Vehicle energy consumption improvement method and system based on user behavior feedback

Abstract

The invention relates to the technical field of vehicle energy consumption analysis, and discloses a vehicle energy consumption improvement method based on user behavior feedback, and the method comprises the following steps: searching a benchmarking vehicle; user behavior comparison and diagnosis: based on Internet of Vehicles big data, user driving behavior classification is established, driving behaviors and corresponding energy consumption of a target vehicle and a benchmarking vehicle are compared, and an association rule of a high-energy-consumption association behavior and a low-energy-consumption association behavior is identified; and improvement and verification of a diagnosis result: pushing personalized driving improvement suggestions, recording oil consumption data before and after the user adopts the suggestions, calculating an energy consumption improvement degree, and forming closed-loop feedback. The invention further discloses a vehicle energy consumption improvement system based on user behavior feedback. According to the vehicle energy consumption improvement method and system based on the user behavior feedback, by constructing a multi-dimensional benchmarking vehicle search mechanism, a refined driving behavior diagnosis model and a closed-loop feedback verification system, energy-saving driving guidance of thousands of people and thousands of faces is achieved, and the vehicle economy is remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle energy consumption analysis technology, specifically to a method and system for improving vehicle energy consumption based on user behavior feedback. Background Technology

[0002] Existing vehicle energy consumption management technologies typically employ an open-loop architecture of "data collection—behavior scoring—generalized prompts." Basic data such as vehicle speed, engine speed, and fuel consumption are collected via a TBox. A driving behavior analysis module then uses preset thresholds to statistically determine events such as rapid acceleration, rapid deceleration, and speeding. Finally, general energy-saving prompts are provided through the in-vehicle human-machine interface (HMI). However, this type of solution has the following drawbacks: (1) Single dimension of user behavior analysis: focusing only on macro events and ignoring the temporal characteristics and operational quality of micro operations; (2) Lack of personalized adaptation: The differences in driver style are not taken into account, resulting in poor universality of the suggestions and low user acceptance; (3) The system is an open-loop structure: the actual effect of the improvement measures cannot be verified, and there is no feedback mechanism for optimizing the analysis model.

[0003] Therefore, there is an urgent need for a method to improve vehicle energy consumption that can achieve a closed loop of "benchmarking-analysis-intervention-verification-optimization". Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of the aforementioned technologies by providing a method and system for improving vehicle energy consumption based on user behavior feedback. By constructing a multi-dimensional benchmark vehicle search mechanism, a refined driving behavior diagnostic model, and a closed-loop feedback verification system, it achieves personalized energy-saving driving guidance for each user, significantly improving vehicle economy.

[0005] To achieve the above objectives, the vehicle energy consumption improvement method based on user behavior feedback designed in this invention includes the following steps: A) Finding benchmark vehicles: Identify the current application scenario of the target vehicle from the scenario library, and extract a list of vehicles with the same application scenario. Based on driving trajectory, vehicle configuration and powertrain configuration, obtain vehicles with higher matching degree to the target vehicle until the number of vehicles is less than the preset threshold. Then, use the current candidate vehicle as the benchmark vehicle. B) User behavior comparison and diagnosis: Based on the big data of the Internet of Vehicles, establish a classification of user driving behavior, divide driving behavior into periodic behavior and specific trajectory line behavior, and identify driving style type by combining cluster analysis, reduce the dimensionality of driving behavior features based on principal component analysis, and establish the association rules between driving behavior and vehicle energy consumption. Compare the driving behavior and corresponding energy consumption of the target vehicle and the benchmark vehicle, and identify the association rules between high energy consumption related behaviors and low energy consumption related behaviors. C) Improvement and verification of diagnostic results: Based on the driving style type of the target vehicle, personalized driving improvement suggestions are pushed based on the aforementioned correlation rules. Fuel consumption data before and after the user adopts the suggestions are recorded, the degree of energy consumption improvement is calculated, the improved energy consumption level of the target vehicle is compared with that of the benchmark vehicle, and an excess percentage prompt message is generated to form a closed-loop feedback.

[0006] Preferably, in step A), the current application scenario of the target vehicle is identified from the scenario library, and a list of vehicles with the same application scenario is extracted. If the number of vehicles is less than a preset threshold, the narrowing filter is no longer performed; otherwise, the filtering continues. Based on the same scenario, the driving trajectories of vehicles in the vehicle list are matched with the driving trajectories of the target vehicles. The driving trajectories of vehicles are divided into typical trajectory segments such as "highway", "national and provincial roads", "urban traffic" or "mountain uphill and downhill". Vehicles with a high degree of overlap and a high number of overlaps with the typical trajectory segments of the target vehicles are extracted. If the number of vehicles is less than the preset threshold, the narrowing of the selection is no longer performed; otherwise, the selection continues. Based on the same trajectory, extract the same vehicle model configuration or powertrain configuration as the target vehicle from the extracted vehicle list to achieve a vehicle configuration that is more consistent with the target vehicle, while reducing the number of vehicles.

[0007] Preferably, machine learning is used to quantify the contribution of scenarios, driving trajectories, vehicle configurations, or powertrain configurations to the selection of benchmark vehicles, generating an interpretable attribution report.

[0008] Preferably, while generating the attribution report, user feedback on the search results for benchmark vehicles is recorded, and the search model for subsequent benchmark vehicles is optimized through an active learning mechanism based on this feedback.

[0009] Preferably, in step B), when establishing the user driving behavior classification, the macro level includes one or more of the following: vehicle speed control, engine speed control, throttle control, braking control, and gear control, to assess the user's driving behavior characteristics. The micro level includes one or more of the following: vehicle speed change rate, engine speed fluctuation rate, throttle change rate, brake pedal linearity, and gear change rate, to assess the user's operation quality and identify hidden inefficient behaviors. At the biometric level, the driver's state is determined through facial recognition using the in-vehicle camera, and physiological data is combined to enhance the analysis dimensions.

[0010] Preferably, the hidden inefficient behaviors include one or more of the following: a timing pattern of rapid acceleration followed by rapid braking, frequent lane changes and overtaking, or excessive reliance on the accelerator on undulating road sections.

[0011] Preferably, in step B), the driving data over a period of time is statistically analyzed and counted as periodic behavior, and the user behavior on a specific trajectory line is monitored and counted as specific trajectory line behavior.

[0012] Preferably, in step B), the driving style type includes one or more of the following: aggressive, conservative, or stable.

[0013] Preferably, in step C), the suggested push format is dynamically adjusted based on the user's historical response behavior. The first push is presented in text form through the mobile terminal, and when it appears repeatedly, it is reminded in voice form through the in-vehicle human-machine interface.

[0014] A vehicle energy consumption improvement system based on user behavior feedback, used in the vehicle energy consumption improvement method based on user behavior feedback, includes: Benchmark vehicle search module: Execute step A). User behavior comparison and diagnosis module: Step B). Improvement and Verification Module: Execution Step C). Data acquisition module: Collects vehicle network data of the target vehicle and the benchmark vehicle through TBox, including vehicle speed, RPM, fuel consumption, gear position, and braking signal; Human-computer interaction module: Pushes personalized driving improvement suggestions to users and receives user feedback; Machine learning optimization module: Based on user feedback, continuously optimizes the vehicle search model through an active learning mechanism.

[0015] Compared with existing technologies, this invention has the following advantages: under different scenarios, routes, vehicle types, and engine displacements, it identifies and compares user behaviors of target vehicles and comparison vehicles, and proposes improvement suggestions. By constructing a multi-dimensional benchmark vehicle search mechanism, a refined driving behavior diagnosis model, and a closed-loop feedback verification system, it achieves personalized energy-saving driving guidance, user behavior feedback and intervention, improves the energy consumption of target vehicles, and significantly enhances vehicle economy. Detailed Implementation

[0016] The technical solution of the present invention will be clearly and completely described below with reference to specific embodiments. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the shown orientation or positional relationships and are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0018] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0019] Example 1 A method for improving vehicle energy consumption based on user behavior feedback includes the following steps: A) Finding benchmark vehicles: Identify the current application scenario of the target vehicle from the scenario library, and extract a list of vehicles with the same application scenario. Based on driving trajectory, vehicle configuration and powertrain configuration, obtain vehicles with higher matching degree to the target vehicle until the number of vehicles is less than the preset threshold. Then, use the current candidate vehicle as the benchmark vehicle. B) User behavior comparison and diagnosis: Based on the big data of the Internet of Vehicles, establish a classification of user driving behavior, divide driving behavior into periodic behavior and specific trajectory line behavior, and identify driving style type by combining cluster analysis, reduce the dimensionality of driving behavior features based on principal component analysis, and establish the association rules between driving behavior and vehicle energy consumption. Compare the driving behavior and corresponding energy consumption of the target vehicle and the benchmark vehicle, and identify the association rules between high energy consumption related behaviors and low energy consumption related behaviors. C) Improvement and verification of diagnostic results: Based on the driving style type of the target vehicle, personalized driving improvement suggestions are pushed based on the aforementioned correlation rules. Fuel consumption data before and after the user adopts the suggestions are recorded, the degree of energy consumption improvement is calculated, the improved energy consumption level of the target vehicle is compared with that of the benchmark vehicle, and an excess percentage prompt message is generated to form a closed-loop feedback.

[0020] In this embodiment, a vehicle energy consumption improvement system based on user behavior feedback is used for a vehicle energy consumption improvement method based on user behavior feedback, including: Benchmark vehicle search module: Execute step A). User behavior comparison and diagnosis module: Step B). Improvement and Verification Module: Execution Step C). Data acquisition module: Collects vehicle network data of the target vehicle and the benchmark vehicle through TBox, including vehicle speed, RPM, fuel consumption, gear position, and braking signal; Human-computer interaction module: Pushes personalized driving improvement suggestions to users and receives user feedback; Machine learning optimization module: Based on user feedback, continuously optimizes the vehicle search model through an active learning mechanism.

[0021] Example 2 A method for improving vehicle energy consumption based on user behavior feedback includes the following steps: A) Finding benchmark vehicles: Identify the current application scenario of the target vehicle from the scenario library, and extract a list of vehicles with the same application scenario. Based on driving trajectory, vehicle configuration and powertrain configuration, obtain vehicles with higher matching degree to the target vehicle until the number of vehicles is less than the preset threshold. Then, use the current candidate vehicle as the benchmark vehicle. B) User behavior comparison and diagnosis: Based on the big data of the Internet of Vehicles, establish a classification of user driving behavior, divide driving behavior into periodic behavior and specific trajectory line behavior, and identify driving style type by combining cluster analysis, reduce the dimensionality of driving behavior features based on principal component analysis, and establish the association rules between driving behavior and vehicle energy consumption. Compare the driving behavior and corresponding energy consumption of the target vehicle and the benchmark vehicle, and identify the association rules between high energy consumption related behaviors and low energy consumption related behaviors. C) Improvement and verification of diagnostic results: Based on the driving style type of the target vehicle, personalized driving improvement suggestions are pushed based on the aforementioned correlation rules. Fuel consumption data before and after the user adopts the suggestions are recorded, the degree of energy consumption improvement is calculated, the improved energy consumption level of the target vehicle is compared with that of the benchmark vehicle, and an excess percentage prompt message is generated to form a closed-loop feedback.

[0022] In step A), the current application scenario of the target vehicle is identified from the scenario library, and a list of vehicles with the same application scenario is extracted. If the number of vehicles is less than a preset threshold, the narrowing filter is no longer performed; otherwise, the filter continues. Based on the same scenario, the driving trajectories of vehicles in the vehicle list are matched with the driving trajectories of the target vehicles. The driving trajectories of vehicles are divided into typical trajectory segments such as "highway", "national and provincial roads", "urban traffic" or "mountain uphill and downhill". Vehicles with a high degree of overlap and a high number of overlaps with the typical trajectory segments of the target vehicles are extracted. If the number of vehicles is less than the preset threshold, the narrowing of the selection is no longer performed; otherwise, the selection continues. Based on the same trajectory, extract the same vehicle model configuration or powertrain configuration as the target vehicle from the extracted vehicle list to achieve a vehicle configuration that is more consistent with the target vehicle, while reducing the number of vehicles.

[0023] In this embodiment, a vehicle energy consumption improvement system based on user behavior feedback is used for a vehicle energy consumption improvement method based on user behavior feedback, including: Benchmark vehicle search module: Execute step A). User behavior comparison and diagnosis module: Step B). Improvement and Verification Module: Execution Step C). Data acquisition module: Collects vehicle network data of the target vehicle and the benchmark vehicle through TBox, including vehicle speed, RPM, fuel consumption, gear position, and braking signal; Human-computer interaction module: Pushes personalized driving improvement suggestions to users and receives user feedback; Machine learning optimization module: Based on user feedback, continuously optimizes the vehicle search model through an active learning mechanism.

[0024] Example 3 A method for improving vehicle energy consumption based on user behavior feedback includes the following steps: A) Finding benchmark vehicles: Identify the current application scenario of the target vehicle from the scenario library, and extract a list of vehicles with the same application scenario. Based on driving trajectory, vehicle configuration and powertrain configuration, obtain vehicles with higher matching degree to the target vehicle until the number of vehicles is less than the preset threshold. Then, use the current candidate vehicle as the benchmark vehicle. B) User behavior comparison and diagnosis: Based on the big data of the Internet of Vehicles, establish a classification of user driving behavior, divide driving behavior into periodic behavior and specific trajectory line behavior, and identify driving style type by combining cluster analysis, reduce the dimensionality of driving behavior features based on principal component analysis, and establish the association rules between driving behavior and vehicle energy consumption. Compare the driving behavior and corresponding energy consumption of the target vehicle and the benchmark vehicle, and identify the association rules between high energy consumption related behaviors and low energy consumption related behaviors. C) Improvement and verification of diagnostic results: Based on the driving style type of the target vehicle, personalized driving improvement suggestions are pushed based on the aforementioned correlation rules. Fuel consumption data before and after the user adopts the suggestions are recorded, the degree of energy consumption improvement is calculated, the improved energy consumption level of the target vehicle is compared with that of the benchmark vehicle, and an excess percentage prompt message is generated to form a closed-loop feedback.

[0025] In step A), the current application scenario of the target vehicle is identified from the scenario library, and a list of vehicles with the same application scenario is extracted. If the number of vehicles is less than a preset threshold, the narrowing filter is no longer performed; otherwise, the filter continues. Based on the same scenario, the driving trajectories of vehicles in the vehicle list are matched with the driving trajectories of the target vehicles. The driving trajectories of vehicles are divided into typical trajectory segments such as "highway", "national and provincial roads", "urban traffic" or "mountain uphill and downhill". Vehicles with a high degree of overlap and a high number of overlaps with the typical trajectory segments of the target vehicles are extracted. If the number of vehicles is less than the preset threshold, the narrowing of the selection is no longer performed; otherwise, the selection continues. Based on the same trajectory, extract the same vehicle model configuration or powertrain configuration as the target vehicle from the extracted vehicle list to achieve a vehicle configuration that is more consistent with the target vehicle, while reducing the number of vehicles.

[0026] Finally, machine learning is used to quantify the contribution of scene, driving trajectory, vehicle configuration, or powertrain configuration to the selection of benchmark vehicles, generating an interpretable attribution report. Simultaneously, user feedback on benchmark vehicle search results is recorded, and based on this feedback, an active learning mechanism is used to optimize subsequent benchmark vehicle search models.

[0027] In this embodiment, a vehicle energy consumption improvement system based on user behavior feedback is used for a vehicle energy consumption improvement method based on user behavior feedback, including: Benchmark vehicle search module: Execute step A). User behavior comparison and diagnosis module: Step B). Improvement and Verification Module: Execution Step C). Data acquisition module: Collects vehicle network data of the target vehicle and the benchmark vehicle through TBox, including vehicle speed, RPM, fuel consumption, gear position, and braking signal; Human-computer interaction module: Pushes personalized driving improvement suggestions to users and receives user feedback; Machine learning optimization module: Based on user feedback, continuously optimizes the vehicle search model through an active learning mechanism.

[0028] Example 4 A method for improving vehicle energy consumption based on user behavior feedback includes the following steps: A) Finding benchmark vehicles: Identify the current application scenario of the target vehicle from the scenario library, and extract a list of vehicles with the same application scenario. Based on driving trajectory, vehicle configuration and powertrain configuration, obtain vehicles with higher matching degree to the target vehicle until the number of vehicles is less than the preset threshold. Then, use the current candidate vehicle as the benchmark vehicle. B) User behavior comparison and diagnosis: Based on the big data of the Internet of Vehicles, establish a classification of user driving behavior, divide driving behavior into periodic behavior and specific trajectory line behavior, and identify driving style type by combining cluster analysis, reduce the dimensionality of driving behavior features based on principal component analysis, and establish the association rules between driving behavior and vehicle energy consumption. Compare the driving behavior and corresponding energy consumption of the target vehicle and the benchmark vehicle, and identify the association rules between high energy consumption related behaviors and low energy consumption related behaviors. C) Improvement and verification of diagnostic results: Based on the driving style type of the target vehicle, personalized driving improvement suggestions are pushed based on the aforementioned correlation rules. Fuel consumption data before and after the user adopts the suggestions are recorded, the degree of energy consumption improvement is calculated, the improved energy consumption level of the target vehicle is compared with that of the benchmark vehicle, and an excess percentage prompt message is generated to form a closed-loop feedback.

[0029] In step A), the current application scenario of the target vehicle is identified from the scenario library, and a list of vehicles with the same application scenario is extracted. If the number of vehicles is less than a preset threshold, the narrowing filter is no longer performed; otherwise, the filter continues. Based on the same scenario, the driving trajectories of vehicles in the vehicle list are matched with the driving trajectories of the target vehicles. The driving trajectories of vehicles are divided into typical trajectory segments such as "highway", "national and provincial roads", "urban traffic" or "mountain uphill and downhill". Vehicles with a high degree of overlap and a high number of overlaps with the typical trajectory segments of the target vehicles are extracted. If the number of vehicles is less than the preset threshold, the narrowing of the selection is no longer performed; otherwise, the selection continues. Based on the same trajectory, extract the same vehicle model configuration or powertrain configuration as the target vehicle from the extracted vehicle list to achieve a vehicle configuration that is more consistent with the target vehicle, while reducing the number of vehicles.

[0030] Finally, machine learning is used to quantify the contribution of scene, driving trajectory, vehicle configuration, or powertrain configuration to the selection of benchmark vehicles, generating an interpretable attribution report. Simultaneously, user feedback on benchmark vehicle search results is recorded, and based on this feedback, an active learning mechanism is used to optimize subsequent benchmark vehicle search models.

[0031] In step B), when establishing the user driving behavior classification, the macro level includes one or more of the following: vehicle speed control, engine speed control, throttle control, braking control, and gear control, to assess the user's driving behavior characteristics. The micro level includes one or more of the following: vehicle speed change rate, engine speed fluctuation rate, throttle change rate, brake pedal linearity, and gear change rate, to assess the quality of user operation and identify hidden inefficient behaviors. At the biometric level, the driver's state is determined through facial recognition using the in-vehicle camera, and physiological data is combined to enhance the analysis dimensions.

[0032] Specifically, hidden inefficient behaviors include one or more of the following: a timing pattern of rapid acceleration followed by rapid braking, frequent lane changes and overtaking, or excessive reliance on the accelerator on undulating road sections.

[0033] In step B), the driving data over a period of time is statistically analyzed and counted as periodic behavior, and user behavior on a specific trajectory line is monitored and counted as behavior on that specific trajectory line.

[0034] In step B), the driving style type includes one or more of the following: aggressive, conservative, or stable.

[0035] In step C), the suggested push format is dynamically adjusted based on the user's historical response behavior. The first push is presented in text form through the mobile terminal, and when it appears repeatedly, it is reminded in voice form through the in-vehicle human-machine interface.

[0036] In this embodiment, a vehicle energy consumption improvement system based on user behavior feedback is used for a vehicle energy consumption improvement method based on user behavior feedback, including: Benchmark vehicle search module: Execute step A). User behavior comparison and diagnosis module: Step B). Improvement and Verification Module: Execution Step C). Data acquisition module: Collects vehicle network data of the target vehicle and the benchmark vehicle through TBox, including vehicle speed, RPM, fuel consumption, gear position, and braking signal; Human-computer interaction module: Pushes personalized driving improvement suggestions to users and receives user feedback; Machine learning optimization module: Based on user feedback, continuously optimizes the vehicle search model through an active learning mechanism.

[0037] Compared with existing technologies, the vehicle energy consumption closed-loop analysis method and system based on big data of this invention have the following differences: 1. Expand user behavior analysis from macro-statistics to micro-level operational quality assessment and driving style clustering to identify hidden inefficient behaviors; 2. By analyzing the correlation between driving behavior and energy consumption, different user behaviors of different vehicles can be identified, and personalized user behavior feedback and intervention can be generated, which improves the problems of no proactive guidance for user driving behavior and no quantitative tracking.

[0038] This invention relates to a vehicle energy consumption improvement method and system based on user behavior feedback. Under different scenarios, routes, vehicle types, and engine displacements, it identifies and compares user behavior between target vehicles and comparison vehicles, and proposes improvement suggestions. By constructing a multi-dimensional benchmark vehicle search mechanism, a refined driving behavior diagnostic model, and a closed-loop feedback verification system, it achieves personalized energy-saving driving guidance, user behavior feedback and intervention, improves the energy consumption of target vehicles, and significantly enhances vehicle economy.

[0039] It should be noted that the above description of the technical solutions is exemplary, and this specification may be embodied in different forms and should not be construed as limiting it to the technical solutions set forth herein. Rather, providing these descriptions will ensure that the disclosure of this invention is thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Furthermore, the technical solutions of this invention are defined only by the scope of the claims.

[0040] The aspects disclosed in this specification and claims are merely examples, and therefore, this specification and claims are not limited to the details shown. In the foregoing description, detailed descriptions of relevant known functions or configurations have been omitted where it would unnecessarily obscure the focus of this specification and claims.

[0041] When using the terms “comprising,” “having,” and “including” as described in this specification, there may be another part or other part unless used, and the terms used are generally singular but may also be plural.

[0042] Finally, it should be noted that the above description is a further detailed explanation of the invention in conjunction with specific embodiments. It should not be considered that the specific implementation of the invention is limited to these descriptions. For those skilled in the art, any simple substitutions made without departing from the concept of the invention should be considered within the scope of protection of this invention. The above embodiments are merely representative examples of the invention. Obviously, the invention is not limited to the above embodiments and many variations are possible. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the invention should be considered within the scope of protection of this invention.

[0043] It should be noted that the above description of the technical solutions is exemplary, and this specification may be embodied in different forms and should not be construed as limiting it to the technical solutions set forth herein. Rather, providing these descriptions will ensure that the disclosure of this invention is thorough and complete, and will fully convey the scope of this specification to those skilled in the art. Furthermore, the technical solutions of this invention are defined only by the scope of the claims. Features of various embodiments of this invention may be combined or spliced ​​together in part or in whole, and may be implemented in various different configurations as will be fully understood by those skilled in the art. Embodiments of this invention may be implemented independently of each other or may be implemented together in an interdependent relationship.

[0044] For those skilled in the art, several simple deductions or substitutions can be made without departing from the concept of the present invention, and the above structures should all be considered to fall within the protection scope of the present invention.

Claims

1. A method for improving vehicle energy consumption based on user behavior feedback, characterized in that: Includes the following steps: A) Finding benchmark vehicles: Identify the current application scenario of the target vehicle from the scenario library, and extract a list of vehicles with the same application scenario. Based on driving trajectory, vehicle configuration and powertrain configuration, obtain vehicles with higher matching degree to the target vehicle until the number of vehicles is less than the preset threshold. Then, use the current candidate vehicle as the benchmark vehicle. B) User behavior comparison and diagnosis: Based on the big data of the Internet of Vehicles, establish a classification of user driving behavior, divide driving behavior into periodic behavior and specific trajectory line behavior, and identify driving style type by combining cluster analysis, reduce the dimensionality of driving behavior features based on principal component analysis, and establish the association rules between driving behavior and vehicle energy consumption. Compare the driving behavior and corresponding energy consumption of the target vehicle and the benchmark vehicle, and identify the association rules between high energy consumption related behaviors and low energy consumption related behaviors. C) Improvement and verification of diagnostic results: Based on the driving style type of the target vehicle, personalized driving improvement suggestions are pushed based on the aforementioned correlation rules. Fuel consumption data before and after the user adopts the suggestions are recorded, the degree of energy consumption improvement is calculated, the improved energy consumption level of the target vehicle is compared with that of the benchmark vehicle, and an excess percentage prompt message is generated to form a closed-loop feedback.

2. The vehicle energy consumption improvement method based on user behavior feedback according to claim 1, characterized in that: In step A), the current application scenario of the target vehicle is identified from the scenario library, and a list of vehicles with the same application scenario is extracted. If the number of vehicles is less than a preset threshold, the narrowing filter is no longer performed; otherwise, the filter continues. Based on the same scenario, the driving trajectories of vehicles in the vehicle list are matched with the driving trajectories of the target vehicles. The driving trajectories of vehicles are divided into typical trajectory segments such as "highway", "national and provincial roads", "urban traffic" or "mountain uphill and downhill". Vehicles with a high degree of overlap and a high number of overlaps with the typical trajectory segments of the target vehicles are extracted. If the number of vehicles is less than the preset threshold, the narrowing of the selection is no longer performed; otherwise, the selection continues. Based on the same trajectory, extract the same vehicle model configuration or powertrain configuration as the target vehicle from the extracted vehicle list to achieve a vehicle configuration that is more consistent with the target vehicle, while reducing the number of vehicles.

3. The vehicle energy consumption improvement method based on user behavior feedback according to claim 2, characterized in that: Machine learning is used to quantify the contribution of scenarios, driving trajectories, vehicle configurations, or powertrain configurations to the selection of benchmark vehicles, generating interpretable attribution reports.

4. The vehicle energy consumption improvement method based on user behavior feedback according to claim 3, characterized in that: While generating attribution reports, user feedback on benchmark vehicle search results is recorded, and the search model for subsequent benchmark vehicles is optimized through an active learning mechanism based on this feedback.

5. The vehicle energy consumption improvement method based on user behavior feedback according to claim 1, characterized in that: In step B), when establishing the user driving behavior classification, the macro level includes one or more of the following: vehicle speed control, engine speed control, throttle control, braking control, and gear control, to assess the user's driving behavior characteristics. The micro level includes one or more of the following: vehicle speed change rate, engine speed fluctuation rate, throttle change rate, brake pedal linearity, and gear change rate, to assess the user's operation quality and identify hidden inefficient behaviors. At the biometric level, the driver's state is determined through facial recognition using the in-vehicle camera, and physiological data is combined to enhance the analysis dimensions.

6. The vehicle energy consumption improvement method based on user behavior feedback according to claim 5, characterized in that: Hidden inefficient behaviors include one or more of the following: a pattern of rapid acceleration followed by rapid braking, frequent lane changes and overtaking, or excessive reliance on the accelerator on undulating road sections.

7. The vehicle energy consumption improvement method based on user behavior feedback according to claim 1, characterized in that: In step B), the driving data over a period of time is statistically analyzed and counted as periodic behavior, and the user behavior on a specific trajectory line is monitored and counted as specific trajectory line behavior.

8. The vehicle energy consumption improvement method based on user behavior feedback according to claim 1, characterized in that: In step B), the driving style type includes one or more of the following: aggressive, conservative, or stable.

9. The vehicle energy consumption improvement method based on user behavior feedback according to claim 1, characterized in that: In step C), the suggested push format is dynamically adjusted based on the user's historical response behavior. The first push is presented in text form through the mobile terminal, and when it appears repeatedly, it is reminded in voice form through the in-vehicle human-machine interface.

10. A vehicle energy consumption improvement system based on user behavior feedback, characterized in that: The vehicle energy consumption improvement method based on user behavior feedback as described in any one of claims 1 to 9 includes: Benchmark vehicle search module: Execute step A). User behavior comparison and diagnosis module: Step B). Improvement and Verification Module: Execution Step C). Data acquisition module: Collects vehicle network data of the target vehicle and the benchmark vehicle through TBox, including vehicle speed, RPM, fuel consumption, gear position, and braking signal; Human-computer interaction module: Pushes personalized driving improvement suggestions to users and receives user feedback; Machine learning optimization module: Based on user feedback, continuously optimize the vehicle search model through an active learning mechanism.