Vehicle endurance mileage prediction method and device, vehicle and product

Abstract

The invention discloses a vehicle endurance mileage prediction method and device, a vehicle and a product, and belongs to the technical field of vehicles, and the method comprises the steps: obtaining mileage attribute data related to the endurance mileage of a target vehicle; performing preprocessing and feature extraction on the mileage attribute data to obtain mileage attribute features of the target vehicle; performing power prediction according to the mileage attribute characteristics to obtain air conditioner power data of the target vehicle and power data of other vehicle components; performing energy consumption prediction according to the mileage attribute characteristics to obtain driving energy consumption data of the target vehicle; according to the air conditioner power data, the power data of other vehicle components and the driving energy consumption data, mileage calculation is conducted, and endurance mileage data of the target vehicle is obtained. The prediction precision of the endurance mileage of the vehicle can be effectively improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, vehicle, and product for predicting vehicle driving range. Background Technology

[0002] Vehicle range is a crucial indicator for new energy vehicles, typically referring to the maximum distance a vehicle can continuously travel at any given moment. Related technologies predict vehicle range by using parameters of the vehicle's battery and pre-trained algorithm models. However, these technologies only consider battery parameters and cannot comprehensively cover the actual range, resulting in low prediction accuracy. Summary of the Invention

[0003] The main objective of this application is to provide a method, device, vehicle, and product for predicting vehicle driving range, which aims to effectively improve the accuracy of vehicle driving range prediction.

[0004] To achieve the above objectives, one aspect of this application proposes a vehicle range prediction method, the method comprising: acquiring range attribute data related to the range of a target vehicle; The mileage attribute data is preprocessed and features are extracted to obtain the mileage attribute features of the target vehicle; Power prediction is performed based on the mileage attribute characteristics to obtain the air conditioning power data and other vehicle component power data of the target vehicle. Based on the mileage attribute characteristics, energy consumption is predicted to obtain the driving energy consumption data of the target vehicle; The driving range data of the target vehicle is obtained by multiplying the air conditioning power data by time, the power data of other vehicle components by time, and the driving energy consumption data.

[0005] In some embodiments, obtaining mileage attribute data related to the driving range of the target vehicle includes: Obtain the historical and current travel data of the target vehicle as the mileage attribute data; The historical trip data includes historical energy consumption data and user profile data. The historical energy consumption data includes the energy consumption data and kinetic energy recovery data of the target vehicle during the historical trip. The user profile data includes data related to the driving habits of the target vehicle during the historical trip. The current trip data includes current battery data, current vehicle control data, current driving data, and current environment data. The current battery data includes data related to the battery status of the target vehicle during the current trip. The current vehicle control data includes data related to the control status of the target vehicle's components during the current trip. The current driving data includes data related to the driving status of the target vehicle during the current trip. The current environment data includes data related to the surrounding environment of the target vehicle during the current trip.

[0006] In some embodiments, the mileage attribute data includes historical trip data and current trip data; the preprocessing and feature extraction of the mileage attribute data to obtain the mileage attribute features of the target vehicle includes: The current trip data is preprocessed to obtain the preprocessed current trip data; Feature extraction is performed on the historical trip data and the preprocessed current trip data to obtain historical trip features, current trip features, and future trip features as the mileage attribute features; The historical trip features include historical energy consumption features; the current trip features include instantaneous vehicle control features, instantaneous driving features, instantaneous environmental features, current user profile features, and current vehicle profile features; and the future trip features include future environmental features.

[0007] In some embodiments, the mileage attribute features include current trip features and future trip features, the current trip features include instantaneous vehicle control features and instantaneous environmental features, and the future trip features include future environmental features; the step of performing power prediction based on the mileage attribute features to obtain the air conditioning power data and other vehicle component power data of the target vehicle includes: Based on the future environmental characteristics, the instantaneous vehicle control characteristics, and the instantaneous environmental characteristics, combined with the first prediction model, the air conditioning power data is obtained.

[0008] In some embodiments, the mileage attribute features include current trip features and future trip features, the current trip features include instantaneous vehicle control features and instantaneous environmental features, and the future trip features include future environmental features; the step of performing power prediction based on the mileage attribute features to obtain the air conditioning power data and other vehicle component power data of the target vehicle includes: Based on the future environmental characteristics, the instantaneous vehicle control characteristics, and the instantaneous environmental characteristics, combined with the second prediction model, the power data of the other vehicle components are obtained.

[0009] In some embodiments, the mileage attribute features include historical trip features, current trip features, and future trip features; the step of predicting energy consumption based on the mileage attribute features to obtain the driving energy consumption data of the target vehicle includes: Based on the historical travel characteristics, the current travel characteristics, and the future travel characteristics, and combined with the third prediction model, the driving energy consumption data is obtained.

[0010] In some embodiments, the step of calculating the driving range data of the target vehicle based on the air conditioning power data, the power data of other vehicle components, and the driving energy consumption data includes: The target energy consumption data of the target vehicle is obtained based on the air conditioning power data, the power data of other vehicle components, and the drive energy consumption data. The driving range data is obtained based on the mileage attribute data and the target energy consumption data.

[0011] To achieve the above objectives, another aspect of this application provides a vehicle range prediction device, the device comprising: The acquisition module is used to acquire mileage attribute data related to the driving range of the target vehicle; The first processing module is used to preprocess and extract features from the mileage attribute data to obtain the mileage attribute features of the target vehicle. The second processing module is used to perform power prediction based on the mileage attribute features to obtain the air conditioning power data and other vehicle component power data of the target vehicle. The third processing module is used to predict energy consumption based on the mileage attribute characteristics to obtain the driving energy consumption data of the target vehicle. The fourth processing module is used to calculate the mileage based on the product of the air conditioning power data and time, the product of the power data of other vehicle components and time, and the driving energy consumption data, so as to obtain the driving range data of the target vehicle.

[0012] To achieve the above objectives, another aspect of this application provides a vehicle, the vehicle comprising: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle range prediction method.

[0013] On the other hand, a computer program product is proposed, including a computer program that, when executed by a processor, implements the vehicle range prediction method described in any of the above technical solutions.

[0014] According to the embodiments of this application, a vehicle range prediction method, apparatus, and vehicle are provided. The method involves acquiring mileage attribute data related to the target vehicle's range; preprocessing and extracting features from the mileage attribute data to obtain the target vehicle's mileage attribute features; performing power prediction based on the mileage attribute features to obtain the target vehicle's air conditioning power data and other vehicle component power data; performing energy consumption prediction based on the mileage attribute features to obtain the target vehicle's drive energy consumption data; and calculating the mileage based on the air conditioning power data, other vehicle component power data, and drive energy consumption data to obtain the target vehicle's range data. The technical solution of this application, by fully considering the correlation between vehicle component energy consumption and drive energy consumption and the vehicle's range, enables the prediction of the vehicle's range. This comprehensively covers the actual vehicle range, effectively improving the prediction accuracy and helping the vehicle plan charging in advance, thus enhancing the driving experience.

[0015] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0016] Figure 1 This is a flowchart of a vehicle range prediction method provided in this application; Figure 2 This is a segmentation example diagram of the current itinerary provided in this application; Figure 3 This is a relationship diagram for power prediction provided in this application; Figure 4 This is another relationship diagram for power prediction provided in this application; Figure 5 This is a diagram showing the relationship between energy consumption predictions provided in this application; Figure 6 This is a structural diagram of a vehicle range prediction device provided in this application; Figure 7 This is an example image of a vehicle provided in this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0018] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0019] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0021] Vehicle range is a crucial indicator for new energy vehicles, typically referring to the maximum distance a vehicle can continuously travel at any given moment. Related technologies predict vehicle range by combining parameters of the vehicle's battery with pre-trained algorithm models. However, these technologies only consider battery parameters, resulting in a limited perspective and an inability to comprehensively capture the true range, leading to low prediction accuracy.

[0022] In view of this, embodiments of this application provide a method, apparatus and vehicle for predicting vehicle driving range, which aims to effectively improve the accuracy of vehicle driving range prediction.

[0023] First, the following will describe in detail, with reference to the accompanying drawings, a method for predicting vehicle driving range provided in the embodiments of this application.

[0024] This application provides a vehicle range prediction method that can be applied to a terminal, a server, or software running on either a terminal or a server. The terminal can be a tablet, laptop, desktop computer, etc., but is not limited to these. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. Furthermore, the server can be a node server in a blockchain network, but is not limited to these. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0025] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user profile data, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirects to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments obtained.

[0026] Reference Figure 1 , Figure 1 This is a flowchart of a vehicle range prediction method provided in this application, which may include the following steps S101-S105: S101, Obtain mileage attribute data related to the target vehicle's driving range; S102, preprocess and extract features from the mileage attribute data to obtain the mileage attribute features of the target vehicle; S103, based on mileage attribute characteristics, performs power prediction to obtain the air conditioning power data and other vehicle component power data of the target vehicle; S104, based on mileage attribute characteristics, predicts energy consumption to obtain the driving energy consumption data of the target vehicle; S105 calculates the target vehicle's range data by multiplying the air conditioning power data by time, the power data of other vehicle components by time, and the driving energy consumption data.

[0027] Specifically, during vehicle operation, energy consumption is primarily related to energy consumption during driving (i.e., drive energy consumption), energy consumption from vehicle components during use, and kinetic energy recovery during braking. Drive energy consumption is the most significant component and is closely related to factors such as vehicle weight, air resistance, road conditions, driving habits, and speed. In hot or cold environments, air conditioning is typically used for cooling or heating, and other vehicle components, such as lighting and entertainment systems, also generate energy consumption when in use. During braking, the vehicle's kinetic energy recovery system converts some kinetic energy into electrical energy and stores it in the battery, thus reducing energy consumption to some extent. Clearly, vehicle energy consumption is highly complex and significantly impacts driving range. Generally, energy consumption is positively correlated with the reduction in driving range; higher energy consumption leads to faster range reduction and a shorter driving range, while lower energy consumption results in slower range reduction and a longer driving range.

[0028] Accordingly, in this embodiment, firstly, mileage attribute data related to the target vehicle's driving range is acquired, including relevant data from historical trips and relevant data from the current trip, so as to predict the vehicle's driving range based on this data in subsequent steps. Then, the mileage attribute data is preprocessed to ensure its quality, and key features related to the actual driving range of the vehicle are extracted from the mileage attribute data, thereby obtaining the target vehicle's mileage attribute features. Next, based on the target vehicle's mileage attribute features, a power prediction operation is performed, thereby obtaining the target vehicle's air conditioning power data and other vehicle component power data. The air conditioning power data indicates the energy consumption of the target vehicle's air conditioning during future trips, while the other vehicle component power data indicates the energy consumption of other vehicle components besides the air conditioning during future trips. Simultaneously, based on the target vehicle's mileage attribute features, an energy consumption prediction operation is performed, thereby obtaining the target vehicle's driving energy consumption data, which indicates the energy consumption caused by the target vehicle during future trips. Finally, using air conditioning power data, power data of other vehicle components, and drive energy consumption data as benchmarks, a mileage calculation is performed to obtain the target vehicle's range data, which is the maximum distance the target vehicle can continuously travel with the current battery charge.

[0029] Therefore, compared with single-dimensional prediction methods, the embodiments of this application, by fully considering the correlation between the energy consumption of vehicle components and driving energy consumption and the vehicle's driving range, can predict the vehicle's driving range. This can comprehensively cover the actual driving range, thereby effectively improving the prediction accuracy of the vehicle's driving range, helping the vehicle to plan charging and replenishing energy in advance, and improving the driving experience.

[0030] The steps described above will be explained in further detail below.

[0031] In some implementations, step S101 above, obtaining mileage attribute data related to the target vehicle's driving range, may include: Obtain the target vehicle's historical and current trip data as mileage attribute data; Among them, historical trip data includes historical energy consumption data and user profile data. Historical energy consumption data includes the target vehicle's energy consumption data and kinetic energy recovery data during historical trips, while user profile data includes data related to the target vehicle's driving habits during historical trips. Current trip data includes current battery data, current vehicle control data, current driving data, and current environmental data. Current battery data includes data related to the target vehicle's battery status during the current trip. Current vehicle control data includes data related to the target vehicle's control status over vehicle components during the current trip. Current driving data includes data related to the target vehicle's driving status during the current trip. Current environmental data includes data related to the target vehicle's surrounding environment during the current trip.

[0032] In this embodiment, historical travel data of the target vehicle is obtained, which may include, but is not limited to, historical energy consumption data and user profile data, as detailed below: Historical energy consumption data can include, but is not limited to, energy consumption data and kinetic energy recovery data of the target vehicle during historical trips. It characterizes the target vehicle's energy consumption performance during historical trips and can be used to compensate for insufficient energy consumption characteristics of the target vehicle in the current trip, such as when the target vehicle does not have sufficient energy consumption characteristics at the beginning of the current trip. In one example, kinetic energy recovery data refers to the energy recovered by the kinetic energy recovery system. Energy consumption data can include, but is not limited to, drive energy consumption data and energy consumption data generated by vehicle components such as air conditioning, lighting systems, and entertainment systems during use (i.e., vehicle component energy consumption data).

[0033] User profile data can include, but is not limited to, data related to the target vehicle's driving habits during historical trips. This data characterizes the target vehicle's driving habits during those trips and can be used to correct the impact of different driving habits on energy consumption. In one example, user profile data can include, but is not limited to, average speed data, cumulative driving time data, acceleration habit data, and braking habit data. Acceleration habit data can include average acceleration time, such as the time required to accelerate from a first speed to a second speed (where the first speed is less than the second speed). Braking habit data can include average deceleration time, such as the time required to decelerate from a third speed to a fourth speed (where the third speed is greater than the fourth speed), but is not limited to these. The aforementioned speeds can be flexibly set according to actual conditions.

[0034] Simultaneously, the current travel data of the target vehicle is obtained, which may include, but is not limited to, current battery data, current vehicle control data, current driving data, and current environmental data, as detailed below: Current battery data may include, but is not limited to, data related to the battery status of the target vehicle during the current trip, which characterizes the vehicle's battery condition during the current trip. In one example, current battery data may include, but is not limited to, current battery charge, current battery current, current battery voltage, current remaining battery charge (State of Charge, SOC), current battery state of health (SOH), current vehicle load data, and current tire data, where current tire data may include, but is not limited to, current tire pressure data.

[0035] Current vehicle control data may include, but is not limited to, data related to the target vehicle's control status over vehicle components during the current journey, which characterizes the vehicle control situation during the current journey. In one example, current vehicle control data may include, but is not limited to, status data of vehicle components such as windows, air conditioning, lighting systems, windshield wipers, and cabin heating systems. Status data may include, but is not limited to, any of the following: open or closed status.

[0036] Current driving data may include, but is not limited to, data related to the driving status of the target vehicle during the current journey, which describes the vehicle's driving situation during the current journey. In one example, current driving data may include, but is not limited to, current vehicle speed data, current wheel speed data, current steering wheel angle data, current brake pedal travel data, and current accelerator pedal travel data.

[0037] In practical applications, factors such as weather and road conditions affect vehicle energy consumption to some extent. For example, vehicle energy consumption often increases when roads are congested, and extreme weather conditions such as heavy rain often require the use of vehicle components such as headlights and windshield wipers, thus increasing energy consumption. Therefore, current environmental data is introduced, which can include, but is not limited to, data related to the surrounding environment of the target vehicle during the current journey, depicting the environmental conditions of the current journey, such as weather conditions and road conditions. In one example, from the perspective of weather, current environmental data can include, but is not limited to, current weather type data, current ambient temperature data, current wind direction data, current wind force level data, and current ambient humidity data. Further introducing the road condition dimension, current environmental data can also include, but is not limited to, current driving route type data and current road condition data. The current driving route type data can include any of the following: urban road type, national highway type, expressway type, tunnel type, or hillside type. The current road condition data can include any of the following: congested state or non-congested state. For example, a vehicle speed below 50% of the normal speed limit or an average speed below 20 km / h can be considered a congested state, but it is not limited to these.

[0038] The historical and current trip data will be output as mileage attribute data.

[0039] In some implementations, refer to Figure 2 The above method can be repeated cyclically with a first preset length as the cycle length. That is, the vehicle's driving range is predicted using the above method in each cycle, thus continuously predicting the vehicle's driving range at every moment throughout the entire trip cycle. This provides a continuous view of the vehicle's driving range and helps improve the driving experience. The first preset length can be flexibly set according to actual conditions. For example, the first preset length can be ten seconds, meaning the above method is executed once every ten seconds. For instance, if one power-on / off cycle is considered a current trip cycle with a cycle length of N seconds, and each calculation is based on N seconds, then by accumulating the energy consumption every N seconds of the entire trip cycle, the vehicle's driving range at every moment throughout the entire trip cycle can be predicted.

[0040] In some implementations, certain key data may be missing at the current moment, such as the lack of current driving data when the vehicle is first started. To address this, in this implementation, the current journey can be a period of time prior to the current moment and a second preset length; the historical journey can be a period of time prior to the current moment and a third preset length; and the future journey can be a period of time after the current moment and a fourth preset length. The historical journey, current journey, and future journey do not overlap. This ensures sufficient current journey data is obtained, reducing the risk of reduced accuracy in predicting vehicle range due to data insufficiency. The second, third, and fourth preset lengths can be flexibly set according to actual conditions. For example, the third preset length could be one week (i.e., the historical journey is the period of one week prior to the current moment), the second preset length could be ten seconds (i.e., the current journey is the period of ten seconds prior to the current moment), and the fourth preset length could be one second (i.e., the future journey is the period of the next second after the current moment), but it is not limited to these. Furthermore, there is no specific limitation on the relationship between the first and second preset lengths; the first and second preset lengths can be the same or different. For example, a current travel cycle can be defined as one power-on / off cycle, with a cycle length of N seconds. Each calculation is based on N seconds. Therefore, the current travel data consists of the relevant data from the N seconds preceding the current moment. This can be understood as dividing the target vehicle's current travel data into multiple sub-travels based on the target vehicle's power-on signal. Each sub-travel is a unit of ten seconds after power-on. Thus, the current travel data can include relevant data collected or calculated in ten-second units. As another example, a historical travel cycle can be defined as one week in length, with each calculation based on one week. Therefore, the historical travel data consists of the relevant data from the week preceding the current moment.

[0041] In some implementations, the aforementioned mileage attribute data may include historical trip data and current trip data; in step S102, preprocessing and feature extraction of the mileage attribute data to obtain the mileage attribute features of the target vehicle may include: The current itinerary data is preprocessed to obtain preprocessed current itinerary data; Feature extraction is performed on historical trip data and preprocessed current trip data to obtain historical trip features, current trip features, and future trip features as mileage attribute features; Among them, historical travel characteristics include historical energy consumption characteristics, current travel characteristics include instantaneous vehicle control characteristics, instantaneous driving characteristics, instantaneous environmental characteristics, current user profile characteristics, and current vehicle profile characteristics, and future travel characteristics include future environmental characteristics.

[0042] In this embodiment, the current trip data is first preprocessed to obtain preprocessed current trip data, thereby effectively improving the quality of the current trip data.

[0043] In one example, preprocessing methods may include: missing logs in the current trip data, time intervals between logs that are less than the preset duration (e.g., ten seconds), and discrepancies between the total log duration and the actual log duration. These issues will affect the final prediction results. Therefore, it is necessary to clean the current trip data of data with missing logs, time intervals between logs that are less than the preset duration, and total log durations that are inconsistent with the actual log duration, to ensure the accuracy of the vehicle's range prediction. Furthermore, preprocessing methods may also include: analyzing and cleaning abnormal data from the tracking points. This data may include, but is not limited to, abnormal current ambient temperature data (e.g., 46 degrees Celsius), abnormal current tire pressure data (e.g., abnormal tire pressure signal values), abnormal current vehicle speed data (e.g., exceeding 180 km / h), and abnormal cumulative driving time data (e.g., too short or too long). Then, feature extraction is performed on historical trip data and preprocessed current trip data to extract key features related to the actual vehicle range. These features are then used to obtain historical trip features, current trip features, and future trip features as mileage attribute features. Historical trip features may include, but are not limited to, historical energy consumption features; current trip features may include, but are not limited to, instantaneous vehicle control features, instantaneous driving features, instantaneous environmental features, current user profile features, and current vehicle profile features; and future trip features may include, but are not limited to, future environmental features. This provides an accurate data benchmark for subsequent predictions of vehicle range.

[0044] In one example, feature extraction methods may include: extracting features from preprocessed historical energy consumption data to obtain historical energy consumption features; extracting features from preprocessed user profile data to obtain current user profile features; extracting features from preprocessed current battery data to obtain current vehicle profile features; extracting features from preprocessed current vehicle control data to obtain instantaneous vehicle control features; extracting features from preprocessed current driving data to obtain instantaneous driving features; and extracting features from preprocessed current environmental data to obtain instantaneous environmental features and future environmental features.

[0045] In this example, the mileage attribute features are divided into three categories based on the time dimension: historical features, current features, and future features. Historical features can include historical energy consumption features. These features are obtained by extracting features from preprocessed historical energy consumption data. Historical energy consumption features characterize the energy consumption performance of the target vehicle in the most recent phase (historical journey) and can be used to compensate for insufficient energy consumption features of the target vehicle in the current journey, such as when the target vehicle does not have sufficient energy consumption features at the beginning of the current journey.

[0046] Current features can include instantaneous features and profile features. Instantaneous features can include instantaneous vehicle control features, instantaneous environmental features, and instantaneous driving features. Instantaneous vehicle control features are obtained by extracting features from preprocessed current vehicle control data; instantaneous driving features are obtained by extracting features from preprocessed current driving data; and instantaneous environmental features are obtained by extracting features from preprocessed current environmental data. Instantaneous vehicle control features characterize the vehicle component control performance of the target vehicle in the current stage (current journey); instantaneous driving features characterize the driving situation of the target vehicle in the current stage (current journey); and instantaneous environmental features characterize the surrounding environment of the target vehicle in the current stage (current journey). Profile features can include current user profile features and current vehicle profile features. Current user profile features are obtained by extracting features from preprocessed user profile data; and current vehicle profile features are obtained by extracting features from preprocessed current battery data. The current user profile features depict the user's driving habits in the recent stage (historical trip), such as average vehicle speed data and cumulative driving time data; the current vehicle profile features depict the vehicle's attributes in the current stage (current trip), such as current battery health status data and current vehicle load data.

[0047] Future features can include future environmental features. These features are obtained by extracting features from preprocessed current environmental data. Future environmental features characterize the surrounding environment of the target vehicle in the future (the journey after the current trip), and have a significant impact on the vehicle's driving range. Examples include future weather type and road conditions.

[0048] Optionally, the feature extraction method can be set according to the actual situation, and this implementation does not impose specific limitations on it. For example, for historical and current features, models such as Transformer and Convolutional Neural Network (CNN) can be used for feature extraction; for future features, preprocessed current environment data is input into a pre-trained environment prediction model to obtain future environment data, and models such as Transformer and Convolutional Neural Network are used for feature extraction to obtain future environment features. The environment prediction model can be flexibly set according to the actual situation, for example, it can be a Long Short-Term Memory (LSTM) network, but it is not limited to this.

[0049] In some implementations, the aforementioned mileage attribute features may include current trip features and future trip features. The current trip features may include instantaneous vehicle control features and instantaneous environmental features, and the future trip features may include future environmental features. In step S103, power prediction based on the mileage attribute features to obtain the target vehicle's air conditioning power data and other vehicle component power data may include: Based on future environmental characteristics, instantaneous vehicle control characteristics, and instantaneous environmental characteristics, combined with the first prediction model, air conditioning power data is obtained.

[0050] In this embodiment, the environmental conditions of the future journey, as well as the vehicle component control status and environmental conditions of the current journey, significantly affect the air conditioning energy consumption. For example, if the current environment is hot and the air conditioning needs to be turned on, it will increase the air conditioning energy consumption; if the environment gradually decreases in the future, the air conditioning may be turned off, thus reducing the air conditioning energy consumption; this will further affect the vehicle's driving range. Accordingly, a first prediction model is trained in advance using multiple preset first samples and the first label information corresponding to each preset first sample. The first samples may include future environmental feature samples, instantaneous vehicle control feature samples, and instantaneous environmental feature samples, and the first label information refers to air conditioning power data. Through training, the first prediction model can learn the mapping relationship between the three elements—future environmental features, instantaneous vehicle control features, and instantaneous environmental features—and the air conditioning power data, such as... Figure 3 As shown. It should be understood that the method of obtaining feature samples is the same as the method of extracting features in the previous embodiments, and will not be repeated here. Based on the above, in power prediction, this embodiment inputs future environmental features, instantaneous vehicle control features, and instantaneous environmental features into the first prediction model, which then performs the prediction operation and outputs air conditioning power data, thereby realizing the prediction of air conditioning energy consumption in future trips. In this way, the prediction accuracy of air conditioning energy consumption can be effectively improved.

[0051] Optionally, the first prediction model can be set according to the actual situation, and this embodiment does not impose specific limitations on it. For example, the first prediction model can be a machine learning model such as XGBoost or LightGBM, or a deep learning model such as Recurrent Neural Network (RNN), Transformer, or LSTM, but it is not limited to these.

[0052] In some implementations, the aforementioned mileage attribute features may include current trip features and future trip features. The current trip features may include instantaneous vehicle control features and instantaneous environmental features, and the future trip features may include future environmental features. In step S103, power prediction based on the mileage attribute features to obtain the target vehicle's air conditioning power data and other vehicle component power data may include: Based on future environmental characteristics, instantaneous vehicle control characteristics, and instantaneous environmental characteristics, combined with the second prediction model, power data for other vehicle components are obtained.

[0053] In this embodiment, the environmental conditions of the future journey, as well as the current vehicle component control and environmental conditions, significantly affect the energy consumption of other vehicle components. For example, if the current weather is rainy, the windshield wipers need to be turned on, increasing their energy consumption and consequently increasing the energy consumption of other vehicle components. If the weather changes from rainy to sunny in the future, the wipers may be turned off, reducing their energy consumption and thus reducing the energy consumption of other vehicle components; this further affects the vehicle's driving range. Accordingly, a second prediction model is pre-trained using multiple preset first samples and the corresponding second label information. The first samples may include future environmental feature samples, instantaneous vehicle control feature samples, and instantaneous environmental feature samples; the second label information refers to the power data of other vehicle components. Through training, the second prediction model can learn the mapping relationship between these three elements—future environmental features, instantaneous vehicle control features, and instantaneous environmental features—and the power data of other vehicle components, such as... Figure 4 As shown. Based on the above, in power prediction, this embodiment inputs future environmental characteristics, instantaneous vehicle control characteristics, and instantaneous environmental characteristics into the second prediction model. The second prediction model performs the prediction operation and outputs power data of other vehicle components, thereby achieving the prediction of the energy consumption of vehicle components other than air conditioning during future journeys. In this way, the prediction accuracy of the energy consumption of other vehicle components can be effectively improved.

[0054] Optionally, the second prediction model can be set according to the actual situation, and this embodiment does not impose specific limitations on it. For example, the second prediction model can be a machine learning model such as XGBoost or LightGBM, or a deep learning model such as recurrent neural network, Transformer, or LSTM, but it is not limited to these.

[0055] Optionally, a feature fusion operation may be included before the features are input into the first or second prediction model. Specifically, the future environmental features, instantaneous vehicle control features, and instantaneous environmental features are normalized. Using the normalized future environmental features as the key and the normalized instantaneous vehicle control features as the query, a self-attention mechanism is used to fuse the normalized future environmental features and the normalized instantaneous vehicle control features to obtain a first fused feature, thereby achieving feature interaction and fusion between the environmental conditions of the future journey and the vehicle component control situation of the current journey. Using the normalized future environmental features as the key and the normalized instantaneous environmental features as the query, a self-attention mechanism is used to fuse the normalized future environmental features and the normalized instantaneous environmental features to obtain a second fused feature, thereby achieving feature interaction and fusion between the environmental conditions of the future journey and the environmental conditions of the current journey. Using the normalized instantaneous environmental features as the key and the normalized instantaneous vehicle control features as the query, a self-attention mechanism is used to fuse the normalized instantaneous environmental features and the normalized instantaneous vehicle control features to obtain a third fused feature, thereby achieving feature interaction and fusion between the environmental conditions of the current journey and the vehicle component control situation of the current journey. The obtained first, second, and third fusion features will serve as inputs to either the first or second prediction model. The first sample used during training of either model can be adaptively modified based on these three fusion features. Thus, through feature fusion and interaction, more implicit key features relevant to the actual vehicle range can be extracted from existing features, enhancing feature diversity and representativeness. This, in turn, helps improve the prediction accuracy of energy consumption for other vehicle components and the air conditioning energy consumption.

[0056] In some implementations, the aforementioned mileage attribute features may include historical trip features, current trip features, and future trip features; in step S104, predicting energy consumption based on the mileage attribute features to obtain the target vehicle's driving energy consumption data may include: Based on historical travel characteristics, current travel characteristics, and future travel characteristics, combined with a third prediction model, we obtain driving energy consumption data.

[0057] In this embodiment, the relevant information of historical trips, current trips, and future trips all significantly affect driving energy consumption, thereby further affecting the vehicle's driving range. For example, in historical trips, the energy recovered by the kinetic energy recovery system can reduce vehicle driving energy consumption to a certain extent. As another example, in the current trip, a rapid decrease in current vehicle speed (i.e., sudden braking) can easily increase vehicle driving energy consumption. Furthermore, in future trips, frequent braking and acceleration during traffic congestion can easily increase vehicle driving energy consumption. Accordingly, a third prediction model is pre-trained using multiple preset second samples and the corresponding third label information for each preset second sample. The second samples can include historical trip feature samples, current trip feature samples, and future trip feature samples, and the third label information refers to driving energy consumption data. Through training, the third prediction model can learn the mapping relationship between historical trip features, current trip features, and future trip features and driving energy consumption data, such as... Figure 5 As shown. Based on the above, in energy consumption prediction, this embodiment inputs historical travel characteristics, current travel characteristics, and future travel characteristics into the third prediction model. The third prediction model performs the prediction operation and outputs driving energy consumption data, thereby realizing the prediction of vehicle driving energy consumption in future trips. This can effectively improve the prediction accuracy of vehicle driving energy consumption.

[0058] Optionally, the third prediction model can be set according to the actual situation, and this implementation does not impose specific limitations on it. For example, the third prediction model can be a machine learning model such as XGBoost or LightGBM, or a deep learning model such as recurrent neural network, Transformer, or LSTM, but it is not limited to these.

[0059] Optionally, feature fusion can be included before inputting features into the third prediction model. Specifically, historical trip features, current trip features, and future trip features are normalized; using the normalized historical trip features as the key and the normalized current trip features as the query, the normalized historical trip features and the normalized current trip features are fused through a self-attention mechanism to obtain a fourth fused feature, thereby achieving feature interaction and fusion between historical and current trip situations; using the normalized historical trip features as the key and the normalized future trip features as the query, the normalized historical trip features and the normalized future trip features are fused through a self-attention mechanism to obtain a fifth fused feature, thereby achieving feature interaction and fusion between future and historical trip situations; using the normalized future trip features as the key and the normalized current trip features as the query, the normalized future trip features and the normalized current trip features are fused through a self-attention mechanism to obtain a sixth fused feature, thereby achieving feature interaction and fusion between future and current trip situations. The obtained fourth, fifth, and sixth fusion features will serve as input to the third prediction model. The third samples used in training the third prediction model can be adaptively modified based on these fusion features. Thus, through feature fusion and interaction, more implicit key features related to the actual vehicle range can be extracted from existing features, improving feature diversity and representativeness, thereby enhancing the accuracy of predicting vehicle driving energy consumption.

[0060] In some implementations, step S105 above, which involves calculating the mileage based on air conditioning power data, power data of other vehicle components, and drive energy consumption data to obtain the target vehicle's driving range data, may include: Based on the air conditioning power data, the power data of other vehicle components, and the drive energy consumption data, the target energy consumption data of the target vehicle is obtained. The driving range data is obtained based on the mileage attribute data and the target energy consumption data.

[0061] In this embodiment, the air conditioning power data, other vehicle component power data, and drive energy consumption data respectively indicate the air conditioning energy consumption, the power consumption of other vehicle components besides the air conditioning, and the vehicle drive energy consumption. These energy consumption conditions are all local energy consumption conditions. Accordingly, using the air conditioning power data, other vehicle component power data, and drive energy consumption data as a benchmark, the target energy consumption data of the target vehicle is calculated, which indicates the global energy consumption of the target vehicle in future journeys. Subsequently, using the original data and target energy consumption data as a benchmark, a mileage calculation operation is performed to calculate the target vehicle's driving range data, that is, the maximum distance the target vehicle can continuously travel with the current battery charge. In this way, by fully considering the global energy consumption of the target vehicle, as well as relevant data from the target vehicle's historical journeys and current journeys, the vehicle's driving range prediction processing is achieved. This can comprehensively cover the actual driving range of the vehicle, thereby effectively improving the prediction accuracy of the vehicle's driving range, helping the vehicle to plan charging and replenishment in advance, and improving the driving experience.

[0062] The following example illustrates this. Based on theoretical calculations, driving energy consumption is calculated as: "Total Energy Consumption + Kinetic Energy Recovery Energy - Air Conditioning Energy Consumption - Energy Consumption of Other Vehicle Components". The energy consumption of air conditioning and other vehicle components is independent of mileage and depends only on settings and time; it is denoted as air conditioning power P. a The air conditioner's energy consumption is W. a ; The power of other vehicle components is P. e The energy consumption of other vehicle components is W. e Drive energy consumption mainly includes the work done to overcome rolling friction, air resistance, and gravity, as well as the work done by the force providing acceleration. It also includes transmission losses in the powertrain. These are related to the distance traveled but not to time t, and are denoted as W. d Energy recovery is related to drive energy consumption, denoted as W. r .

[0063] In summary, we have: ; Therefore, based on the unknown value, we need to know the actual average drive energy consumption F. d Air conditioner power P a Other vehicle component power P e The air conditioning power usage fits the environment and settings for P. a The mapping relationship is as follows Figure 3 As shown. The power of other vehicle components was determined using the fitting environment and settings for P. e The mapping relationship is as follows Figure 4 As shown.

[0064] In modeling drive energy consumption, a single journey is considered as a whole. Based on the law of conservation of energy, we have: ; , Indicates changes in kinetic and potential energy. This represents the negative work done by various resistances during the journey, such as rolling friction, air resistance, and fixed losses in the powertrain. The average loss force during the process is: ; Similarly, the model fits the Floss value. This value may be related to the driver's driving habits, route geometry, weather conditions during the journey, and transmission belt mechanical wear, among other factors. The model defaults to a zero change in kinetic energy; the change in potential energy due to altitude is relatively small and can also be ignored, defaulting to zero.

[0065] Therefore, combining the above formulas: Therefore, the actual modeling fit is usually the formula. In this solution, the implementation process first involves acquiring historical and current data from the vehicle. The historical data includes historical energy consumption and user profiles from the vehicle's past journeys, while the current data includes preliminary data from the current journey and environmental data from the current trip. These data are input into the model and processed through procedures such as cleaning to establish a mapping relationship with target values, thereby obtaining the target values. In this solution, the target values ​​are the driving energy consumption, air conditioning energy consumption, and energy consumption of other vehicle components during the journey.

[0066] A feasible implementation method: Drive energy consumption, air conditioning energy consumption, and energy consumption of other vehicle components can all be implemented using ensemble tree model algorithms, such as XGBoost and LightGBM; or deep neural network algorithms, such as RNN, Transformer, and LSTM. Historical data, current data, and future estimated data from the vehicle side mainly include three categories from the time dimension of features: 1. Historical energy consumption features: mainly characterizing the vehicle's recent energy consumption performance. They can also supplement the current trip's energy consumption features, such as the fact that the current trip has not yet started. 2. Current trip features: including instantaneous features and profile features. Instantaneous features mainly include vehicle control features, instantaneous driving features, and weather features within the current trip. Profile features include user profiles and vehicle profiles. User profiles include historical user habits, such as historical average speed and historical trip duration. Vehicle profiles include vehicle weight and battery SOH. 3. Future features: including weather and navigation road conditions, which directly affect future energy consumption. This data can be used in the modeling stage or to assist in inferring the remaining driving range. These features are used to construct a mapping relationship with the target value to obtain... A machine learning algorithm is used to train a model on a large amount of data to obtain a predictive model for driving energy consumption.

[0067] Taking a driving energy consumption prediction model as an example: the algorithm input includes feature data. Algorithm output: Predicted driving energy consumption for the future journey. The model obtained after training is formalized as follows: ; Through training, the model can be iteratively updated, and the internal parameters can be determined. This allows the target value of the driving energy consumption to be calculated based on the input.

[0068] Similarly, the energy consumption prediction methods for air conditioning and other vehicle components are similar to those for driving energy consumption, except that they use different data dimensions. Based on similar principles, the air conditioning power P can be predicted through a model. a Power P of other vehicle components e .

[0069] Based on three models—driving energy consumption, air conditioning energy consumption, and energy consumption of other vehicle components—we consider that in future driving scenarios, assuming unchanged environment, road conditions, vehicle design, and driving habits, the overall kinetic and potential energy will remain constant, W. remanin Representing the remaining usable energy of the vehicle under current conditions, then all W remanin Once consumed, the following will occur:

[0070] When estimating the maximum mileage, a simplification is generally adopted, treating both the kinetic energy difference and potential energy difference as zero, and using the current speed or the average of historical speeds, or calculating relevant values ​​(speed, time, remaining distance) from future navigation data, resulting in the simplified formula: ; The remaining driving range can be obtained by solving for the maximum value of S in the simplified formula above.

[0071] The remaining driving range is: .

[0072] In addition, refer to Figure 6 This application also provides a vehicle range prediction device, which may include: The acquisition module 301 is used to acquire mileage attribute data related to the driving range of the target vehicle; The first processing module 302 is used to preprocess and extract features from the mileage attribute data to obtain the mileage attribute features of the target vehicle. The second processing module 303 is used to perform power prediction based on mileage attribute characteristics to obtain the air conditioning power data and other vehicle component power data of the target vehicle. The third processing module 304 is used to predict energy consumption based on mileage attribute characteristics and obtain the driving energy consumption data of the target vehicle. The fourth processing module 305 is used to calculate the mileage based on the product of air conditioning power data and time, the product of power data of other vehicle components and time, and drive energy consumption data, so as to obtain the driving range data of the target vehicle.

[0073] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0074] Finally, refer to Figure 7 This application also provides a vehicle, which includes: At least one processor 401; At least one memory 402 is used to store at least one program; When at least one program is executed by at least one processor 401, the at least one processor 401 implements the above-described vehicle range prediction method.

[0075] The aforementioned vehicles can be private cars, such as sedans, sport utility vehicles (SUVs), multi-purpose vehicles (MPVs), or pickup trucks, or commercial vehicles, such as vans, buses, small trucks, or large trailers, or new energy vehicles such as hybrid and pure electric vehicles.

[0076] The aforementioned memory 402, as a non-transitory network system, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory 402 may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 402 may optionally include memory 402 remotely located relative to processor 401, and these remote memories 402 can be connected to processor 401 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0077] The aforementioned memory 402 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). Memory 402 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in memory 402 and called by processor 401 to execute the methods of the embodiments of this application.

[0078] The processor 401 described above can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0079] In some embodiments, the vehicle may further include: Input / output interfaces are used to implement information input and output; The communication interface is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). The bus transmits information between various components of the device (such as processor 401, memory 402, input / output interface and communication interface); The processor 401, memory 402, input / output interface, and communication interface can communicate with each other within the device via a bus.

[0080] The content of the above method embodiments is applicable to this vehicle embodiment. The specific functions implemented in this vehicle embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0081] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0082] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0083] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0085] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0086] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0088] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0089] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0090] If the integrated unit is implemented as 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 this application, in essence, or the part that contributes to the prior art, or all or part 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 multiple 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 of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0091] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for predicting vehicle driving range, characterized in that, The method includes: acquiring mileage attribute data related to the driving range of the target vehicle; The mileage attribute data is preprocessed and features are extracted to obtain the mileage attribute features of the target vehicle; Power prediction is performed based on the mileage attribute characteristics to obtain the air conditioning power data and other vehicle component power data of the target vehicle. Based on the mileage attribute characteristics, energy consumption is predicted to obtain the driving energy consumption data of the target vehicle; The driving range data of the target vehicle is obtained by multiplying the air conditioning power data by time, the power data of other vehicle components by time, and the driving energy consumption data.

2. The method according to claim 1, characterized in that, The acquisition of mileage attribute data related to the target vehicle's driving range includes: Obtain the historical and current travel data of the target vehicle as the mileage attribute data; The historical trip data includes historical energy consumption data and user profile data. The historical energy consumption data includes the energy consumption data and kinetic energy recovery data of the target vehicle during the historical trip. The user profile data includes data related to the driving habits of the target vehicle during the historical trip. The current trip data includes current battery data, current vehicle control data, current driving data, and current environment data. The current battery data includes data related to the battery status of the target vehicle during the current trip. The current vehicle control data includes data related to the control status of the target vehicle's components during the current trip. The current driving data includes data related to the driving status of the target vehicle during the current trip. The current environment data includes data related to the surrounding environment of the target vehicle during the current trip.

3. The method according to claim 1, characterized in that, The mileage attribute data includes historical trip data and current trip data; the preprocessing and feature extraction of the mileage attribute data to obtain the mileage attribute features of the target vehicle includes: The current trip data is preprocessed to obtain the preprocessed current trip data; Feature extraction is performed on the historical trip data and the preprocessed current trip data to obtain historical trip features, current trip features, and future trip features as the mileage attribute features; The historical trip features include historical energy consumption features; the current trip features include instantaneous vehicle control features, instantaneous driving features, instantaneous environmental features, current user profile features, and current vehicle profile features; and the future trip features include future environmental features.

4. The method according to claim 1, characterized in that, The mileage attribute features include current trip features and future trip features. The current trip features include instantaneous vehicle control features and instantaneous environmental features. The future trip features include future environmental features. The step of performing power prediction based on the mileage attribute features to obtain the air conditioning power data and other vehicle component power data of the target vehicle includes: Based on the future environmental characteristics, the instantaneous vehicle control characteristics, and the instantaneous environmental characteristics, combined with the first prediction model, the air conditioning power data is obtained.

5. The method according to claim 1, characterized in that, The mileage attribute features include current trip features and future trip features. The current trip features include instantaneous vehicle control features and instantaneous environmental features. The future trip features include future environmental features. The step of performing power prediction based on the mileage attribute features to obtain the air conditioning power data and other vehicle component power data of the target vehicle includes: Based on the future environmental characteristics, the instantaneous vehicle control characteristics, and the instantaneous environmental characteristics, combined with the second prediction model, the power data of the other vehicle components are obtained.

6. The method according to claim 1, characterized in that, The mileage attribute features include historical trip features, current trip features, and future trip features; The step of predicting energy consumption based on the mileage attribute features to obtain the driving energy consumption data of the target vehicle includes: Based on the historical travel characteristics, the current travel characteristics, and the future travel characteristics, and combined with the third prediction model, the driving energy consumption data is obtained.

7. The method according to claim 1, characterized in that, The step of calculating the driving range data of the target vehicle based on the air conditioning power data, the power data of other vehicle components, and the driving energy consumption data includes: The target energy consumption data of the target vehicle is obtained based on the air conditioning power data, the power data of other vehicle components, and the drive energy consumption data. The driving range data is obtained based on the mileage attribute data and the target energy consumption data.

8. A vehicle range prediction device, characterized in that, The device includes: The acquisition module is used to acquire mileage attribute data related to the driving range of the target vehicle; The first processing module is used to preprocess and extract features from the mileage attribute data to obtain the mileage attribute features of the target vehicle. The second processing module is used to perform power prediction based on the mileage attribute features to obtain the air conditioning power data and other vehicle component power data of the target vehicle. The third processing module is used to predict energy consumption based on the mileage attribute characteristics to obtain the driving energy consumption data of the target vehicle. The fourth processing module is used to calculate the mileage based on the product of the air conditioning power data and time, the product of the power data of other vehicle components and time, and the driving energy consumption data, so as to obtain the driving range data of the target vehicle.

9. A vehicle, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a vehicle range prediction method as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle range prediction method according to any one of claims 1 to 7.

Images