Vehicle power utilization strategy reminding method and device, computer equipment and storage medium

Abstract

The invention relates to the field of intelligent automobiles, and discloses a vehicle power utilization strategy reminding method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining power utilization data, including basic energy consumption, driving behaviors and navigation travel data, of a target vehicle in a driving process; according to the power consumption data, whether the power consumption data of the target vehicle meets a travel demand or not is predicted, when the travel demand is not met, the priority of power consumption scenes is divided based on the basic energy consumption data, the driving behavior data and the navigation travel data, and the power consumption scenes comprise vehicle driving, driving behaviors and vehicle-mounted function scenes; generating a vehicle driving strategy, a driving behavior strategy and a vehicle-mounted function adjustment strategy based on the priority of the power consumption scene; and executing reminding operation according to the vehicle driving strategy, the driving behavior strategy and the vehicle-mounted function adjustment strategy. The problems of inaccurate dynamic electric quantity prediction and lack of multi-scene energy consumption hierarchical control caused by static threshold early warning and single-dimensional analysis in a vehicle electric quantity early warning technology are solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicles, and particularly to a reminder method, device, computer device and storage medium for vehicle power consumption strategies. Background Art

[0002] With the intelligent development of new energy vehicles, power management has become the core technical direction for improving user experience. Existing technologies mainly trigger low-power reminders through preset thresholds. For example, when the remaining battery power is lower than a fixed percentage, a warning or a recommended charging station is triggered. Although such solutions can achieve basic warning functions, they have two major limitations: First, the static threshold setting cannot adapt to the dynamic driving behaviors of users and the real-time itinerary requirements, and false alarms or missed alarms are likely to occur; Second, the single-dimensional power monitoring lacks in-depth analysis of the power consumption characteristics of vehicles in multiple scenarios, and it is difficult to implement differential energy-saving control strategies for different power consumption scenarios. In complex vehicle usage scenarios, users often face compound problems such as the mismatch between the remaining navigation mileage and the power consumption rate, the aggravation of power consumption due to driving behaviors, and excessive power consumption of in-vehicle functions. Traditional methods are difficult to provide accurate solutions.

[0003] In the prior art, the power management scheme only realizes early warning by comparing the remaining power with a fixed threshold. It neither integrates the real-time driving behavior characteristics of users and navigation itinerary data for dynamic prediction, nor establishes a priority evaluation system for multi-dimensional power consumption scenarios. This results in the system being unable to actively identify high-power consumption risk scenarios, and lacking the ability to generate hierarchical control strategies based on the scenario priorities, causing problems such as delayed warnings, misalignment between the recommended charging stations and the actual needs, and rough energy-saving control in emergency scenarios, ultimately exacerbating users' power consumption anxiety. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a reminder method, device, computer device and storage medium for vehicle power consumption strategies to solve the problems of inaccurate dynamic power prediction and lack of hierarchical control of multi-scenario energy consumption caused by static threshold early warning and single-dimensional analysis in traditional vehicle power early warning technologies.

[0005] In a first aspect, an embodiment of the present invention provides a reminder method for vehicle power consumption strategies, the method comprising:

[0006] Obtaining power consumption data of a target vehicle during driving, wherein the power consumption data includes basic energy consumption data, driving behavior data, and navigation itinerary data;

[0007] Predicting whether the power consumption data of the target vehicle meets the itinerary requirements according to the power consumption data, and when it does not meet the itinerary requirements, dividing the priorities of power consumption scenarios based on the basic energy consumption data, the driving behavior data, and the navigation itinerary data, wherein the power consumption scenarios include vehicle driving scenarios, driving behavior scenarios, and in-vehicle function scenarios;

[0008] Generate a vehicle driving strategy, a driving behavior strategy, and an in-vehicle function adjustment strategy based on the priority of the power consumption scenario;

[0009] Perform corresponding reminder operations according to the vehicle driving strategy, the driving behavior strategy, and the in-vehicle function adjustment strategy.

[0010] Further, predicting whether the power consumption data of the target vehicle meets the trip demand according to the power consumption data includes:

[0011] Obtain the remaining mileage in the navigation trip data and the historical energy consumption data in the basic energy consumption data;

[0012] Calculate the initial power consumption according to the remaining mileage and the historical energy consumption data, and correct the initial power consumption by using the abnormal energy consumption coefficient in the driving behavior data to obtain the predicted power consumption;

[0013] When the predicted power consumption exceeds the remaining power in the basic energy consumption data, determine that the power consumption data of the target vehicle does not meet the trip demand.

[0014] Further, dividing the priority of the power consumption scenario based on the basic energy consumption data, the driving behavior data, and the navigation trip data includes:

[0015] Obtain the original priority corresponding to each power consumption scenario;

[0016] Adjust the original priority based on the basic energy consumption data, the driving behavior data, and the navigation trip data to obtain the priority of each power consumption scenario;

[0017] Among them, the priority adjustment strategy of the power consumption scenario includes:

[0018] When the remaining power in the basic energy consumption data is lower than the predicted power consumption, lock the priority of the vehicle driving scenario as the first priority;

[0019] Obtain the road condition congestion index in the navigation trip data and the braking frequency in the driving behavior data. When the road condition congestion index and the braking frequency reach the preset conditions, increase the priority of the driving behavior scenario;

[0020] Monitor the descending gradient of the remaining power in the basic energy consumption data, and reduce the priority of the in-vehicle function scenario according to the descending gradient until all in-vehicle functions in the in-vehicle function scenario are turned off.

[0021] Further, generating a vehicle driving strategy, a driving behavior strategy, and an in-vehicle function adjustment strategy based on the priority of the power consumption scenario includes:

[0022] For the vehicle driving scenario, determine a preset charging range according to the priority of the vehicle driving scenario, determine a list of charging stations based on the preset charging range, and construct a vehicle driving strategy using the list of charging stations;

[0023] For the driving behavior scenario, determine a driving parameter range according to the priority of the driving behavior scenario, and construct a driving behavior strategy using the driving parameter range;

[0024] For the in-vehicle function scenario, determine at least one restriction instruction for the in-vehicle function according to the priority of the in-vehicle function scenario, and construct an in-vehicle function adjustment strategy using the restriction instruction.

[0025] Further, the determining the list of charging stations according to the preset charging range includes:

[0026] Decompose the navigation path in the navigation trip data into a sequence of continuous road segments;

[0027] Query multiple candidate charging stations within the preset charging range of the navigation path, and generate a charging path corresponding to the candidate charging station;

[0028] Calculate the number of overlapping road segments between each charging path and the navigation path, and sort the charging paths according to the number of overlapping road segments to obtain a list of charging stations.

[0029] Further, the performing corresponding reminder operations according to the vehicle driving strategy, the driving behavior strategy, and the in-vehicle function adjustment strategy includes:

[0030] Generate a first reminder message according to multiple restriction instructions in the in-vehicle function adjustment strategy;

[0031] Obtain the current driving data of the target vehicle, and determine whether the current driving data meets the driving parameter range in the vehicle driving strategy to obtain a judgment result, and generate a second reminder message according to the judgment result;

[0032] Select a target charging station from the list of charging stations in the vehicle driving strategy, and generate a third reminder message according to the charging path corresponding to the target charging station;

[0033] Perform the playback operation of the first reminder message, the second reminder message, and the third reminder message.

[0034] Further, after performing the corresponding reminder operations according to the in-vehicle function adjustment strategy and the vehicle driving strategy, the method further includes:

[0035] Monitor the deviation value between the actual power consumption and the predicted power consumption of the target vehicle during driving;

[0036] If the deviation value exceeds the preset deviation value, trigger a policy update mechanism to re-prioritize the power consumption scenarios and adjust the vehicle driving policy, the driving behavior policy, and the in-vehicle function adjustment policy;

[0037] After the remaining power of the target vehicle reaches the preset power threshold, adjust the in-vehicle functions on the target vehicle to the original configuration state.

[0038] In a second aspect, an embodiment of the present invention provides a reminder device for a vehicle power consumption strategy, and the device includes:

[0039] An acquisition module, configured to acquire power consumption data of a target vehicle during driving, where the power consumption data includes basic energy consumption data, driving behavior data, and navigation itinerary data;

[0040] A prediction module, configured to predict whether the power consumption data of the target vehicle meets the itinerary requirements according to the power consumption data. When the itinerary requirements are not met, prioritize the power consumption scenarios based on the basic energy consumption data, the driving behavior data, and the navigation itinerary data, where the power consumption scenarios include a vehicle driving scenario, a driving behavior scenario, and an in-vehicle function scenario;

[0041] A generation module, configured to generate a vehicle driving policy, a driving behavior policy, and an in-vehicle function adjustment policy based on the priorities of the power consumption scenarios;

[0042] An execution module, configured to perform corresponding reminder operations according to the vehicle driving policy, the driving behavior policy, and the in-vehicle function adjustment policy.

[0043] In a third aspect, an embodiment of the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the method according to the first aspect or any corresponding implementation manner thereof.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the method according to the first aspect or any corresponding implementation manner thereof.

[0045] The method provided by the embodiments of the present application has the following beneficial effects:

[0046] The method provided by the embodiments of this application realizes multi-dimensional dynamic power consumption monitoring by obtaining basic energy consumption data, driving behavior data, and navigation trip data in real time, breaks through the dependence on a single threshold, and improves the comprehensiveness of data coverage; predicts the matching degree between vehicle power and trip demand based on multi-source data fusion, accurately identifies the power gap, and divides the priorities of vehicle driving scenarios, driving behavior scenarios, and in-vehicle function scenarios to solve the misjudgment problem of static early warning; generates a differential control strategy through scenario priorities, optimizes route planning in the vehicle driving strategy, guides energy-saving operations in the driving behavior strategy, and intelligently shuts down unnecessary loads in the in-vehicle function adjustment strategy to achieve hierarchical and accurate energy consumption control; finally, executes multi-modal reminder operations, actively pushes charging station recommendations, driving suggestions, and function adjustment instructions to users, completes the closed-loop management from dynamic early warning to scenario-based intervention, significantly improves the intelligent level of power management, and effectively alleviates users' range anxiety. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0048] Figure 1 is a flowchart of a reminder method for a vehicle power consumption strategy according to an embodiment of the present invention;

[0049] Figure 2 is a schematic diagram of a predefined scenario priority mapping table according to an embodiment of the present invention;

[0050] Figure 3 is a schematic diagram of the system processing flow of a vehicle power consumption strategy reminder system according to an embodiment of the present invention;

[0051] Figure 4 is a schematic diagram of the cross-platform service interaction process of a vehicle power consumption strategy reminder system according to an embodiment of the present invention;

[0052] Figure 5 is a structural block diagram of a reminder device for a vehicle power consumption strategy according to an embodiment of the present invention;

[0053] Figure 6 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0055] According to an embodiment of the present invention, there is provided a reminder method, device, computer device, and storage medium for a vehicle power consumption strategy. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0056] In this embodiment, a reminder method for a vehicle power consumption strategy is provided. Figure 1 It is a flowchart of a reminder method for a vehicle power consumption strategy according to an embodiment of the present invention. As Figure 1 shown, the process includes the following steps:

[0057] Step S11, obtaining power consumption data of a target vehicle during driving, where the power consumption data includes basic energy consumption data, driving behavior data, and navigation itinerary data.

[0058] In the embodiments of the present application, multi-dimensional dynamic data streams in the vehicle driving scenario are collected in real time through an in-vehicle sensor network. Among them, the basic energy consumption data is extracted through the battery management system (BMS) and the vehicle controller area network (CAN) bus, including the remaining power of the power battery (SOC), the real-time power consumption curves of each subsystem (drive motor, air conditioner compressor, in-vehicle entertainment host), and the historical energy consumption trends. The driving behavior data is captured through acceleration sensors, brake pressure sensors, and in-vehicle cameras, covering quantization indexes such as the change rate of the accelerator pedal opening, the braking frequency, and the average vehicle speed deviation value. At the same time, combined with the lane keeping state and following distance data output by the ADAS system, an abnormal driving mode recognition map for sudden acceleration and sudden braking is constructed. The navigation trip data obtains structured path information through the vehicle navigation system interface, including the real-time remaining mileage, the heat map of the slope distribution of the planned path, the traffic congestion index matrix, and the POI topology data of charging stations along the way, and synchronously receives the correction parameters of the energy consumption prediction model for dynamic road condition events (such as construction sections, accident points) sent from the cloud. After the above three types of data are aligned by time stamps, a multi-dimensional feature vector is formed. Among them, the basic energy consumption data uses a sliding window mechanism to achieve second-level updates, the driving behavior data reduces the system load through event-triggered acquisition, and the navigation data establishes a long connection channel with a high-precision map service provider to ensure the freshness of information, providing a holographic data basis for subsequent scenario-based power prediction.

[0059] Step S12, predict whether the power consumption data of the target vehicle meets the trip requirements according to the power consumption data. When the trip requirements are not met, prioritize the power consumption scenarios based on the basic energy consumption data, driving behavior data, and navigation trip data. Among them, the power consumption scenarios include vehicle driving scenarios, driving behavior scenarios, and in-vehicle function scenarios.

[0060] In the embodiments of the present application, predicting whether the power consumption data of the target vehicle meets the trip requirements according to the power consumption data includes the following steps A1 - A3:

[0061] Step A1, obtain the remaining mileage in the navigation trip data and the historical energy consumption data in the basic energy consumption data.

[0062] Specifically, by parsing the structured path information output by the in-vehicle navigation system, the remaining mileage is extracted (such as 50 kilometers remaining to the destination), and at the same time, historical energy consumption characteristic data is retrieved from the vehicle battery management system (BMS) and the historical energy consumption database. The historical energy consumption data includes: the average energy consumption per unit mileage based on different road conditions (urban / highway / mountainous) (such as 15 kWh / 100 km in the urban area, 18 kWh / 100 km on the highway), the energy consumption curve in the time dimension (such as a 20% increase in energy consumption during the morning and evening rush hours), and the energy consumption baseline of the subsystem (such as the typical power consumption of the air conditioning system in summer is 2 kW). In addition, combined with the slope data of the high-precision map (such as a 3% continuous uphill section is included in the planned path), the historical energy consumption benchmark value is dynamically corrected to form a scenario-based energy consumption reference model.

[0063] Step A2, calculate the initial power consumption according to the remaining mileage and the historical energy consumption data, and correct the initial power consumption using the abnormal energy consumption coefficient in the driving behavior data to obtain the predicted power consumption.

[0064] Specifically, based on the remaining mileage (L = 50 km) and the scenario-based historical energy consumption benchmark (E base = 18 kWh / 100 km), calculate the initial power consumption E initial = L × E base / 100 = 9 kWh. Further introduce the abnormal energy consumption coefficient K in the driving behavior data (calculated by real-time monitoring of indicators such as the change rate of the accelerator pedal opening Δα, the braking frequency F brake etc., for example, when Δα > 30% / s, a rapid acceleration mark is triggered, and when F brake > 5 times / minute, a frequent braking mark is triggered, and comprehensively obtain K = 1.15). The predicted power consumption E predict = E initial × K = 9 × 1.15 = 10.35 kWh. At the same time, if the navigation data detects a traffic congestion event (congestion index ≥ 70) 5 kilometers ahead, then superimpose the road condition correction factor β = 1.2, so that E predict is further adjusted to 10.35 × 1.2 = 12.42 kWh, realizing power prediction in a dynamic environment.

[0065] Step A3, when the predicted power consumption exceeds the remaining power in the basic energy consumption data, determine that the power consumption data of the target vehicle does not meet the travel requirements.

[0066] Specifically, compare the predicted power consumption E predict (12.42 kWh) with the real-time remaining power E remain (10 kWh) reported by the BMS. If E predict > E remain(12.42 > 10), it is determined that the current vehicle power cannot meet the travel demand, and a power shortage risk warning is triggered. This judgment introduces a fault tolerance threshold γ (e.g., γ = 5%), when E remain ≥ E predict × (1 - γ) (i.e., the remaining power ≥ 11.8 kWh), only a mild prompt is given; when E remain < E predict × (1 - γ), then an emergency intervention process is started. At the same time, the system continuously monitors the power decay rate (e.g., a decrease of 0.2 kWh per minute), and dynamically updates the E predict value to achieve rolling prediction.

[0067] The method provided by the embodiment of the present application constructs a dynamic power prediction baseline by obtaining the remaining mileage and historical energy consumption data in the navigation itinerary in real time, breaks through the limitations of the traditional fixed threshold model, and improves the accuracy of power gap identification; by introducing the abnormal energy consumption coefficient in the driving behavior data to dynamically correct the initial power consumption, it realizes the coupled calculation of the user's personalized driving mode and real-time road conditions, and solves the problem of the disconnection between static energy consumption prediction and actual driving scenarios; finally, through the intelligent comparison of the predicted power consumption and the remaining power, a hierarchical early warning trigger mechanism is established, and an early warning is actively triggered before the power gap reaches the critical value, effectively avoiding the power shortage risk caused by delayed judgment in the traditional scheme, and upgrading the power management from passive response to active predictive control.

[0068] In the embodiment of the present application, the priorities of power consumption scenarios are divided based on basic energy consumption data, driving behavior data, and navigation itinerary data, including the following steps B1 - B2:

[0069] Step B1, obtain the original priorities corresponding to each power consumption scenario.

[0070] Specifically, the initial scenario weights are loaded through a predefined scenario priority mapping table (vehicle driving power P0, driving habits P1, in - vehicle system P2). The original priorities are divided based on the necessity of vehicle basic functions: the vehicle driving scenario (drive system, path planning) is set as the highest priority (P0) because it directly affects the achievement of the cruising range; the driving behavior scenario (sharp acceleration / braking) has a secondary sensitivity to energy consumption fluctuations (P1); the in - vehicle function scenario (air conditioner, entertainment system) is set as the lowest (P2) as a non - core load. This mapping table is stored in the in - vehicle system ROM, supports dynamic update strategies (such as temporarily increasing the priority of the air conditioner in rainy weather), and reads the list of currently activated scenario types in real time through the vehicle state machine.

[0071] As an example, such as Figure 2As shown in the figure, it is a predefined scenario priority mapping table. Specifically, when the vehicle is running on electricity (P0), the power-consuming functions are to overcome rolling resistance, air resistance, etc. The low-battery strategy recommends selecting an appropriate vehicle speed (such as reducing the speed in a high-speed scenario) and choosing a charging station from the service candidate set. Voice announcements are made to prompt reducing the vehicle speed or providing information about the charging station ahead; in the case of in-vehicle system power consumption (P2), for internal electrical appliances (such as lighting, audio, etc.), it is recommended to turn off non-essential functions (such as in-vehicle video, music) when the battery is low. Voice prompts are given to turn off entertainment functions. For the air-conditioning system, it is recommended to turn it off or turn it down while ensuring the temperature (such as setting it to 26°C in summer and turning it off according to the clothing situation in winter). Voice prompts are given to adjust the temperature or turn off the air conditioner; under the influence of driving habits and road conditions (P1), for the power consumption problems caused by rapid acceleration and sudden braking, "smooth" driving is recommended, and voice prompts are given to reduce such operations to maintain the battery power.

[0072] Step B2: Adjust the original priorities based on the basic energy consumption data, driving behavior data, and navigation itinerary data to obtain the priorities of each power-consuming scenario.

[0073] In the embodiment of the present application, the priority adjustment strategy for power-consuming scenarios includes steps B21 - B23:

[0074] Step B21: When the remaining battery power in the basic energy consumption data is lower than the predicted power consumption, lock the priority of the vehicle driving scenario as the first priority.

[0075] Specifically, when the remaining battery power (SOC = 15%) is lower than the predicted power consumption (E predict = 18%), trigger the emergency power management mode: forcibly raise the priority of the vehicle driving scenario to P0 and it cannot be downgraded. Specifically, use the hard interrupt mechanism to preempt computing resources, suspend the priority calculation threads of other scenarios, and activate the real-time energy consumption recalculation module for the navigation path. For example, if the remaining battery power only supports driving 30 kilometers while the remaining distance of the planned path is 50 kilometers, immediately call the charging station retrieval algorithm, expand the search for charging piles within a radius of 5 kilometers on the navigation path (breaking through the original calibration range of 1 - 10 KM), and at the same time freeze the power consumption strategy adjustment permission of the in-vehicle entertainment system to ensure that all computing resources are concentrated on path replanning and charging station matching.

[0076] Step B22: Obtain the traffic congestion index in the navigation itinerary data and the braking frequency in the driving behavior data. When the traffic congestion index and the braking frequency reach the preset conditions, raise the priority of the driving behavior scenario.

[0077] Specifically, extract the road congestion index from the navigation data (such as the 0-100 score provided by the map, and ≥75 is defined as severe congestion), and combine it with the braking pedal action frequency collected by the CAN bus (for example, 3 emergency brakes are triggered within 10 seconds). When both jointly trigger the threshold (congestion index ≥75 and braking frequency ≥0.3 times / second), the priority of the driving behavior scenario dynamically rises from P1 to P0.5 (between P0 and P1). At this time, start the driving behavior correction mode: by shortening the driving behavior monitoring period to 200 ms (originally 1 second), calculate the acceleration pedal gradient change rate (dα / dt) in real time. If 5 consecutive rapid accelerations (dα / dt > 40% / s) are detected, immediately generate a voice prompt and limit the motor torque output to the steady driving mode (for example, limit the acceleration not to exceed 0.3g).

[0078] Step B23, monitor the descending gradient of the remaining power in the basic energy consumption data, and reduce the priority of the in-vehicle function scenario according to the descending gradient until all in-vehicle functions in the in-vehicle function scenario are turned off.

[0079] Specifically, calculate the remaining power descending gradient ΔSOC / Δt through the sliding window algorithm (for example, it drops 0.5% per minute). When ΔSOC / Δt exceeds the preset threshold (such as 0.3% / minute), reduce the priority of the in-vehicle function scenario in stages according to the gradient value:

[0080] Gradient 0.3 - 0.5% / minute: downgrade P2 to P2.5, and turn off non-essential functions such as the ambient light and seat massage;

[0081] Gradient 0.5 - 1% / minute: further downgrade to P3, and force the air conditioner to enter the energy-saving mode (temperature floating range ±2°C);

[0082] Gradient >1% / minute: completely turn off the in-vehicle entertainment system (including the backlight of the central control screen), and only retain the minimum safe power consumption load.

[0083] This process introduces a hysteresis filtering algorithm to avoid false triggering caused by short-term power fluctuations. The downgrade operation is only executed when the gradient value exceeds the limit for 10 consecutive seconds, and the downgraded state is marked by a red flash on the HMI interface.

[0084] The method provided in the embodiment of the present application establishes a basic control framework by pre-defining the original priority of the scene, and combines multi-dimensional dynamic data such as the remaining power, road congestion index and braking frequency to achieve real-time adaptive adjustment of the scene priority; when the remaining power is lower than the predicted value, the vehicle driving scene is forced to be locked as the highest priority to ensure the priority of the core endurance; based on the composite conditions of the congestion index and the braking frequency, the driving behavior scene priority is improved, and high-energy consumption driving behavior is optimized in a targeted manner; by monitoring the power decline gradient, the vehicle function scene is dynamically downgraded, and non-essential loads are gradually turned off to form a progressive energy-saving control strategy. This dynamic adjustment mechanism with multi-factor linkage effectively solves the problem of rigid energy consumption control caused by the solidification of scene priorities in traditional solutions.

[0085] Step S13, generating a vehicle travel strategy, a driving behavior strategy, and a vehicle function adjustment strategy based on the priority of the power consumption scenarios.

[0086] In the embodiment of the present application, step S13 includes the following steps C1-C3:

[0087] Step C1, for the vehicle driving scenario, determine the preset charging range according to the priority of the vehicle driving scenario, determine the charging station list according to the preset charging range, and use the charging station list to build a vehicle driving strategy.

[0088] In the embodiment of the present application, determining a list of charging stations according to a preset charging range includes the following steps C11-C13:

[0089] Step C11, decomposing the navigation path in the navigation trip data into a sequence of continuous road segments.

[0090] Specifically, through the path topology parsing algorithm of the high-precision map, the planned path in the navigation trip data (such as a 50-kilometer route from A to B) is cut into continuous segment units (Segments), and each segment is defined by the latitude and longitude coordinates of the starting / end point, the length of the segment, the slope value, the number of lanes and other attributes. For example, a highway can be decomposed into an entrance ramp (500 meters, a slope of 3%), a straight section of the main road (5 kilometers, a slope of 0%), a curve section (2 kilometers, a slope of -1%), etc. The decomposition process adopts a dynamic window mechanism, and dynamically adjusts the segment boundaries in combination with real-time road conditions (such as construction areas) to ensure that each segment has independent road condition energy consumption evaluation conditions. The decomposed segment sequence forms a segment list for subsequent charging station matching algorithm calls.

[0091] Step C12, querying the navigation path for multiple candidate charging stations within a preset charging range, and generating charging paths corresponding to the candidate charging stations.

[0092] Specifically, based on the continuous road segment sequence, with the midpoint of each road segment as the center, a spatial search buffer is generated according to a preset charging range radius (such as 5 kilometers). The charging pile POI database of the self-built charging platform and third-party services is called, and the charging stations within the coverage are quickly retrieved through a spatial index (R-tree). For each candidate charging station, a path planning engine (such as the Dijkstra algorithm) is called to generate a charging path from the current road segment to the charging station, and the path attributes include driving distance, estimated time, number of traffic lights, etc. For example, 3 charging stations are retrieved on the highway section, and the corresponding off-ramp detour paths (2 kilometers) and service area direct connection paths (0.5 kilometers) are generated respectively, and the charging paths are bound to the road segment nodes of the original navigation path.

[0093] Step C13, calculate the number of overlapping road segments between each charging path and the navigation path, and sort the charging paths according to the number of overlapping road segments to obtain a list of charging stations.

[0094] Specifically, perform geometric overlap analysis on the charging path of each candidate charging station and the original navigation path: use a GPS trajectory point sequence matching algorithm (such as Hausdorff distance calculation) to count the number of co-linear road segments within a 500-meter accuracy range of the two paths (such as 80% overlap between the charging path and the navigation path). Sort by the overlap rate from high to low, and preferentially retain charging stations that are completely co-linear (such as service area charging stations) or have a high overlap rate (detour <1 kilometer). For example, the charging path of charging station A is co-linear with 4 road segments of the navigation path (overlap rate 90%), and the charging path of charging station B detours 3 road segments (overlap rate 60%), then A is ranked higher than B. Finally, a list of charging stations (Top1-TopN) is generated with co-linearity first and distance second, as the core input of the vehicle driving strategy.

[0095] The method provided by the embodiment of the present application uses a high-precision path topology decomposition technology to cut the navigation path into continuous road segment units, combines a spatial index algorithm to quickly match candidate charging stations within a preset charging range; adopts geometric overlap analysis of the charging path and the original path to accurately count the number of co-linear road segments and generate a priority ranking; optimizes the charging station list generation logic through a dynamic weight distribution mechanism, so that the recommendation result takes into account both the path convenience and reachability. This path-driven charging station matching algorithm has significantly improved the recommendation accuracy compared with the traditional Euclidean distance screening method.

[0096] Step C2, for the driving behavior scenario, determine the driving parameter range according to the priority of the driving behavior scenario, and construct a driving behavior strategy using the driving parameter range.

[0097] Specifically, according to the priority of the driving behavior scenario (such as P1), load dynamic parameter thresholds from the driving behavior knowledge base: Acceleration limit: When the scenario priority ≥ P1, limit the motor output torque so that the acceleration ≤ 0.25g (the normal mode is 0.35g); Braking frequency monitoring: If the number of hard brakes within 10 seconds ≥ 2 times, trigger a voice prompt and activate the kinetic energy recovery intensity to automatically increase to the highest gear; Cruise speed recommendation: Based on real-time road conditions (such as smooth / congested) and slope data, calculate the optimal economic speed (such as 90 km / h recommended for flat highways), and write it to the instrument panel display and voice broadcast through the CAN bus. The strategy construction adopts fuzzy control rules. For example, "IF the power gap > 20% AND the driving style = aggressive THEN the speed limit value = recommended speed × 0.9", to ensure that the strategy is dynamically adapted to the risk level.

[0098] Step C3, for the in-vehicle function scenario, determine at least one restriction instruction for the in-vehicle function according to the priority of the in-vehicle function scenario, and construct an in-vehicle function adjustment strategy using the restriction instruction.

[0099] Specifically, according to the downgraded state of the in-vehicle function scenario (such as P2→P2.5), call the hierarchical control instruction from the policy rule library: P2-level restriction: Turn off the ambient light and seat ventilation, and reduce the brightness of the central control screen to 50%; P2.5-level restriction: Force the air conditioner to enter the constant temperature mode (26°C ± 2°C in summer, 18°C ± 2°C in winter), and temporarily stop the in-vehicle video playback; P3-level restriction: Completely turn off the entertainment system, only retain the core navigation function, and switch the air conditioner to the external circulation natural wind. The instruction is sent through the API interface of the vehicle domain controller (such as the body control module BCM and the entertainment system host). For example, call SetAcPowerLevel(ECO_MODE) through the SWC component of the AutoSAR architecture, and verify the function status through the diagnostic protocol (UDS) after execution to ensure that the policy takes effect.

[0100] The method provided by the embodiments of the present application realizes precise energy consumption control through a sub-scenario differential strategy generation mechanism: For the vehicle driving scenario, dynamically expand the charging station search radius based on the priority and optimize the path matching logic to ensure that the charging station recommendation highly matches the user's itinerary; For the driving behavior scenario, set hierarchical speed limit thresholds and acceleration control curves in combination with the priority, and write the control parameters to the vehicle in real time through the CAN bus; For the in-vehicle function scenario, generate a function shutdown instruction chain according to the priority, and ensure the reliable execution of the instruction through the AutoSAR architecture. This scenario decoupled strategy generation mode significantly improves the refinement level of the vehicle's power management.

[0101] Step S14, perform corresponding reminder operations according to the vehicle driving strategy, driving behavior strategy, and in-vehicle function adjustment strategy.

[0102] In the embodiment of the present application, step S14 includes the following steps D1-D4:

[0103] Step D1, generating first reminder information according to multiple restriction instructions in the vehicle function adjustment strategy.

[0104] Specifically, the restriction instruction is converted into structured voice text through the natural language generation (NLG) engine. For example, when the vehicle function adjustment strategy requires turning off the air conditioner, the predefined voice template library (such as the "it is recommended to turn off the air conditioner" template) is called, and the real-time parameters (such as the current temperature of 26°C) are dynamically inserted to generate voice text: "The power is tight. It is recommended to adjust the air conditioner temperature from 24°C to 26°C to save energy. Please say "OK" to confirm the adjustment." At the same time, a visual prompt card is generated through the vehicle HMI (human-machine interface), showing the restricted function icon (such as the gray air conditioner icon) and the estimated power saving value (such as "turning off the air conditioner can increase the range by 5 kilometers"). The voice command is bound to the vehicle control bus (CAN). If the user confirms it by voice, the HVAC_SetTemperature(26) service is called through the RTE layer of the AutoSAR architecture to realize the closed-loop control of the function.

[0105] Step D2, obtaining the current driving data of the target vehicle, and determining whether the current driving data meets the driving parameter range in the vehicle driving strategy, obtaining a determination result, and generating a second reminder message according to the determination result.

[0106] Specifically, the vehicle driving data (such as vehicle speed, acceleration, and motor power) is collected from the CAN bus in real time and matched with the parameter range in the driving behavior strategy: if the strategy requires an economic speed of 90km / h, and the actual vehicle speed is 110km / h, the speeding ratio (22.2%) is calculated, and a graded prompt is triggered (when the speeding is ≤20%, the prompt is "appropriate speed reduction", and when it is >20%, the warning is "immediately reduce speed to 90km / h"); when the vehicle is in sports mode, if the power gap is detected to be more than 15%, a strong intervention prompt is generated: "Insufficient power, it is recommended to switch to ECO mode", and the driving mode is forced to switch through the gateway controller (GW) (write DrivingMode = ECO). The judgment result outputs a confidence score (such as a speeding risk score of 85 / 100) through a fuzzy logic algorithm, driving the voice assistant to use different broadcast intensities (the warning-level voice speeds up to 1.5 times the normal rate).

[0107] Step D3, selecting a target charging station from the list of charging stations in the vehicle driving strategy, and generating third reminder information according to the charging path corresponding to the target charging station.

[0108] Specifically, extract the top 1 candidate charging station from the charging station list and call the map API to generate navigation guidance information: decompose the charging route into a sequence of steering instructions (such as "exit the highway 2 kilometers ahead on the right and enter the service area"), and overlay it with real-time traffic conditions (such as "congestion at the exit, expected delay 3 minutes"); integrate third-party platform data to generate voice text: "It is recommended to go to charging station X, with 4 remaining idle charging piles, a fast charging power of 120 kW, an electricity price of 1.2 yuan / kWh, and the remaining battery power is expected to be 12% after arrival". At the same time, obtain the real-time status of the charging pile through V2X communication (such as the fault information of the pile group). If the top 1 station is unavailable, immediately switch to the top 2 and trigger a voice update: "The target charging station is busy, and the next station has been optimally selected for you".

[0109] Step D4, perform the playback operations of the first reminder message, the second reminder message, and the third reminder message.

[0110] Specifically, adopt a hierarchical broadcast strategy: Voice channel: Synthesize a voice stream through the TTS engine. High-priority reminders (such as charging station recommendations) are broadcast in full duplex (can interrupt the current media playback), and low-priority prompts (such as air conditioner adjustment) are output in a background sound noise reduction mode; Visual channel: Display the three types of reminder information (function limit red warning box, speed suggestion green floating bar, charging station navigation thumbnail) in different areas on the instrument panel and the central control screen, and detect the driver's gaze area through eye tracking technology to dynamically adjust the information layout; Tactile channel: For emergency reminders (such as the battery power is lower than 5%), enhance the warning through the steering wheel vibration module (frequency 10 Hz) and the seat belt pretensioner pulse tightening (force 3 N). Record the user feedback during the broadcast process (such as voice refusal to turn off the air conditioner) and upload it to the cloud in real time through DDS (Data Distribution Service) for optimizing the generation of subsequent strategies.

[0111] The method provided by the embodiment of the present application realizes hierarchical reminders through multi-modal interaction channels: Generate structured voice instructions based on the in-vehicle function adjustment strategy and achieve natural semantic broadcast through the TTS engine; Compare the vehicle driving data with the strategy parameter range in real time to trigger visual warning icons and voice strong reminders; Combine the charging station path coincidence degree to optimize the target station and generate navigation guidance information with real-time traffic conditions. This multi-channel collaborative reminder mechanism of voice, vision, and touch improves the user response rate compared with the single reminder method and effectively guarantees the execution effect of the strategy.

[0112] In the embodiment of the present application, after performing the corresponding reminder operations according to the in-vehicle function adjustment strategy and the vehicle driving strategy, the method further includes steps E1 - E3:

[0113] Step E1, monitor the deviation value between the actual power consumption and the predicted power consumption of the target vehicle during driving.

[0114] Specifically, the actual discharge curve of the power battery is collected in real time by the in-vehicle battery management system (BMS) (e.g., recording the SOC change value every minute), and is time-aligned with the theoretical power consumption output by the prediction model. The root mean square error (RMSE) of the deviation between the two is calculated using a sliding window algorithm (window length 5 minutes, step size 1 second). For example, when the actual SOC drops faster than the prediction by 0.5% / minute, the deviation value Δ = (actual value - predicted value) / predicted value × 100% = 15% is triggered. At the same time, Kalman filtering is introduced to suppress sensor noise and ensure the stability of deviation calculation. The deviation data is uploaded to the cloud through the in-vehicle T-Box for triggering the dynamic correction of subsequent strategies.

[0115] Step E2, if the deviation value exceeds the preset deviation value, trigger the policy update mechanism, re-divide the priority of the power consumption scenarios, and adjust the vehicle driving strategy, driving behavior strategy, and in-vehicle function adjustment strategy.

[0116] Specifically, when Δ exceeds the preset threshold for 10 seconds (e.g., Δ≥20%), it is determined that the current policy fails, and multi-dimensional data re-calculation is started: extract data such as the acceleration pedal opening gradient (dα / dt) and braking frequency in the latest 5 minutes from the CAN bus, and re-calculate the abnormal energy consumption coefficient K (e.g., corrected from 1.1 to 1.3); call the real-time traffic flow data of the navigation (e.g., the congestion index rises to 80), superimpose it on the energy consumption prediction model, and generate a correction factor β = 1.25; based on the updated K and β values, re-execute the priority adjustment process of the power consumption scenarios. For example, due to aggressive driving, the priority of the in-vehicle function scenario drops from P2.5 to P3, and more non-essential loads are forcibly turned off. The updated policy is sent to the vehicle end through OTA, and a "Policy has been optimized" prompt is displayed on the human-machine interface.

[0117] Step E3, after the remaining power of the target vehicle reaches the preset power threshold, adjust the in-vehicle functions on the target vehicle to the original configuration state.

[0118] Specifically, when the BMS detects that the SOC rises back to the safety threshold (e.g., ≥20%), start the progressive recovery process: first restore the P0-level core functions (e.g., the navigation screen brightness to 100%), and delay the restoration of the P2-level functions by 5 minutes (e.g., set the air conditioner to 24°C); ask through voice interaction "The power has been restored. Do you want to turn on the entertainment system?" If the user agrees, execute the EntertainmentSystem_PowerOn() instruction; upload the function reset record (such as air conditioner temperature, seat heating status) to the cloud user profile for generating personalized strategies for subsequent trips. The reset process ensures the instruction timing consistency of each ECU (electronic control unit) through the service gateway to avoid instantaneous power consumption overload.

[0119] The method provided by the embodiments of this application continuously optimizes the power management strategy by establishing a closed-loop feedback mechanism: it monitors the deviation between the actual power consumption and the predicted value in real time, and triggers the recalibration of model parameters when the deviation exceeds the limit; it dynamically updates the strategy through OTA and resets the scenario priority to ensure that the system adapts to sudden changes in road conditions or driving mode switches; after the power is restored to the safety threshold, it adopts a progressive function restoration strategy and uses voice confirmation to prevent misoperations. This adaptive mechanism enables the continuous iterative optimization of the power prediction model, improving the prediction accuracy compared to the static strategy version.

[0120] Figure 3 is a schematic diagram of the system processing flow of the vehicle power consumption strategy reminder system according to the embodiments of the present invention. As Figure 3 shown, from data production to the final result presentation. The bottom layer is data production, which collects multi-source data such as user data, user behavior data, vehicle data, and content service data; after preprocessing (cleaning, sorting, and annotation), feature extraction is performed to form user tags (age, gender, hobbies, driving habits, etc.) and service tags (price, type, location, evaluation, status, etc.). Through recommendation strategies (collaborative filtering, hybrid recommendation, content-based recommendation, etc.), it enters two branches: service recall and scenario judgment: Service recall: candidate sets are generated through the recall strategy and model, and then sorted by the rough ranking model, fine ranking rules, and intervention rules; Scenario judgment: scenarios are generated using the scenario strategy and service model, and sorted by the rough ranking rules, fine ranking rules, and scenario generation ranking. Finally, through AI + voice (realizing scenario judgment, semantic generation, and service recommendation), the results are presented to the voice assistant service of the in-vehicle system, completing the entire process.

[0121] Figure 4 is a schematic diagram of the cross-platform service interaction flow of the vehicle power consumption strategy reminder system according to the embodiments of the present invention. As Figure 4 shown, this process is divided into two stages: "scenario decision-making" and "voice service", involving three parties: the user, the cloud platform, and the third-party platform. In the "scenario decision-making" stage, when the user uses the vehicle, vehicle data and user data are transmitted to the cloud platform database, and at the same time, the cloud platform obtains service data from the third-party platform database. The cloud platform processes the data through the "recommendation strategy". Entering the "voice service" stage, the cloud platform generates voice text through "push decision-making", and the user side conducts "voice interaction" (including voice broadcast and function interaction) based on this, and finally the process ends. This figure clearly presents the complete data flow and processing process from user vehicle use to voice service.

[0122] In this embodiment, a reminder device for the vehicle power consumption strategy is further provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated here. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0123] This embodiment provides a reminder device for the vehicle power consumption strategy, as Figure 5 shown, including:

[0124] An acquisition module 51, configured to acquire the power consumption data of the target vehicle during driving, where the power consumption data includes basic energy consumption data, driving behavior data, and navigation itinerary data;

[0125] A prediction module 52, configured to predict whether the power consumption data of the target vehicle meets the itinerary requirements according to the power consumption data. When the itinerary requirements are not met, the priorities of the power consumption scenarios are divided based on the basic energy consumption data, driving behavior data, and navigation itinerary data, where the power consumption scenarios include vehicle driving scenarios, driving behavior scenarios, and in-vehicle function scenarios;

[0126] A generation module 53, configured to generate a vehicle driving strategy, a driving behavior strategy, and an in-vehicle function adjustment strategy based on the priorities of the power consumption scenarios;

[0127] An execution module 54, configured to perform corresponding reminder operations according to the vehicle driving strategy, the driving behavior strategy, and the in-vehicle function adjustment strategy.

[0128] Further, the prediction module 52 includes a correction sub-module and a division sub-module;

[0129] The correction sub-module is configured to acquire the remaining mileage in the navigation itinerary data and the historical energy consumption data in the basic energy consumption data; calculate the initial power consumption according to the remaining mileage and the historical energy consumption data, and correct the initial power consumption by using the abnormal energy consumption coefficient in the driving behavior data to obtain the predicted power consumption; when the predicted power consumption exceeds the remaining power in the basic energy consumption data, determine that the power consumption data of the target vehicle does not meet the itinerary requirements.

[0130] The division sub-module is configured to acquire the original priorities corresponding to each power consumption scenario; adjust the original priorities based on the basic energy consumption data, driving behavior data, and navigation itinerary data to obtain the priorities of each power consumption scenario.

[0131] Further, the sub-module for division further includes: an adjustment unit, configured to lock the priority of the vehicle driving scenario as the first priority when the remaining power in the basic energy consumption data is lower than the predicted power consumption; obtain the road condition congestion index in the navigation trip data and the braking frequency in the driving behavior data, and increase the priority of the driving behavior scenario when the road condition congestion index and the braking frequency reach the preset conditions; monitor the decreasing gradient of the remaining power in the basic energy consumption data, and reduce the priority of the in-vehicle function scenario according to the decreasing gradient until all the in-vehicle functions in the in-vehicle function scenario are turned off.

[0132] Further, the generation module 53 includes: a first construction sub-module, a second construction sub-module, and a third construction sub-module;

[0133] The first construction sub-module is configured to, for the vehicle driving scenario, determine a preset charging range according to the priority of the vehicle driving scenario, determine a list of charging stations according to the preset charging range, and construct a vehicle driving strategy by using the list of charging stations;

[0134] The second construction sub-module is configured to, for the driving behavior scenario, determine a driving parameter range according to the priority of the driving behavior scenario, and construct a driving behavior strategy by using the driving parameter range;

[0135] The third construction sub-module is configured to, for the in-vehicle function scenario, determine at least one restriction instruction for the in-vehicle function according to the priority of the in-vehicle function scenario, and construct an in-vehicle function adjustment strategy by using the restriction instruction.

[0136] Further, the first construction sub-module further includes: a decomposition unit, configured to decompose the navigation path in the navigation trip data into a sequence of continuous road segments; query multiple candidate charging stations within the preset charging range of the navigation path, and generate charging paths corresponding to the candidate charging stations; calculate the number of overlapping road segments between each charging path and the navigation path, and sort the charging paths according to the number of overlapping road segments to obtain a list of charging stations.

[0137] Further, the execution module 54 is configured to generate a first reminder message according to multiple restriction instructions in the in-vehicle function adjustment strategy; obtain the current driving data of the target vehicle, and determine whether the current driving data meets the driving parameter range in the vehicle driving strategy to obtain a judgment result, and generate a second reminder message according to the judgment result; select a target charging station from the list of charging stations in the vehicle driving strategy, and generate a third reminder message according to the charging path corresponding to the target charging station; perform the playback operation of the first reminder message, the second reminder message, and the third reminder message.

[0138] Further, the device further includes an update module, configured to monitor a deviation value between the actual power consumption and the predicted power consumption of the target vehicle during driving; if the deviation value exceeds a preset deviation value, trigger a policy update mechanism to re - divide the priority levels of power - consumption scenarios and adjust the vehicle driving policy, driving behavior policy, and in - vehicle function adjustment policy; after the remaining power of the target vehicle reaches a preset power threshold, adjust the in - vehicle functions of the target vehicle to their original configuration states.

[0139] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the present invention. As Figure 6 shown, the computer device includes one or more processors 10, a memory 20, and interfaces for connecting various components, including a high - speed interface and a low - speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as an array of servers, a set of blade servers, or a multi - processor system).

[0140] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above - mentioned hardware chip can be an application - specific integrated circuit, a programmable logic device, or a combination thereof. The above - mentioned programmable logic device can be a complex programmable logic device, a field - programmable gate array, a generic array logic, or any combination thereof.

[0141] Among them, the memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the methods shown in the above - mentioned embodiments.

[0142] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of a computer device for the display of a kind of mini-program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0143] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 may further include a combination of the above types of memories.

[0144] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0145] The embodiments of the present invention also provide a computer-readable storage medium. The methods according to the embodiments of the present invention may be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and to be stored in a local storage medium, so that the methods described herein can be stored in such software processes on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium may further include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods shown in the above embodiments are implemented.

[0146] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A reminder method for an electric power strategy of a vehicle, characterized in that, The method includes: Obtaining the power consumption data of the target vehicle during driving, where the power consumption data includes basic energy consumption data, driving behavior data, and navigation itinerary data; Predicting whether the power consumption data of the target vehicle meets the itinerary requirements according to the power consumption data. When the itinerary requirements are not met, dividing the priority levels of power consumption scenarios based on the basic energy consumption data, the driving behavior data, and the navigation itinerary data, where the power consumption scenarios include vehicle driving scenarios, driving behavior scenarios, and in-vehicle function scenarios; Generating a vehicle driving strategy, a driving behavior strategy, and an in-vehicle function adjustment strategy based on the priority levels of the power consumption scenarios; Performing corresponding reminder operations according to the vehicle driving strategy, the driving behavior strategy, and the in-vehicle function adjustment strategy.

2. The method according to claim 1, characterized in that, The predicting whether the power consumption data of the target vehicle meets the itinerary requirements according to the power consumption data includes: Obtaining the remaining mileage in the navigation itinerary data and the historical energy consumption data in the basic energy consumption data; Calculating the initial power consumption according to the remaining mileage and the historical energy consumption data, and correcting the initial power consumption by using the abnormal energy consumption coefficient in the driving behavior data to obtain the predicted power consumption; When the predicted power consumption exceeds the remaining power in the basic energy consumption data, determining that the power consumption data of the target vehicle does not meet the itinerary requirements.

3. The method according to claim 2, wherein The dividing the priority levels of power consumption scenarios based on the basic energy consumption data, the driving behavior data, and the navigation itinerary data includes: Obtaining the original priority levels corresponding to each power consumption scenario; Adjusting the original priority levels based on the basic energy consumption data, the driving behavior data, and the navigation itinerary data to obtain the priority levels of each power consumption scenario; Among them, the priority level adjustment strategy of the power consumption scenario includes: When the remaining power in the basic energy consumption data is lower than the predicted power consumption, locking the priority level of the vehicle driving scenario as the first priority level; Obtaining the road condition congestion index in the navigation itinerary data and the braking frequency in the driving behavior data, and when the road condition congestion index and the braking frequency reach the preset conditions, raising the priority level of the driving behavior scenario; Monitoring the descending gradient of the remaining power in the basic energy consumption data, and reducing the priority level of the in-vehicle function scenario according to the descending gradient until all the in-vehicle functions in the in-vehicle function scenario are turned off.

4. The method according to claim 1, wherein The generating a vehicle driving strategy, a driving behavior strategy, and an in-vehicle function adjustment strategy based on the priority levels of the power consumption scenarios includes: For the vehicle driving scenario, determining a preset charging range according to the priority level of the vehicle driving scenario, determining a list of charging stations according to the preset charging range, and constructing a vehicle driving strategy by using the list of charging stations; For the driving behavior scenario, determining a driving parameter range according to the priority level of the driving behavior scenario, and constructing a driving behavior strategy by using the driving parameter range; For the in-vehicle function scenario, determining at least one restriction instruction for the in-vehicle function according to the priority level of the in-vehicle function scenario, and constructing an in-vehicle function adjustment strategy by using the restriction instruction.

5. The method according to claim 4, wherein Determining a list of charging stations according to the preset charging range includes: Decomposing the navigation path in the navigation trip data into a sequence of continuous road segments; Querying multiple candidate charging stations within the preset charging range of the navigation path and generating charging routes corresponding to the candidate charging stations; Calculating the number of overlapping road segments between each charging route and the navigation path, and sorting the charging routes according to the number of overlapping road segments to obtain a list of charging stations.

6. The method according to claim 1, characterized in that, Performing corresponding reminder operations according to the vehicle driving strategy, the driving behavior strategy, and the in-vehicle function adjustment strategy, including: Generating a first reminder message according to multiple restriction instructions in the in-vehicle function adjustment strategy; Obtaining the current driving data of the target vehicle, and determining whether the current driving data meets the driving parameter range in the vehicle driving strategy to obtain a judgment result, and generating a second reminder message according to the judgment result; Selecting a target charging station from the list of charging stations in the vehicle driving strategy and generating a third reminder message according to the charging route corresponding to the target charging station; Performing the playback operations of the first reminder message, the second reminder message, and the third reminder message.

7. The method according to claim 1, wherein After performing corresponding reminder operations according to the in-vehicle function adjustment strategy and the vehicle driving strategy, the method further includes: Monitoring the deviation value between the actual power consumption and the predicted power consumption of the target vehicle during driving; If the deviation value exceeds a preset deviation value, triggering a strategy update mechanism to re-divide the priority levels of the power consumption scenarios and adjust the vehicle driving strategy, the driving behavior strategy, and the in-vehicle function adjustment strategy; After the remaining power of the target vehicle reaches a preset power threshold, adjusting the in-vehicle functions of the target vehicle to the original configuration state.

8. A reminder device for a vehicle's power consumption strategy, characterized in that, The device includes: An acquisition module for acquiring power consumption data of a target vehicle during driving, where the power consumption data includes basic energy consumption data, driving behavior data, and navigation trip data; A prediction module for predicting whether the power consumption data of the target vehicle meets the trip requirements according to the power consumption data, and when the trip requirements are not met, dividing the priority levels of power consumption scenarios based on the basic energy consumption data, the driving behavior data, and the navigation trip data, where the power consumption scenarios include vehicle driving scenarios, driving behavior scenarios, and in-vehicle function scenarios; A generation module for generating a vehicle driving strategy, a driving behavior strategy, and an in-vehicle function adjustment strategy based on the priority levels of the power consumption scenarios; An execution module for performing corresponding reminder operations according to the vehicle driving strategy, the driving behavior strategy, and the in-vehicle function adjustment strategy.

9. A computer device, characterized in that, Including: A memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

Images