A vehicle torque control method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a vehicle torque control method and device, electronic equipment and storage medium, relating to the technical field of vehicle control. The method comprises: obtaining user features based on user interaction data; obtaining a working condition feature vector based on cloud data; obtaining real-time data features based on vehicle-end data; performing data fusion based on the user features, the working condition feature vector, the real-time data features and a set weight to obtain a fused feature vector; and performing adaptive torque control based on the fused feature vector. The method realizes deep fusion of vehicle-cloud-person data by obtaining user features, working condition feature vectors and real-time vehicle data features, thereby accurately identifying driving intentions and vehicle use scenarios, and realizing adaptive adjustment of vehicle torque to meet the individual needs of drivers, solving the problem that existing single-dimensional vehicle torque control methods cannot accurately adapt to driving needs in different driving scenarios.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and more specifically, to a method, device, electronic equipment, and storage medium for controlling the torque of a vehicle. Background Technology

[0002] With the rapid development of intelligent vehicles, people's demands for vehicle torque are becoming increasingly diverse and intelligent. Traditional torque control technology mainly relies on the driver manually selecting driving modes, coasting energy recovery levels, torque sensitivity settings, and front-to-rear axle torque distribution coefficients to identify driving styles. However, existing methods of controlling vehicle torque through a single dimension cannot accurately adapt to the driving needs of different driving scenarios. Summary of the Invention

[0003] The purpose of this application is to provide a vehicle torque control method, device, electronic device, and storage medium. By acquiring user characteristics, operating condition feature vectors, and real-time vehicle data characteristics, it achieves deep fusion of vehicle-cloud-human data, thereby accurately identifying driving intentions and vehicle usage scenarios, and realizing adaptive adjustment of vehicle torque to meet the personalized needs of drivers. This solves the problem that existing methods of controlling vehicle torque through a single dimension cannot accurately adapt to driving needs under different driving scenarios.

[0004] In a first aspect, this application provides a vehicle torque control method, which includes: obtaining user characteristics based on user interaction data; obtaining a working condition feature vector based on cloud data; obtaining real-time data features based on vehicle-side data; performing data fusion based on the user characteristics, the working condition feature vector, the real-time data features, and a set weight to obtain a fused feature vector; and performing adaptive torque control based on the fused feature vector.

[0005] In the technical solution of this application embodiment, user characteristics are obtained based on user interaction data, operating condition feature vectors are obtained from cloud data, and real-time vehicle data characteristics are obtained from vehicle-side data. The user characteristics, operating condition feature vectors, and real-time data characteristics are then fused, and the vehicle torque is adaptively adjusted based on the fusion result. This method achieves deep fusion of vehicle-cloud-human data, thereby accurately identifying the driver's driving intentions and usage scenarios to meet the driver's personalized needs.

[0006] In some embodiments, obtaining user features based on user interaction data includes: concatenating and weighting user interaction data and user profiles to obtain user features. Specifically, this involves: obtaining normalized feature values ​​corresponding to each type of user interaction data and user profile, wherein the user interaction data includes manually set data and voice input data; concatenating the normalized feature values ​​to generate concatenated features; and performing weighted fusion based on the concatenated features and pre-set weights for each type of user interaction data and the user profile to generate user features. Since manually set data, voice input, and historical profiles can all be used to characterize a user's driving style, concatenating and weighting them can achieve accurate identification of the user's driving style.

[0007] In some embodiments, user features are obtained by weight fusion based on the splicing features, pre-set weights for each type of user interaction data, and the weights of the user profile, including: weight fusion using a weighted average method to obtain user features. ;in, This represents the normalized feature value in the splicing feature. n Indicates the number of normalized eigenvalues. This represents the weight corresponding to the normalized feature value, and the sum of all weights is 1. The user feature value is obtained by using a weighted average method to calculate a weighted average of each type of user interaction data and its corresponding weight.

[0008] In some embodiments, cloud data includes road condition information and weather information. Obtaining a working condition feature vector based on the cloud data includes: obtaining a normalized value of road condition information based on power demand, where the normalized value ranges from 0 to 1, where 0 represents the working condition with the lowest power demand and 1 represents the working condition with the highest power demand; obtaining a normalized value of weather information based on power capability, where the normalized value ranges from 0 to 1, where 0 represents the weather with the lowest power capability and 1 represents the weather with the highest power capability; performing fuzzy logic operations based on the normalized values ​​of the road condition information and the weather information to obtain working condition feature values; and generating a working condition feature vector based on the working condition feature values. The working condition feature vector is obtained by analyzing the road condition and weather information using fuzzy logic.

[0009] In some embodiments, the step of fusing data based on the user characteristics, operating condition feature vector, real-time data characteristics, and set weights to obtain a fused feature vector includes: if it is determined based on the real-time data characteristics that the current vehicle is in a stable state, then performing a weighted average based on the user characteristics, the operating condition feature values, and the corresponding weights to obtain a weight factor; and generating a fused feature vector based on the weight factor, the normalized value of road condition information, and the normalized value of weather information. By using the user characteristics, the operating condition feature values, and the corresponding weights to perform a weighted average to obtain the weight factor, deep fusion of vehicle-cloud-person data is achieved.

[0010] In some embodiments, adaptive torque control based on the fused feature vector includes: obtaining the driver's required torque based on the fused feature vector; and distributing torque between the front and rear axle motors based on the driver's required torque and the fused feature vector. Adaptive adjustment of the driver's required torque according to the fused feature vector satisfies the driver's personalized needs.

[0011] In some embodiments, obtaining the driver's required torque based on the fused feature vector includes: if the weighting factor is greater than 0, then the driver's required torque is: ;in, Indicates the torque required by the driver. Indicates the original torque demand. Indicates the maximum torque. This represents the weighting factor in the fused feature vector; if the weighting factor is less than 0, then the driver's required torque is: ;in, This represents the minimum torque. A weighted factor is used to adaptively adjust the torque required by the driver, thus achieving personalized torque adjustment for the driver.

[0012] Secondly, this application provides a vehicle torque control device. The device includes: a user feature acquisition module for obtaining user features based on user interaction data; a working condition feature acquisition module for obtaining a working condition feature vector based on cloud data; a real-time data feature acquisition module for obtaining real-time data features based on vehicle-side data; a data fusion module for performing data fusion based on the user features, working condition feature vector, real-time data features, and set weights to obtain a fused feature vector; and a torque control module for performing adaptive torque control based on the fused feature vector. By acquiring and fusing user features, working condition feature vector, and real-time vehicle data features to obtain a shared feature vector, deep fusion of vehicle-cloud-human data is achieved. This allows for accurate identification of driving intentions and usage scenarios, enabling adaptive adjustment of vehicle torque to meet the driver's personalized torque needs. This solves the problem that existing methods of controlling vehicle torque through a single dimension cannot accurately adapt to driving needs in different driving scenarios.

[0013] Thirdly, this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the above-described vehicle communication data encryption method.

[0014] Fourthly, this application provides a readable storage medium storing computer program instructions, which are read and executed by a processor to perform the above-described vehicle communication data encryption method. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart of a vehicle torque control method provided in this application embodiment; Figure 2 A flowchart illustrating the generation process of user features provided in this application embodiment; Figure 3 A flowchart illustrating the acquisition of working condition feature vectors provided in this application embodiment; Figure 4 A flowchart illustrating the acquisition of fused feature vectors provided in this application embodiment; Figure 5 The adaptive torque control flowchart provided in the embodiments of this application; Figure 6 This is a specific block diagram illustrating the implementation of vehicle torque control in an embodiment of this application. Figure 7 This is a structural block diagram of the vehicle torque control device provided in an embodiment of this application.

[0017] icon: 110 - User feature acquisition module; 120 - Operating condition feature acquisition module; 130 - Real-time data feature acquisition module; 140 - Data fusion module; 150 - Torque control module. Detailed Implementation

[0018] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0019] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0020] With the rapid development of intelligent vehicles, people's demand for vehicle torque is becoming more and more diversified. However, the existing torque adjustment methods, such as the driver manually selecting the driving mode, result in a relatively simple human-computer interaction method, which cannot accurately identify driving style and user preferences. As a result, the method of controlling vehicle torque through a single dimension cannot accurately adapt to the driving needs in different driving scenarios.

[0021] To address the aforementioned technical issues, this application provides a vehicle torque control method. This method fuses user characteristics, operating condition feature vectors, and real-time vehicle data features, achieving deep integration of vehicle-cloud-human data. The fused feature vector obtained through data fusion is used to adaptively adjust the vehicle torque. Since this torque adjustment method integrates user driving style preferences, vehicle operating conditions, and other data features, it can quickly respond to driving needs in different driving scenarios.

[0022] Please refer to Figure 1 , Figure 1 A flowchart of a vehicle torque control method provided in this application embodiment is included, the method comprising the following steps: S110: Obtain user characteristics based on user interaction data; S120: Obtain operating condition feature vectors based on cloud data; S130: Acquire real-time data features based on vehicle-side data; S140: Based on the user characteristics, the working condition feature vector, the real-time data characteristics, and the set weights, data fusion is performed to obtain a fused feature vector; S150: Adaptive torque control based on the fused feature vector.

[0023] For example, user interaction data includes, but is not limited to, manual settings data and voice input data. Manual settings data includes settings for power adjustment, energy recovery adjustment, torque sensitivity adjustment, and front / rear axle torque distribution coefficients, used to form basic torque curves and torque gradient curves. Voice input data includes common user complaints, such as: sluggish power response, slight motion sickness, weak overtaking power, etc., to extract the user's pain points regarding current driving characteristics. User profiling: Based on historical data, the user's driving style is identified.

[0024] Cloud data is used to obtain real-time weather conditions, road conditions, and other information. The operating condition feature vector obtained through cloud data is used as a factor to consider in torque adjustment, so that the torque adjustment results can adapt to the needs of extreme weather and special road conditions.

[0025] Vehicle-side data refers to real-time recorded vehicle status information, including but not limited to information on vehicle speed, throttle, steering, motor, battery, and chassis. This information is used to characterize the current state of the vehicle and to assess vehicle safety. It also includes other vehicle information, such as steering responsiveness and suspension information, which indirectly reflect the user's driving characteristics.

[0026] Incorporating user interaction data into torque adjustment is because user interaction data reflects the user's driving style and preferences. At the same time, by fusing user characteristics, operating condition feature vectors, and real-time data features, a deep integration of vehicle-cloud-human data is achieved, enabling the torque adjustment results to meet the user's driving needs while adapting to various driving scenarios.

[0027] In some embodiments, obtaining user features based on user interaction data includes: splicing and weighting user interaction data and user profiles to obtain user features.

[0028] User interaction data is concatenated and weighted for fusion. Since user interaction data comes in various forms, such as manual settings, voice input, and user profiles, all reflecting a user's driving style, manual settings are the most accurate. Their importance can be represented by corresponding numerical values, such as normalized feature values. These normalized feature values ​​are then concatenated to form a feature vector. The concatenated feature vector is then used with corresponding weights to calculate weight fusion. By concatenating and weighting user interaction data and user profiles, user characteristics are obtained, enabling a quantitative representation of user interaction data. Concatenating and fusing user interaction data, user profiles, and other data, combined with current and historical data, allows for the determination of a user's driving style.

[0029] Please refer to Figure 2 , Figure 2 The flowchart for generating user features shows that, in some embodiments, user interaction data and user profiles are concatenated and weighted to obtain user features, including: S111: Obtain the normalized feature value corresponding to each type of user interaction data and user profile, wherein the user interaction data includes manually set data and voice input data; S112: Concatenate the normalized feature values ​​to generate concatenated features; S113: Based on the splicing features and the weights of each type of user interaction data and user profile set in advance, perform weight fusion to generate user features.

[0030] User interaction data and user profiles are concatenated and weighted. For example, the manual setting data, voice input data, and user profiles representing driving styles are normalized using values ​​from -1 to 1, i.e., represented by normalized feature values. Here, -1 represents the gentlest, and 1 represents the most aggressive. The normalized feature values ​​are then concatenated to obtain the concatenated feature. For example, the concatenated feature can be represented as [a, b, c], where a represents the normalized feature value corresponding to the manual setting data, b represents the normalized feature value corresponding to the voice input data, and c represents the normalized feature value corresponding to the user profile, as shown in the table below:

[0031] Among them, the concatenated feature [1, 0.1, -1] represents a user whose manually set data is aggressive (the normalized feature value corresponding to the manually set data is 1), whose user voice complaining motivation is weak (the normalized feature value corresponding to the voice input data is 0.1), and whose user profile is mild (the normalized feature value corresponding to the user profile is -1). The concatenated feature [-0.5, -0.1, 1] represents a user whose manually set data is relatively mild (the normalized feature value corresponding to the manually set data is -0.5), whose user voice complaining motivation is strong (the normalized feature value corresponding to the voice input data is -0.1), and whose user profile is aggressive (the normalized feature value corresponding to the user profile is 1).

[0032] Combining manually set data, voice input data, and user profiles ensures the accuracy of user characteristics. Furthermore, this approach, which combines manual setting data, voice input data, and user profiles to describe user driving style, considers not only current and historical data but also multiple human-computer interaction modes. Compared to a single human-computer interaction mode, such as physical user input, this results in more accurate recognition of user driving style.

[0033] In some embodiments, weight fusion is performed based on the splicing features and the pre-set weights of each type of user interaction data to obtain user features, including: weight fusion using a weighted average method to obtain user features. ; in, This represents the normalized feature value in the splicing feature. n Indicates the number of normalized eigenvalues. This represents the weights corresponding to the normalized eigenvalues, and the sum of all weights is 1.

[0034] User features, or user feature values, are numerical values ​​calculated by weighted averaging of each normalized feature value in the concatenated features with its corresponding weight. The weights are set based on the principle of prioritizing current user input and supplementing with user profile data. For example, in the current driving cycle, if the driver manually inputs (sets data), the weight is 0.8; otherwise, it's 0. If there's voice input regarding power requirements, the weight is 0.1; otherwise, it's 0. The remaining values ​​from the three historical user profiles are used to ensure that the sum of the weights of the three user features equals 1. Examples are shown in the table below:

[0035] The user features can be obtained by multiplying the concatenated features and their corresponding weights and then adding them together.

[0036] By employing a weighted average method for weight fusion, user characteristics that characterize a user's driving style can be obtained. Furthermore, these characteristics integrate manually set data, voice input data, and user profiles, resulting in more accurate identification of a user's driving style.

[0037] In some embodiments, obtaining a working condition feature vector based on cloud data includes: obtaining a corresponding working condition feature vector based on the road condition information and weather information.

[0038] Cloud data includes road condition information and weather information. Among the operating conditions, weather information and road condition information, such as slope information, are strongly correlated with subsequent torque control, so they need to be output as feature quantities.

[0039] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the process of obtaining the operating condition feature vector. In some embodiments, obtaining the corresponding operating condition feature vector based on road condition information and weather information includes: S121: Obtain road condition information based on the normalized value of power demand, and the range of the normalized value of road condition information is 0-1, where 0 represents the working condition with the minimum power demand and 1 represents the working condition with the maximum power demand. S122: Obtain weather information based on the normalized value of dynamic capability, and the normalized value of weather information is in the range of 0-1, where 0 represents the weather with the weakest dynamic capability and 1 represents the weather with the strongest dynamic capability. S123: Perform fuzzy logic operations based on the normalized values ​​of the road condition information and the normalized values ​​of the weather information to obtain the operating condition characteristic values; S124: Generate a working condition feature vector based on the working condition feature values.

[0040] The working condition feature vector here is to normalize common road condition information and weather conditions, and then concatenate them into the same vector. The working condition feature vector can be represented as [d,e,f], where d represents the working condition feature value, e represents the normalized value of road condition information, and f represents the normalized value of weather information.

[0041] Common road condition information includes, but is not limited to: urban expressways, highways, mountain roads, starting on mountain roads, and congestion. This is normalized to a range of 0 to 1, where 0 represents the condition with the lowest power demand, such as urban congestion, and 1 represents the condition with the highest power demand, such as starting on a mountain road. Common weather information includes, but is not limited to: sunny, cloudy, rainy, heavy rain, and snowy weather. This is also normalized to a range of 0 to 1, where 0 represents the weather with the weakest power capacity, such as snowy weather, and 1 represents the weather with the strongest power capacity, such as sunny weather.

[0042] The analysis of operating condition characteristics is based on fuzzy logic operations. Normalized values ​​of road condition information and weather information are used as inputs, and the output operating condition characteristic analysis results are the operating condition characteristic values. The fuzzy logic operation rules are shown in the table below:

[0043] For example, if the identified driving condition is congested traffic and the weather is sunny, the output driving condition feature value is 0.8. Another example is starting on a snowy mountain road; the output driving condition feature vector would be [0.5, 1, 0]. Here, 0.5 represents the driving condition feature value; 1 indicates starting on a mountain road; and 0 indicates snowy weather.

[0044] By using road condition and weather information to perform fuzzy logic operations to obtain operating condition feature vectors, these vectors are used as the basis for subsequent torque adjustment, enabling the torque adjustment results to adapt to the current road conditions and weather.

[0045] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the process of obtaining the fused feature vector. In some embodiments, data fusion is performed based on the user features, working condition feature vector, real-time data features, and set weights to obtain the fused feature vector, including: S141: If it is determined that the current vehicle is in a stable state based on the real-time data characteristics, then a weighted average is performed based on the user characteristics, the operating condition characteristic values ​​and the corresponding weights to obtain a weighting factor; S142: Generate a fused feature vector based on the weighting factor, the normalized value of road condition information, and the normalized value of weather information.

[0046] Real-time data features include information on vehicle speed, throttle, steering, motor, battery, and chassis, used to assess vehicle safety. Specifically: 0 indicates the vehicle is in a stable state, the motor and battery are not overheating, chassis-related functions are not activated, and adaptive torque adjustment is possible; 1 indicates the vehicle is in an unsafe state, exceeding safety boundary values, requiring the entire powertrain to respond to these safety boundary values, prioritizing vehicle safety control, and in this case, adaptive torque adjustment is not possible.

[0047] For the weighting factor, the user features, operating condition features and their corresponding weights are weighted and averaged. The weights of user features and operating condition features can be set based on priority. User features represent the user's driving style and preferences, so they have a higher priority. For example, the weights of user features and operating condition features can be set to 0.7 and 0.3 respectively, and then weighted and averaged to obtain the weighting factor.

[0048] The fused feature vector is represented as [w, e, f], where w represents the weight factor, e represents the normalized value of road condition information, and f represents the normalized value of weather information, as shown in the table below:

[0049] For example, the fused feature vector [0.78,1,0], where 0.78 represents the weight factor, is calculated as follows: user feature 0.9*0.7 + working condition feature value 0.5*0.3 = 0.78, where the weights of the user feature and the working condition feature value are 0.7 and 0.3 respectively.

[0050] Because this application has the function of correcting user characteristics based on user profiles, if the weight of user characteristics is relatively large compared to user habits, the user will be gradually judged as a mild user based on driving habits, thus reducing the user characteristic value. The resulting weight factor will adaptively decrease to meet the overall user habits. Conversely, if the weight of user characteristics is relatively small compared to user driving habits, the user will be gradually judged as an aggressive user based on driving habits, thus increasing the user characteristic value. The resulting weight factor will adaptively increase.

[0051] This application adjusts the torque based on the driver's original torque requirements. Therefore, when the driver manually inputs data, adjustments must be made according to the driver's needs, and this has the highest priority. If the driver does not manually input data, it means that the driver has not actively adjusted their torque requirements, and the original requirements can be maintained. In this case, the weighting factor is 0, indicating that no adjustments are needed based on the driver's manual input. Therefore, the weighting factor can be used to achieve adaptive adjustment of the vehicle's torque to meet the driver's needs.

[0052] Please refer to Figure 5 , Figure 5 This is a flowchart of adaptive torque control. In some embodiments, adaptive torque control based on the fused feature vector includes: S151: Obtain the driver's required torque based on the fused feature vector; S152: Distribute the torque between the front and rear axle motors based on the driver's required torque and the fused feature vector.

[0053] After obtaining the fused feature vector, the torque required by the driver can be adaptively adjusted based on the weighting factor. Since the weighting factor is a comprehensive weighting factor that integrates user interaction data and operating conditions, it can meet the driver's personalized needs and adapt to the vehicle usage scenario.

[0054] In some embodiments, obtaining the driver's required torque based on the fused feature vector includes: If the weighting factor is greater than 0, then the driver's required torque is: ; in, Indicates the torque required by the driver. Indicates the original torque demand. Indicates the maximum torque. This represents the weighting factor in the fused feature vector; If the weighting factor is less than 0, then the driver's required torque is: ; in, This indicates the minimum torque.

[0055] In vehicle torque control, the driver's required torque is calibrated based on the driving mode. Generally, Sport mode (launch control) is set as the maximum torque within hardware limits, while Snow mode is the weakest power mode. Therefore, when performing adaptive torque control, the driver's torque needs to be controlled between the weakest and strongest values. Thus, the maximum torque can be the required torque in Sport mode, and the minimum torque can be the required torque in Snow mode.

[0056] In addition, the required torque ramp (ramp function) can also be linearly calculated based on the above formula to obtain a torque ramp that is between snow mode and sport mode.

[0057] Based on the driver's required torque and the fused feature vector, multi-objective torque distribution between the front and rear axle motors can be achieved. For example, the torque distribution between the front and rear axles can be optimized with power, economy and stability as the objectives. In addition, the distribution process needs to take into account the characteristics of the operating conditions. For example, for acceleration / climbing conditions, torque distribution should prioritize power; for turning / slippery road conditions, torque distribution should prioritize stability; and for constant speed / low energy consumption conditions, torque distribution should prioritize economy.

[0058] Because the torque distribution process takes into account specific operating conditions, stability control can be achieved based on the specific state of the vehicle, thus improving driving safety.

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below. In some embodiments, please refer to... Figure 6 , Figure 6 To illustrate the specific block diagram for achieving vehicle torque control, the vehicle torque control method includes: S201: Acquire user interaction data, including manual settings and voice input data. Manual settings, such as power adjustment, energy recovery adjustment, torque sensitivity adjustment, and front / rear axle torque distribution coefficients, are used to generate basic torque curves and torque gradient curves. Voice input data includes user comments on power, such as sluggish power response, weak power, non-linear acceleration, motion sickness, overly aggressive power mode, overly conservative economy mode, and difficulty controlling torque at low speeds, used to extract user pain points regarding current driving characteristics. It also includes acquiring basic data such as operating condition data, vehicle information, user profiles, and other vehicle settings. Operating condition data, such as traffic congestion, highways, mountain roads, and heavy rain, enables subsequent adaptive torque adjustments to adapt to extreme weather and special road conditions. Vehicle information records real-time vehicle status, such as accelerator, pedal, steering, motor, and battery, to determine the safety boundaries of the current vehicle status. User profiles identify driving styles based on historical data, such as aggressive, gentle, and normal driving styles. Other vehicle settings, such as steering sensitivity and suspension, indirectly reflect the user's driving characteristics. S202: The data obtained in S201 is spliced, filtered and analyzed: the user interaction data is spliced ​​and fused to obtain user features, and the working condition feature vector and real-time data features are obtained by using working condition data and vehicle information respectively. Data characteristics are analyzed based on user features, operating condition feature vectors, and real-time data features, and data fusion algorithms such as weighted average method are used to fuse data to obtain fused feature vectors. S203: Adaptive torque control is achieved by using fused feature vectors. Specifically, within the motor torque safety boundary (when the vehicle is in a stable state), adaptive torque adjustment is performed using weighting factors to obtain the torque required by the driver. The required torque at the wheel ends is adjusted in real time using PedalMap (accelerator pedal characteristics), coasting torque, torque filtering, etc., and multi-objective front and rear axle torque distribution can be achieved based on the working conditions in the fused feature vectors. S204: Send the adaptive torque adjustment results to VDC (vehicle running dynamic control system).

[0060] Please refer to Figure 7 , Figure 7 The structural block diagram of the vehicle torque control device provided in this application should be understood to be related to... Figure 1 The method embodiment executed in this document corresponds to the method described above, and is capable of performing the steps involved in the aforementioned method. The specific functions of this device can be found in the description above; to avoid repetition, detailed descriptions are appropriately omitted here. This device includes, but is not limited to: User feature acquisition module 110 is used to obtain user features based on user interaction data; The working condition feature acquisition module 120 is used to obtain working condition feature vectors based on cloud data. Real-time data feature acquisition module 130 is used to acquire real-time data features based on vehicle-side data; The data fusion module 140 is used to perform data fusion based on the user characteristics, working condition feature vector, real-time data characteristics and set weights to obtain a fused feature vector; The torque control module 150 is used for adaptive torque control based on the fused feature vector.

[0061] In the technical solution of this application embodiment, a data fusion method combining vehicle-cloud-human is adopted to provide a basis for accurately identifying driving intentions and vehicle usage scenarios, thereby meeting the personalized needs of drivers.

[0062] According to some embodiments of this application, the user feature acquisition module 110 is specifically used to splice and weight fusion user interaction data and user profiles to obtain user features.

[0063] According to some embodiments of this application, the specific process of splicing includes: obtaining normalized feature values ​​corresponding to each type of user interaction data, wherein the user interaction data includes manually set data and voice input data; splicing the normalized feature values ​​to generate spliced ​​features; and performing weight fusion based on the spliced ​​features and the pre-set weights of each type of user interaction data to generate user features.

[0064] According to some embodiments of this application, the specific process of weight fusion includes: performing weight fusion using a weighted average method to obtain user features. ;in, This represents the normalized feature value in the splicing feature. n Indicates the number of normalized eigenvalues. This represents the weights corresponding to the normalized eigenvalues, and the sum of all weights is 1.

[0065] According to some embodiments of this application, the working condition feature acquisition module 120 is specifically used to: obtain the corresponding working condition feature vector based on the road condition information and weather information.

[0066] According to some embodiments of this application, the specific process for generating the working condition feature vector includes: Road condition information is obtained based on the normalized value of power demand, and the normalized value ranges from 0 to 1, where 0 represents the condition with the minimum power demand and 1 represents the condition with the maximum power demand. Weather information is obtained based on the normalized value of power capability, and the normalized value ranges from 0 to 1, where 0 represents the weather with the weakest power capability and 1 represents the weather with the strongest power capability. Fuzzy logic operations are performed on the normalized values ​​of road condition information and weather information to obtain condition feature values. A condition feature vector is generated based on the condition feature values.

[0067] According to some embodiments of this application, the data fusion module 140 is specifically used for: If the vehicle is determined to be in a stable state based on the real-time data features, a weighted average is performed based on the user features, the operating condition feature values, and the corresponding weights to obtain a weight factor; a fusion feature vector is generated based on the weight factor, the normalized value of road condition information, and the normalized value of weather information.

[0068] According to some embodiments of this application, the torque control module 150 is specifically used for: The required torque for the driver is obtained based on the fused feature vector; the torque distribution between the front and rear axle motors is performed based on the required torque for the driver and the fused feature vector.

[0069] According to some embodiments of this application, the specific process for obtaining the driver's required torque is as follows: If the weighting factor is greater than 0, then the driver's required torque is: ;in, Indicates the original torque demand. Indicates the maximum torque. This represents the weighting factor in the fused feature vector; if the weighting factor is less than 0, then the driver's required torque is: ;in, This indicates the minimum torque.

[0070] This application provides an electronic device including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to cause the electronic device to perform the methods in any of the aforementioned optional implementations.

[0071] This application provides a readable storage medium storing computer program instructions, which, when read and executed by a processor, perform the methods in any of the aforementioned optional implementations.

[0072] The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0074] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0075] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0077] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0078] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for controlling the torque of a vehicle, characterized in that, The method includes: User characteristics are obtained based on user interaction data; Obtaining a working condition feature vector based on cloud data includes: acquiring a normalized value of road condition information based on power demand, where the normalized value ranges from 0 to 1, and 0 represents the working condition with the lowest power demand, while 1 represents the working condition with the highest power demand; acquiring a normalized value of weather information based on power capability, where the normalized value ranges from 0 to 1, and 0 represents the weather with the lowest power capability, while 1 represents the weather with the highest power capability; performing fuzzy logic operations based on the normalized values ​​of the road condition information and the weather information to obtain working condition feature values; and generating a working condition feature vector based on the working condition feature values; wherein the cloud data includes road condition information and weather information. Real-time data features are obtained based on vehicle-side data; Based on the user characteristics, the working condition feature vector, the real-time data characteristics, and the set weights, data fusion is performed to obtain a fused feature vector; Adaptive torque control is performed based on the fused feature vector.

2. The vehicle torque control method according to claim 1, characterized in that, The method of obtaining user characteristics based on user interaction data includes: User interaction data and user profiles are spliced ​​and weighted to obtain user characteristics, specifically: Obtain the normalized feature values ​​corresponding to each type of user interaction data and user profile, wherein the user interaction data includes manually set data and voice input data; The normalized feature values ​​are concatenated to generate concatenated features; User features are generated by weight fusion based on the splicing features, the pre-set weights of each user interaction data, and the weights of the user profile.

3. The vehicle torque control method according to claim 2, characterized in that, The process of weight fusion based on the splicing features, pre-set weights for each type of user interaction data, and the weights of the user profile to obtain user features includes: User characteristics are obtained by weighted averaging and fusion. ； in, This represents the normalized feature value in the splicing feature. n Indicates the number of normalized eigenvalues. This represents the weights corresponding to the normalized eigenvalues, and the sum of all weights is 1.

4. The vehicle torque control method according to claim 1, characterized in that, The process of fusing data based on the user characteristics, working condition feature vector, real-time data characteristics, and set weights to obtain a fused feature vector includes: If it is determined that the current vehicle is in a stable state based on the real-time data features, then a weighted average is performed based on the user features, the operating condition feature values, and the corresponding weights to obtain a weighting factor. A fused feature vector is generated based on the weighting factors, the normalized values ​​of road condition information, and the normalized values ​​of weather information.

5. The vehicle torque control method according to claim 4, characterized in that, The adaptive torque control based on the fused feature vector includes: The driver's required torque is obtained based on the fused feature vector; The torque distribution between the front and rear axle motors is based on the driver's required torque and the fused feature vector.

6. The vehicle torque control method according to claim 5, characterized in that, The process of obtaining the driver's required torque based on the fused feature vector includes: If the weighting factor is greater than 0, then the driver's required torque is: ； in, Indicates the torque required by the driver. Indicates the original torque demand. Indicates the maximum torque. This represents the weighting factor in the fused feature vector; If the weighting factor is less than 0, then the driver's required torque is: ； in, This indicates the minimum torque.

7. A vehicle torque control device, characterized in that, The device includes: The user feature acquisition module is used to obtain user features based on user interaction data. The operating condition feature acquisition module is used to obtain operating condition feature vectors based on cloud data, including: acquiring normalized values ​​of road condition information based on power demand, where the normalized values ​​range from 0 to 1, where 0 represents the operating condition with the lowest power demand and 1 represents the operating condition with the highest power demand; acquiring normalized values ​​of weather information based on power capability, where the normalized values ​​range from 0 to 1, where 0 represents the weather with the lowest power capability and 1 represents the weather with the highest power capability; performing fuzzy logic operations based on the normalized values ​​of road condition information and weather information to obtain operating condition feature values; and generating operating condition feature vectors based on the operating condition feature values; wherein, the cloud data includes road condition information and weather information; The real-time data feature acquisition module is used to acquire real-time data features based on vehicle-side data. The data fusion module is used to perform data fusion based on the user characteristics, working condition feature vector, real-time data characteristics, and set weights to obtain a fused feature vector; A torque control module is used for adaptive torque control based on the fused feature vector.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the vehicle torque control method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that, The readable storage medium stores computer program instructions, which, when read and executed by a processor, perform the vehicle torque control method according to any one of claims 1 to 6.

Images