Vehicle adaptive gear shifting guidance method and device, electronic device

Abstract

This disclosure provides a vehicle adaptive shift guidance method, device, and electronic device, relating to the field of vehicle technology. It collects and preprocesses multi-dimensional vehicle state data in real time, identifies multi-dimensional operating conditions based on feature data streams, and combines real-time vehicle state with a driver habit model to correct the shift strategy and generate a target gear command. Furthermore, it compares the actual gear position with the target gear command to generate tiered shift prompts and records driver response behavior to optimize the driver habit model. Therefore, it can solve the problems of static and fixed shift strategies lacking adaptive capability, lacking real-time intelligent shift guidance, failing to personalize driver habits, and lacking closed-loop optimization of data and driving operations in existing technologies. It achieves the technical effects of providing real-time and accurate shift guidance, dynamically adapting to vehicle operating conditions and driving habits, forming a continuous optimization loop for driving habits, and improving fuel economy and driving adaptability.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and in particular to a vehicle adaptive shifting guidance method and device, and electronic equipment. Background Technology

[0002] As core equipment in highway logistics, the fuel economy of commercial vehicles directly impacts the industry's operational efficiency. With the development of vehicle-to-everything (V2X) technology, existing fuel-saving systems, through the collaborative operation of onboard ECUs, remote monitoring platforms, and driving behavior analysis, have constructed a closed-loop technology system from data collection to post-event evaluation. Specifically, this system encompasses key aspects such as real-time shift prompts based on fixed RPM thresholds, and fuel consumption diagnostics and fleet management relying on cloud-based big data, aiming to optimize engine operating conditions and reduce operating costs.

[0003] However, existing shift guidance methods rely on static preset logic or offline statistical analysis, failing to achieve multi-dimensional operating condition recognition and adaptive fusion of driving habits. Fixed thresholds cannot respond to dynamic changes in load, gradient, and road conditions, and remote diagnostics lacks real-time intervention capabilities, resulting in a severe mismatch between shift timing and real-time operating conditions. This disconnect between data and execution causes the engine to deviate from its economic operating range for extended periods, significantly increasing fuel consumption and failing to effectively correct poor driver habits due to the lack of personalized guidance. Summary of the Invention

[0004] This disclosure provides a vehicle adaptive shift guidance method, apparatus, and electronic device. Its main objective is to at least partially address one of the technical problems in the related art.

[0005] According to a first aspect of this disclosure, a vehicle adaptive shift guidance method is provided, comprising:

[0006] Real-time acquisition of multi-dimensional status data during vehicle operation, and preprocessing of the multi-dimensional status data to generate feature data stream; Based on the feature data stream, multi-dimensional operating condition identification is performed on the current operating scenario of the vehicle to generate an operating condition label that represents the current operating scenario. Based on the operating condition identifier, the basic shift strategy is matched with the real-time vehicle status, and the basic shift strategy is modified in combination with the driver habit model to generate the target gear command. The system compares the current actual gear position with the target gear position command, generates graded shift prompts based on the comparison deviation, outputs them through the vehicle's human-machine interface, and records the driver's response to the graded shift prompts to optimize the driver's habit model.

[0007] According to a second aspect of this disclosure, a vehicle adaptive shift guidance device is provided, comprising: The acquisition unit is used to acquire multi-dimensional status data during vehicle operation in real time and preprocess the multi-dimensional status data to generate a feature data stream. The identification unit is used to perform multi-dimensional working condition identification of the current operating scenario of the vehicle based on the feature data stream, so as to generate a working condition identifier that represents the current operating scenario. The correction unit is used to match the basic shift strategy and real-time vehicle status according to the working condition identifier, and to correct the basic shift strategy in combination with the driver habit model to generate the target gear command. The output unit is used to compare the current actual gear position with the target gear position command, generate graded shift prompt information based on the comparison deviation and output it through the vehicle human-machine interface, and record the driver's response behavior to the graded shift prompt information in order to optimize the driver habit model.

[0008] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0009] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0010] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0011] The vehicle adaptive shifting guidance method, device, and electronic equipment disclosed herein acquire and preprocess multi-dimensional vehicle state data in real time, complete multi-dimensional operating condition identification based on feature data streams, and combine real-time vehicle state and driver habit model to correct shifting strategies and generate target gear commands. Furthermore, it compares the actual gear and target gear commands to generate graded shifting prompts and records driver response behavior to optimize the driver habit model. Therefore, it can solve the problems of static and fixed shifting strategies without adaptive capabilities, lack of real-time intelligent shifting guidance, inability to personalize driver habits, and lack of closed-loop optimization of data and driving operations in existing technologies. It achieves the technical effects of providing real-time and accurate shifting guidance, dynamically adapting to vehicle operating conditions and driving habits, forming a continuous optimization closed loop of driving habits, and improving fuel economy and driving adaptability.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is a flowchart illustrating a vehicle adaptive shift guidance method provided in an embodiment of the present disclosure; Figure 2 This is a schematic diagram of the structure of a vehicle adaptive shifting guidance device provided in an embodiment of the present disclosure; Figure 3 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0014] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0015] The following description, with reference to the accompanying drawings, describes a vehicle adaptive shifting guidance method, apparatus, and electronic device according to embodiments of the present disclosure.

[0016] Figure 1 This is a schematic flowchart of a vehicle adaptive shifting guidance method provided in an embodiment of this disclosure.

[0017] like Figure 1 As shown, the method includes the following steps: Step 101: Collect multi-dimensional state data during vehicle operation in real time, and preprocess the multi-dimensional state data to generate a feature data stream.

[0018] In the embodiments of this disclosure, multi-dimensional status data during vehicle operation is collected in real time through on-board sensing components, vehicle CAN bus, and vehicle-to-everything (V2X) communication interface. The collection process performs time synchronization processing on various types of data to ensure data timing consistency. The on-board preprocessing unit performs preprocessing operations on the collected raw multi-dimensional status data. Preprocessing includes data validity verification, abnormal data processing, and data feature extraction. Invalid, missing, and distorted raw data are removed through verification; abnormal data is marked or reconstructed; and core features characterizing the vehicle's operating status are extracted from the cleaned data, ultimately generating a feature data stream that can be used for subsequent operating condition identification. As an example, the multi-dimensional status data may include engine operating parameters, vehicle status parameters, load environment parameters, driver operating parameters, and external environment parameters. Preprocessing can remove abnormal data exceeding reasonable thresholds and extract core data such as engine speed features, vehicle speed features, and gradient features to form a feature data stream.

[0019] By collecting real-time, multi-dimensional vehicle status data and completing standardized preprocessing, accurate and regular data input can be provided for subsequent working condition identification, effectively reducing the impact of raw data noise on the system processing flow and ensuring the accuracy and stability of subsequent data processing.

[0020] Step 102: Based on the feature data stream, perform multi-dimensional working condition identification on the current operating scenario of the vehicle to generate a working condition identifier that represents the current operating scenario.

[0021] In the embodiments of this disclosure, the feature data stream output in step 101 is received, key feature vectors reflecting the vehicle's operating scenario are extracted from the feature data stream, and a comprehensive judgment is made on the vehicle's current operating scenario based on a preset multi-dimensional operating condition recognition logic. The recognition dimensions cover road characteristics, load status, slope conditions, traffic density, and driving mode, etc., and the quantitative analysis and scenario classification of each operating condition parameter are completed. Finally, an operating condition identifier that can uniquely represent the current operating scenario is generated. As an example, operating condition recognition can be achieved through an operating condition classification decision tree. Based on feature parameters such as slope, vehicle speed, and speed fluctuation, typical operating scenarios such as uphill, downhill, urban congestion, urban smooth traffic, suburban roads, and highways are distinguished. The operating condition is quantified by combining load level and driving style, and an operating condition identifier containing operating condition code and scenario attributes is generated.

[0022] Based on the regular feature data stream, multi-dimensional operation scenario identification is completed, and standardized operating condition labels are generated. This provides accurate scenario basis for subsequent shift strategy matching, ensuring that the system processing logic matches the actual operating state of the vehicle.

[0023] Step 103: Match the basic shifting strategy and real-time vehicle status according to the working condition identifier, and modify the basic shifting strategy in combination with the driver habit model to generate the target gear command.

[0024] In the embodiments of this disclosure, based on the operating condition identifier generated in step 102, a basic shifting strategy corresponding to the current operating scenario is matched from a preset basic shifting strategy library; simultaneously, real-time vehicle status data is retrieved, and the basic shifting strategy is calibrated to adapt to the real-time vehicle status; then, a pre-built driver habit model is invoked, and based on personalized parameters such as driver shifting preferences, operating characteristics, and driving behavior patterns stored in the model, the calibrated basic shifting strategy is dynamically corrected to eliminate the adaptation deviation between the general strategy and personalized driving needs, and finally, a target gear instruction adapted to the current scenario, vehicle status, and driving habits is generated. As an example, when the operating condition identifier represents an unloaded highway scenario, an economy-first basic shifting strategy is matched, combined with vehicle status calibration such as real-time vehicle speed and engine torque, and then the shift point is fine-tuned based on the parameters of the economy-oriented driver habit model to generate the corresponding target gear instruction.

[0025] Through multi-level processing including operating condition identification matching, vehicle status calibration, and driver habit model correction, dynamic adaptation and personalized optimization of shifting strategies are achieved, ensuring that the target gear command conforms to the actual operating conditions of the vehicle and the driver's operating characteristics.

[0026] Step 104: Compare the current actual gear position with the target gear position command, generate graded gear shift prompt information based on the comparison deviation and output it through the vehicle human-machine interface, and record the driver's response behavior to the graded gear shift prompt information in order to optimize the driver habit model.

[0027] In the embodiments of this disclosure, the current actual gear position signal of the vehicle is acquired in real time. This actual gear position is compared item by item with the target gear position command generated in step 103 to calculate and determine the deviation value and type. According to the preset deviation grading judgment rules, based on the magnitude and direction of the deviation obtained from the comparison, a corresponding level of shift prompt information is generated. Different levels correspond to different prompt intensities and operation instructions. The on-board processing unit transmits the graded shift prompt information to the on-board human-machine interface, where the interface completes the output presentation of the prompt information. At the same time, the system continuously collects and records the driver's response behavior to the graded shift prompt information, including whether the prompt operation is executed, the response delay time, and the matching degree between the actual operation and the prompt. The above response behavior data is used as the basis for model optimization and is sent back to the driver habit model to update the model parameters and adjust the behavior judgment rules, thereby completing the iterative optimization of the driver habit model. As an example, when the deviation between the actual gear position and the target gear position is large, an enhanced shift prompt is generated; when the deviation is small, a suggested shift prompt is generated. The system records the driver's operation response data and optimizes the corresponding driving behavior feature parameters in the model accordingly.

[0028] By comparing gear deviations, providing tiered prompts, and recording response behavior, a closed-loop execution logic is formed. This not only ensures precise delivery of gear shifting guidance but also continuously optimizes the habit model based on driver response data, allowing the system's guidance capabilities to continuously adapt and improve with usage.

[0029] The adaptive gear shifting guidance method for vehicles disclosed herein collects and preprocesses multi-dimensional vehicle state data in real time, completes multi-dimensional operating condition identification based on feature data streams, and combines real-time vehicle state and driver habit model to correct the gear shifting strategy and generate target gear command. Furthermore, it compares the actual gear and target gear command to generate graded gear shifting prompts and records driver response behavior to optimize the driver habit model. Therefore, it can solve the problems of static and fixed gear shifting strategies without adaptive capabilities, lack of real-time intelligent gear shifting guidance, inability to personalize and adapt to driver habits, and lack of closed-loop optimization of data and driving operation in existing technologies. It achieves the technical effects of providing real-time and accurate gear shifting guidance, dynamically adapting to vehicle operating conditions and driving habits, forming a continuous optimization closed loop of driving habits, and improving fuel economy and driving adaptability.

[0030] As a specific implementation of this disclosure, based on the basic solution, multi-dimensional state data during vehicle operation is collected in real time, and the multi-dimensional state data is preprocessed to generate a feature data stream. This is further defined as follows: multi-dimensional state data consisting of engine operating parameters, vehicle driving state parameters, load environment parameters, driver operation parameters, and external environment parameters is collected synchronously by the onboard controller and sensors; the collected multi-dimensional state data is synchronized and aligned with a unified timestamp, and data validity verification is performed to identify abnormal data; data repair operations are performed on the identified abnormal data, and the repaired data is merged with the data not identified as abnormal to form a complete state dataset; feature extraction operations are performed on the complete state dataset to generate a feature data stream carrying data quality labels, and the feature data stream is uploaded to the cloud.

[0031] Specifically, the system, through the onboard controller and in collaboration with engine sensors, body sensors, load sensors, slope sensors, and environmental sensing modules, synchronously collects multi-dimensional status data consisting of engine operating parameters, vehicle driving status parameters, load environment parameters, driver operation parameters, and external environment parameters. After collection, the system aligns all dimensional data with a unified UTC timestamp to eliminate data asynchrony issues caused by acquisition delays from different sensing units. Subsequently, it performs data validity verification, identifying missing, distorted, or out-of-range abnormal data through threshold comparison and parameter logical correlation. For identified abnormal data, the system uses linear interpolation and mean imputation to repair the data, merging the repaired data with normal data to form a complete status dataset. The system extracts core operational features from the complete status dataset, labels the feature data with valid and repaired data quality tags, generates a feature data stream carrying quality tags, and uploads it to the cloud. Furthermore, abnormal data processing can also be achieved using sliding window filtering, and timestamp synchronization can also employ an onboard local clock synchronization scheme.

[0032] By synchronously collecting data from multiple sources, aligning time sequences, repairing anomalies, and labeling with quality tags, the integrity, temporal consistency, and reliability of the feature data stream are effectively improved, providing high-fidelity data support for subsequent working condition identification.

[0033] As a specific implementation of this disclosure, based on the basic scheme, the collected multidimensional state data is synchronized and aligned with a unified timestamp, and data validity verification is performed to identify abnormal data. It is further defined as follows: the parameter groups are time-series aligned based on the unified timestamp to construct a multidimensional time series dataset; the multidimensional time series dataset is traversed, and data points that exceed the normal fluctuation range are detected according to the preset data threshold range and rate of change constraints, and the data points are marked as abnormal data.

[0034] Specifically, using the vehicle's unified timestamp as a benchmark, point-by-point time-series alignment is performed on various parameter groups related to engine operating conditions, vehicle driving status, load environment, driver operation, and external environment. This integrates and consolidates multi-source parameters from the same sampling time, constructing a continuous, time-consistent multi-dimensional time-series dataset. After dataset construction, the system traverses the multi-dimensional time-series dataset in the order of data sampling, matching preset numerical threshold ranges and rate-of-change constraints for different types of parameters, and performing dual detection on each data point. If the actual value of a data point exceeds the preset normal threshold range for the corresponding parameter, or if the rate of change of the parameter per unit time exceeds the set rate-of-change constraint, the data point is determined to be abnormal and marked. Furthermore, abnormal data detection can also be achieved by combining logical correlation verification between parameters, and time-series alignment can be completed using linear interpolation to match time points.

[0035] By constructing a standard multidimensional time series dataset through time series alignment and employing dual constraints of threshold and rate of change for detection, the accuracy of anomaly data identification is significantly improved, effectively avoiding false detections and missed detections caused by a single judgment rule.

[0036] As a specific implementation of this disclosure, based on the basic scheme, multi-dimensional operating condition identification of the vehicle's current operating scenario is performed based on the feature data stream to generate an operating condition identifier representing the current operating scenario. This is further defined as follows: extracting key feature vectors from the feature data stream and calculating dynamic features reflecting the balance between vehicle traction and resistance, energy flow features reflecting the matching relationship between fuel consumption and power output, operating mode features reflecting the driver's operating frequency and amplitude, and environmental constraint features reflecting the influence of external roads and the environment; inputting the dynamic features, energy flow features, operating mode features, and environmental constraint features into a pre-trained operating condition classification model to identify the vehicle's current slope state and road scenario category; based on the scenario category identification results, parameter quantization processing is performed on the slope value, load weight, driving style type, and traffic density level; and mapping the quantized parameter combination to a unique operating condition identifier.

[0037] Specifically, key feature vectors are extracted from the feature data stream, and four types of core features are calculated: dynamic features reflecting the balance between traction and resistance, obtained from vehicle force analysis; energy flow features reflecting the matching relationship between fuel consumption and power output, obtained from engine power and fuel consumption calculations; operation mode features reflecting the frequency and amplitude of driver operations, obtained from operation frequency and amplitude statistics; and environmental constraint features reflecting the influence of external roads and the environment, obtained from road and environmental perception. These four types of features are simultaneously input into a pre-trained condition classification model. The model, through feature fusion and judgment, identifies the vehicle's current slope state and road scene category. Based on the scene recognition results, the slope value, load weight, driving style type, and traffic density level are standardized and quantized. The quantized parameters are then combined and mapped according to preset rules to generate a unique condition identifier representing the current condition. Alternatively, the condition classification model can also be implemented using a condition classification decision tree, and parameter quantization can be completed using a hierarchical assignment method.

[0038] By extracting multi-dimensional features and classifying and recognizing models, combined with parameter quantization and coding, the operating condition identification accurately covers all dimensions of vehicle operation attributes, providing a more concrete and reliable scenario basis for subsequent shifting strategy matching.

[0039] As a specific implementation of this disclosure, based on the basic scheme, dynamic characteristics, energy flow characteristics, operating mode characteristics, and environmental constraint characteristics are input into a pre-trained working condition classification model to identify the current slope state and road scene category of the vehicle. Further, the following is specified: real-time acceleration and slope estimation values ​​from the dynamic characteristics are input into the root node of the decision tree model to determine whether the vehicle is in a climbing, descending, or flat road condition; if it is determined to be a climbing or descending condition, the instantaneous fuel consumption rate and engine load rate from the energy flow characteristics are input into the next layer node to further differentiate the working condition type; if it is determined to be a flat road condition, the operating frequency and constant speed driving ratio from the operating mode characteristics are input into the branch node to identify the specific driving scenario.

[0040] Specifically, a pre-built decision tree model is used as the operating condition classification model. First, the real-time acceleration and slope estimation values ​​from the dynamic features are input into the root node of the decision tree model. Based on preset slope thresholds and acceleration judgment rules, the system determines whether the vehicle is currently in an uphill, downhill, or flat road condition. If the root node determines it to be an uphill or downhill condition, the system inputs the instantaneous fuel consumption rate and engine load rate from the energy flow features into the next level node of the decision tree. Combining the correlation thresholds between fuel consumption and load, it further distinguishes different intensities of uphill and downhill sub-conditions. If the root node determines it to be a flat road condition, the system inputs the operation frequency and constant speed driving ratio from the operation mode features into the corresponding branch node. Based on the operation frequency range and constant speed ratio threshold, it identifies specific driving scenarios such as urban congestion, urban smooth traffic, suburban roads, and highways. Furthermore, the decision tree model can also be replaced with a lightweight classifier to complete the operating condition discrimination; the feature input order can be adaptively adjusted according to the vehicle's hardware configuration.

[0041] By adopting a hierarchical and progressive decision tree discrimination logic and diverting feature inputs according to working condition type, the computational overhead of working condition classification is reduced, and the response speed and classification accuracy of slope status and road scene recognition are significantly improved.

[0042] As a specific implementation of this disclosure, based on the basic scheme, a basic shift strategy is matched according to the operating condition identifier, the real-time vehicle status, and the driver habit model to modify the basic shift strategy and generate a target gear command. This is further defined as follows: A matching basic shift strategy curve is retrieved from a pre-set shift strategy library based on the operating condition identifier. The basic shift strategy curve includes an economy-priority strategy, a power-priority strategy, and a smoothness-priority strategy. Current real-time vehicle status data, driver historical behavior parameters retrieved from the driver habit model, and preset safety boundary conditions are obtained. A dynamic adjustment factor for modifying the basic shift strategy curve is calculated based on the real-time vehicle status data, driver historical behavior parameters, and safety boundary conditions. The shift speed threshold in the basic shift strategy curve is modified using the dynamic adjustment factor to generate an actual shift line adapted to the current scenario. The current actual engine speed is compared with the theoretical optimal speed on the actual shift line to determine the target gear command.

[0043] Specifically, based on the operating condition identifier, the system retrieves a matching basic shift strategy curve from the pre-shift strategy library. This library contains three types of basic shift strategy curves: economy priority, power priority, and smoothness priority. Each curve corresponds to a different shift speed range and shift point setting rule. The system simultaneously acquires real-time vehicle status data such as engine speed, vehicle speed, and load. It retrieves historical behavioral habit parameters from the driver's habit model, including shift timing preferences, operation response speed, and driving style level. It also retrieves preset safety boundary conditions, including engine safe speed, minimum stable speed, and clutch adaptation threshold. Based on these three types of parameters, a dynamic adjustment factor for correcting the basic shift strategy curve is calculated through weighted fusion calculation. The system uses this dynamic adjustment factor to offset the shift speed threshold in the basic shift strategy curve, generating an actual shift line adapted to the current scenario, vehicle status, and driving habits. Subsequently, the system compares the real-time actual engine speed with the theoretical optimal speed on the actual shift line, and determines the final target gear command based on the magnitude and direction of the speed deviation. In addition, the dynamic adjustment factor can also be calculated using a fuzzy control algorithm, and the actual shift line can also be generated through piecewise linear fitting.

[0044] By matching multiple types of basic strategies and fusion of multi-dimensional parameters to calculate dynamic adjustment factors, and combining precise comparison of engine speed to determine the target gear, the shifting strategy takes into account scenario adaptation, driving habits and safety boundary constraints, greatly improving the rationality and adaptability of gear commands.

[0045] As a specific implementation of this disclosure, based on the basic scheme, a dynamic adjustment factor for correcting the basic shifting strategy curve is calculated based on real-time vehicle status data, driver historical behavior parameters, and safety boundary conditions. This is further defined as follows: analyzing the load change rate and road adhesion coefficient in the real-time vehicle status data to generate a status correction coefficient reflecting the vehicle's physical state; analyzing the operation frequency score, anticipatory braking score, and average shifting timing deviation value in the driver's historical behavior parameters to generate a habit correction coefficient reflecting the driver's operating style; analyzing the engine torque limit value, clutch slippage risk threshold, and transmission system impact limit value in the safety boundary conditions to generate a boundary correction coefficient reflecting safety constraints; and substituting the status correction coefficient, habit correction coefficient, and boundary correction coefficient into a weighted fusion algorithm to calculate a comprehensive dynamic adjustment factor.

[0046] Specifically, the system first analyzes real-time vehicle status data, extracting the load change rate and road adhesion coefficient. Through normalized mapping operations, it generates state correction coefficients characterizing the vehicle's physical load and road adaptability. Next, it analyzes the driver's historical behavioral habits, extracting operation frequency scores, predictive braking scores, and average shift timing deviations. Based on the parameter score ranges and deviation values, it generates habit correction coefficients that match the driver's operating characteristics. Then, it analyzes safety boundary conditions, extracting engine torque limits, clutch slippage risk thresholds, and transmission system impact limits. According to safety constraint level conversion rules, it generates boundary correction coefficients that define the system's safe operating range. Finally, the state correction coefficients, habit correction coefficients, and boundary correction coefficients are substituted into a preset weighted fusion algorithm. Weighted calculations and normalization are performed according to fixed weight ratios to obtain a comprehensive dynamic adjustment factor that takes into account multi-dimensional constraints. Furthermore, the weighted fusion algorithm can also be implemented using fuzzy logic reasoning, and the correction coefficients can be generated through piecewise fitting functions.

[0047] By decomposing and generating three types of special correction coefficients and then weighting and fusing them, the dynamic adjustment factors are precisely coupled with vehicle status, driving habits and safety boundaries, making the shift strategy correction more in line with actual operating conditions and safety constraints.

[0048] As a specific implementation of this disclosure, based on the basic scheme, the current actual gear position is compared with the target gear position command. Based on the comparison deviation, a tiered shift prompt message is generated and output through the in-vehicle human-machine interface. The driver's response to the tiered shift prompt message is recorded to optimize the driver habit model. Further, the method is as follows: the absolute value of the gear difference between the current actual gear position and the target gear position command is calculated, and the absolute value of the gear difference is compared with a preset immediate shift threshold and a suggested shift threshold. When the absolute value of the gear difference is greater than the immediate shift threshold, an immediate shift command including an audible and visual alarm is generated and output through the instrument panel and audio components. When the absolute value of the gear difference is between the suggested shift threshold and the immediate shift threshold, a suggested shift prompt message is generated and output through the instrument panel display. Within a preset time window after the prompt message is output, the driver's shifting operation behavior is monitored, recording whether the driver performs a shift, the delay time of the shift, and the change in vehicle speed after the shift. The recorded behavioral data is used as samples to input into the driver habit learning algorithm to update the driving style classification and score in the driver habit model.

[0049] Specifically, the system first calculates the absolute value of the gear difference between the current actual gear and the target gear command, and then compares this absolute value with preset immediate shift thresholds and suggested shift thresholds. When the absolute value of the gear difference exceeds the immediate shift threshold, the system determines that the gear deviation exceeds the limit and generates an immediate shift command with audible and visual alarms, which is simultaneously output through the vehicle's instrument panel indicator and audio components. When the absolute value of the gear difference is between the suggested shift threshold and the immediate shift threshold, the system determines that the gear deviation is moderate and generates a plain text suggested shift prompt message, which is output separately through the vehicle's instrument panel display. Within a preset time window after outputting the prompt message, the system continuously monitors the driver's shifting behavior, accurately recording three data points: whether the driver performed the suggested shift operation, the shift operation delay time, and the change in vehicle speed after shifting. The system uses the recorded behavioral data as samples to input into the driver habit learning algorithm, completing the update and iteration of the driving style classification and behavior score in the driver habit model. In addition, the prompt output can be equipped with tiered voice broadcasts, and the time window duration can be dynamically adjusted according to operating conditions.

[0050] By using gear difference grading to achieve differentiated output of prompts, driving safety is ensured while reducing prompt interference. At the same time, accurate behavioral samples are collected to iterate the model and improve the accuracy of driver habit recognition.

[0051] It should be noted that the embodiments of this disclosure may include multiple steps. For ease of description, these steps are numbered, but these numbers are not a limitation on the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of this disclosure do not limit this.

[0052] Corresponding to the aforementioned vehicle adaptive shift guidance method, this disclosure also proposes a vehicle adaptive shift guidance device. Since the device embodiments of this disclosure correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to the method embodiments described above, and will not be repeated here.

[0053] Figure 2 This is a schematic diagram of the structure of a vehicle adaptive shift guidance device provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, it includes: The acquisition unit 21 is used to acquire multi-dimensional status data during vehicle operation in real time and preprocess the multi-dimensional status data to generate a feature data stream. The identification unit 22 is used to perform multi-dimensional working condition identification of the current operating scenario of the vehicle based on the feature data stream, so as to generate a working condition identifier that represents the current operating scenario. The correction unit 23 is used to match the basic shifting strategy and real-time vehicle status according to the working condition identifier, and to correct the basic shifting strategy in combination with the driver habit model to generate the target gear command. The output unit 24 is used to compare the current actual gear position with the target gear position command, generate graded shift prompt information based on the comparison deviation and output it through the vehicle human-machine interface, and record the driver's response behavior to the graded shift prompt information in order to optimize the driver habit model.

[0054] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0055] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0056] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0057] like Figure 3As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 302 or a computer program loaded from storage unit 308 into RAM (Random Access Memory) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O (Input / Output) interface 305 is also connected to the bus 304.

[0058] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0059] The computing unit 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the vehicle adaptive shift guidance method. For example, in some embodiments, the vehicle adaptive shift guidance method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the aforementioned vehicle adaptive shift guidance method by any other suitable means (e.g., by means of firmware).

[0060] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0061] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0062] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0063] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0064] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0065] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0066] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0067] The various numerical designations such as "first," "second," etc., used in this disclosure are merely for ease of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate a sequential order.

[0068] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0069] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0070] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A vehicle adaptive gear shifting guidance method, characterized in that, include: Multidimensional status data of the vehicle during operation is collected in real time, and the multidimensional status data is preprocessed to generate a feature data stream; Based on the feature data stream, multi-dimensional operating condition identification is performed on the current operating scenario of the vehicle to generate an operating condition identifier that represents the current operating scenario. Based on the operating condition identifier, the basic shifting strategy and real-time vehicle status are matched, and the basic shifting strategy is modified in combination with the driver habit model to generate the target gear command. The current actual gear position is compared with the target gear position command. Based on the comparison deviation, a graded gear shift prompt message is generated and output through the vehicle human-machine interface. The driver's response behavior to the graded gear shift prompt message is recorded to optimize the driver habit model.

2. The adaptive shifting guidance method for commercial vehicles according to claim 1, characterized in that, The real-time acquisition of multi-dimensional state data during vehicle operation, and the preprocessing of the multi-dimensional state data to generate a feature data stream, includes: The vehicle controller and sensors synchronously collect the multi-dimensional state data, which consists of engine operating parameters, vehicle driving status parameters, load environment parameters, driver operation parameters, and external environment parameters. The collected multidimensional status data is synchronized and aligned with a unified timestamp, and data validity is verified to identify abnormal data. Perform data repair operations on the identified abnormal data, and merge the repaired data with the data that was not identified as abnormal into a complete state dataset; A feature extraction operation is performed on the complete state dataset to generate the feature data stream carrying data quality labels, and the feature data stream is uploaded to the cloud.

3. The adaptive shifting guidance method for commercial vehicles according to claim 2, characterized in that, The process of synchronizing and aligning the collected multidimensional state data with a unified timestamp, and performing data validity checks to identify abnormal data, includes: Based on the unified timestamp, time series alignment is performed on each parameter group to construct a multidimensional time series dataset; The multidimensional time series dataset is traversed, and data points that exceed the normal fluctuation range are detected based on the preset data threshold range and rate of change constraints. These data points are then marked as abnormal data.

4. The adaptive shifting guidance method for commercial vehicles according to claim 1, characterized in that, The step of performing multi-dimensional condition identification on the vehicle's current operating scenario based on the feature data stream to generate a condition identifier representing the current operating scenario includes: Key feature vectors are extracted from the feature data stream, and dynamic features reflecting the balance between vehicle traction and resistance, energy flow features reflecting the matching relationship between fuel consumption and power output, operation mode features reflecting the frequency and amplitude of driver operation, and environmental constraint features reflecting the influence of external roads and environment are calculated. The dynamic characteristics, energy flow characteristics, operating mode characteristics, and environmental constraint characteristics are input into a pre-trained working condition classification model to identify the current slope state and road scene category of the vehicle. Based on the scene category recognition results, the slope value, load weight, driving style type and traffic density level are quantified. The quantized parameter combination is mapped to a unique operating condition identifier.

5. The adaptive shifting guidance method for commercial vehicles according to claim 4, characterized in that, The step of inputting the dynamic characteristics, energy flow characteristics, operating mode characteristics, and environmental constraint characteristics into a pre-trained condition classification model to identify the current slope state and road scene category of the vehicle includes: The real-time acceleration and slope estimation values ​​from the aforementioned dynamic characteristics are input into the root node of the decision tree model to determine whether the vehicle is in a climbing, descending, or flat road condition. If the condition is determined to be either uphill or downhill, the instantaneous fuel consumption rate and engine load rate in the energy flow characteristics are input into the next layer node to further distinguish the molecular condition type. If the driving condition is determined to be a flat road, the operation frequency and constant speed driving ratio in the operation mode features are input into the branch node to identify the specific driving scenario.

6. The adaptive shifting guidance method for commercial vehicles according to claim 1, characterized in that, The step of matching the basic shift strategy with the operating condition identifier and the real-time vehicle status, and modifying the basic shift strategy in conjunction with the driver habit model to generate a target gear command includes: Based on the operating condition identifier, a matching basic shift strategy curve is retrieved from the preset shift strategy library. The basic shift strategy curve includes an economy-priority strategy, a power-priority strategy, and a smoothness-priority strategy. The system acquires current real-time vehicle status data, driver historical behavior parameters retrieved from the driver habit model, and preset safety boundary conditions. Based on the real-time vehicle status data, the driver's historical behavior parameters, and the safety boundary conditions, a dynamic adjustment factor is calculated to correct the basic shift strategy curve. The shift speed threshold in the basic shift strategy curve is corrected using the dynamic adjustment factor to generate an actual shift line that adapts to the current scenario. The current actual engine speed is compared with the theoretical optimal speed on the actual shift line to determine the target gear command.

7. The adaptive shifting guidance method for commercial vehicles according to claim 6, characterized in that, The dynamic adjustment factor calculated based on the real-time vehicle status data, the driver's historical behavior parameters, and the safety boundary conditions to correct the basic shift strategy curve includes: The load change rate and road adhesion coefficient in the real-time vehicle status data are analyzed to generate a status correction coefficient that reflects the physical state of the vehicle. The operation frequency score, anticipatory braking score, and average shift timing deviation value in the driver's historical behavior habit parameters are analyzed to generate habit correction coefficients that reflect the driver's operating style. The engine torque limit, clutch slip risk threshold, and transmission system impact limit in the safety boundary conditions are analyzed to generate boundary correction coefficients that reflect safety constraints. The state correction coefficient, the habit correction coefficient, and the boundary correction coefficient are substituted into the weighted fusion algorithm to calculate the comprehensive dynamic adjustment factor.

8. The adaptive shifting guidance method for commercial vehicles according to claim 1, characterized in that, The process of comparing the current actual gear position with the target gear position command, generating graded shift prompts based on the comparison deviation and outputting them through the vehicle's human-machine interface, and recording the driver's response to the graded shift prompts to optimize the driver habit model includes: Calculate the absolute value of the gear difference between the current actual gear and the target gear command, and compare the absolute value of the gear difference with the preset immediate shift threshold and the suggested shift threshold; When the absolute value of the gear difference is greater than the immediate shift threshold, an immediate shift command including an audible and visual alarm is generated and output through the instrument and audio components. When the absolute value of the gear difference is between the suggested shift threshold and the immediate shift threshold, a suggested shift prompt message is generated and output through the instrument display screen. Within a preset time window after the prompt message is output, the driver's gear shifting behavior is monitored, and it is recorded whether the driver performs a gear shift, the delay time of the gear shift, and the change in vehicle speed after the gear shift. The recorded behavioral data is used as samples to input into the driver habit learning algorithm to update the driving style classification and rating in the driver habit model.

9. A vehicle adaptive shift guidance device, characterized in that, include: The acquisition unit is used to acquire multi-dimensional status data during vehicle operation in real time, and to preprocess the multi-dimensional status data to generate a feature data stream. The identification unit is used to perform multi-dimensional working condition identification on the current operating scenario of the vehicle based on the feature data stream, so as to generate a working condition identifier that represents the current operating scenario. The correction unit is used to match the basic shifting strategy and real-time vehicle status according to the working condition identifier, and to correct the basic shifting strategy in combination with the driver habit model to generate the target gear command. The output unit is used to compare the current actual gear position with the target gear position command, generate graded shift prompt information based on the comparison deviation and output it through the vehicle human-machine interface, and record the driver's response behavior to the graded shift prompt information in order to optimize the driver habit model.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

Images