A vehicle energy consumption and driving mode matching method, device, storage medium and TICE

Abstract

Embodiments of the present application provide a vehicle energy consumption and driving mode matching method, device, storage medium and vehicle networked voice communication system assembly. The method comprises: acquiring multi-source information collected by a plurality of data acquisition units; inputting the multi-source information into an energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information; and sending the driving mode and energy consumption adjustment information to a vehicle control unit for the vehicle control unit to perform adaptive adjustment according to the driving mode and energy consumption adjustment information. Through the conflict coordination mechanism of the plurality of data acquisition units, it is ensured that the multi-source information is consistent with the actual environment, providing reliable input for the energy consumption and driving mode matching model, which can improve the matching degree of vehicle energy consumption and driving mode, reduce invalid energy consumption and balance the energy consumption and driving experience in all scenarios.

Description

Technical Field

[0001] This invention relates to the field of vehicle intelligent control and energy management technology, and in particular to a method, device, storage medium and TICE for matching vehicle energy consumption with driving mode. Background Technology

[0002] Current vehicle energy consumption and driving mode matching technologies often rely on a single threshold condition (such as vehicle speed ≥ 80km / h) to trigger driving mode switching. The identification and judgment of driving behavior also depend solely on a single operating parameter such as throttle opening, resulting in a limited judgment dimension and simple control logic. Furthermore, they employ indiscriminate and untargeted preheating strategies for the battery under low-temperature conditions and fail to implement corresponding energy consumption control for the air conditioning system during high-speed driving, making it difficult to achieve accurate matching between vehicle energy consumption and actual operating conditions.

[0003] Because of its single data dimension and isolated execution logic, the vehicle's energy consumption is poorly matched with the driving mode, resulting in high vehicle energy consumption and an inability to balance energy consumption and driving experience across all scenarios. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, device, storage medium and TICE for matching vehicle energy consumption with driving mode, so as to improve the matching degree between vehicle energy consumption and driving mode, reduce ineffective energy consumption, and balance energy consumption and driving experience in all scenarios.

[0005] On one hand, embodiments of the present invention provide a method for matching vehicle energy consumption with driving mode, including: Acquire multi-source information collected by various data acquisition units; The multi-source information is input into the energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information. The driving mode and energy consumption adjustment information are sent to the vehicle control unit so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information.

[0006] Optionally, acquiring multi-source information collected by multiple data acquisition units includes: Raw multi-source information is obtained from different sensors of multiple data acquisition units, wherein the raw multi-source information includes: any combination of vehicle scene data, vehicle status data, driving behavior data, vehicle environment data, vehicle energy consumption data and / or user preference data; The original multi-source information is subjected to conflict detection and arbitration decision processing to generate multi-source information.

[0007] Optionally, the step of performing conflict detection and arbitration decision processing on the original multi-source information to generate multi-source information includes: Conflict detection is performed on two or more original multi-source information representing the same parameter collected by multiple data acquisition units. If the data deviation of the two or more original multi-source information representing the same parameter is greater than a set deviation threshold, arbitration decision processing is performed on the two or more original multi-source information representing the same parameter according to one or any combination of the set sensor priority, dynamic weight allocation and / or cross-validation process, to generate multi-source information.

[0008] Optionally, acquiring multi-source information collected by multiple data acquisition units includes: When one of the multiple data acquisition units fails, another data acquisition unit that can represent the same parameter is used as a substitute, and multi-source information is generated based on the original multi-source data obtained from the substitute data acquisition unit.

[0009] Optionally, when one of the multiple data acquisition units fails, another data acquisition unit capable of representing the same parameter is used as a replacement, and multi-source information is generated based on the original multi-source data obtained from the replacement data acquisition unit, including: When cameras in multiple data acquisition units fail, redundancy verification and replacement processing are performed on the cameras through the navigation API, radar, and slope sensors. Multi-source information is generated based on the raw multi-source data collected by the navigation API, radar, and slope sensors; or, When radar fails in multiple data acquisition units, redundancy verification and replacement processing are performed on the radar using the navigation API, vehicle speed sensor, and pedal sensor. Multi-source information is generated based on the raw multi-source data collected by the navigation API, vehicle speed sensor, and pedal sensor; or, When the navigation API fails in multiple data acquisition units, the navigation API is redundantly verified and replaced by cameras, radar, and pre-stored POIs. Multi-source information is generated based on the raw multi-source data collected by cameras, radar, and pre-stored POIs.

[0010] Optionally, before calculating the multi-source information based on the energy consumption and driving mode matching model to generate driving mode and energy consumption adjustment information, the following steps are included: Acquire multi-source information from samples collected by various data acquisition units; The random forest algorithm is used to train the multi-source information of the samples based on the Python sklearn library, and the matching relationship between energy consumption and driving mode is output to build an energy consumption and driving mode matching model through the random forest algorithm.

[0011] Optionally, inputting the multi-source information into the energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information includes: The multi-source information is calculated based on the energy consumption and driving mode matching model to generate the matching relationship between energy consumption and driving mode. Based on the matching relationship between energy consumption and driving mode and the obtained current energy consumption and driving mode, driving mode and energy consumption adjustment information is generated.

[0012] On the other hand, embodiments of the present invention provide a vehicle energy consumption and driving mode matching device, comprising: The acquisition module is used to acquire multi-source information collected by various data acquisition units; The generation module is used to input the multi-source information into the energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information. The sending module is used to send driving mode and energy consumption adjustment information to the vehicle control unit, so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information.

[0013] On the other hand, embodiments of the present invention provide a storage medium including a stored program, wherein, when the program is running, it controls the device where the storage medium is located to execute the above-mentioned vehicle energy consumption and driving mode matching method.

[0014] On the other hand, embodiments of the present invention provide a vehicle connected voice communication system assembly, including a memory and a processor. The memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. When the program instructions are loaded and executed by the processor, the steps of the above-mentioned vehicle energy consumption and driving mode matching method are implemented.

[0015] The technical solution provided in this invention involves acquiring multi-source information collected by various data acquisition units; inputting this multi-source information into an energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information; and sending this driving mode and energy consumption adjustment information to the vehicle control unit so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information. Through a conflict coordination mechanism among multiple data acquisition units, the multi-source information is ensured to conform to the actual environment, providing reliable input to the energy consumption and driving mode matching model. This improves the matching degree between vehicle energy consumption and driving mode, reduces ineffective energy consumption, and balances energy consumption and driving experience across all scenarios. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1A flowchart of a method for matching vehicle energy consumption with driving mode according to an embodiment of the present invention; Figure 2 A flowchart illustrating another method for matching vehicle energy consumption with driving mode according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a vehicle energy consumption and driving mode matching device according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a vehicle-connected voice communication system assembly provided in an embodiment of the present invention. Detailed Implementation

[0018] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0019] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0020] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0021] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0022] In related technologies, vehicle energy consumption and driving mode matching control technology has gradually evolved from completely manual adjustment to the stage of basic scenario preset control. However, there are still many technical defects in practical applications, mainly reflected in the following aspects: First, the scenario adjustment strategy is relatively static and lacks control flexibility. It usually only triggers driving mode switching based on a single threshold condition such as vehicle speed (e.g., vehicle speed greater than or equal to 80km / h), without effectively verifying the authenticity of the road scenario. Furthermore, there is a lack of coordinated control logic between various control parameters. For example, in congested conditions, it simply reduces power output without optimizing for the increased energy consumption caused by frequent gear shifts.

[0023] Secondly, the accuracy of driving behavior recognition is low, and misjudgments are prone to occur. Relying solely on single operating parameters such as throttle opening to determine driving behavior results in a limited recognition dimension and a high likelihood of misjudgments. Furthermore, the lack of coordination between mode adjustment and transmission control leads to poor control performance.

[0024] Third, the lack of balance in overall vehicle energy consumption optimization can easily lead to conflicts between energy-saving goals and component protection and driving experience. For example, the use of untargeted preheating strategies for the battery in low-temperature environments and the lack of reasonable energy consumption control for the air conditioning system during high-speed driving make it difficult to balance energy efficiency, component lifespan, and driving comfort.

[0025] Fourth, in the process of judging the same scene, data contradictions can easily occur between different sensing sources. For example, navigation information may determine that the road is on a highway, while the visual acquisition device may determine that it is a rural road due to environmental factors such as heavy fog; radar information may misjudge traffic congestion due to stationary vehicles. Such problems of insufficient data accuracy can easily lead to decision biases in the control model and affect the reliability of control.

[0026] In summary, due to the limited data acquisition dimensions and the isolated control logic of each execution unit, the relevant technologies struggle to balance vehicle energy consumption and driving experience across all operating scenarios.

[0027] To overcome the above-mentioned deficiencies, this invention constructs a closed-loop control framework that integrates multi-source information acquisition, sensor conflict collaborative processing, dynamic decision-making, scenario-based execution, and feedback correction, thereby solving the technical problems existing in the prior art.

[0028] One embodiment of the present invention provides a method for matching vehicle energy consumption with driving mode. Figure 1 This is a flowchart illustrating a method for matching vehicle energy consumption with driving mode according to an embodiment of the present invention. Figure 2 A flowchart of another vehicle energy consumption and driving mode matching method provided in an embodiment of the present invention is shown below. Figure 1 or Figure 2 As shown, the method includes: Step 102: Obtain multi-source information collected by various data acquisition units.

[0029] In this embodiment of the invention, each step uses the Telematics and In-Vehicle Communication Ensemble (TICE) as the core decision-making unit, and constructs a four-layer architecture (conflict coordination layer, decision layer, execution layer, and feedback layer) through a Controller Area Network (CAN) bus (data acquisition frequency 100ms / time, control command response time ≤200ms). The "conflict coordination layer" used to execute step 102 ensures data authenticity.

[0030] In this embodiment of the invention, the conflict coordination layer, decision layer, execution layer and feedback layer communicate in real time via CAN bus. The conflict coordination algorithm is deployed on the TICE embedded chip, and the calculation time is ≤30ms, which does not affect the data acquisition frequency.

[0031] In this embodiment of the invention, the various data acquisition units may include: a navigation application programming interface (API), a camera, radar, a slope sensor, a vehicle speed sensor, a vehicle control unit (VCU), a fuel level sensor, a pedal sensor, a temperature sensor, a visibility sensor, a power control unit (PCU), and / or one or any group thereof from the cockpit API. The radar may include millimeter-wave radar.

[0032] In this embodiment of the invention, raw multi-source information can be obtained from different sensors of various data acquisition units. The raw multi-source information includes any combination of vehicle scene data, vehicle status data, driving behavior data, vehicle environment data, vehicle energy consumption data, and / or user preference data.

[0033] For example, vehicle scene data can be acquired through navigation APIs, cameras, radar, and slope sensors. Vehicle status data can be acquired through vehicle speed sensors, VCUs, or fuel level sensors. Driving behavior data can be acquired through pedal sensors. Vehicle environmental data can be acquired through temperature and visibility sensors. Vehicle energy consumption data can be acquired through PCUs or VCUs. User preference data can be acquired through cockpit APIs.

[0034] For example, Table 1 is a table of original multi-source information collection.

[0035] Table 1

[0036] Among them, road types can be classified according to lane width (for example, highways are level 3, urban roads are level 2 and rural roads are level 1). The judgment deviation between highways (level 3) and urban roads (level 2) is level 1, the judgment deviation between highways (level 3) and rural roads (level 1) is level 2, and the judgment deviation between urban roads (level 2) and rural roads (level 1) is level 1. When the judgment deviation of multiple sensors is ≥ level 2, conflict detection and arbitration decision processing are performed on the original multi-source information to generate multi-source information.

[0037] In this embodiment of the invention, conflict detection is performed on two or more original multi-source information representing the same parameter collected by multiple data acquisition units. If the data deviation of the two or more original multi-source information representing the same parameter is greater than a set deviation threshold, arbitration decision processing is performed on the two or more original multi-source information representing the same parameter according to one or any combination of the set sensor priority, dynamic weight allocation and / or cross-validation process, to generate multi-source information.

[0038] In this embodiment of the invention, "the same parameter" refers to a parameter that describes the same environmental attribute or scene feature, but the data is provided by different data acquisition units. Although these data acquisition units measure the same physical quantity or scene feature, they may produce different judgment results due to factors such as their respective working principles, accuracy, and environmental conditions. In this case, conflict detection and arbitration decision-making are required.

[0039] For example, the navigation API determines the current road type as a highway based on the road code (Gxx), and the camera determines the current road type as a rural road without markings through image recognition. The original multi-source information measured by these two data acquisition units is used to represent the road type. Therefore, the road type is "the same parameter". The road code collected by the navigation API and the road image collected by the camera are "two original multi-source information representing the same parameter".

[0040] In this embodiment of the invention, for two high-frequency scenarios, namely "road type conflict" and "road condition conflict ahead", problems such as heavy fog, sensor contamination, and interference from stationary targets are solved in the following ways.

[0041] In this embodiment of the invention, multiple data acquisition units can synchronously acquire raw multi-source information (such as road codes acquired by navigation API, lane lines acquired by cameras, and vehicle distances acquired by radar) at 100ms / time. The deviations of data acquired by multiple data acquisition units representing the same parameter are compared. If the deviation exceeds a set threshold, arbitration decision processing is triggered (e.g., if navigation determines "highway" and camera determines "rural road", the deviation is determined to be level 2). Arbitration decision processing is performed on two or more raw multi-source information representing the same parameter according to one or more of the set sensor priority, dynamic weight allocation and / or cross-validation process or any combination thereof, generating multi-source information, and transmitting the multi-source information to the energy consumption and driving mode matching model, storing conflict logs for use in Over-the-Air (OTA) technology iteration.

[0042] The following description uses two specific scenarios.

[0043] Scenario 1: Road type conflict (navigation vs. camera). Common conflict: Navigation determines the current road as a "highway" (code Gxx), while the camera, due to fog / dirt, determines the current road as an "unmarked rural road".

[0044] 1. Sensor Priority: Basic priority "Navigation (coding reliability ≥98%) > Camera (85%) > Radar (lane width assist)"; if the navigation signal is normal (≥4 satellites, positioning error ≤5m), the navigation conclusion is adopted directly, and abnormal camera data is skipped.

[0045] 2. Cross-verification (when navigation is abnormal): If the navigation signal is lost (in a tunnel), activate the "radar lane width + camera median strip" verification: If the radar detects a lane width ≥ 3.75m and the camera recognizes a "fully enclosed median strip", then the current road is determined to be a "highway"; if the radar detects a lane width ≤ 3m and the camera does not recognize a median strip, then the current road is determined to be a "rural road".

[0046] 3. Time window filtering: If the camera conflicts due to momentary obstruction (truck blocking), and 4 out of 5 consecutive data collections (500ms) are consistent with the navigation, it is judged as "momentary conflict" and the anomaly is ignored.

[0047] Scenario 2: Road condition conflict ahead (millimeter-wave radar vs. navigation API). Common conflict: Radar detects stationary vehicles (parked in the emergency lane) and judges it as "congested," while the navigation API judges it as "unobstructed."

[0048] 1. Dynamic weight allocation: Weights are adjusted according to the environment (total 100%). Table 2 shows the dynamic weight allocation for various data acquisition units, as shown in Table 2 below: Table 2

[0049] 2. Target attribute filtering: The radar distinguishes between "moving vehicles" (outline 4-6m, relative speed difference ≤20km / h) and "stationary targets" (≤2m or speed = vehicle speed). Stationary targets are directly excluded from the congestion judgment.

[0050] 3. Navigation history verification: If there is a conflict between radar and navigation, the traffic conditions within the last 5 minutes of navigation are retrieved: if the navigation changes from "smooth" to "congested", then the real-time radar data is used; if it remains smooth, then the navigation conclusion is used (excluding interference from stationary targets).

[0051] In this embodiment of the invention, when one of the multiple data acquisition units fails, another data acquisition unit that can represent the same parameter is used as a substitute, and multi-source information is generated based on the original multi-source data obtained by the substitute data acquisition unit, so as to ensure that the acquisition of original multi-source information is not interrupted.

[0052] For example, when a camera fails in multiple data acquisition units, redundancy verification and replacement processing are performed on the camera using the navigation API, radar, and slope sensor, generating multi-source information based on the original multi-source data collected by the navigation API, radar, and slope sensor; or, when radar fails in multiple data acquisition units, redundancy verification and replacement processing are performed on the radar using the navigation API, vehicle speed sensor, and pedal sensor, generating multi-source information based on the original multi-source data collected by the navigation API, vehicle speed sensor, and pedal sensor; or, when the navigation API fails in multiple data acquisition units, redundancy verification and replacement processing are performed on the navigation API using the camera, radar, and pre-stored POIs, generating multi-source information based on the original multi-source data collected by the camera, radar, and pre-stored POIs.

[0053] Table 3 is a replacement table for failed data acquisition units, as shown in Table 3 below.

[0054] Table 3

[0055] Step 104: Input the multi-source information into the energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information.

[0056] In this embodiment of the invention, the decision-making layer can deploy an energy consumption and driving mode matching model, and output the optimal driving mode and energy consumption adjustment information based on the coordinated multi-source information.

[0057] In this embodiment of the invention, a random forest algorithm can be used to construct an energy consumption and driving mode matching model to improve decision-making accuracy. Specifically, multi-source information from various data acquisition units can be obtained; the random forest algorithm is used to train the multi-source information based on the Python sklearn library to output the matching relationship between energy consumption and driving mode.

[0058] For example, the construction of multi-source sample information involves collecting 120,000 sets of real-vehicle data, covering: 3 types of vehicle models (fuel / pure electric / hybrid), 4 scenarios (including extreme environments such as heavy fog / heavy rain), and 3 types of driving behaviors. Each set of multi-source sample information includes "the collaboratively generated multi-source information and its output labels," as shown in the example. Input: Highway (G15 navigation + lane width 4.0m collected by radar) + vehicle speed 90km / h + smooth driving + no charging station; Output: High-speed cruise mode + fuel power coefficient 0.7 + recovery 50% + energy conservation 60%.

[0059] For example, a random forest algorithm is used to train the sample based on multi-source information using the Python sklearn library. The Python sklearn library contains 100 decision trees with a maximum depth of 10 layers, and the cross-validation accuracy is ≥95%. Deployment platform: TICE embedded chip, single decision time ≤50ms.

[0060] Table 4 shows the matching relationship between output energy consumption and driving mode, as shown in Table 4 below.

[0061] Table 4

[0062] In this embodiment of the invention, multi-source information can be calculated based on an energy consumption and driving mode matching model to generate a matching relationship between energy consumption and driving mode; and driving mode and energy consumption adjustment information can be generated based on the matching relationship between energy consumption and driving mode and the obtained current energy consumption and driving mode.

[0063] For example, Table 5 is a table of driving mode and energy consumption adjustment information, as shown in Table 5 below.

[0064] Table 5

[0065] Step 106: Send the driving mode and energy consumption adjustment information to the vehicle control unit so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information.

[0066] In this embodiment of the invention, the vehicle control unit includes one or any combination of a PCU, BMS, and / or a transmission control unit.

[0067] In this embodiment of the invention, the execution layer can send driving mode and energy consumption adjustment information to the vehicle control unit, so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information. Simultaneously, the execution layer can feed back data to the conflict coordination layer in real time. For example, if a sensor experiences three consecutive conflicts and its accuracy is low after arbitration (e.g., accuracy < 85%), its weight is automatically reduced (e.g., the weight of a camera in heavy fog is reduced from 40% to 30%).

[0068] In this embodiment of the invention, adaptive adjustment may include scene adaptive adjustment, driving behavior adaptive adjustment, and dynamic energy consumption optimization. Specific examples are described below.

[0069] 1. Scene adaptive adjustment (1) High-speed scenario: Trigger: Vehicle speed ≥ 80km / h for 2 minutes + road type after coordination = highway. Execution: Fuel vehicle: PCU fuel injection reduced by 10%, ignition advance angle optimized by 2° (fuel consumption reduced by 10%); Hybrid: 60% battery protection when no charging station is available (avoiding battery depletion), 45% battery protection when charging station is available (no waste); AC control: AC automatically turns off when vehicle speed ≥ 100km / h, energy consumption ≤ 5% after manual activation.

[0070] (2) Congestion scenario: Trigger: vehicle speed ≤ 40km / h for 1 minute + road conditions after coordination = congestion; Execution: power-recovery coordination: coefficient 0.5 + recovery 90% (recovery of start-stop kinetic energy increases by 40%); transmission limits 1-2 gears (number of gear shifts reduced by 60%, mechanical loss reduced by 30%); pop-up prompt "crawl mode activated".

[0071] (3) Slope scenario: Trigger: After coordination, the slope is ≥5% (uphill) / ≤-5% (downhill); Execution: Uphill: Fuel injection increases by 15% (avoiding high load fuel consumption), hybrid power increases by 20%; Downhill: 0.2g braking force (brake pad wear reduced by 30%) + electric vehicle recycling 80% (energy consumption reduced by 20%).

[0072] 2. Adaptive adjustment of driving behavior (1) Smooth driving (throttle ≤30% and braking ≤1 time / min): Maintain recovery of 80% + upshift 200ms in advance (engine low speed, fuel consumption reduced by 8%). (2) Aggressive driving (throttle ≥70% or brake ≥3 times / minute): power coefficient 0.9 + downshift delay 100ms (to avoid power interruption and reduce fuel consumption from deep pressing).

[0073] 3. Dynamic energy consumption optimization (balancing energy saving and user experience) (1) Low temperature environment (≤-10℃): BMS preheating (power ≤3kW, from -20℃ to 0℃ in 10 minutes, power consumption increase ≤10%); VCU power limit ≤80% (battery over-discharge risk reduced by 50%, range deviation reduced from 20% to 7%).

[0074] For gasoline vehicles cruising at high speeds: AC automatically shuts off (air supply remains), and when manually turned on, the PCU controls the compressor power (energy consumption increase ≤5%).

[0075] In this embodiment of the invention, a feedback layer is also included. The feedback layer is used to feed back the executed data (behavioral changes, energy consumption deviations) to the decision layer to optimize the parameters of the energy consumption and driving mode matching model. The feedback layer is also used to feed back the executed data (behavioral changes, energy consumption deviations) to the conflict coordination layer to update the dynamic weight allocation of multiple data acquisition units, forming a double closed loop of "conflict coordination-decision-execution-feedback".

[0076] In this embodiment of the invention, the cockpit software may include a "smart / manual" button: manual mode allows the user to adjust the mode / recovery; smart mode automatically performs the above process.

[0077] In this embodiment of the invention, users can view the current status of the data acquisition unit (e.g., "Foggy day: navigation weight 60%, camera weight 30%)", thereby increasing trust.

[0078] In this embodiment of the invention, if more than three data acquisition units conflict simultaneously (extreme scenario), an emergency plan of "historical data + factory calibration" (such as default flat road or economic mode) is activated to maintain 75% optimization effect.

[0079] In this embodiment of the invention, if the CAN bus fails, TICE triggers a backup command to switch to "standard mode" (power 0.8 + recovery 50%) to ensure safe driving.

[0080] The technical solution provided in this invention involves acquiring multi-source information collected by various data acquisition units; inputting this multi-source information into an energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information; and sending this driving mode and energy consumption adjustment information to the vehicle control unit so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information. Through a conflict coordination mechanism among multiple data acquisition units, the multi-source information is ensured to conform to the actual environment, providing reliable input to the energy consumption and driving mode matching model. This improves the matching degree between vehicle energy consumption and driving mode, reduces ineffective energy consumption, and balances energy consumption and driving experience across all scenarios.

[0081] In this embodiment of the invention, a conflict coordination mechanism (dynamic weighting, cross-validation) of multiple data acquisition units is used to resolve data inconsistencies between navigation and cameras, and between radar and navigation APIs (such as in foggy or stationary target interference scenarios). This ensures that the collected data closely matches the actual environment, provides reliable input for the energy consumption and driving mode matching model, significantly reduces the risk of incorrect mode switching, and improves decision-making accuracy.

[0082] In this embodiment of the invention, the limitations of static parameters are overcome. By combining original multi-source information, the power output, energy recovery, shifting logic and power conservation ratio are dynamically adapted for fuel / pure electric / hybrid vehicles and scenarios such as high speed, congestion, slope, and low temperature. With the help of low temperature component protection and high speed auxiliary energy consumption control, ineffective energy consumption is reduced and optimal energy efficiency is achieved in all scenarios.

[0083] In this embodiment of the invention, dual parameters are used to accurately identify driving behavior, emphasizing smoothness and energy saving during stable driving and ensuring continuous power during aggressive driving; a new mode switching pop-up window is added to improve transparency.

[0084] In this embodiment of the invention, a proactive safety strategy is implemented in slope and congestion scenarios (enhanced power uphill and assisted braking downhill) to reduce operational burden and safety risks.

[0085] In this embodiment of the invention, when a sensor fails, other sensors are used as replacements, and a backup command is preset for bus failures to avoid system failure.

[0086] In this embodiment of the invention, it is compatible with three types of vehicle powertrains, eliminating the need for redundant development. It supports OTA updates to adapt to changes in road conditions, climate, and driving habits.

[0087] In this embodiment of the invention, both intelligent mode (fully automatic process) and manual mode (autonomous parameter adjustment) are considered, and energy consumption sensitivity settings (energy saving / power / balance) are supported to meet the needs of daily commuting and personalized driving.

[0088] One embodiment of the present invention provides a vehicle energy consumption and driving mode matching device. Figure 3 This is a schematic diagram of a vehicle energy consumption and driving mode matching device according to an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes: an acquisition module 11, a generation module 12, and a transmission module 13.

[0089] The acquisition module 11 is used to acquire raw multi-source information collected by various data acquisition units.

[0090] The generation module 12 is used to input multi-source information into the energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information.

[0091] The sending module 13 is used to send driving mode and energy consumption adjustment information to the vehicle control unit, so that the vehicle control unit can perform adaptive adjustment according to the driving mode and energy consumption adjustment information.

[0092] In this embodiment of the invention, the acquisition module 11 is specifically used to obtain raw multi-source information from different sensors of multiple data acquisition units. The raw multi-source information includes: vehicle scene data, vehicle status data, driving behavior data, vehicle environment data, vehicle energy consumption data and / or user preference data in any combination. The raw multi-source information is then subjected to conflict detection and arbitration decision processing to generate multi-source information.

[0093] In this embodiment of the invention, the acquisition module 11 is specifically used to perform conflict detection on two or more original multi-source information representing the same parameter collected by multiple data acquisition units. If the data deviation of the two or more original multi-source information representing the same parameter is greater than a set deviation threshold, arbitration decision processing is performed on the two or more original multi-source information representing the same parameter according to one of the set sensor priority, dynamic weight allocation and / or cross-validation process or any combination thereof, to generate multi-source information.

[0094] In this embodiment of the invention, the acquisition module 11 is specifically used to replace one of the multiple data acquisition units with another data acquisition unit that can represent the same parameter when one of the data acquisition units fails, and to generate multi-source information based on the original multi-source data acquired by the other data acquisition unit.

[0095] In this embodiment of the invention, the acquisition module 11 is specifically used to perform redundancy verification and replacement processing on the camera through the navigation API, radar, and slope sensor when the camera in multiple data acquisition units fails, and generate multi-source information based on the original multi-source data collected by the navigation API, radar, and slope sensor; or, when the radar in multiple data acquisition units fails, to perform redundancy verification and replacement processing on the radar through the navigation API, vehicle speed sensor, and pedal sensor, and generate multi-source information based on the original multi-source data collected by the navigation API, vehicle speed sensor, and pedal sensor; or, when the navigation API in multiple data acquisition units fails, to perform redundancy verification and replacement processing on the navigation API through the camera, radar, and pre-stored POIs, and generate multi-source information based on the original multi-source data collected by the camera, radar, and pre-stored POIs.

[0096] In this embodiment of the invention, the device further includes a construction module 14.

[0097] Module 14 is used to acquire multi-source information of samples collected by various data acquisition units; the random forest algorithm is used to train the multi-source information of the samples based on the Python sklearn library, and the matching relationship between energy consumption and driving mode is output to build an energy consumption and driving mode matching model through the random forest algorithm.

[0098] In this embodiment of the invention, the generation module 12 is specifically used to calculate the multi-source information based on the energy consumption and driving mode matching model to generate a matching relationship between energy consumption and driving mode; and to generate driving mode and energy consumption adjustment information based on the matching relationship between energy consumption and driving mode and the obtained current energy consumption and driving mode.

[0099] The technical solution provided in this invention involves acquiring multi-source information collected by various data acquisition units; inputting this multi-source information into an energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information; and sending this driving mode and energy consumption adjustment information to the vehicle control unit so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information. Through a conflict coordination mechanism among multiple data acquisition units, the multi-source information is ensured to conform to the actual environment, providing reliable input to the energy consumption and driving mode matching model. This improves the matching degree between vehicle energy consumption and driving mode, reduces ineffective energy consumption, and balances energy consumption and driving experience across all scenarios.

[0100] The vehicle energy consumption and driving mode matching device provided in this embodiment of the invention can be used to achieve the above. Figure 1 or Figure 2 The method for matching vehicle energy consumption with driving mode can be described in detail in the above-described embodiment of the method for matching vehicle energy consumption with driving mode, and will not be repeated here.

[0101] This invention provides a storage medium that includes a stored program. When the program runs, it controls the device where the storage medium is located to execute the steps of the above-described vehicle energy consumption and driving mode matching method. For a detailed description, please refer to the above-described vehicle energy consumption and driving mode matching method embodiments.

[0102] This invention provides a vehicle-connected voice communication system assembly, including a memory and a processor. The memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. When the program instructions are loaded and executed by the processor, they implement the steps of the above-described vehicle energy consumption and driving mode matching method. For a detailed description, please refer to the above-described vehicle energy consumption and driving mode matching method.

[0103] Figure 4 This is a schematic diagram of a vehicle-to-everything (V2X) voice communication system assembly provided as an embodiment of the present invention. Figure 4 As shown, the vehicle-to-everything (V2X) voice communication system assembly 20 of this embodiment includes: a processor 21, a memory 22, and a computer program 23 stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program 23, it implements the method for matching vehicle energy consumption and driving mode as described in the embodiment. To avoid repetition, these details are not elaborated here. Alternatively, when the processor 21 executes the computer program, it implements the functions of each model / unit in the vehicle energy consumption and driving mode matching device as described in the embodiment. To avoid repetition, these details are not elaborated here.

[0104] The vehicle-to-everything (V2X) voice communication system assembly 20 includes, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that... Figure 4 This is merely an example of the vehicle-to-everything (V2X) voice communication system assembly 20 and does not constitute a limitation on the V2X voice communication system assembly 20. It may include more or fewer components than shown, or combine certain components, or different components. For example, the V2X voice communication system assembly may also include input / output devices, network access devices, buses, etc.

[0105] The processor 21 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0106] The memory 22 can be an internal storage unit of the vehicle-to-everything (V2X) voice communication system assembly 20, such as a hard drive or RAM within the V2X. The memory 22 can also be an external storage device of the V2X, such as a plug-in hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card installed on the V2X. Furthermore, the memory 22 can include both internal and external storage units of the V2X. The memory 22 is used to store computer programs and other programs and data required by the V2X voice communication system assembly. The memory 22 can also be used to temporarily store data that has been output or will be output.

[0107] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0108] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units 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 an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0109] The units described 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.

[0110] Furthermore, the functional units in the various embodiments of the present invention 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 in the form of hardware plus software functional units.

[0111] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for matching vehicle energy consumption with driving mode, characterized in that, include: Acquire multi-source information collected by various data acquisition units; The multi-source information is input into the energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information. The driving mode and energy consumption adjustment information are sent to the vehicle control unit so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information.

2. The method according to claim 1, characterized in that, The acquisition of multi-source information collected by various data acquisition units includes: Raw multi-source information is obtained from different sensors of multiple data acquisition units, wherein the raw multi-source information includes: any combination of vehicle scene data, vehicle status data, driving behavior data, vehicle environment data, vehicle energy consumption data and / or user preference data; The original multi-source information is subjected to conflict detection and arbitration decision processing to generate multi-source information.

3. The method according to claim 1, characterized in that, The process of performing conflict detection and arbitration decision-making on the original multi-source information to generate multi-source information includes: Conflict detection is performed on two or more original multi-source information representing the same parameter collected by multiple data acquisition units. If the data deviation of the two or more original multi-source information representing the same parameter is greater than a set deviation threshold, arbitration decision processing is performed on the two or more original multi-source information representing the same parameter according to one or any combination of the set sensor priority, dynamic weight allocation and / or cross-validation process, to generate multi-source information.

4. The method according to claim 1, characterized in that, The acquisition of multi-source information collected by various data acquisition units includes: When one of the multiple data acquisition units fails, another data acquisition unit that can represent the same parameter is used as a substitute, and multi-source information is generated based on the original multi-source data obtained from the substitute data acquisition unit.

5. The method according to claim 4, characterized in that, When one of the multiple data acquisition units fails, another data acquisition unit capable of representing the same parameter is used as a replacement, and multi-source information is generated based on the original multi-source data obtained from the replacement data acquisition unit, including: When cameras in multiple data acquisition units fail, redundancy verification and replacement processing are performed on the cameras through the navigation API, radar, and slope sensors. Multi-source information is generated based on the raw multi-source data collected by the navigation API, radar, and slope sensors; or, When radar fails in multiple data acquisition units, redundancy verification and replacement processing are performed on the radar using the navigation API, vehicle speed sensor, and pedal sensor. Multi-source information is generated based on the raw multi-source data collected by the navigation API, vehicle speed sensor, and pedal sensor; or, When the navigation API fails in multiple data acquisition units, the navigation API is redundantly verified and replaced by cameras, radar, and pre-stored POIs. Multi-source information is generated based on the raw multi-source data collected by cameras, radar, and pre-stored POIs.

6. The method according to claim 1, characterized in that, Before calculating the multi-source information based on the energy consumption and driving mode matching model to generate driving mode and energy consumption adjustment information, the following steps are included: Acquire multi-source information from samples collected by various data acquisition units; The random forest algorithm is used to train the multi-source information of the samples based on the Python sklearn library, and the matching relationship between energy consumption and driving mode is output to build an energy consumption and driving mode matching model through the random forest algorithm.

7. The method according to claim 6, characterized in that, The step of inputting the multi-source information into the energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information includes: The multi-source information is calculated based on the energy consumption and driving mode matching model to generate the matching relationship between energy consumption and driving mode. Based on the matching relationship between energy consumption and driving mode and the obtained current energy consumption and driving mode, driving mode and energy consumption adjustment information is generated.

8. A vehicle energy consumption and driving mode matching device, characterized in that, include: The acquisition module is used to acquire multi-source information collected by various data acquisition units; The generation module is used to input the multi-source information into the energy consumption and driving mode matching model to obtain driving mode and energy consumption adjustment information. The sending module is used to send driving mode and energy consumption adjustment information to the vehicle control unit, so that the vehicle control unit can perform adaptive adjustments based on the driving mode and energy consumption adjustment information.

9. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the storage medium to perform the vehicle energy consumption and driving mode matching method according to any one of claims 1 to 7.

10. A vehicle-connected voice communication system assembly, comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that, When the program instructions are loaded and executed by the processor, they implement the steps of the vehicle energy consumption and driving mode matching method according to any one of claims 1 to 7.

Images