Battery use suggestion information generation method and device, medium and electronic equipment

Abstract

The invention discloses a battery use suggestion information generation method and device, a medium and electronic equipment, and the method comprises the steps: analyzing the charging data of a battery of a vehicle, and obtaining the charging feature information; analyzing the driving data of the vehicle to obtain driving characteristic information; analyzing the battery use data of the vehicle to obtain energy consumption influence information of the environmental parameters on the battery; performing energy consumption analysis on the configuration data of the vehicle to obtain basic energy consumption information of the battery; and according to the charging characteristic information, the driving characteristic information, the energy consumption influence information of the environmental parameters on the battery and the basic energy consumption information of the battery, generating battery use suggestion information of the vehicle. According to the method, the battery use suggestions are provided for the user in combination with data in multiple aspects.

Description

Technical Field

[0001] The present application belongs to the field of vehicle technology, and in particular, relates to a method, device, medium and electronic device for generating battery usage recommendation information. Background Art

[0002] With the rapid development of new energy vehicle technology, more and more users are using electric vehicles. Solid-state batteries are the main power source for electric vehicles. The performance of batteries in electric vehicles is not only related to the structure and composition of the battery itself, but also closely related to the user's battery usage habits. Bad battery usage behavior will greatly reduce battery performance and shorten the battery life. Therefore, it is necessary to provide users with battery usage recommendations. Summary of the invention

[0003] Embodiments of the present application provide a method, device, medium, and electronic device for generating battery usage recommendation information, which can generate battery usage recommendation information for the vehicle in a targeted manner by analyzing the vehicle's actual charging data, driving data, battery usage data, and configuration data.

[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0005] According to a first aspect of an embodiment of the present application, a method for generating battery usage recommendation information is provided, comprising: analyzing charging data of a vehicle's battery to obtain charging characteristic information; analyzing driving data of the vehicle to obtain driving characteristic information; analyzing battery usage data of the vehicle to obtain information on the impact of environmental parameters on energy consumption of the battery; performing energy consumption analysis on configuration data of the vehicle to obtain basic energy consumption information of the battery; and generating battery usage recommendation information for the vehicle based on the charging characteristic information, the driving characteristic information, the information on the impact of environmental parameters on energy consumption of the battery, and the basic energy consumption information of the battery.

[0006] According to a second aspect of an embodiment of the present application, a device for generating battery usage recommendation information is provided, including: a charging characteristic information determination module, used to analyze the charging data of a vehicle's battery to obtain charging characteristic information; a driving characteristic information determination module, used to analyze the driving data of the vehicle to obtain driving characteristic information; an energy consumption impact information determination module, used to analyze the battery usage data of the vehicle to obtain information on the impact of environmental parameters on the energy consumption of the battery; a basic energy consumption information determination module, used to perform energy consumption analysis on the configuration data of the vehicle to obtain basic energy consumption information of the battery; and a recommendation information generation module, used to generate battery usage recommendation information for the vehicle based on the charging characteristic information, the driving characteristic information, the information on the impact of environmental parameters on the energy consumption of the battery, and the basic energy consumption information of the battery.

[0007] According to a third aspect of an embodiment of the present application, a computer program product is provided, which includes computer instructions stored in a computer-readable storage medium and suitable for being read and executed by a processor, so that an electronic device having the processor executes the method provided in the first aspect above.

[0008] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, in which computer program instructions are stored. The computer program instructions are loaded and executed by a processor to implement the method provided in the first aspect above.

[0009] According to the fifth aspect of an embodiment of the present application, there is provided an electronic device, comprising a processor and a memory, wherein the memory stores computer program instructions that can be executed by the processor, and when the processor executes the computer program instructions, the method provided in the first aspect above is implemented.

[0010] In the present application, the charging characteristic information obtained from the battery charging data, the driving characteristic information extracted from the vehicle driving data, the information on the impact of environmental parameters on the battery energy consumption extracted from the battery usage data, and the basic energy consumption information of the battery are combined to generate targeted battery usage recommendations for the vehicle. The charging characteristic information reflects the characteristics of the user's charging behavior of the battery in the vehicle, and the driving characteristic information can reflect the characteristics of the user's driving behavior. Based on the charging characteristic information and the driving characteristic information, the charging and driving behaviors that have a greater impact on the battery energy consumption can be effectively analyzed, so that the user can be advised to reduce the charging and driving behaviors that have a greater impact on the battery energy consumption through subsequent battery usage recommendations, and it is recommended to adopt charging and driving behaviors that have a smaller impact on the battery energy consumption, which is beneficial to improving the battery life and reducing the impact on the battery energy consumption.

[0011] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0013] Figure 1 This is a flowchart of a method for generating battery usage suggestion information according to an embodiment of the present application.

[0014] Figure 2 A flowchart of step 150 in an embodiment of the present application is shown.

[0015] Figure 3 A flow chart showing a method for generating battery usage suggestion information in another embodiment of the present application is shown.

[0016] Figure 4 It is a parameter collected during the data collection process shown in an embodiment of the present application.

[0017] Figure 5 This is a process of analyzing battery usage habits according to an embodiment of the present application.

[0018] Figure 6 A and B in the figure respectively show the schematic diagrams of the vehicle speed before and after the vehicle speed is denoised by sliding filtering.

[0019] Figure 7 It is a schematic diagram showing the clustering result of charging frequencies according to an embodiment of the present application.

[0020] Figure 8 It is a schematic diagram showing prediction of the next recommended charging time period according to an embodiment of the present application.

[0021] Fig. 9 It is a schematic diagram of a predicted charging method according to an embodiment of the present application.

[0022] Fig.10 It is a schematic diagram of a vehicle acceleration analysis result according to an embodiment of the present application.

[0023] Fig.11 An acceleration time series graph drawn for a user is shown as an example.

[0024] Fig.12An acceleration distribution diagram drawn based on all users is exemplarily shown.

[0025] Fig.13 The diagram shows the changes of vehicle speeds of three users over time.

[0026] Fig.14 A vehicle speed profile is shown as an example.

[0027] Fig.15 This is the result of clustering users according to their mileage at different times as shown in an embodiment of the present application.

[0028] Fig.16 This is the result of performing a regression analysis on users according to their mileage at different times, as shown in an embodiment of the present application.

[0029] Fig.17 It is a decision tree for predicting mileage according to an embodiment of the present application.

[0030] Fig.18 The figure shows the statistical analysis results of driving time and mileage.

[0031] Fig.19 is a graph showing the relationship between temperature and charging times according to an embodiment of the present application.

[0032] Fig. 20 4 is a graph showing the relationship between temperature and discharge depth according to an embodiment of the present application.

[0033] Fig.21 4 is a graph showing the regression analysis results of temperature and charging times according to an embodiment of the present application.

[0034] Fig. 22 It is a schematic diagram showing predicted battery capacity and actual battery capacity at various humidity levels according to an embodiment of the present application.

[0035] Fig.23 is a schematic diagram showing an altitude analysis result according to an embodiment of the present application.

[0036] Fig.24 It is a schematic diagram of a road condition analysis result according to an embodiment of the present application.

[0037] Fig.25 It is a schematic diagram of a traffic environment analysis result according to an embodiment of the present application.

[0038] Fig.26 This is a diagram of clustering results under different usage modes according to an embodiment of the present application.

[0039] Fig. 27A schematic diagram showing the battery life under different battery capacities predicted by the linear regression model.

[0040] Fig.28 The result diagram of grouping is shown as an example.

[0041] Fig.29 , a flowchart for generating usage recommendations based on a battery life threshold is shown by way of example.

[0042] Fig.30 It is a schematic diagram of the regression result between motor power and battery energy consumption according to an embodiment of the present application.

[0043] Fig.31 It is a schematic diagram showing the clustering result of battery current and voltage according to an embodiment of the present application.

[0044] Fig.32 It is a schematic diagram of a battery pack status analysis result according to an embodiment of the present application.

[0045] Fig.33 It is a schematic diagram of the charging and discharging habit analysis results of the data in the battery management system according to an embodiment of the present application.

[0046] Fig.34 It is an architecture diagram of a big data platform according to an embodiment of the present application.

[0047] Fig.35 A block diagram of a device for generating battery usage suggestion information in an embodiment of the present application is shown.

[0048] Fig.36 A schematic diagram of an electronic device in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0051] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0052] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0053] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0054] In order to enable those skilled in the art to better understand the present application, the application scenarios involved in the present application are first briefly described.

[0055] With the rapid development of new energy vehicle technology, more and more users are using electric vehicles. Solid-state batteries are the main power source of electric vehicles. The performance of batteries in electric vehicles is not only related to the structure and composition of the battery itself, but also closely related to the user's battery usage habits. Bad battery usage behavior will greatly reduce battery performance and shorten the battery life. Therefore, it is necessary to provide users with battery usage recommendations to prompt users to use the vehicle's battery in a healthy way to reduce the impact of bad battery usage behavior on battery performance and service life.

[0056] Figure 1This is a flowchart of a method for generating battery usage suggestion information according to an embodiment of the present application. The method can be executed by an electronic device, such as a vehicle or a server (which can be a physical server or a cloud server), which is not specifically limited here. Figure 1 As shown, the method for generating battery usage suggestion information includes at least steps 110 to 150, which are described in detail as follows:

[0057] Step 110, analyzing the charging data of the battery of the vehicle to obtain charging characteristic information.

[0058] In the present application, a battery is provided on the vehicle, and the battery on the vehicle is used as the power of the vehicle, and the motor in the vehicle is used to drive the vehicle to travel. The battery on the vehicle can be a solid-state battery, and the type of the solid-state battery is not limited, and can be a lead-acid battery, a zinc-carbon battery, a lithium battery, etc.

[0059] The battery charging data refers to the data recording the charging process of the battery on the vehicle, which may include multiple battery charging records of the battery. Each battery charging record may include the battery charging method, the battery charging start time, the battery charging end time, the battery charging time, the battery charging current, the battery power when the battery starts charging, the battery power when the battery ends charging and other information.

[0060] The battery charging methods include fast charging, slow charging, and battery replacement. Fast charging refers to charging the battery on the vehicle through a charging station or a mobile charging vehicle. It mainly uses a large current to directly charge the battery, so that the battery can be charged to about 80% in a short time, and it can generally be fully charged in 1 hour. This method charges quickly, but may have a certain impact on the battery life.

[0061] Slow charging refers to charging the battery on the vehicle through an onboard charger or a household wall-mounted charging station. The charging current and power of this charging method are smaller than those of the fast charging method, but the charging time usually takes 6 to 8 hours. This method has a stable charging process and less damage to the battery.

[0062] Battery replacement means that when the battery on the vehicle runs out of power, a fully charged battery is used to replace the low-power battery pack, and then the replaced low-power battery can be sent to a charging station for charging. This method can save charging time, but the convenience and cost of battery replacement need to be considered.

[0063] The charging characteristic information refers to information reflecting the user's battery charging habits, or in other words, the charging characteristic information refers to information reflecting the charging characteristics of the battery on the vehicle.

[0064] In some embodiments, the charging characteristic information may include at least one of a charging frequency characteristic, a charging duration characteristic, and a charging method characteristic. Correspondingly, step 110 may include at least one of the following 1)-3):

[0065] 1) Perform charging frequency statistics on charging data to obtain charging frequency characteristics.

[0066] The charging frequency feature refers to a feature that reflects the characteristics of the charging frequency. For example, the charging frequency feature may include the charging frequency. At least one of the maximum charging frequency, the minimum charging frequency, the average charging frequency, and the charging frequency as the mode in the charging frequencies of multiple statistical cycles may be used as the charging frequency feature. The duration of a statistical cycle can be set according to actual needs, for example, it can be one week, one month, three months, half a year, etc., and is not specifically limited here.

[0067] The charging frequency characteristic directly reflects the charging frequency, and the charging frequency determines the number of times the battery is charged and discharged. The number of times the battery is charged and discharged will affect the battery life. That is, although frequent charging of the battery can ensure that the battery is always at a high level of power, too many charge and discharge cycles will accelerate the aging of the battery. On the contrary, too few charging times may cause the battery to be deeply discharged, which is also not good for the battery life. Therefore, by analyzing the charging frequency characteristics of the battery, it is possible to analyze whether this charging frequency characteristic has an adverse effect on the performance and life of the battery. If the current charging frequency characteristic is not good for the performance and life of the battery, the user can be prompted and advised to charge at a charging frequency that has less impact on the performance and life of the battery.

[0068] In some embodiments, the charging data includes multiple battery charging records, and the number of battery charging records within multiple statistical periods can be counted, and the number of battery charging records within a statistical period can be used as the number of charging times within the statistical period to further determine the charging frequency within each statistical period, and then the charging frequency within multiple statistical periods can be statistically analyzed to determine the charging frequency characteristics.

[0069] In some embodiments, charging frequency clustering can be performed on charging data of multiple vehicles to determine multiple charging frequency clustering categories, and then the charging frequency of the vehicle in multiple statistical periods can be obtained from the current vehicle charging data, and the charging frequency clustering category to which the vehicle belongs can be determined from the multiple charging frequency clustering categories according to the charging frequency of the vehicle in multiple statistical periods, and the charging frequency clustering category to which the determined vehicle belongs can be used as the charging frequency feature. Among them, a charging frequency clustering category can reflect the charging frequency at the center of the category under the category.

[0070] 2) Perform charging time statistics on the charging data to obtain charging time characteristics.

[0071] The charging time feature refers to the feature that reflects the characteristics of the charging time. The charging time feature may refer to the preferred charging time, the longest charging time, the shortest charging time, the average charging time, the standard deviation of multiple charging times, the charging time corresponding to the charging period with the most charging times, the charging time with the most charging times, the charging time with the least charging times, the charging time with the number of charging times exceeding a fourth threshold, etc. The preferred charging time may refer to the average charging time of multiple charging time periods.

[0072] In some embodiments, based on the start charging time and the end charging time in each battery charging record in the charging data, the charging time of each charging can be calculated. After that, multiple charging times are statistically analyzed, and the number of charging times corresponding to each charging time can also be counted, and the charging time characteristics as above can be determined.

[0073] In some embodiments, based on the start charging time and the end charging time in each battery charging record in the charging data, the charging time period corresponding to each battery charging record can be determined, the number of charging times in each charging time period can be counted, and the charging time corresponding to each charging time period can be determined, and the charging time characteristics as above can be determined.

[0074] Charging time can also affect battery performance. Long-term charging or discharging may cause the battery to overheat or overcool, thus affecting its performance. In addition, irregular charging time may also cause large fluctuations in battery power, which is not conducive to the stable use of the battery. Therefore, by analyzing the charging time characteristics of the battery, it is possible to analyze whether there is an adverse effect on the battery performance under this charging time characteristic. If the current charging time characteristic is not conducive to the battery performance, targeted suggestions and prompts can be given to the user, such as suggesting that the user should try to choose a relatively fixed charging time and ensure that the battery is charged within an appropriate temperature range.

[0075] 3) Perform charging mode statistics on the charging data to obtain charging mode characteristics.

[0076] The charging mode feature refers to a feature that reflects the characteristics of the charging mode. The charging mode feature may be a preferred charging mode, and the preferred charging mode may refer to a charging mode with the most charging times, or a charging mode with the charging times exceeding a second number threshold. The second number threshold may be set according to actual needs and is not specifically limited here.

[0077] In a specific embodiment, based on multiple battery charging records in the charging data, the charging method corresponding to each charging is obtained from each battery charging record, and then the charging times of each charging method are counted. According to the charging times of each charging method, a statistical analysis is performed on the multiple charging methods to determine the characteristics of the charging methods.

[0078] Step 120: Analyze the vehicle's driving data to obtain driving characteristic information.

[0079] The driving data of a vehicle refers to the data recording the driving process of the vehicle, and may include the speed, acceleration, mileage, acceleration time, deceleration time, gear position, etc. of the vehicle at each time point. Driving characteristic information refers to the information reflecting the driving behavior characteristics of the user corresponding to the vehicle, and can also be understood as information reflecting the driving habits of the user corresponding to the vehicle.

[0080] In some embodiments, the driving characteristic information includes at least one of an acceleration characteristic, a deceleration characteristic, a vehicle speed characteristic, and a mileage characteristic; correspondingly, step 120 includes at least one of the following ①-④:

[0081] ① Extract acceleration features from the vehicle’s driving data to obtain acceleration features.

[0082] Acceleration features refer to features that reflect the characteristics of user acceleration behavior. Acceleration features may include features that reflect the frequency of acceleration, features that reflect the magnitude of acceleration under acceleration, and features that reflect the smoothness of acceleration. Features that reflect the frequency of acceleration may include the maximum acceleration frequency, mean acceleration frequency, minimum acceleration frequency, etc. Features that reflect the magnitude of acceleration under acceleration may include the average value of acceleration under acceleration, the standard deviation of acceleration under acceleration, the maximum acceleration under acceleration, the minimum acceleration under acceleration, etc. Features that reflect the smoothness of acceleration may include the interquartile range of acceleration under acceleration.

[0083] The acceleration behavior of the vehicle will affect the performance of the vehicle's battery. For example, when accelerating suddenly, the battery needs to release a large amount of current in a short period of time to meet the vehicle's power needs, which will cause the chemical reaction inside the battery to accelerate and generate more heat, thereby accelerating the aging of the battery. Frequent sudden acceleration will cause the battery to be in a high-load state for a long time, increase the temperature, affect the battery's charging and discharging efficiency, reduce the battery's range, reduce the battery's overall energy efficiency, and may even cause irreversible damage. In addition, excessive acceleration will also cause uneven wear inside the battery and shorten the battery's life. Therefore, analyzing the acceleration characteristics of the vehicle can effectively determine whether the user's current acceleration behavior has a greater impact on the battery's performance, so as to facilitate subsequent battery usage recommendations for the user. For example, in order to extend the battery life and ensure the performance of the battery, the driver should be advised to avoid frequent and sudden acceleration and try to maintain a stable speed.

[0084] As described above, the vehicle's driving data includes the vehicle's acceleration at multiple time points and the speed at multiple time points. Therefore, the vehicle's acceleration time period can be determined first, and the acceleration can be statistically analyzed based on the vehicle's acceleration at multiple time points in the acceleration time period to determine the acceleration characteristics.

[0085] ② Extract the deceleration feature of the vehicle's driving data to obtain the deceleration feature.

[0086] The deceleration feature refers to a feature that reflects the deceleration characteristics of the user's vehicle operation. The deceleration feature may include a feature that reflects the deceleration frequency, a feature that reflects the magnitude of the acceleration under deceleration (in this case, the acceleration is a negative number), and a feature that reflects the smoothness of the deceleration. The feature that reflects the deceleration frequency may be the maximum deceleration frequency, the mean deceleration frequency, the minimum deceleration frequency, etc. The feature that reflects the magnitude of the acceleration under deceleration may be the mean acceleration under deceleration, the standard deviation of the acceleration under deceleration, the maximum acceleration under deceleration, the minimum acceleration under deceleration, etc. The feature that reflects the smoothness of the deceleration may be the interquartile range of the acceleration under deceleration.

[0087] The deceleration behavior of the vehicle will also affect the performance of the vehicle's battery. For example, in the case of sudden deceleration or sudden braking, the battery needs to quickly recover energy, which will have a certain impact on the battery. In addition, frequent sudden deceleration may also lead to reduced energy recovery efficiency and waste of electricity. Therefore, analyzing the deceleration characteristics of the vehicle can effectively determine whether the user's current deceleration behavior has a greater impact on the performance of the battery, so as to provide battery usage recommendations for users in the future. For example, during driving, try to avoid sudden deceleration and sudden braking, and use a gentle deceleration method, which is conducive to protecting the battery and improving energy recovery efficiency.

[0088] Similarly, since the vehicle's driving data includes the vehicle's acceleration at multiple time points and the speed at multiple time points, the vehicle's deceleration time period can be determined first, and the acceleration can be statistically analyzed based on the vehicle's acceleration at multiple time points in the deceleration time period to determine the deceleration characteristics.

[0089] ③ Extract the speed features of the vehicle’s driving data to obtain the vehicle speed features.

[0090] The speed feature refers to a feature that reflects the speed characteristics of the vehicle. The speed feature can be the average speed, maximum speed, minimum speed, standard deviation of the speed, preferred speed range, etc. If the proportion of the time period in which the speed is within a speed range to the total time period exceeds a proportion threshold, the speed range is called the preferred speed range.

[0091] As described above, the driving data of the vehicle includes the speed of the vehicle at multiple time points. Therefore, the speed of the vehicle at multiple time points can be statistically analyzed to obtain the above vehicle speed characteristics.

[0092] The speed of the vehicle during driving will also affect the performance of the vehicle's battery. For example, when driving at high speed, the vehicle needs to overcome greater air resistance and friction, which will increase battery energy consumption. In addition, high-speed driving may also cause problems such as battery overheating, affecting the safety and life of the battery. Therefore, analyzing the vehicle's speed characteristics can effectively determine whether the vehicle's current speed has a greater impact on the performance of the battery, so as to facilitate subsequent battery usage recommendations for users. For example, users can be advised to maintain a moderate speed under suitable road conditions, which will help reduce battery energy consumption and extend battery life.

[0093] ④ Extract mileage features from the vehicle’s driving data to obtain mileage features.

[0094] Mileage characteristics refer to characteristics that reflect the mileage characteristics of a vehicle. Mileage characteristics may include a single maximum mileage, average mileage, minimum mileage, etc.

[0095] In a specific embodiment, the mileage in a driving period can be counted according to the driving data of the vehicle, and then the mileage in multiple driving time periods can be counted to determine the mileage characteristics, for example, the maximum single mileage, average mileage, minimum mileage, etc. A driving time period refers to the time period from the start time to the end time period, and there is no intermediate driving end time point.

[0096] The vehicle's mileage will also affect the performance of the vehicle's battery. For example, long-term high-mileage driving may cause the battery to be over-discharged and over-charged, accelerating the battery's aging process. Therefore, analyzing the vehicle's mileage characteristics can effectively determine whether the vehicle's current mileage or the mileage in the recent period has a greater impact on the battery's performance, so as to provide battery usage recommendations for users in the future. For example, users are advised to avoid unnecessary long-distance driving to reduce the burden on the battery and extend its service life.

[0097] Step 130 , analyzing the battery usage data of the vehicle to obtain information on the impact of environmental parameters on battery energy consumption.

[0098] The battery usage data of the vehicle may include the battery usage record data of the vehicle under different environments, and the battery usage record data may include the number of times the battery is charged, the discharge depth of the battery, the battery temperature, the continuous power supply time of the battery, etc.

[0099] In some embodiments, the environmental parameter includes at least one of temperature, humidity, altitude, road roughness, and traffic environment; correspondingly, step 130 includes at least one of the following (1)-(5):

[0100] (1) Analyze the battery usage data of the vehicle at different temperatures to obtain information on the impact of temperature on battery performance.

[0101] Temperature (referring to the external ambient temperature, that is, the temperature of the vehicle's environment) is one of the key factors affecting battery performance. The ideal operating temperature of the battery is usually between 20℃-25℃. Too high or too low temperature will affect the battery's charging and discharging efficiency, life and safety. In a high temperature environment, the chemical reaction inside the battery is accelerated, which may cause the battery to overheat, swell or even explode. In a low temperature environment, the viscosity of the electrolyte inside the battery increases, and the conductivity decreases, resulting in a decrease in the battery's charging and discharging performance. Therefore, different temperatures have different effects on battery performance.

[0102] The information about the impact of temperature on battery energy consumption is used to reflect the impact of different temperatures on battery performance, or in other words, to reflect the relationship between temperature and battery performance, that is, how the battery energy consumption changes with temperature.

[0103] The battery usage data of the vehicle at different temperatures may include the number of times the battery is charged at different temperatures, the discharge depth of the battery, the battery temperature, and the continuous power supply time of the battery, where the continuous power supply time of the battery refers to the cumulative power supply time when the battery power drops from a first percentage to a second percentage. The first percentage and the second percentage can be set according to actual needs, for example, the first percentage is 100%, the second percentage is 10%, etc.

[0104] Based on the battery usage data of the vehicle at different temperatures, the number of charges at different temperatures, the depth of discharge at different temperatures, the battery temperature at different temperatures, and the battery power supply time at different temperatures can be obtained. Then, the relationship between temperature and the number of charges, the relationship between temperature and the depth of discharge, the relationship between temperature and the battery temperature, and the relationship between temperature and continuous power supply time can be established. The established relationship is used as information on the impact of temperature on battery energy consumption.

[0105] (2) Analyze the battery usage data of the vehicle under different humidity conditions to obtain information on the impact of humidity on battery energy consumption.

[0106] The information about the impact of humidity on battery energy consumption is used to reflect the degree of impact of different humidity on battery performance, or in other words, to reflect the changing relationship between humidity and battery performance. Humidity will also affect battery performance. A high humidity environment may cause internal corrosion of the battery, affect conductivity, and even cause a short circuit. It can be seen that humidity changes will affect battery performance.

[0107] In some embodiments, since the battery capacity can reflect the performance of the battery, the effect of humidity on the battery performance can be reflected in the effect of humidity on the battery capacity. Under different humidity conditions, the capacity of the same battery may be different. Therefore, the battery usage data of the vehicle at different humidity levels may include the battery capacity of the battery at different humidity levels. On this basis, the battery capacity of the vehicle at multiple humidity levels can be fitted to obtain a change curve reflecting the relationship between humidity and battery capacity, or a functional relationship between battery capacity and humidity changes. It is worth mentioning that the relationship between the change in humidity of different battery capacities may be different.

[0108] (3) Analyze the battery usage data of the vehicle at different altitudes to obtain information on the impact of altitude on battery energy consumption.

[0109] The information about the impact of altitude on battery energy consumption reflects the degree of impact of different altitudes on battery performance, or in other words, is used to reflect how battery performance changes with altitude.

[0110] Altitude also has a significant impact on battery performance. The thin oxygen in high altitude areas affects the battery discharge performance, the cruising range may be shortened, and it may also affect the battery consumption rate. In other words, the impact of altitude on battery performance is mainly reflected in the impact on the battery's cruising range. Generally speaking, the higher the altitude, the shorter the battery's cruising range and the faster the battery consumption rate.

[0111] Therefore, the information about the impact of altitude on battery energy consumption can reflect the relationship between the battery's range and altitude, and can reflect the relationship between the battery's battery consumption rate and altitude.

[0112] The information about the impact of altitude on battery energy consumption can be determined by analyzing the cruising range of the same battery at different altitudes and the battery consumption rate at different altitudes. In some embodiments, the cruising range of the same battery at different altitudes can be fitted to obtain a curve of the battery's cruising range changing with altitude, or to obtain a functional relationship between the battery's cruising range and altitude. Similarly, the battery consumption rate of the same battery at different altitudes can be fitted to obtain a curve of the battery's battery consumption rate changing with altitude, or to obtain a functional relationship between the battery's battery consumption rate and altitude. The obtained curve of the battery's cruising range changing with altitude (or the functional relationship between the battery's cruising range and altitude) and the curve of the battery's battery consumption rate changing with altitude (or the functional relationship between the battery's battery consumption rate and altitude) are used as the information about the impact of altitude on battery energy consumption.

[0113] (4) Analyze the battery usage data of the vehicle on multiple roads with different road roughness to obtain information on the impact of road roughness on battery energy consumption.

[0114] The ruggedness of the road can reflect the ruggedness of the road surface. The higher the ruggedness, the more rugged the road is, and the lower the ruggedness, the flatter the road is. The more rugged the road is, the greater the resistance of the vehicle will be, resulting in increased battery energy consumption; conversely, the flatter the road is, the less resistance the vehicle will have, and the corresponding battery energy consumption will be reduced.

[0115] The information on the impact of road roughness on battery energy consumption is used to reflect the impact of different road roughness on TV energy consumption.

[0116] In some embodiments, the battery usage data of a vehicle on multiple roads with different degrees of road ruggedness may include the battery charge, and then the battery consumption rate of the vehicle on the multiple roads with different degrees of road ruggedness may be calculated. It can be understood that the higher the road ruggedness, the greater the battery consumption rate, and conversely, the lower the road ruggedness, the smaller the battery consumption rate.

[0117] In some embodiments, multiple road roughness levels may be pre-set, and then the battery consumption rate of the vehicle on multiple roads with different roughness levels is obtained, and the battery consumption rate is fitted to obtain the relationship between the battery consumption rate and the road roughness level.

[0118] In some embodiments, a linear regression model can be used to simulate the effect of different road roughness levels (for example, the road roughness level can be set to 1 to represent very rugged, and the road roughness level can be set to 0 to represent flat) on battery energy consumption. Subsequently, the linear regression model can be used to determine the battery consumption rate of the vehicle under the current road roughness level.

[0119] In some embodiments, since the battery consumption rate of the battery on the road is also related to the driver's driving skills, generally speaking, on the same road, for the same vehicle, the battery consumption rate of the vehicle driven by a person with higher driving skills is lower. Therefore, in a specific embodiment, in the process of training the linear regression model, the driver's driving skill label (for example, 0 represents a novice, 1 represents an expert) and the road roughness can be used as inputs of the linear regression model, so that the linear regression model learns the relationship between the battery consumption rate and the driver's driving skill label and the road roughness.

[0120] (5) Analyze the battery usage data of vehicles in multiple traffic environments with different congestion levels to obtain information on the impact of the traffic environment on battery energy consumption.

[0121] The multiple traffic environments divided may include smooth traffic environments and congested traffic environments. In a congested traffic environment (such as congested urban roads), frequent starting and stopping of vehicles will consume more electric energy; while in a smooth traffic environment (such as a smooth highway), the vehicle can maintain a constant speed and the battery energy consumption is reduced.

[0122] In some embodiments, the battery energy consumption per unit time (e.g., power consumed) or the battery energy consumption per unit distance of the vehicle in the same traffic environment with the same degree of congestion can be determined based on the battery usage data of the vehicle in the same traffic environment. Afterwards, the battery energy consumption per unit time of the vehicle in multiple different traffic environments is linearly fitted to obtain information on the impact of the traffic environment on the battery energy consumption, which can reflect the impact relationship of different traffic environments on the battery energy consumption.

[0123] In some embodiments, the impact of traffic environment on battery energy consumption can be simulated by a random forest algorithm.

[0124] Step 140: Perform energy consumption analysis on the configuration data of the vehicle to obtain basic energy consumption information of the battery.

[0125] The vehicle's configuration data includes information on the vehicle's basic configurations. The vehicle's basic configurations include software configuration and hardware configuration. Software configuration refers to the software system running on the vehicle, such as the battery management system, intelligent driving assistance system, vehicle anti-lock braking system, etc.; the vehicle's hardware configuration includes the vehicle's battery capacity (maximum battery capacity or rated battery capacity), battery type, motor performance and power, vehicle materials (such as interior sound insulation materials, seat materials, body materials), vehicle weight, vehicle structure, etc.

[0126] The performance and efficiency of the vehicle's battery will vary depending on the vehicle's basic configuration. For example, the more software systems running on the vehicle, the more energy the vehicle's battery consumes. The different battery capacities and battery types of the vehicle also directly affect the battery performance of the vehicle.

[0127] The basic energy consumption information of the battery is used to indicate the basic energy consumption of the battery determined by the basic configuration of the vehicle and the energy information that the battery itself can provide (such as the maximum cruising range, etc.).

[0128] In some embodiments, the basic energy consumption information includes at least one of the battery life information, the impact of motor performance on battery energy consumption, the impact of infrastructure on battery energy consumption, and the energy consumption information of the software system; step 140 includes at least one of the following A1-A4:

[0129] A1, determine the vehicle's endurance information based on the battery type and battery capacity in the vehicle's configuration data.

[0130] Different types of batteries (e.g., lithium-ion batteries, nickel-metal hydride batteries) have different characteristics in terms of energy density, charging speed, and safety. Therefore, the vehicle's endurance performance can be analyzed based on the vehicle's battery type and battery capacity, that is, the vehicle's endurance information can be determined. The vehicle's endurance information can include the vehicle's theoretical maximum endurance mileage.

[0131] In some embodiments, since the vehicle's cruising range varies in different usage modes, the vehicle's cruising range information may include the vehicle's cruising range in each usage mode.

[0132] A2, determining the influence of the motor performance of the vehicle on the battery energy consumption according to the motor performance information in the configuration data of the vehicle and the battery energy consumption under different motor performances.

[0133] The performance and power of the motor in the vehicle determine the acceleration performance and maximum speed of the vehicle, and also affect the energy consumption of the battery. By analyzing the performance information of the motor in the vehicle, the vehicle's power performance and energy efficiency can be evaluated. The performance information of the motor can include the power of the motor. Based on the relationship between the power of the motor and the battery energy consumption, and the power of the current motor of the vehicle, the battery energy consumption of the current vehicle can be determined as the impact information of the motor performance of the vehicle on the battery energy consumption.

[0134] In some embodiments, different motor powers and battery energy consumption of the vehicle may be fitted in advance to determine the relationship between the motor power and the battery energy consumption, so as to use the relationship as a basis for subsequently determining the impact of the motor performance of the vehicle on the battery energy consumption. Of course, the determined relationship between the motor power and the battery energy consumption can also be used to determine the battery energy consumption of the vehicle at each real-time power of the motor.

[0135] A3, determining the influence of the vehicle infrastructure on the battery energy consumption based on the vehicle infrastructure information and the battery energy consumption under different infrastructures in the vehicle configuration data.

[0136] The basic structural information of the vehicle includes the weight and basic structure of the vehicle, and further includes basic information such as the volume and material of the vehicle. The weight and structural design of the vehicle body will affect the energy consumption and stability of the vehicle battery. The information on the impact of the basic structure of the vehicle on the battery energy consumption can reflect the relationship between the basic structure of the vehicle and the battery energy consumption of the vehicle.

[0137] A4, determining energy consumption information of software systems in the vehicle based on basic operation information of various software systems in the configuration data of the vehicle.

[0138] It is understandable that the more software systems are running in the vehicle, the higher the operating power of the software systems, and the higher the battery energy consumption caused by the software systems in the vehicle per unit time. The energy consumption information of the software systems in the vehicle is used to indicate the energy of the battery in the vehicle consumed by running the software systems in the vehicle. The software systems in the vehicle are, for example, battery management systems, air conditioning systems, entertainment systems, intelligent driving assistance systems, etc., which are not specifically limited here.

[0139] The basic operating information of the software system may include the operating power of the software system. In a specific embodiment, the operating powers of all software systems executable on the vehicle may be added together, and the result of the addition may be used as the energy consumption information of the software system in the vehicle.

[0140] Step 150 , generating battery usage recommendation information for the vehicle based on the charging characteristic information, the driving characteristic information, the information on the impact of environmental parameters on the battery energy consumption, and the basic energy consumption information of the battery.

[0141] Based on the charging characteristic information, it can be determined whether the user's charging frequency is too high, whether the charging time is too long or too short, and whether the commonly used charging method is not conducive to the performance of the battery. In this way, targeted prompts and suggestions can be given to users. For example, for users who frequently fast charge, they can be advised to adopt slow charging methods to extend battery life.

[0142] Similarly, based on the driving characteristics information, the driving behaviors that are not conducive to battery performance can be determined in the user's driving characteristics, so that the user can be advised to reduce driving behaviors that will greatly reduce battery performance, and to adopt driving behaviors that have less impact on battery performance. And based on the information on the impact of environmental parameters on battery energy consumption, users who often drive on congested roads can be advised to provide energy-saving driving modes to reduce battery energy consumption.

[0143] In some embodiments, Figure 2 As shown, step 150 includes the following steps 210 to 250:

[0144] Step 210: Generate charging suggestion information based on the charging characteristic information and the influence of different charging characteristics on battery energy consumption.

[0145] The user's charging characteristic information can reflect the user's charging characteristics for the battery. If, based on the charging characteristic information and the relationship between the impact of different charging characteristics on battery energy consumption, it is determined that the current user's charging characteristic information contains charging characteristics that will reduce battery energy consumption, such as too high charging frequency (for example, exceeding the first threshold), too low charging frequency (for example, below the second threshold, the second threshold is less than the first threshold), unfixed charging time, and a high frequency of fast charging in the charging method, etc., charging suggestion information can be generated for the user to adopt charging behaviors that have less impact on battery energy consumption, such as reducing the charging frequency, controlling the battery charging time within a relatively fixed time range, and using a slow charging method for charging. That is, the generated charging suggestion information is used to suggest that the user adopt charging behaviors that have less impact on battery energy consumption.

[0146] Step 220 , generating driving suggestion information according to the driving characteristic information and the influence relationship between different driving characteristics on battery energy consumption.

[0147] The user's driving characteristic information can reflect the user's driving behavior characteristics for the battery. If, based on the driving characteristic information and the relationship between the impact of different driving characteristics on battery energy consumption, it is determined that the current user's driving characteristic information contains driving characteristics that will reduce battery energy consumption, such as excessive acceleration frequency, excessive deceleration, excessive mileage, long-term high-speed driving, etc., it can generate a suggestion for the user to reduce driving behaviors that have a greater impact on battery energy consumption, and to recommend the user to drive with driving behaviors that have a lower impact on battery energy consumption. That is, the generated driving suggestion information is used to recommend the user to adopt driving behaviors that have a lower impact on battery energy consumption, and to reduce driving behaviors that have a higher impact on battery energy consumption.

[0148] Step 230 , generating suggestion information for the vehicle in the current environment based on the information on the impact of different environmental parameters on the energy consumption of the battery and the current environment of the vehicle.

[0149] Based on the current environment of the vehicle and the information on the impact of different environmental parameters on the battery energy consumption, it can be determined that the current environment of the vehicle has a greater impact on the battery energy consumption, and recommendations can be generated for users to adopt driving behaviors that can reduce battery energy consumption in the current environment. For example, if the user is driving in a congested traffic environment, the vehicle's recommendation information in the current environment may be to recommend that the user adopt an energy-saving driving mode to reduce battery energy consumption.

[0150] Step 240, generating current energy consumption prompt information of the vehicle according to the basic energy consumption information of the battery and the current power information of the battery in the vehicle.

[0151] Based on the basic energy consumption information of the battery and the current power information of the battery in the vehicle, the remaining power of the battery and the mileage that the remaining power of the battery can support can be determined, and the mileage that the remaining power of the battery can support can be used as the energy consumption prompt information of the vehicle. And when it is determined based on the remaining power of the battery that the remaining power is less than the power threshold, or the mileage that the remaining power of the battery can support is less than the mileage threshold, a prompt message is generated to prompt the user to charge as soon as possible.

[0152] Step 250 , combining the charging suggestion information, the driving suggestion information, the suggestion information of the vehicle in the current environment and the current energy consumption prompt information of the vehicle to obtain the battery use suggestion information of the vehicle.

[0153] By combining the suggestion information under the above multiple dimensions, it can be ensured that the battery usage suggestion information seen by the user includes the suggestion information under the multiple dimensions, so as to provide the user with multi-faceted battery usage suggestions.

[0154] In the present application, the charging characteristic information obtained from the battery charging data, the driving characteristic information extracted from the vehicle driving data, the information on the impact of environmental parameters on the battery energy consumption extracted from the battery usage data, and the basic energy consumption information of the battery are combined to generate targeted battery usage recommendations for the vehicle. The charging characteristic information reflects the characteristics of the user's charging behavior of the battery in the vehicle, and the driving characteristic information can reflect the characteristics of the user's driving behavior. Based on the charging characteristic information and the driving characteristic information, the charging and driving behaviors that have a greater impact on the battery energy consumption can be effectively analyzed, so that the user can be advised to reduce the charging and driving behaviors that have a greater impact on the battery energy consumption through subsequent battery usage recommendations, and it is recommended to adopt charging and driving behaviors that have a smaller impact on the battery energy consumption, which is beneficial to improving the battery life and reducing the impact on the battery energy consumption.

[0155] In some embodiments, after step 150, the method further includes: sending battery usage recommendation information to the vehicle; receiving feedback information returned by the vehicle in response to the battery usage recommendation information; and updating the battery usage recommendation information for the vehicle based on the feedback information.

[0156] The battery usage suggestion information may be displayed on the vehicle's onboard terminal. The feedback information returned may be user feedback on the battery usage suggestion information, such as satisfaction with the battery usage suggestion information, or other feedback information. Thereafter, the battery usage suggestion information for the vehicle may be updated based on the feedback information. For example, targeted suggestions may be made based on the user's preferred content or aspects in the feedback information.

[0157] In some embodiments, when the charging characteristic information includes a charging frequency characteristic and a charging duration characteristic, the method further includes the following B1-B3:

[0158] B1, predict the next recommended charging time period for the vehicle based on the charging time characteristics and the vehicle's current battery power information.

[0159] As described above, using a relatively fixed charging time has a lower impact on the performance of the battery. Therefore, based on this principle, the next recommended charging time period of the vehicle can be predicted according to the charging time characteristics, the current battery power information of the vehicle, and the current time. The duration of the next recommended charging time period can be the average charging time in the charging time characteristics. The next recommended charging time period can be the time point when the power of the vehicle is estimated to be lower than the first power threshold.

[0160] Predicting the next recommended charging window helps them better plan when using their devices and avoid running out of battery at critical moments.

[0161] B2, predicting the recommended charging method for the next charge of the vehicle based on the charging method characteristics and the current battery power information of the vehicle.

[0162] In some embodiments, charging can be performed according to the principle of recommending users to use a charging method that has less impact on battery performance. In some embodiments, the recommended charging method for the next charging of the vehicle can be predicted in combination with the user's current location information, the deployment address of the charging pile equipment around the vehicle, the charging method characteristics, and the current battery power information of the vehicle. For example, the most convenient charging method for the user's current location can be used as the recommended charging method for the next charging.

[0163] In some embodiments, a classifier of a multi-layer perceptron (MLP, also known as an artificial neural network) algorithm may be used to predict the charging mode.

[0164] From the user's perspective, accurate charging method prediction can help car owners arrange charging plans reasonably, avoid long waiting times for charging or missing charging opportunities, and thus improve the car-using experience.

[0165] B3, adding the next recommended charging time period of the vehicle and the recommended charging method for the next charging of the vehicle to the battery usage recommendation information.

[0166] That is, the next recommended charging time period and the recommended charging method for the next charging of the vehicle are also added to the battery usage recommendation information as suggestions for users. This makes it easier for users to plan their trips and charging plans reasonably, avoid waiting too long for charging, and improve the car-using experience.

[0167] In some embodiments, the battery usage data of the vehicle at different temperatures is analyzed to obtain information on the impact of temperature on battery performance, including the following C1-C5:

[0168] C1, obtains the battery charging times, battery discharge depth and battery temperature at multiple different temperatures from the battery usage data of the vehicle at multiple different temperatures.

[0169] C2, determining information on the effect of temperature on the number of battery charging times according to the number of battery charging times at multiple different temperatures.

[0170] The number of battery charge times at multiple different temperatures can be fitted to obtain a curve reflecting the influence of temperature on the number of battery charge times, or a functional relationship reflecting the change of the number of battery charge times with temperature. The obtained curve reflecting the influence of temperature on the number of battery charge times, or the functional relationship reflecting the change of the number of battery charge times with temperature can be used as information on the influence of temperature on the number of battery charge times.

[0171] C3, determining information on the effect of temperature on the battery discharge depth according to the battery discharge depth at multiple different temperatures.

[0172] The battery discharge depths at multiple different temperatures can be fitted to obtain a curve reflecting the influence of temperature on the battery discharge depth, or a functional expression reflecting the change of the battery discharge depth with temperature. The obtained curve reflecting the influence of temperature on the battery discharge depth, or the functional expression reflecting the change of the battery discharge depth with temperature can be used as information on the influence of temperature on the battery discharge depth.

[0173] C4, performing correlation analysis based on the battery temperature at multiple different temperatures to determine the influence of the temperature on the battery temperature.

[0174] The battery temperature at multiple different temperatures can be fitted to obtain a curve reflecting the influence of temperature on the battery temperature, or a functional relationship reflecting the change of battery temperature with temperature. The obtained curve reflecting the influence of temperature on the battery temperature, or the functional relationship reflecting the change of battery temperature with temperature is used as information on the influence of temperature on the battery temperature.

[0175] C5, generating information on the impact of temperature on battery performance according to the information on the impact of temperature on the number of battery charges, the information on the impact of temperature on the battery discharge depth, and the information on the impact of temperature on the battery temperature.

[0176] The information on the influence of temperature on the number of battery charges, the information on the influence of temperature on the battery discharge depth, and the information on the influence of temperature on the battery temperature may be combined to obtain the information on the influence of temperature on the battery performance.

[0177] The solution of the present application is described below in conjunction with a specific embodiment.

[0178] like Figure 3 As shown, the method comprises the following steps:

[0179] Step 310, data collection. The original data of the vehicle and the driver, namely the battery charging data, vehicle driving data, vehicle battery usage data and vehicle configuration data mentioned above, can be collected by using vehicle-mounted sensors, wireless communication devices and Internet of Things technologies.

[0180] Figure 4 It is a parameter collected during the data collection process shown in an embodiment of the present application, that is, one field name corresponds to one parameter. Figure 4 This is just an example. In practice, the collected parameters can be Figure 4 More or less than shown.

[0181] Step 320, data preprocessing: cleaning, sorting, de-duplication, de-noising, filling missing values, etc. are performed on the collected data.

[0182] Step 330, feature extraction and selection. Extract key features from the preprocessed data and select a feature set for subsequent analysis. The selected key features are always extracted from the collected data for subsequent analysis. The extracted key features can be Figure 4 In step 330, the aim is to extract features (parameters) that have a key impact on battery performance and efficiency from a large amount of data. This process is of great significance for optimizing battery management, improving the endurance of pure electric vehicles, and ensuring driving safety. In the process of feature extraction and selection, some technical means are also needed, such as dimensionality reduction processing, correlation analysis, etc., to screen out the most representative and predictive features, and provide strong support for subsequent analysis and optimization.

[0183] Step 340: battery usage habit analysis, including charging habit analysis, driving habit analysis, environmental factor analysis, and vehicle configuration analysis.

[0184] The charging habit analysis is the process of step 110 mentioned above, the driving habit analysis is the process of step 120 mentioned above, the environmental factor analysis is the process of step 130 mentioned above, and the vehicle configuration analysis is the process of step 140 mentioned above.

[0185] In the charging habit analysis, feature extraction and selection mainly focus on key indicators such as charging frequency, charging time, charging location and charging method. For example, by analyzing the user's charging frequency, we can understand the user's demand for battery life and the convenience of charging facilities; while the choice of charging time and location can reflect the user's daily travel pattern and the layout of charging facilities.

[0186] In terms of driving habit analysis, feature extraction and selection focus on factors such as acceleration habits, driving speed, mileage, and braking habits. These features can directly reflect the impact of driving style on battery energy consumption and performance. For example, frequent sudden acceleration and braking will cause the battery to experience high current discharge and charging in a short period of time, which will have a negative impact on battery life.

[0187] In the environmental factor analysis, feature extraction and selection mainly focus on natural conditions such as temperature, humidity, and altitude, as well as external factors such as road conditions and traffic environment. Changes in these features will directly affect the performance and efficiency of the battery. For example, the heat dissipation performance of the battery will be challenged in a high temperature environment, while the charging and discharging performance of the battery will be affected in a low temperature environment.

[0188] In vehicle configuration analysis, feature extraction and selection focus on the vehicle’s own configuration and performance, such as battery capacity, motor performance, and battery management system. These features have an important impact on evaluating battery usage habits and performance.

[0189] Step 350, application and feedback: applying the analysis results to actual scenarios, and continuously optimizing the analysis process and method based on feedback. That is, the battery usage recommendation information for the vehicle can be updated based on the user's feedback information.

[0190] The following specifically explains the charging habit analysis, driving habit analysis, environmental factor analysis, and vehicle configuration analysis involved above. First, the charging habit analysis will be explained.

[0191] The battery usage habit analysis process includes data collection, data preprocessing, feature extraction and selection, battery usage habit analysis, and application feedback.

[0192] The battery usage habit analysis process can be as follows Figure 5 As shown, the data can be cleaned first, and the subsequent processes include missing value processing, outlier processing, data standardization / normalization and denoising. Among them, the main purpose of data cleaning is to clean the original data, remove duplicate, invalid or abnormal data records, ensure the quality and integrity of the data, and improve the robustness of the model.

[0193] In a specific embodiment, an IQR (Interquartile Range) method may be used to process outliers. The IQR method may be used to process outliers as follows:

[0194] #Example: Detect and remove outliers using the IQR method

[0195] Q1 = data.quantile(0.25)

[0196] Q3 = data.quantile(0.75)

[0197] IQR=Q3-Q1

[0198] data=data[~((data<(Q1-1.5*IQR))|(data>(Q3+1.5*IQR))).any(axis=1)].

[0199] Missing value filling refers to filling missing values ​​in data using appropriate interpolation methods or statistical information based on historical data to reduce the impact of missing data on analysis results. When missing values ​​are detected in a data set, missing value filling can be performed. In a specific embodiment, missing value filling can be performed using the mean method.

[0200] Data standardization / normalization processing aims to convert the original data into a unified scale, thereby eliminating the dimensional differences between different features and improving the stability and accuracy of the model.

[0201] De-noising is aimed at removing noise from data. Filtering or smoothing techniques can be used to denoise data to improve the signal-to-noise ratio of the data.

[0202] In the analysis of user driving habits, the parameters that need to be denoised usually include continuously changing signals such as speed, acceleration, steering angle, etc. These signals may contain random fluctuations or outliers caused by sensor noise, signal transmission errors or other factors, which may affect the accuracy of driving habit analysis.

[0203] In order to remove these noises, filtering methods can be used, such as sliding average filtering, median filtering or Kalman filtering, etc. Among them, sliding average filtering is a simple and effective denoising method, which smoothes the signal by calculating the average value of data points over a period of time. Figure 6 A and B in FIG. 1 respectively show the schematic diagram of the speed before and after the sliding filter is used to remove the noise of the vehicle speed, where Figure 6 Figure A in the figure is the speed-time diagram before denoising. Figure 6 B in FIG. 1 shows the velocity-time diagram after denoising.

[0204] After this series of data preprocessing steps, a high-quality, standardized data set can be obtained, laying a solid foundation for subsequent driving habit analysis.

[0205] (1) Analysis of charging habits;

[0206] Please continue reading Figure 4As shown, the charging habit analysis includes charging frequency analysis (i.e., the process of extracting charging frequency characteristics in the above text), charging time analysis (i.e., the process of extracting charging time characteristics in the above text) and charging method analysis (i.e., the process of extracting charging method characteristics in the above text).

[0207] 1)Charging frequency analysis;

[0208] The charging frequency directly determines the number of times the battery is charged and discharged, thus affecting its lifespan. Although frequent charging can ensure that the battery always maintains a high charge, too many charge and discharge cycles will accelerate the aging of the battery. On the contrary, charging too few times may cause the battery to be deeply discharged, which is also not good for the battery life. Therefore, users should reasonably control the charging frequency according to actual usage.

[0209] In a specific embodiment, a K-means algorithm may be used to perform cluster analysis on charging frequency data (the charging frequency data includes the user's daily battery charging frequency). The number of clusters (num_clusters) in the K-means algorithm is preset, and different numbers of clusters may lead to different results. The selection of an appropriate number of clusters needs to be adjusted according to actual needs and data.

[0210] The clustering results are as follows Figure 7 As shown, Figure 7 A, B and C are the charging frequency characteristics of different users. Figure 7 The horizontal axis of each figure represents the day (i.e., date), and the vertical axis represents the cluster category, which is divided according to the charging frequency. Figure 7 As can be seen from A in , users have a relatively stable charging habit, such as charging at a fixed time every day, or charging at a high frequency overall. Figure 7 As can be seen from B in , this user exhibits more fluctuating charging behavior, such as frequent charging on some days and less charging on other days. Figure 7 As can be seen from C, the user prefers to charge when the battery is extremely low, and his charging frequency has specific periodic changes.

[0211] It can be seen that different clustering results reveal the differences in charging habits of different users. Based on the obtained charging frequency characteristics, personalized charging strategy recommendations can be provided to users in the future to optimize battery efficiency and extend battery life. Furthermore, based on the charging frequency characteristics, intelligent charging reminders and power optimization recommendations for vehicles can be proposed.

[0212] 2)Charging time analysis;

[0213] As described above, charging time is also a key factor affecting battery usage habits. Long-term charging or discharging may cause the battery to overheat or overcool, thus affecting its performance. In addition, irregular charging time may also cause large fluctuations in battery power, which is not conducive to stable battery use. Therefore, users should try to choose a fixed charging time and ensure that the battery is charged within a suitable temperature range.

[0214] In some embodiments, after obtaining the charging time characteristics through charging time analysis, the user's charging time in the future time period can be predicted based on the charging time characteristics, that is, the predicted next recommended charging time period mentioned above.

[0215] In a specific embodiment, the random forest regression algorithm can be used to predict the charging time under different usage modes of the vehicle to obtain the next recommended charging time period of the vehicle relative to the current one. In this case, the input of the random forest regression model includes the usage mode of the vehicle in addition to the extracted charging time feature and the current battery power information of the vehicle's battery. Of course, if the vehicle has only one usage mode, the input of the random forest regression model includes the charging time feature and the current battery power information of the vehicle's battery.

[0216] The next recommended charging time period can be predicted by the random forest regression algorithm. Figure 8 As shown, in Figure 8 In the figure, the horizontal axis represents the usage mode, and the vertical axis represents the charging time (the charging time may represent the time interval between the current time and the start time of the next recommended charging time period). Figure 8 In the figure, the gray dots represent the predicted charging time and the blue dots represent the actual charging time.

[0217] from Figure 8 As can be seen from the figure, there is a certain correspondence between the predicted charging time (grey dots) and the actual charging time (blue dots), indicating that the random forest regression model has a certain accuracy in capturing the relationship between usage patterns and charging time. This shows that the random forest regression model can effectively predict charging time based on usage patterns.

[0218] Predicting charging time (predicting the next recommended charging time period for the vehicle) helps them better plan the time to use the device and avoid low power at critical moments. In addition, for equipment manufacturers or service providers, understanding the charging time under different usage modes can help them optimize product design or provide more accurate charging recommendations, thereby improving user experience and satisfaction. Furthermore, accurate charging time prediction can also help optimize energy use and improve system efficiency. In summary, it can be seen that predicting charging time not only demonstrates the effectiveness of the random forest regression model, but also has practical application value, which helps to improve user experience and system efficiency.

[0219] 3)Charging method analysis;

[0220] The choice of charging method will also affect the performance of the battery. Although the fast charging method can quickly replenish the power, the excessive current may cause an impact on the battery; although the slow charging method takes a longer time, the current is stable and more friendly to the battery. Users can choose the appropriate charging method according to their own needs and battery conditions.

[0221] In some embodiments, the charging method can be predicted by a multi-layer perceptron, that is, the multi-layer perceptron can predict the recommended charging method for the next charging of the vehicle based on the charging method characteristics and the current battery power information of the vehicle, that is, the charging method characteristics and the current battery power information of the vehicle are used as the input of the multi-layer perceptron, and the recommended charging method for the next charging of the vehicle is the output of the multi-layer perceptron. The prediction result can be as follows Fig. 9 shown. Fig. 9 In the figure, the horizontal axis represents the predicted charging method, the vertical axis represents the actual charging method, and the 0, 1, and 2 in the horizontal and vertical axes represent three different charging methods (fast charging method, slow charging method, and battery replacement method). Fig. 9 The numbers in the boxes indicate the number of times the corresponding charging method is used.

[0222] From the user's perspective, accurate charging method prediction can help car owners arrange charging plans reasonably, avoid waiting too long for charging or missing the charging opportunity, and thus improve the car experience. At the same time, the prediction results can also guide car owners to choose the appropriate charging method to extend battery life and reduce charging costs. From an industry perspective, charging method prediction helps the planning and construction of charging infrastructure. By predicting the demand distribution and growth trend of different charging methods, charging piles and battery swap stations can be laid out more accurately, improving the utilization rate and coverage of charging facilities. In summary, the prediction of pure electric vehicle charging methods can not only help improve user experience, but also promote the optimal layout of charging infrastructure and the sustainable development of the new energy vehicle industry.

[0223] (2) Analysis of driving habits;

[0224] Please continue reading Figure 4 As shown, driving habit analysis includes vehicle acceleration analysis (i.e., the process of extracting acceleration features in the above text), vehicle deceleration analysis (i.e., the process of extracting charging and deceleration features in the above text), driving speed analysis (i.e., the process of extracting vehicle speed features in the above text) and mileage analysis (i.e., the process of extracting mileage features in the above text).

[0225] In terms of driving habits, we mainly focus on the impact of acceleration, deceleration, driving speed and mileage on battery performance. These factors are not only directly related to the energy consumption and life of the battery, but also affect the overall performance and driving experience of pure electric vehicles.

[0226] 1) Vehicle acceleration analysis;

[0227] Driving habits have a significant impact on battery usage habits. When accelerating suddenly, the battery needs to release a large amount of current in a short period of time to meet the vehicle's power needs, which will cause large pressure and temperature changes inside the battery, thereby increasing the aging rate of the battery. Frequent sudden acceleration will also reduce the battery's range and reduce overall energy efficiency. Therefore, using acceleration methods that have less impact on battery performance, such as smooth starts and gradual acceleration, is crucial to extending battery life and improving energy efficiency.

[0228] The process of vehicle acceleration analysis can include the following ①-④:

[0229] ① Extract the user’s vehicle speed at each time point;

[0230] ② Calculate the user’s acceleration and extract features such as acceleration frequency, acceleration magnitude, acceleration mean, acceleration standard deviation, acceleration interquartile range (used to measure acceleration smoothness) and acceleration peak frequency.

[0231] ③ Draw the acceleration mean distribution graph, acceleration standard deviation distribution graph, acceleration interquartile range distribution graph, and acceleration peak frequency distribution graph. Fig.10 As shown, Fig.10 A in the middle shows the average acceleration distribution diagram (the horizontal axis represents the average acceleration). Fig.10 B in the middle shows the acceleration standard deviation distribution diagram (the horizontal axis represents the acceleration standard deviation); Fig.10 The middle C shows the acceleration interquartile range distribution diagram (the horizontal axis represents the acceleration interquartile range); Fig.10 D in the middle shows the acceleration peak frequency distribution diagram (the horizontal axis represents the acceleration peak frequency).

[0232] ④Statistical methods to analyze features

[0233] For example, you can plot the acceleration time series of each user, and visualize the acceleration distribution (e.g., plot a histogram of the acceleration of all users). Fig.11 An acceleration time series graph drawn for a user is exemplarily shown, which shows the acceleration at multiple time points. Fig.12 An acceleration distribution diagram drawn based on all users is exemplarily shown (the horizontal axis represents acceleration).

[0234] In some embodiments, an acceleration prediction model can also be established through a deep neural network such as a long short-term memory neural network and a gated recurrent unit to predict the acceleration information of the user in the future time period. In this case, the input of the acceleration prediction model includes the motion information (such as acceleration, speed, cumulative motion time) at the current time and the acceleration features extracted for the user, and the output of the acceleration prediction model is the acceleration information (such as acceleration) of the future time period. It can be judged whether the acceleration is too large based on the predicted acceleration, and if the acceleration is too large, the user can be reminded to suggest that the user reduce the acceleration.

[0235] In order to extend the battery life and improve the efficiency of use, the driver should avoid frequent and sudden acceleration and try to maintain a stable speed. At the same time, it is also necessary to regularly check the battery temperature and performance to ensure that the battery is in the best working condition. Through good driving habits and battery maintenance, the battery performance can be fully utilized and the vehicle efficiency can be improved.

[0236] 2) Vehicle deceleration analysis;

[0237] Deceleration habits also affect battery usage. When decelerating or braking suddenly, the battery needs to recover energy quickly, which will also have a certain impact on the battery. In addition, frequent sudden deceleration may also lead to reduced energy recovery efficiency and waste of electricity. Therefore, during driving, try to avoid sudden deceleration and sudden braking, and use a gentle deceleration method to protect the battery and improve energy recovery efficiency. The vehicle deceleration analysis can be performed in a similar process to the vehicle acceleration analysis above, and the specific process will not be repeated.

[0238] 3) Driving speed analysis;

[0239] Driving speed is also an important factor affecting battery usage habits. When driving at high speed, the vehicle needs to overcome greater air resistance and friction, which will increase battery energy consumption. In addition, high-speed driving may also cause problems such as battery overheating, affecting battery safety and life. Therefore, maintaining a moderate driving speed under appropriate road conditions will help reduce battery energy consumption and extend battery life.

[0240] Fig.13 The speed of three users over time is shown as an example, where one color represents one user. Based on the speed data of multiple users (i.e., the speed at multiple time points), a speed distribution diagram can be drawn, for example, Fig.14 As shown, Fig.14 The horizontal axis represents speed, and the vertical axis represents the corresponding frequency.

[0241] In some embodiments, a time sliding window and gated recurrent unit neural network algorithm may be used to establish a user's driving speed model. The driving speed model may be used to predict the user's speed in a future time period. If the predicted speed exceeds a speed threshold, the user may be reminded to suggest that the user reduce the speed. The input of the driving speed model may include the extracted speed feature and the current motion information of the vehicle. The output of the driving speed model includes the predicted speed of the user in a future time period.

[0242] Vehicle speed has a significant impact on battery usage habits. When driving at high speed, the vehicle faces greater air resistance and friction, so the battery power consumption will increase. This means that at the same distance, high-speed driving will shorten the battery's range. In order to use the battery power more effectively, drivers should avoid unnecessary speeding. At the same time, rapid changes in vehicle speed will cause the battery to charge and discharge frequently, which not only reduces the charging efficiency but may also damage the battery structure. Maintaining a stable vehicle speed can reduce the number of charge and discharge cycles, thereby extending the battery life. In addition, high-speed driving may cause the battery to overheat. Excessive temperature will accelerate the chemical reaction inside the battery, generate too much heat, and may even cause safety problems. Therefore, drivers should pay attention to the battery temperature when driving at high speeds to ensure that it is within a safe range.

[0243] In summary, in order to maximize battery efficiency and safety, based on the extracted vehicle speed characteristics, it is recommended that the driver should adjust the vehicle speed according to the actual situation, avoid driving too fast, and maintain a stable speed.

[0244] 4) Mileage analysis

[0245] Driving distance also has an impact on the performance of the battery. Long-term high-mileage driving may cause the battery to be over-discharged and over-charged, accelerating the battery aging process. Therefore, rationally planning the driving route and avoiding unnecessary long-distance driving can help reduce the burden on the battery and extend its service life.

[0246] The process of mileage analysis can include the following steps ① to ④:

[0247] ① Cluster analysis (K-means) of driving time and mileage;

[0248] Cluster analysis is an unsupervised learning method used to classify data points into different clusters or groups. In the analysis of driving time and mileage, K-means clustering can help identify groups of drivers with similar driving patterns. Fig.15 is the result of clustering users according to the mileage at different times shown in an embodiment of the present application, Fig.15 In the figure, the horizontal axis represents driving time (i.e. driving duration), the vertical axis represents mileage, and one color corresponds to one clustering category.

[0249] ② Regression analysis of mileage corresponding to driving time;

[0250] Regression analysis is used to study the relationship between variables, specifically to predict how one variable changes based on changes in other variables. In a time and mileage analysis, linear regression can be used to analyze the effect of time on mileage. Fig.16 is the result of performing regression analysis on users according to the mileage at different times as shown in an embodiment of the present application. Fig.16 In the figure, the horizontal axis represents driving time (i.e. driving duration), the vertical axis represents mileage, and the red straight line represents the regression line determined by regression analysis.

[0251] ③ Analyze the impact of different factors on mileage through decision trees and random forests;

[0252] Decision trees and random forests are supervised learning algorithms that can be used for classification or regression problems. In driving time and mileage analysis, they can help understand the impact of different factors on driving mileage and provide decision rules.

[0253] Fig.17 This is a decision tree for predicting mileage according to an embodiment of the present application. A decision tree is a supervised learning algorithm that uses a tree model to make decisions and predictions. The decision tree predicts mileage based on input features (such as extracted mileage features and current vehicle motion information). The predicted mileage can be the accumulated mileage over a period of time in the future.

[0254] At the top of the tree is the root node, which usually contains the entire data set. Starting from this node, the decision tree divides the data into different subsets based on the value of the feature, with each subset corresponding to a branch. These branches continue to split until a termination condition is met (such as reaching the maximum depth, too few samples in the node, etc.), at which time a leaf node is formed. Leaf nodes usually contain predicted values, that is, the average mileage or other statistics of the sample set represented by the node. In this decision tree, each node represents a judgment condition for a feature, such as a specific vehicle parameter or driving habits. The lines between nodes represent the value range or classification of the feature, and the direction pointed by the arrow indicates under which condition the data continues to split downward. The end point of each branch is a leaf node, which gives the predicted mileage under that condition.

[0255] By observing this decision tree, we can understand which features have an important influence on predicting mileage and how these features interact to influence the final prediction results. For example, some features may only affect the prediction under certain conditions, while other features may have a significant impact on the entire dataset.

[0256] It should be noted that the complexity and accuracy of a decision tree depends on multiple factors, including the maximum depth of the tree, the feature selection method, and whether pruning techniques are used to prevent overfitting. In practical applications, these parameters usually need to be adjusted according to the characteristics of the data set and the requirements of the prediction task.

[0257] In summary, this decision tree provides an intuitive way to understand how to predict mileage based on vehicle characteristics and driving conditions. By observing and analyzing this decision tree, we can gain a deeper understanding of the impact of vehicle performance and driving habits on mileage. For example, based on this decision tree, we can output the feature importance shown in Table 1 below:

[0258] Table 1

[0259]

[0260]

[0261] After that, you can sort the features from high to low in terms of importance. In this way, you can clearly see which features play a key role in predicting mileage.

[0262] ④ Statistical analysis of driving time and mileage;

[0263] Based on the driving data of each vehicle, a single driving mileage distribution map, a single driving time distribution map, a total driving mileage statistics map, an average driving mileage statistics map, and a total mileage TOP10 map can be drawn. Fig.18 The figure shows the statistical analysis results of driving time and mileage. Fig.18 Among them, A shows the single driving mileage distribution diagram (the horizontal axis represents the driving mileage), B is the single driving time distribution diagram (the horizontal axis is the driving time); C is the total mileage statistics diagram (the horizontal axis is the total mileage); D is the average mileage statistics diagram (the horizontal axis is the average mileage); E is the total mileage TOP10 diagram.

[0264] In summary, driving habits have a significant impact on battery usage habits. By optimizing driving habits such as acceleration, deceleration, driving speed, and mileage, battery energy consumption can be effectively reduced, battery life can be extended, and the overall performance of pure electric vehicles can be improved.

[0265] (3) Analysis of environmental factors;

[0266] In this embodiment, the influence of temperature, humidity, altitude, road conditions and traffic environment on battery performance is mainly analyzed.

[0267] 1. Temperature

[0268] Temperature is one of the key factors affecting battery performance. The ideal operating temperature of a battery is usually between 20℃ and 25℃. Too high or too low a temperature will affect the battery's charge and discharge efficiency, life, and safety. In a high temperature environment, the chemical reaction inside the battery accelerates, which may cause the battery to overheat, swell, or even explode. In a low temperature environment, the viscosity of the electrolyte inside the battery increases and the conductivity decreases, thus affecting the battery's charge and discharge performance.

[0269] In a specific embodiment, battery usage data at different temperatures may be collected, including charging times, discharge depth, battery temperature, etc. By constructing a relationship model between temperature and battery performance, the changing trend of battery usage habits at different temperatures is analyzed, thereby guiding users to use batteries reasonably under different temperature conditions.

[0270] Fig.19 1 is a graph showing the relationship between temperature and charging times according to an embodiment of the present application, wherein the horizontal axis represents temperature and the vertical axis represents charging times. Fig. 20 is a graph showing the relationship between temperature and discharge depth according to an embodiment of the present application, Fig. 20 The horizontal axis represents temperature, and the vertical axis represents discharge depth.

[0271] In some embodiments, a polynomial regression model can be used to analyze the effect of temperature on the number of charging times, and a polynomial regression line can be drawn.

[0272] Use the Polynomial Regression model to analyze, draw the polynomial regression line, and make suggestions. Fig.21 It is a regression analysis result diagram of temperature and charging times according to an embodiment of the present application, wherein the horizontal axis represents temperature, the vertical axis represents charging times, and the red straight line represents the regression line determined by the regression analysis.

[0273] Based on the determined polynomial regression line (i.e., reflecting the relationship between temperature and charging times), the number of times the user will charge in the future at any future temperature can be predicted, and suggestions can be made to the user based on the predicted number of charging times. For example, if the predicted number of charging times is small and the impact on battery performance is small, a prompt message indicating "the battery performance is good and can be used normally" can be provided; if the predicted number of charging times is within the first number range, it has a certain impact on the performance of the battery, and a suggestion message indicating "the battery performance is average, please reduce the intensity of use appropriately" can be provided; if the predicted number of charging times exceeds the first number range, it has a great impact on the performance of the battery, and a suggestion message indicating "the battery performance is poor, it is recommended to avoid high-load use and charge as soon as possible" can be provided.

[0274] 2. Humidity

[0275] Humidity also has an important impact on battery performance. A high humidity environment may cause internal corrosion of the battery, affect conductivity, and even cause a short circuit. In humid areas, users need to pay attention to waterproofing and moisture-proofing of the battery.

[0276] In some embodiments, the relationship between humidity and battery performance can be learned through a multi-layer perceptron, and then the multi-layer perceptron can be used to predict the battery performance (specifically, battery capacity) at various humidity levels in the future. Fig. 22 It is a schematic diagram showing predicted battery capacity and actual battery capacity at various humidity levels according to an embodiment of the present application. Fig. 22 In the figure, the horizontal axis represents humidity, the vertical axis represents battery capacity, the points on the red straight line are the predicted battery capacity, and the blue ones represent the actual battery capacity.

[0277] 3. Altitude

[0278] Altitude also has a significant impact on battery performance. The thin oxygen in high altitude areas affects battery discharge performance and may shorten the driving range. Users in these areas need to pay more attention to charging strategies and driving range performance.

[0279] Use a multi-layer perceptron to analyze the effect of altitude on battery performance, and draw graphs to present the results, including a graph of altitude versus battery consumption rate (actual data), an altitude distribution histogram, and a battery consumption rate distribution histogram. Fig.23 is a schematic diagram showing an altitude analysis result according to an embodiment of the present application, Fig.23 A is a schematic diagram of the predicted battery consumption rate and the actual consumption rate, wherein the horizontal axis represents the actual battery consumption rate and the vertical axis represents the predicted battery consumption rate; B is a graph showing the relationship between altitude and actual battery consumption rate (plotted based on actual data), wherein the vertical axis represents the actual battery consumption rate and the horizontal axis is altitude; C is an altitude distribution histogram (with the horizontal axis being altitude); D is a battery consumption rate distribution histogram (with the horizontal axis being battery consumption rate).

[0280] 4. Road conditions

[0281] Road conditions affect driving energy consumption. Rough roads will increase vehicle resistance, resulting in increased battery energy consumption. Users need to master driving skills and reduce unnecessary acceleration and braking to save power.

[0282] A linear regression model is used to simulate the effect of road conditions (roughness: 0 represents flat, 1 represents very rough) on battery energy consumption, including road roughness and driving skills (0 represents novice, 1 represents expert) as features, and the battery energy consumption calculated from this is used as a label. The data is fitted using a linear regression model and the performance of the model is evaluated; a graph of the relationship between road roughness and battery energy consumption, as well as a graph of the relationship between driving skills and battery energy consumption are plotted. The linear regression model is used to predict the battery energy consumption under various road conditions (i.e., road roughness).

[0283] For example, if road_roughness represents the roughness of the road (0 represents flat and 1 represents very rough); and driving_skill represents driving skills (0 represents novice and 1 represents expert), the battery consumption battery_consumption can be calculated according to the following formula:

[0284] battery_consumption=0.5*road_roughness+0.3*(1-driving_skill)+0.2*np.random.normal(size=num_samples).

[0285] Fig.24 is a schematic diagram showing a road condition analysis result according to an embodiment of the present application, Fig.24 A in the figure is a schematic diagram showing the relationship between the actual battery energy consumption and the actual battery energy consumption, wherein the horizontal axis is the actual battery energy consumption and the vertical axis is the predicted battery energy consumption; B is a schematic diagram showing the battery energy consumption under different road ruggedness, wherein the horizontal axis represents the road ruggedness and the vertical axis represents the battery energy consumption; C is a schematic diagram showing the battery energy consumption under different driving skills, wherein the horizontal axis represents the driving skills and the vertical axis represents the battery energy consumption.

[0286] 4. Traffic environment

[0287] Traffic environment is also important. In congested urban roads, vehicles frequently start and stop, which consumes more electricity; on unobstructed roads such as highways, vehicles can maintain a constant speed and reduce energy consumption. Users need to adjust their driving strategies according to the traffic environment.

[0288] In this embodiment, a random forest regression model is used to simulate the impact of traffic environment on battery energy consumption. Specifically, by considering the impact of three factors on battery energy consumption, traffic congestion, speed variance and battery capacity, a box plot of battery energy consumption and traffic congestion and a scatter plot of battery energy consumption and speed variance are drawn. After training, the random forest regression model can be used to predict battery energy consumption under different traffic environments. Fig.25 is a schematic diagram showing the traffic environment analysis result according to an embodiment of the present application, wherein: Fig.25 Figure A shows a schematic diagram of the relationship between the actual battery energy consumption and the actual battery energy consumption, where the horizontal axis is the actual battery energy consumption and the vertical axis is the predicted battery energy consumption; Figure B shows a box plot of battery energy consumption and traffic congestion, where the horizontal axis represents traffic congestion (non-congested means no traffic congestion, congested means traffic congestion), and the vertical axis is battery energy consumption; Figure C shows a scatter plot of battery energy consumption and speed variance, where the horizontal axis represents speed variance, and the vertical axis is battery energy consumption.

[0289] As can be seen above, environmental factors are crucial to analyzing battery usage habits. By comprehensively analyzing these factors, we can have a more comprehensive understanding of battery performance and provide users with personalized recommendations.

[0290] (iv) Vehicle configuration analysis;

[0291] Vehicle configuration analysis is an important part of battery usage habit analysis, which involves various hardware and software configurations of the vehicle, which not only affect the performance and efficiency of the battery, but also directly relate to the user's driving experience and safety. It includes battery capacity and type analysis (i.e., the process of determining the vehicle's endurance information as mentioned above), motor performance and power analysis (i.e., the process of determining the impact of motor performance on battery energy consumption as mentioned above), software system analysis (i.e., the process of determining the energy consumption information of the software system as mentioned above, specifically including battery management system analysis, other auxiliary systems of the vehicle, and intelligent driving assistance system analysis), and vehicle overall design and material analysis (i.e., the process of determining the impact of the vehicle's infrastructure on battery energy consumption as mentioned above).

[0292] ①Battery capacity and type analysis

[0293] The main analysis is about the impact of the vehicle's battery capacity and type on the vehicle's endurance. Battery capacity is a key factor in determining battery endurance. Different types of batteries (such as lithium-ion batteries, nickel-metal hydride batteries, etc.) have different characteristics in terms of energy density, charging speed, safety, etc. By analyzing these data, we can understand the vehicle's endurance performance in different usage scenarios and provide users with reasonable charging and usage suggestions.

[0294] In some embodiments, the K-Means algorithm can be used to cluster and plot usage patterns, wherein usage patterns are divided according to average usage time (i.e., average driving time), and usage patterns are divided into 0 to 5. According to the average time, the degree of usage ranges from light to heavy, taking a continuous value, that is, when the usage pattern is 5, the average usage time exceeds the average usage time when the usage pattern is 4.

[0295] Fig.26 is a clustering result diagram under different usage modes shown according to an embodiment of the present application, Fig.26 In the figure, the horizontal axis represents the usage mode, the vertical axis represents the battery usage time (that is, the battery power supply time, or the battery life), and one color represents a cluster category.

[0296] In some embodiments, a linear regression model may be used to predict the changing trend of battery life as the battery capacity changes. Fig. 27 A schematic diagram showing the battery life under different battery capacities predicted by the linear regression model. Fig. 27 In the figure, the horizontal axis represents the battery capacity and the vertical axis represents the battery life. The blue color represents the actual value and the green color represents the predicted value.

[0297] In some embodiments, the average cruising range under different battery capacities and types can also be calculated, that is, the vehicles can be grouped according to the battery type and capacity, and the average cruising range can be calculated. Fig.28 The schematic diagram of the grouping result is shown as an example. Fig.28 In the figure, the horizontal axis represents the grouping and the vertical axis represents the calculated average battery life.

[0298] Furthermore, a battery life threshold can be determined for each group based on the average battery life calculated for each group. The battery life threshold can be 80% of the average battery life (of course, it can also be other proportions and can be adjusted according to actual needs). Thereafter, for the vehicles in each group, recommendations can be made based on the vehicle's current battery life and the battery life threshold corresponding to the group to which the vehicle belongs. For example, if the current battery life reaches the corresponding battery life threshold, the user can be advised to charge in time.

[0299] Fig.29 The flowchart for generating usage suggestions based on the battery life threshold is exemplified in the figure. The usage suggestion function definition is first given, and the usage suggestion function is used to output the generated usage suggestion information, such as "If the current battery life reaches the corresponding battery life threshold, the user can be advised to charge in time" in the above text; then, the average battery life is solved, that is, the average battery life is calculated based on the battery life of the vehicles in a group; then, the battery life threshold is determined based on the average battery life; after obtaining the battery life, the current battery life is compared with the corresponding battery life threshold, and the usage suggestion is output by using the suggestion function.

[0300] ② Motor performance and power analysis;

[0301] The motor performance and power of the vehicle are also important aspects of vehicle configuration analysis. The motor performance and power directly determine the vehicle's acceleration performance and maximum speed, and also affect the battery's energy consumption. By analyzing the motor data, the vehicle's power performance and energy efficiency can be evaluated, providing users with appropriate driving modes and energy-saving suggestions.

[0302] In some embodiments, the relationship between motor performance (eg, power) and battery energy consumption may be explored using a linear regression model. Fig.30 is a schematic diagram of the regression result between the motor power and the battery energy consumption according to an embodiment of the present application, Fig.30 The horizontal axis represents the motor power, the vertical axis represents the battery energy consumption, and the red line is the determined regression line, which expresses the trend of battery energy consumption changing with motor power.

[0303] In some embodiments, driving mode and energy-saving suggestions can be provided based on the determined regression line of the battery energy consumption changing with the motor power: the driving mode and energy-saving suggestion function can be defined first: recommend_driving_mode(power_kw); then, the battery energy consumption is predicted according to the current motor power through a linear regression model; then, the current motor power is compared with the set energy-saving threshold Energy_Effici_Threshold, and driving suggestions are given. For example, if it is less than the energy-saving threshold, it is recommended to drive in economic mode; if it is greater than the energy-saving threshold, it is recommended to drive in power mode.

[0304] ③ Software system analysis; including: battery management system analysis, other vehicle auxiliary systems, and intelligent driving assistance system analysis.

[0305] 1) Battery management system analysis;

[0306] The battery management system is a key system responsible for monitoring and managing the battery status, including real-time monitoring of battery voltage, current, temperature, SOC (State of Charge, which indicates the ratio of the remaining power of the battery to its rated capacity), and control of the charging and discharging process. By analyzing the data of the battery management system, we can understand the working status of the battery, discover potential safety hazards in a timely manner, and provide data support for battery optimization and maintenance.

[0307] In some embodiments, the currents and voltages of different cells may be clustered. Fig.31 is a schematic diagram showing the clustering result of battery current and voltage according to an embodiment of the present application, Fig.31 In the figure, the horizontal axis represents the battery voltage, the vertical axis represents the battery current, one color represents one cluster category, and different colors represent different cluster categories.

[0308] In some embodiments, the battery pack status can also be analyzed, including SOC distribution when the vehicle starts, SOC distribution when the vehicle stops, maximum temperature distribution of single cells, minimum temperature distribution of single cells, and temperature difference distribution of single cells. Fig.32 is a schematic diagram showing a battery pack status analysis result according to an embodiment of the present application, Fig.32 A is the SOC distribution diagram when the vehicle starts (the horizontal axis represents SOC), B is the SOC distribution diagram when the vehicle stops (the horizontal axis represents SOC); C is the maximum temperature distribution diagram of the single cell (the horizontal axis represents the maximum temperature of the single cell); D is the minimum temperature distribution diagram of the single cell (the horizontal axis represents the minimum temperature of the single cell); E is the temperature difference distribution diagram of the single cell (the horizontal axis represents the temperature difference of the single cell).

[0309] In some embodiments, charging and discharging habits analysis can also be performed based on data in the battery management system. For example, the analysis can include the distribution of SOC values ​​at the start of charging, the distribution of SOC values ​​at the end of charging, the distribution of time periods in which charging starts, the distribution of time periods in which charging ends, the distribution of charging times at different charging durations, charging frequency analysis, and fast and slow charging ratio analysis. Fig.33 It is a schematic diagram of the charging and discharging habit analysis results of the data in the battery management system according to an embodiment of the present application. Fig.33 A is the SOC value distribution diagram at the beginning of charging (the horizontal axis represents SOC), B is the SOC value distribution diagram at the end of charging (the horizontal axis represents SOC); C is the distribution diagram of the hourly time segments at the beginning of charging (the horizontal axis represents the time segment); D is the distribution diagram of the hourly time segments at the end of charging (the horizontal axis represents the time segment); E is the distribution of the number of charging times with different charging durations (the horizontal axis represents the charging duration); F is the charging frequency analysis diagram (the horizontal axis represents the charging frequency); G is the fast and slow charging ratio analysis diagram (the horizontal axis represents the fast and slow charging ratio).

[0310] 2) Analysis of other auxiliary systems of the vehicle;

[0311] Other auxiliary systems of the vehicle will also have an impact on battery usage. For example, the vehicle's air conditioning system and entertainment system will consume battery energy. Therefore, when analyzing the vehicle configuration, it is also necessary to consider the energy consumption of these auxiliary systems and provide users with reasonable usage suggestions to avoid unnecessary energy waste. The basic operating information of other auxiliary systems of the vehicle can be obtained so that users can monitor battery energy consumption later.

[0312] 3) Analysis of intelligent driving assistance systems;

[0313] The vehicle's intelligent driving assistance system can sense and judge the vehicle's surrounding environment through advanced sensors and algorithms, thereby assisting the driver in driving more safely. When analyzing vehicle configuration, it is also necessary to pay attention to the performance and energy consumption of these systems to evaluate their impact on battery energy consumption; that is, to obtain basic operating information of the intelligent driving assistance system so that users can monitor battery energy consumption later.

[0314] ④Vehicle overall design and material analysis;

[0315] The overall design and material of the vehicle will also affect battery usage. For example, the weight and structural design of the vehicle body will affect the energy consumption and stability of the vehicle; the sound insulation materials and seat materials in the vehicle will also affect the comfort and energy consumption of passengers. Therefore, when conducting vehicle configuration analysis, we also need to consider these factors comprehensively to provide a more comprehensive and accurate analysis of battery usage habits.

[0316] Based on the above charging habit analysis results, driving habit analysis results, environmental factor analysis results and vehicle configuration analysis results, battery usage recommendation information can be generated and sent to the user.

[0317] By analyzing the user's charging habits, driving habits, environmental factors, and vehicle configuration data, battery usage recommendations can be tailored for the user. For example, for users who frequently fast charge, they can be advised to use slow charging to extend battery life; for users who often drive on congested roads, energy-saving driving modes can be provided to reduce battery energy consumption. At the same time, the application will continue to optimize based on user feedback. If the user finds that a suggestion is not suitable for him or her, he or she can provide feedback through the application, and the system will adjust the analysis model based on these feedbacks to make it more accurately reflect the user's actual needs.

[0318] In short, the application and feedback of battery usage habit analysis is a continuous optimization process, aiming to provide users with more intelligent and personalized battery management solutions.

[0319] The code for implementing the method of the present application can be integrated into a big data platform to generate personalized battery usage recommendation information for vehicle owners (i.e., vehicle users) through the big data platform. Fig.34 is an architecture diagram of a big data platform according to an embodiment of the present application, such as Fig.34 As shown, the big data platform includes:

[0320] A data collection platform that can collect data from various types of vehicle batteries;

[0321] Big data cluster, which can collect data from data collection platform.

[0322] Backend server: used to consume data in the big data cluster.

[0323] Dynamic data cluster: used to transfer dynamic data in the background server to the background server for real-time consumption, and send the real-time results returned by the background server to the big data cluster.

[0324] Static data cluster: used to transfer static data in the background server to the background server for consumption, and send the offline results returned by the background server to the big data cluster.

[0325] Page display module: provides a window for interaction with users. The driving behavior analysis module provides strong support for optimizing driving experience and improving driving safety through in-depth mining of user driving data; at the same time, the page display module also provides a data API interface, allowing other business platforms or systems to easily access and obtain the required data.

[0326] The following describes an embodiment of the device of the present application, which can be used to execute the vehicle rearview mirror heating control method in the above embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method for generating battery usage suggestion information in the above embodiment of the present application.

[0327] See also Fig.35 , showing a block diagram of a device for generating battery usage suggestion information in an embodiment of the present application. The device for generating battery usage suggestion information includes: a charging characteristic information determination module 3510, used to analyze the charging data of the battery of the vehicle to obtain charging characteristic information; a driving characteristic information determination module 3520, used to analyze the driving data of the vehicle to obtain driving characteristic information; an energy consumption impact information determination module 3530, used to analyze the battery usage data of the vehicle to obtain the energy consumption impact information of the environmental parameters on the battery; a basic energy consumption information determination module 3540, used to perform energy consumption analysis on the configuration data of the vehicle to obtain the basic energy consumption information of the battery; and a suggestion information generation module 3550, used to generate the battery usage suggestion information of the vehicle according to the charging characteristic information, driving characteristic information, the energy consumption impact information of the environmental parameters on the battery and the basic energy consumption information of the battery.

[0328] In some embodiments, the charging characteristic information includes at least one of a charging frequency characteristic, a charging duration characteristic, and a charging method characteristic; the charging characteristic information determination module includes at least one of the following: a first statistical unit, used to perform charging frequency statistics on the charging data to obtain a charging frequency characteristic; a second statistical unit, used to perform charging time statistics on the charging data to obtain a charging duration characteristic; a third statistical unit, used to perform charging method statistics on the charging data to obtain a charging method characteristic.

[0329] In some embodiments, the charging characteristic information includes charging time characteristics and charging method characteristics; the device for generating battery usage recommendation information also includes: a first prediction module, used to predict the next recommended charging time period of the vehicle based on the charging time characteristics and the current battery power information of the vehicle; a second prediction module, used to predict the recommended charging method for the next charging of the vehicle based on the charging method characteristics and the current battery power information of the vehicle; an adding module, used to add the next recommended charging time period of the vehicle and the recommended charging method for the next charging of the vehicle to the battery usage recommendation information.

[0330] In some embodiments, the driving characteristic information includes at least one of an acceleration characteristic, a deceleration characteristic, a vehicle speed characteristic and a mileage characteristic; the driving characteristic information determination module 3520 includes at least one of the following: a first extraction module, used to extract acceleration characteristics from the vehicle's driving data to obtain an acceleration characteristic; a second extraction module, used to extract deceleration characteristics from the vehicle's driving data to obtain a deceleration characteristic; a third extraction module, used to extract speed characteristics from the vehicle's driving data to obtain a vehicle speed characteristic; a fourth extraction module, used to extract mileage characteristics from the vehicle's driving data to obtain a mileage characteristic.

[0331] In some embodiments, the environmental parameters include at least one of temperature, humidity, altitude, road roughness and traffic environment; the energy consumption impact information determination module 3530 includes at least one of the following: a first analysis unit, used to analyze the battery usage data of the vehicle at different temperatures to obtain information on the impact of temperature on the battery performance; a second analysis unit, used to analyze the battery usage data of the vehicle at different humidity to obtain information on the impact of humidity on the battery energy consumption; a third analysis unit, used to analyze the battery usage data of the vehicle at different altitudes to obtain information on the impact of altitude on the battery energy consumption; a fourth analysis unit, used to analyze the battery usage data of the vehicle on multiple roads with different degrees of road roughness to obtain information on the impact of road roughness on the battery energy consumption; a fifth analysis unit, used to analyze the battery usage data of the vehicle in multiple traffic environments with different degrees of congestion to obtain information on the impact of the traffic environment on the battery energy consumption.

[0332] In some embodiments, a first analysis unit includes: an acquisition unit for acquiring the number of battery charge times, battery discharge depth and battery temperature at multiple different temperatures from battery usage data of the vehicle at multiple different temperatures; a first determination unit for determining information on the influence of temperature on the number of battery charge times based on the number of battery charge times at multiple different temperatures; a second determination unit for determining information on the influence of temperature on the battery discharge depth based on the battery discharge depth at multiple different temperatures; a third determination unit for performing correlation analysis based on the battery temperature at multiple different temperatures to determine information on the influence of temperature on the battery temperature; a generation unit for generating information on the influence of temperature on battery performance based on information on the influence of temperature on the number of battery charge times, information on the influence of temperature on the battery discharge depth and information on the influence of temperature on the battery temperature.

[0333] In some embodiments, basic energy consumption information includes at least one of battery life information, information on the impact of motor performance on battery energy consumption, information on the impact of infrastructure on battery energy consumption, and energy consumption information of software systems; a basic energy consumption information determination module 3540 includes at least one of the following: a battery life information determination unit, used to determine the battery life information of the vehicle based on the battery type and battery capacity in the vehicle's configuration data; a first information determination unit, used to determine the impact of the vehicle's motor performance on battery energy consumption based on the motor performance information in the vehicle's configuration data and the battery energy consumption under different motor performances; a second information determination unit, used to determine the impact of the vehicle's infrastructure on battery energy consumption based on the vehicle's infrastructure information in the vehicle's configuration data and the battery energy consumption under different infrastructures; a third determination unit, used to determine the energy consumption information of the software systems in the vehicle based on the basic operating information of each software system in the vehicle's configuration data.

[0334] In some embodiments, the recommendation information generation module 3550 includes: a first generation unit, which is used to generate charging recommendation information based on charging feature information and the influence of different charging features on battery energy consumption; a second generation unit, which is used to generate driving recommendation information based on driving feature information and the influence of different driving features on battery energy consumption; a third generation unit, which is used to generate recommendation information for the vehicle in the current environment based on the information on the influence of different environmental parameters on the battery's energy consumption and the current environment of the vehicle; a fourth generation unit, which is used to generate the vehicle's current energy consumption prompt information based on the battery's basic energy consumption information and the current power information of the battery in the vehicle; a combination unit, which is used to combine the charging recommendation information, driving recommendation information, the vehicle's recommendation information in the current environment and the vehicle's current energy consumption prompt information to obtain the vehicle's battery usage recommendation information.

[0335] In some embodiments, the device for generating battery usage recommendation information also includes: a sending module for sending battery usage recommendation information to a vehicle; a feedback information receiving module for receiving feedback information returned by the vehicle in response to the battery usage recommendation information; and an updating module for updating the battery usage recommendation information for the vehicle based on the feedback information.

[0336] Based on the same inventive concept, an embodiment of the present application further provides a computer program product, which includes computer instructions stored in a computer-readable storage medium and suitable for being read and executed by a processor to implement the above method.

[0337] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, in which at least one computer program instruction is stored, and the at least one computer program instruction is loaded and executed by a processor to implement the above method.

[0338] Based on the same inventive concept, the embodiment of the present application further provides a vehicle, referring to Fig.36 , shows a schematic diagram of the structure of an electronic device in an embodiment of the present application, the electronic device includes one or more memories 1004, one or more processors 1002 and at least one computer program (computer program instruction) stored in the memory 1004 and executable on the processor 1002, and the processor 1002 implements the above method when executing the computer program.

[0339] Among them, Fig.36 In the embodiment of the present invention, a bus architecture (represented by bus 1000) is shown, bus 1000 may include any number of interconnected buses and bridges, bus 1000 links various circuits including one or more processors represented by processor 1002 and memory represented by memory 1004. Bus 1000 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 1005 provides an interface between bus 1000 and receiver 1001 and transmitter 1003. Receiver 1001 and transmitter 1003 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 1002 is responsible for managing bus 1000 and general processing, while memory 1004 may be used to store data used by processor 1002 when performing operations.

[0340] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on a computer-readable medium or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these. In addition, each functional unit may be integrated into a processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit.

[0341] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0342] The units described as separate components may or may not be physically separated, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed in multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0343] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store computer program instructions.

[0344] The above description is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method for generating battery usage suggestion information, characterized in that: include: Analyze the charging data of the vehicle's battery to obtain charging characteristic information; Analyzing the driving data of the vehicle to obtain driving characteristic information; Analyzing the battery usage data of the vehicle to obtain information on the impact of environmental parameters on the energy consumption of the battery; Performing energy consumption analysis on the configuration data of the vehicle to obtain basic energy consumption information of the battery; Battery usage recommendation information for the vehicle is generated according to the charging characteristic information, the driving characteristic information, the information on the impact of the environmental parameters on the energy consumption of the battery, and the basic energy consumption information of the battery.

2. The method according to claim 1, characterized in that: The charging characteristic information includes at least one of a charging frequency characteristic, a charging duration characteristic, and a charging method characteristic; The charging data of the battery of the vehicle is analyzed to obtain the charging characteristic information, including at least one of the following: Performing charging frequency statistics on the charging data to obtain a charging frequency feature; Performing charging time statistics on the charging data to obtain charging time characteristics; The charging data is subjected to charging mode statistics to obtain charging mode characteristics.

3. The method according to claim 2, characterized in that The charging characteristic information includes charging time characteristics and charging mode characteristics; the method further includes: Predicting the next recommended charging time period for the vehicle based on the charging time characteristics and the current battery power information of the vehicle; Predicting a recommended charging method for the next charging of the vehicle based on the charging method characteristics and the current battery power information of the vehicle; The next recommended charging time period of the vehicle and the recommended charging method for the next charging of the vehicle are added to the battery usage suggestion information.

4. The method according to claim 1, characterized in that The driving characteristic information includes at least one of an acceleration characteristic, a deceleration characteristic, a vehicle speed characteristic, and a mileage characteristic; The analyzing the driving data of the vehicle to obtain driving characteristic information includes at least one of the following: Extracting acceleration features from the driving data of the vehicle to obtain acceleration features; Extracting deceleration features from the driving data of the vehicle to obtain deceleration features; Extracting speed features from the driving data of the vehicle to obtain vehicle speed features; A mileage feature is extracted from the driving data of the vehicle to obtain a mileage feature.

5. The method according to claim 1, characterized in that The environmental parameters include at least one of temperature, humidity, altitude, road roughness and traffic environment; The analyzing the battery usage data of the vehicle to obtain the information on the impact of environmental parameters on the energy consumption of the battery includes at least one of the following: Analyzing battery usage data of the vehicle at different temperatures to obtain information on the impact of temperature on the performance of the battery; Analyzing the battery usage data of the vehicle under different humidity conditions to obtain information on the impact of humidity on the energy consumption of the battery; Analyzing battery usage data of the vehicle at different altitudes to obtain information on the impact of altitude on energy consumption of the battery; Analyzing battery usage data of the vehicle on multiple roads with different degrees of road roughness to obtain information on the impact of road roughness on energy consumption of the battery; The battery usage data of the vehicle in multiple traffic environments with different congestion levels are analyzed to obtain information on the impact of the traffic environment on the energy consumption of the battery.

6. The method according to claim 5, characterized in that The analyzing the battery usage data of the vehicle at different temperatures to obtain information on the impact of temperature on the performance of the battery includes: acquiring the battery charge times, battery discharge depth and battery temperature at multiple different temperatures from the battery usage data of the vehicle at multiple different temperatures; Determining, according to the number of times the battery is charged at a plurality of different temperatures, information on the effect of temperature on the number of times the battery is charged; Determine information on the effect of temperature on the battery discharge depth according to the battery discharge depth at multiple different temperatures; Perform correlation analysis based on battery temperatures at multiple different temperatures to determine the impact of temperature on battery temperature; The information on the influence of temperature on the battery performance is generated according to the information on the influence of temperature on the battery charging times, the information on the influence of temperature on the battery discharge depth and the information on the influence of temperature on the battery temperature.

7. The method according to claim 1, characterized in that The basic energy consumption information includes at least one of the following: battery life information, information on the impact of motor performance on battery energy consumption, information on the impact of infrastructure on battery energy consumption, and energy consumption information of the software system; The energy consumption analysis of the configuration data of the vehicle to obtain the basic energy consumption information of the battery includes at least one of the following: Determine the cruising range information of the vehicle based on the battery type and battery capacity in the configuration data of the vehicle; Determining information on the influence of the motor performance of the vehicle on the battery energy consumption according to the motor performance information in the configuration data of the vehicle and the battery energy consumption under different motor performances; Determine the influence of the basic structure of the vehicle on the battery energy consumption based on the basic structure information of the vehicle and the battery energy consumption under different basic structures in the configuration data of the vehicle; The energy consumption information of the software systems in the vehicle is determined according to the basic operation information of each software system in the configuration data of the vehicle.

8. The method according to claim 1, characterized in that: The generating the battery usage suggestion information of the vehicle according to the charging characteristic information, the driving characteristic information, the information on the impact of the environmental parameters on the energy consumption of the battery, and the basic energy consumption information of the battery includes: Generate charging suggestion information according to the charging characteristic information and the influence relationship of different charging characteristics on battery energy consumption; generating driving suggestion information according to the driving characteristic information and the influence relationship between different driving characteristics on battery energy consumption; Generate suggestion information for the vehicle in the current environment according to the information on the impact of different environmental parameters on the energy consumption of the battery and the current environment of the vehicle; Generate current energy consumption prompt information of the vehicle according to the basic energy consumption information of the battery and the current power information of the battery in the vehicle; The charging suggestion information, the driving suggestion information, the suggestion information of the vehicle in the current environment and the current energy consumption prompt information of the vehicle are combined to obtain the battery use suggestion information of the vehicle.

9. The method according to claim 1, characterized in that: After generating the battery usage suggestion information of the vehicle according to the charging characteristic information, the driving characteristic information, the information on the impact of the environmental parameters on the energy consumption of the battery, and the basic energy consumption information of the battery, the method further includes: sending the battery usage suggestion information to the vehicle; receiving feedback information returned by the vehicle in response to the battery usage suggestion information; The battery usage suggestion information for the vehicle is updated according to the feedback information.

10. An electronic device comprising a processor and a memory, characterized in that: The memory stores computer program instructions that can be executed by the processor, and when the processor executes the computer program instructions, the method according to any one of claims 1 to 9 is implemented.

Images