

[0170] Furthermore, this application analyzes the user's influence on vehicle degradation based on user behavior data. This user primarily uses slow charging, with a fast charging dependency of only 10%, lower than the average user's 30% fast charging rate, and the charging depth remains within a moderate range. Therefore, the user's behavioral degradation impact coefficient is calculated based on degradation influencing factors such as fast charging dependency and charging / discharging depth. =0.85, indicating that the user's driving and charging behavior can slow down vehicle degradation, which is a relatively friendly usage habit.

[0171] Based on current vehicle status parameters, user future behavior patterns, and behavior degradation impact coefficient The combined degradation dynamics model predicts the vehicle's degradation trajectory over the next 12 months. The prediction results show that the vehicle will remain in the early degradation stage for the next 7 months and is expected to enter the mid-degradation stage in the 7th month.

[0172] In the specific operation, the data acquisition module collects user behavior data, vehicle status data, and battery degradation dynamics data; the data processing module cleans, normalizes, and extracts degradation features from the collected data; the user profile building module clusters users into the "high-frequency commuting, high willingness to pay" type based on their driving behavior, service usage, and payment behavior, predicting that the user's willingness to pay is approximately 12-15 yuan / month, and simultaneously calculates the behavioral degradation impact coefficient. =0.85.

[0173] Subsequently, the joint degradation dynamics module predicts the degradation trajectory for the next 12 months based on the above data, and calculates the service cost trajectory based on the trend of battery health value changes. Since the vehicle is currently in the early degradation stage, the vehicle's health status is relatively stable for the first 7 months, and the corresponding maintenance costs change little; when the vehicle enters the mid-degradation stage, as the battery health value declines, maintenance needs increase, and service costs begin to rise.

[0174] Furthermore, this application constructs service consumption degradation feedback data through service consumption degradation feedback modeling. For preventative maintenance services, a corresponding degradation impact vector is established, and the improvement in battery health value after purchasing this service is calculated to be approximately +2%. Simultaneously, based on the service effect decay function, the service decay period is set to 6 months, meaning the service improvement effect will gradually decrease over time. If a user purchases this preventative maintenance service, this application predicts that the future degradation trajectory will improve, and the future service cost trajectory is expected to decrease by approximately 15%.

[0175] Based on vehicle degradation trajectory, service cost trajectory, and service consumption degradation feedback data, a forward-looking dynamic pricing strategy is adopted for cross-cycle joint optimization to determine service pricing sequences corresponding to multiple time periods. In the first 7 months, when the vehicle is in the early degradation stage, user experience-related in-vehicle services are the main recommendations, and the pricing strategy focuses on improving user conversion rates and user stickiness. Starting from the 7th month, when the vehicle enters the mid-degradation stage, the system recommends preventive maintenance packages in advance and adopts an "early bird discount" strategy.

[0176] Specifically, although the current period may result in a short-term revenue loss of about 5 yuan due to the preferential pricing, the preventive maintenance service can delay vehicle degradation and reduce maintenance costs in subsequent periods by about 12 yuan. Therefore, from the perspective of the entire life cycle, this pricing strategy can achieve the overall optimization of service revenue, vehicle health status and long-term user value.

[0177] During the degradation perception recommendation process, since the vehicle is currently in the early degradation stage, the recommendation strategy focuses on experiential services such as in-vehicle entertainment and in-vehicle office. At the same time, users are shown preventive maintenance discount plans for when the vehicle enters the mid-term degradation stage, so that users can understand the future maintenance needs of the vehicle in advance.

[0178] During the degradation trajectory correction process, the system continuously compares the predicted degradation trajectory with the actual vehicle state changes. The current prediction error is less than 1%, which has not reached the correction threshold, so there is no need to adjust the degradation model parameters.

[0179] Through the above methods, users can obtain cost-effective experience services in the early degradation stage, while the system plans maintenance service recommendations and pricing strategies in advance for the mid-stage, achieving full lifecycle optimization of "low price to increase user stickiness and high-value service conversion in the future".

[0180] In the above embodiments, the user has a low degradation impact coefficient and the vehicle is in the early degradation stage. This application achieves a balance between user value, vehicle health and service revenue by predicting future degradation trends in advance and combining experiential services with preventive maintenance services.

[0181] Furthermore, to illustrate the adaptability of this application under different user behavior patterns and different vehicle degradation states, the following uses a user scenario with frequent fast charging and rapid degradation as an example to further explain the in-vehicle service recommendation method provided by this application.

[0182] In another embodiment of this application, the user is 28 years old, self-employed, has a need to travel late at night, and has a moderate overall willingness to pay, belonging to the mid-lifecycle value user category.

[0183] Regarding the vehicle's condition, this is a new energy vehicle that has been in use for 30 months. The current battery health value is 85%, which is in the mid-term degradation stage. The energy consumption per 100 kilometers is 15kWh, which is higher than the industry average.

[0184] Furthermore, this application analyzes the impact of user degradation based on user behavior data. This user frequently uses fast charging, with a fast charging rate of 60%, significantly higher than the average user's 30%. Simultaneously, there is a high proportion of deep discharge behavior, reaching 45%. The behavioral degradation impact coefficient is calculated based on degradation influencing factors such as fast charging dependence, deep discharge rate, and high-rate discharge. =1.35, indicating that the user's driving and charging behavior will accelerate vehicle degradation.

[0185] Based on current vehicle status parameters, user future behavior patterns, and behavior degradation impact coefficient A joint degradation dynamics model predicts the vehicle degradation trajectory over the next 12 months. The prediction results show that if users continue with their current charging habits, the vehicle is expected to enter the late degradation stage in the 5th month and the final degradation stage in the 9th month, with a degradation rate significantly faster than the average user.

[0186] Specifically, this application collects vehicle charging and discharging data for degradation characteristic analysis. The charging and discharging voltage curves show that the battery internal resistance increases at an accelerated rate, and the peak value of the capacity increment curve (dQ / dV) shows a significant shift, indicating that the vehicle has entered the accelerated degradation range.

[0187] Based on user behavior data, service usage data, and payment data, the user profiling module clusters the user into the "mid-frequency at night, moderate willingness to pay" type and calculates the behavioral degradation impact coefficient. =1.35.

[0188] Subsequently, the joint degradation kinetics module predicted the degradation trajectory over the next 12 months. The prediction results indicate that without service intervention, the vehicle will enter the final degradation stage in the 9th month. Simultaneously, based on the trends in battery health values ​​and internal resistance growth, the service cost trajectory was calculated, revealing a rapid increase in vehicle maintenance costs and energy-related costs after the 5th month.

[0189] Furthermore, this application constructs service consumption degradation feedback data through service consumption degradation feedback modeling. For battery health management services, a corresponding degradation impact vector is established, calculating that the improvement in battery health value after purchasing the service is approximately +3%, and setting the service effect decay period to 12 months. If a user purchases this service, this application predicts that the vehicle degradation trajectory will be improved, the time to enter the late degradation stage is expected to be delayed by approximately 2 months, and the future service cost trajectory is expected to decrease by approximately 20%.

[0190] Based on vehicle degradation trajectories, service cost trajectories, and service consumption degradation feedback data, a forward-looking dynamic pricing strategy is employed for cross-cycle joint optimization to determine service pricing sequences for multiple time periods. The system recommends the battery health management service and sets its price at 25 yuan / month, lower than the 35 yuan / month price for purchasing the corresponding service separately.

[0191] Through joint optimization calculations, the current period's revenue is reduced by about 5 yuan due to preferential pricing. However, since the service can delay vehicle degradation, the service cost in subsequent periods is reduced by about 40 yuan. Therefore, the net revenue over the entire life cycle increases by about 35 yuan, achieving a three-way optimal balance between user vehicle health protection, automaker service revenue, and user long-term value.

[0192] During the degradation perception recommendation process, since the user's vehicle is in the mid-stage of degradation and the behavioral degradation impact coefficient is high, the system calculates that the battery health management service has the highest degradation improvement index, prioritizes recommending this service, and displays the reasons for the recommendation to the user: "Based on your charging habits and the degradation trend of your vehicle's battery, we recommend this battery health management service, which can delay vehicle degradation by about 4 months and save you about 40 yuan in subsequent maintenance costs." During the degradation trajectory correction process, after a user purchases a service, the system continuously collects vehicle operation data and updates the degradation trajectory prediction results, while also monitoring whether the user improves their charging habits. If the system identifies a user exhibiting a behavior trend that continuously accelerates vehicle degradation, it uses degradation awareness to recommend and guide the user to adopt services that can improve the vehicle's degradation trajectory.

[0193] Through these methods, users can gain access to visualization of vehicle degradation status and economic incentives, thereby increasing their willingness to purchase services; automakers can optimize service recommendations and pricing strategies based on the vehicle's entire lifecycle status, achieving a three-way optimal balance between user value, vehicle health maintenance, and service revenue.

[0194] In summary, the overall structure of this application is as follows: Figure 2 As shown, the details are as follows: First, user behavior data, vehicle status data, and battery degradation data are acquired. Based on the user behavior data, user profiles are built to predict users' willingness to pay. At the same time, the user behavior degradation impact coefficient is calculated to quantify the degree of impact of users' driving and charging habits on battery degradation.

[0195] Furthermore, by combining the battery electrochemical degradation model and the user behavior degradation coupling function, the battery degradation trajectory for multiple future time periods is predicted based on vehicle status data, battery degradation data, and user behavior degradation impact coefficient, and the service cost trajectory is calculated based on the degradation trajectory.

[0196] Based on this, service consumption degradation feedback data is constructed according to the impact vector of in-vehicle services on battery degradation trajectory and service effect decay function. Then, forward-looking dynamic pricing is carried out by combining vehicle degradation trajectory, service cost trajectory and service consumption degradation feedback data to generate service pricing sequence and in-vehicle service recommendation results.

[0197] At the same time, the degradation trajectory is updated and corrected based on the actual service effect, realizing closed-loop optimization of degradation prediction, service pricing and service recommendation processes.

[0198] The specific process of the vehicle service recommendation method in this application embodiment is as follows: Figure 3 As shown, the details are as follows: First, user behavior data, vehicle status data, and battery degradation data are acquired and processed to extract feature information related to user behavior and battery degradation.

[0199] User profiles are constructed based on processed user behavior data, and user behavior degradation impact coefficients are calculated to quantify the impact of different driving and charging habits on the battery degradation process. Furthermore, by combining a battery electrochemical degradation model and a user behavior degradation coupling function, battery degradation trajectories for multiple future time periods are predicted based on vehicle state data, battery degradation data, and user behavior degradation impact coefficients. The corresponding service cost trajectories are then calculated based on these degradation trajectories.

[0200] Building upon this foundation, by combining the impact vector of in-vehicle services on battery degradation trajectory and the service effectiveness decay function, service consumption degradation feedback data is constructed to describe the impact of user service purchases on vehicle degradation status and subsequent service costs. Furthermore, based on vehicle degradation trajectory, service cost trajectory, and service consumption degradation feedback data, forward-looking dynamic pricing optimization is performed to generate a service pricing sequence.

[0201] Finally, a recommended list of in-vehicle services is generated based on the battery degradation stage, service pricing results, and user needs. The recommendations are then ranked based on user preference matching, pricing rationality, and the effectiveness of service degradation improvement. Simultaneously, through degradation trajectory error monitoring and online model parameter correction, closed-loop optimization is achieved, improving the accuracy of degradation prediction, dynamic pricing, and service recommendations.

[0202] like Figure 4 As shown, the overall process of the in-vehicle service recommendation method in this application revolves around battery degradation trajectory prediction, service cost trajectory calculation, service consumption degradation feedback, service pricing optimization, and model calibration, as detailed below: First, the battery degradation trajectory is predicted based on user behavior data, vehicle status data, and battery degradation data. Specifically, user profiles and degradation impact coefficients are determined based on user behavior data, and the amount of battery degradation at multiple future time points is calculated by combining vehicle status data and battery degradation data, generating a health trajectory sequence and an internal resistance trajectory sequence corresponding to multiple future time periods.

[0203] Furthermore, the service cost trajectory of the vehicle is calculated based on the battery degradation trajectory. Maintenance service costs are calculated based on the health trajectory sequence, energy consumption service costs are calculated based on the internal resistance trajectory sequence, and failure risk costs are calculated based on the health trajectory sequence and internal resistance trajectory sequence, thus obtaining the service cost trajectories for multiple future periods.

[0204] Based on this, the consumption degradation feedback data of in-vehicle services is calculated according to the impact vector of in-vehicle services on battery degradation trajectory and the service effect decay value. This data is used to describe the improvement effect of users purchasing in-vehicle services on battery degradation trajectory and the impact of service effect on changes over time.

[0205] Furthermore, a service pricing sequence is calculated based on vehicle degradation trajectory, service cost trajectory, and consumer degradation feedback data. Service revenue, vehicle health, and user value are jointly optimized using an objective function to obtain service price data for multiple time periods. Finally, an in-vehicle service recommendation list is generated based on the battery degradation trajectory and service pricing sequence.

[0206] Finally, based on the degradation data after actual service execution, the predicted battery degradation trajectory is monitored for error, and the degradation prediction results are updated online by correcting the model parameters, thereby achieving closed-loop optimization of the in-vehicle service recommendation and service pricing process.

[0207] According to the in-vehicle service recommendation method proposed in this application, firstly, user behavior data, vehicle status data, and battery degradation data are acquired and fused to construct a multidimensional dataset reflecting user usage characteristics, vehicle operating status, and battery health status. By fusing multi-source data, a data foundation is provided for subsequent battery degradation trend prediction. Secondly, based on user behavior data, vehicle status data, and battery degradation data, the future degradation process of the battery is predicted to obtain the battery degradation trajectory. By establishing a dynamic prediction model for battery degradation, the trend of health status changes within the future operating cycle of the vehicle is obtained, avoiding service decisions based solely on the current state and improving the foresight of service pricing. Then… This method calculates the service cost trajectory corresponding to the vehicle based on the battery degradation trajectory. Combining the impact vector of in-vehicle services on the battery degradation trajectory and the service effect decay value, it calculates the consumption degradation feedback data of in-vehicle services. By establishing the correlation between service cost changes and service consumption impact, it quantifies the impact of different in-vehicle services on vehicle status changes. Finally, based on the vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data, it calculates the pricing sequence of in-vehicle services. Combining the battery degradation trajectory and service pricing sequence, it generates a recommended list of in-vehicle services. By comprehensively considering the impact of vehicle status changes, service cost changes, and service feedback, it achieves dynamic pricing and accurate recommendations for in-vehicle value-added services, improving service matching and user experience. This solves the problems of related technologies that adjust value-added service prices based on user data, vehicle status data, or market information, making price adjustments solely based on existing data, and resulting in pricing results that do not match actual user needs.

[0208] Next, the in-vehicle service recommendation device proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0209] Figure 5 This is a block diagram of an in-vehicle service recommendation device according to an embodiment of this application.

[0210] like Figure 5 As shown, the in-vehicle service recommendation device 10 includes: an acquisition module 100, a prediction module 200, a calculation module 300, and a generation module 400.

[0211] The system includes: an acquisition module 100 for acquiring user behavior data, vehicle status data, and battery degradation data; a prediction module 200 for predicting the battery degradation trajectory based on the user behavior data, vehicle status data, and battery degradation data; a calculation module 300 for calculating the vehicle's service cost trajectory based on the battery degradation trajectory, and calculating the consumption degradation feedback data of the in-vehicle service based on the influence vector of the in-vehicle service on the battery degradation trajectory and the service effect attenuation value; and a generation module 400 for calculating the service pricing sequence based on the vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data, and generating a recommendation list of in-vehicle services based on the battery degradation trajectory and service pricing sequence.

[0212] It should be noted that the foregoing explanation of the in-vehicle service recommendation method embodiment also applies to the in-vehicle service recommendation device of this embodiment, and will not be repeated here.

[0213] According to the in-vehicle service recommendation device proposed in this application, firstly, user behavior data, vehicle status data, and battery degradation data are acquired and fused to construct a multidimensional dataset reflecting user usage characteristics, vehicle operating status, and battery health status. By fusing multi-source data, a data foundation is provided for subsequent battery degradation trend prediction. Secondly, based on the user behavior data, vehicle status data, and battery degradation data, the future battery degradation process is predicted to obtain the battery degradation trajectory. By establishing a dynamic battery degradation prediction model, the trend of vehicle health status changes within future operating cycles is obtained, avoiding service decisions based solely on the current state and improving the foresight of service pricing. Then… This method calculates the service cost trajectory corresponding to the vehicle based on the battery degradation trajectory. Combining the impact vector of in-vehicle services on the battery degradation trajectory and the service effect decay value, it calculates the consumption degradation feedback data of in-vehicle services. By establishing the correlation between service cost changes and service consumption impact, it quantifies the impact of different in-vehicle services on vehicle status changes. Finally, based on the vehicle degradation trajectory, service cost trajectory, and consumption degradation feedback data, it calculates the pricing sequence of in-vehicle services. Combining the battery degradation trajectory and service pricing sequence, it generates a recommended list of in-vehicle services. By comprehensively considering the impact of vehicle status changes, service cost changes, and service feedback, it achieves dynamic pricing and accurate recommendations for in-vehicle value-added services, improving service matching and user experience. This solves the problems of related technologies that adjust value-added service prices based on user data, vehicle status data, or market information, making price adjustments solely based on existing data, and resulting in pricing results that do not match actual user needs.

[0214] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0215] When the processor 602 executes the program, it implements the in-vehicle service recommendation method provided in the above embodiments.

[0216] Furthermore, electronic devices also include: Communication interface 603 is used for communication between memory 601 and processor 602.

[0217] The memory 601 is used to store computer programs that can run on the processor 602.

[0218] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0219] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0220] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0221] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0222] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0223] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0224] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0225] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0226] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0227] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for recommending in-vehicle services, characterized in that, Includes the following steps: Acquire user behavior data, vehicle status data, and battery degradation data; Predict the battery degradation trajectory based on the user behavior data, the vehicle status data, and the battery degradation data; The service cost trajectory of the vehicle is calculated based on the battery degradation trajectory, and the consumption degradation feedback data of the vehicle service is calculated based on the influence vector of the vehicle service on the battery degradation trajectory and the service effect attenuation value. The service pricing sequence is calculated based on the vehicle degradation trajectory, the service cost trajectory, and the consumer degradation feedback data. A recommended list of in-vehicle services is generated based on the battery degradation trajectory and the service pricing sequence.

2. The in-vehicle service recommendation method according to claim 1, characterized in that, The step of predicting the battery degradation trajectory based on the user behavior data, the vehicle status data, and the battery degradation data includes: Based on the user behavior data, determine the user profile and degradation impact coefficient; Calculate the amount of battery degradation at multiple future moments based on the vehicle status data and the battery degradation data; The battery degradation trajectory is generated based on the user profile, the degradation impact coefficient, and the battery degradation amount at multiple future time points.

3. The in-vehicle service recommendation method according to claim 2, characterized in that, The process of determining the user profile and degradation impact coefficient based on the user behavior data includes: Extract user driving behavior data, in-vehicle service usage data, payment history data, and user information from the user behavior data; Multiple degradation influencing factors are determined based on the user driving behavior data, and the degradation influencing coefficient is calculated by weighting the multiple degradation influencing factors. User category tags are determined based on the user driving behavior data, the in-vehicle service usage data, and the payment history data. The user profile is then constructed based on the user category tags and the user information.

4. The in-vehicle service recommendation method according to claim 2, characterized in that, The step of generating the battery degradation trajectory based on the user profile, the degradation impact coefficient, and the battery degradation amount at multiple future time points includes: Predict future user behavior patterns based on the user profile, and extract current battery state parameters from the battery degradation data; Based on the current battery state parameters, the user's future behavior pattern, the degradation impact coefficient, and the amount of battery degradation at multiple future moments, predict the health value and internal resistance value at multiple future moments; A health trajectory sequence is generated based on the health values ​​at multiple future time points, an internal resistance trajectory sequence is generated based on the internal resistance values ​​at multiple future time points, and the battery degradation trajectory is generated based on the health trajectory sequence and the internal resistance trajectory sequence.

5. The in-vehicle service recommendation method according to claim 2, characterized in that, Before generating the battery degradation trajectory based on the user profile, the degradation impact coefficient, and the battery degradation amount at multiple future time points, the method further includes: Extract the charging data from the battery degradation data; The degradation increment of the vehicle is calculated based on the charging data; The amount of battery degradation in the vehicle is corrected based on the degradation increment.

6. The in-vehicle service recommendation method according to claim 1, characterized in that, The step of calculating the service cost trajectory of the vehicle based on the battery degradation trajectory includes: Extract the health trajectory sequence and internal resistance trajectory sequence from the battery degradation trajectory; The battery degradation stage is identified based on the health trajectory sequence, and the service cost structure of the vehicle is determined based on the degradation stage. The service cost trajectory of the vehicle is calculated based on the service cost structure, the health trajectory sequence, and the internal resistance trajectory sequence.

7. The in-vehicle service recommendation method according to claim 6, characterized in that, The step of calculating the service cost trajectory of the vehicle based on the service cost structure, the health trajectory sequence, and the internal resistance trajectory sequence includes: The maintenance and repair service cost of the vehicle is calculated based on the health trajectory sequence. The energy service cost of the vehicle is calculated based on the internal resistance trajectory sequence. The failure risk cost of the vehicle is calculated based on the health trajectory sequence and the internal resistance trajectory sequence. The service cost trajectory of the vehicle is calculated by identifying the target cost corresponding to each period in the service cost structure, wherein the target cost corresponding to each period includes at least one of the maintenance service cost, the energy consumption service cost, and the failure risk cost.

8. The in-vehicle service recommendation method according to claim 1, characterized in that, The step of calculating the service pricing sequence based on the vehicle degradation trajectory, the service cost trajectory, and the consumption degradation feedback data includes: Read the pre-set objective function, which includes service revenue, vehicle health, and total vehicle value; The vehicle degradation trajectory, the service cost trajectory, and the consumption degradation feedback data are input into the objective function; The service price data for at least one in-vehicle service is determined by solving the objective function, and a service pricing sequence is generated based on the service price data of at least one in-vehicle service.

9. The in-vehicle service recommendation method according to claim 1, characterized in that, The step of generating a recommended list of in-vehicle services based on the battery degradation trajectory and the service pricing sequence includes: Extract the health trajectory sequence from the battery degradation trajectory; The battery degradation stage is identified based on the health trajectory sequence; The target recommendation strategy for in-vehicle services is determined based on the battery degradation stage. A recommendation list of in-vehicle services is generated based on the target recommendation strategy and the service pricing sequence.

10. The in-vehicle service recommendation method according to claim 9, characterized in that, After generating the recommended list of in-vehicle services based on the target recommendation strategy and the service pricing sequence, the method further includes: The preference matching weight of the in-vehicle service is determined based on the user behavior data. The pricing rationality weight of the in-vehicle service is determined based on the service pricing sequence; The service degradation improvement index and degradation stage weight of the in-vehicle service are determined based on the battery degradation trajectory. The recommendation priority of the in-vehicle service is calculated based on the user preference matching weight, the pricing rationality weight, the service degradation improvement index, and the degradation stage weight. The in-vehicle services in the recommendation list are then sorted according to the recommendation priority.

11. An in-vehicle service recommendation device, characterized in that, include: The acquisition module is used to acquire user behavior data, vehicle status data, and battery degradation data. The prediction module is used to predict the battery degradation trajectory based on the user behavior data, the vehicle status data, and the battery degradation data. The calculation module is used to calculate the service cost trajectory of the vehicle based on the battery degradation trajectory, and to calculate the consumption degradation feedback data of the vehicle service based on the influence vector of the vehicle service on the battery degradation trajectory and the service effect attenuation value. The generation module is used to calculate a service pricing sequence based on the vehicle degradation trajectory, the service cost trajectory, and the consumer degradation feedback data, and to generate a recommendation list of the in-vehicle services based on the battery degradation trajectory and the service pricing sequence.

12. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the in-vehicle service recommendation method according to any one of claims 1-10.

Images