Range-extended automobile charging decision-making method, system and device and storage medium

Abstract

The invention discloses a charging decision-making method, system and device for an extended-range automobile and a storage medium, and relates to the technical field of electric automobiles, and the method comprises the steps that first automobile state data and first external environment data are collected; setting a first parameter according to the first vehicle state data and the first external environment data; dynamically generating a charging decision rule according to the first parameter; decision making is carried out on the candidate charging stations according to the charging decision rule, and candidate charging station recommendation schemes are generated; evaluating the candidate charging station according to the candidate charging station recommendation scheme to obtain a target charging station; and feeding back the target charging station to the user and generating a route map for navigating to the target charging station. According to the technical scheme provided by the invention, the rule can be dynamically generated based on the real-time environment data, and the target charging decision system is provided through the multi-target optimization algorithm, so that the user experience and the energy utilization efficiency are improved.

Description

Technical Field

[0001] This application relates to the field of electric vehicle technology, and in particular to a method, system, device and storage medium for range-extended vehicle charging decision-making. Background Technology

[0002] With the transformation of the global energy structure and the increasing awareness of environmental protection, new energy vehicles, especially range-extended electric vehicles (REEVs), have become an important development direction for the automotive industry. Currently, the charging strategies for REEVs mainly rely on preset fixed rules or models based on simple algorithms. For example, some vehicles trigger a charging reminder when the battery level falls below a certain threshold and plan a navigation route according to pre-stored charging station location information. Furthermore, existing technologies typically select charging stations based on a single factor, such as distance or electricity price, providing limited recommendations through static databases or offline map data. A few solutions incorporate real-time traffic information to optimize route planning, but they still lack the ability to comprehensively analyze multi-dimensional data and respond in real time when dynamically adjusting charging strategies.

[0003] Therefore, there is an urgent need for a methodology for range-extended vehicle charging decisions to improve user experience and energy efficiency. Summary of the Invention

[0004] This application provides a method, system, device, and storage medium for range-extended vehicle charging decision-making. The system can dynamically generate rules based on real-time environmental data and provide target charging decisions through a multi-objective optimization algorithm to improve user experience and energy utilization efficiency.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application provides a method for determining the charging status of a range-extended electric vehicle, the method comprising: Collect the first vehicle status data and the first external environment data; A first parameter is set based on the first vehicle status data and the first external environment data; wherein, the first parameter includes a battery threshold and a preset distance threshold; The charging decision rules are dynamically generated based on the first parameter; the candidate charging stations are decided based on the charging decision rules, and a recommended scheme for the candidate charging stations is generated. The candidate charging stations are evaluated according to the recommended scheme to obtain the target charging station; The target charging station is fed back to the user, and a route map is generated to navigate to the target charging station.

[0006] In some possible implementations, the first vehicle status data includes the vehicle's remaining battery power, vehicle speed, destination distance, and vehicle location; the first external environment data includes traffic flow and road segment information; and a first parameter is set based on the first vehicle status data and the first external environment data, including: Based on the preset safety redundancy coefficient, the user's preferred battery level, the vehicle's remaining battery level, and the destination distance, a battery level threshold for triggering a charging decision is determined. Based on the traffic flow, the road segment information, the vehicle's remaining battery power, the vehicle's speed, the preset search radius coefficient, and the user-defined preferred distance, a preset distance threshold for searching candidate charging stations is determined.

[0007] In some possible implementations, the step of dynamically generating charging decision rules based on the first parameter includes: The first parameter is parsed, and the parsed first parameter is mapped to condition variables that constitute the charging decision rule; Based on the condition variables, a matching rule template is instantiated from a pre-set rule template library to form the initial decision logic; The initial decision logic is matched and bound with the first vehicle state data and the first external environment data to generate charging decision rules.

[0008] In some possible implementations, the first external environment data further includes weather information, and the method further includes: The system acquires historical charging records of the vehicle, trains a model based on these records, and uses the training results as optimization factors for charging decision rules. It analyzes user charging behavior patterns using machine learning algorithms and uses the analysis results as adjustment factors for the first parameter. The first parameter is updated based on the adjustment factors to obtain the updated first parameter. The charging decision rules are then dynamically updated based on the updated first parameter and the optimization factors. In some possible implementations, the method further includes: Based on the weather information and traffic flow, assess the risk level of the current environment to vehicle energy consumption; Based on the risk level, a preset parameter adjustment strategy is invoked to make compensatory adjustments to the power threshold and the preset distance threshold.

[0009] In some possible implementations, the step of evaluating candidate charging stations according to the candidate charging station recommendation scheme to obtain the target charging station includes: Construct a comprehensive scoring model, which includes at least evaluation dimensions related to trip time, charging cost, and service reliability; Under the evaluation dimensions related to trip time, charging cost, and service reliability, sub-scores for time, cost, and reliability are determined. Based on the user's preset preference weights, the time consumption sub-score, the cost sub-score, and the reliability sub-score are weighted and fused to obtain a comprehensive score for each candidate charging station. The target charging station is determined based on the comprehensive score of each candidate charging station.

[0010] In some possible implementations, the method further includes: Users can set power thresholds and preset distances based on their needs, and select their preferred charging station type.

[0011] Secondly, this application provides a range-extended vehicle charging decision system, the system comprising: The data acquisition module is used to collect the first vehicle status data and the first external environment data; The rule engine module is used to set a first parameter based on the first vehicle status data and the first external environment data; wherein, the first parameter includes a power threshold and a preset distance threshold; dynamically generate charging decision rules based on the first parameter; and make decisions on candidate charging stations based on the charging decision rules to generate a candidate charging station recommendation scheme. The heuristic algorithm module is used to evaluate candidate charging stations based on the candidate charging station recommendation scheme to obtain the target charging station; The user interaction module is used to provide feedback on the target charging station to the user and generate a route map to navigate to the target charging station.

[0012] Thirdly, this application provides a computing device, including a memory and a processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0013] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0014] Fifthly, this application provides a computer program product comprising one or more computer instructions, wherein when the computer instructions are executed by a computer, the computer performs the method as described in any one of the first aspects.

[0015] As can be seen from the above technical solution, this application has at least the following beneficial effects: This application provides a charging decision-making method for range-extended electric vehicles (REEVs). The method includes: collecting first vehicle status data and first external environment data; setting first parameters based on the first vehicle status data and the first external environment data; dynamically generating charging decision rules based on the first parameters; making decisions on candidate charging stations based on the charging decision rules to generate a recommended candidate charging station scheme; evaluating candidate charging stations based on the recommended candidate charging station scheme to obtain a target charging station; and providing feedback on the target charging station to the user and generating a route map to the target charging station. Due to the transformation of the global energy structure and the increasing awareness of environmental protection, new energy vehicles have become an important development direction for the automotive industry. However, most current range-extended electric vehicles on the market still rely on fixed rules or simple algorithm models for their charging strategies, lacking the ability to dynamically adjust according to real-time environmental changes. Therefore, this application provides a technical solution that can dynamically generate rules based on real-time environmental data and provide a target charging decision method through a multi-objective optimization algorithm to improve user experience and energy utilization efficiency.

[0016] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0017] Figure 1 A schematic diagram illustrating an application scenario provided in an embodiment of this application; Figure 2 A flowchart of a range-extended vehicle charging decision method provided in this application embodiment; Figure 3 A schematic diagram of a range-extended vehicle charging decision system provided in an embodiment of this application; Figure 4 This is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0018] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0019] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0020] To ensure clarity and conciseness in the description of the following embodiments, a brief introduction to the related technologies is given first: Currently, charging strategies for range-extended electric vehicles (REEVs) primarily rely on pre-set fixed rules or models based on simple algorithms. For example, some vehicles trigger a charging reminder when the battery level falls below a certain threshold and plan a navigation route based on pre-stored charging station location information. Furthermore, existing technologies typically select charging stations based on a single factor, such as distance or electricity price, providing limited recommendations through static databases or offline map data. A few solutions incorporate real-time traffic information to optimize route planning, but they still lack the ability to comprehensively analyze multi-dimensional data and respond in real-time when dynamically adjusting charging strategies.

[0021] However, the above methods have shortcomings in practical applications: First, vehicles may not be able to find the nearest available charging station in a timely manner when the battery is low, leading to range anxiety or even the risk of breakdown for users; second, the charging decision does not fully integrate multiple objective factors such as electricity price fluctuations, queue times, and traffic congestion, increasing the time and economic costs for users; finally, the impact of severe weather (such as rain, snow, and high temperatures) on energy consumption is not included in the charging strategy, resulting in biased energy consumption predictions and a surge in emergency charging demand. Therefore, there is an urgent need for a system that can dynamically generate rules based on real-time environmental data and provide targeted charging decisions through multi-objective optimization algorithms to improve user experience and energy efficiency.

[0022] In view of this, embodiments of this application provide a range-extended vehicle charging decision method, the method comprising: The system collects first vehicle status data and first external environment data; sets first parameters based on the first vehicle status data and first external environment data; dynamically generates charging decision rules based on the first parameters; makes decisions on candidate charging stations based on the charging decision rules, generating a candidate charging station recommendation scheme; evaluates the candidate charging stations based on the candidate charging station recommendation scheme to obtain the target charging station; and provides feedback on the target charging station to the user and generates a route map to the target charging station. The technical solution provided in this application can dynamically generate rules based on real-time environmental data and provide a system for target charging decision-making through a multi-objective optimization algorithm, thereby improving user experience and energy utilization efficiency.

[0023] To make the technical solution of this application clearer and easier to understand, the application scenarios of the technical solution of this application are described below with reference to the accompanying drawings. Figure 1 As shown in the figure, this figure is a schematic diagram of an application scenario provided by an embodiment of this application.

[0024] In this application scenario, car D, located at the bottom right of the screen, is a sedan with simple lines, representing the vehicle about to depart for its destination. Destination E, located at the top left of the screen, is marked by a black triangle and is the car's final destination. A curved line connects the two, simulating the actual driving route. There are three charging stations distributed along the actual driving route and in the surrounding area: charging station A (top left), charging station B (top center), and charging station C (right side), representing facilities that can recharge the car. Car D departs for destination E, but needs to charge due to insufficient battery power before reaching destination E. Before reaching destination E, there are three charging stations to choose from.

[0025] To address this, this application provides a charging decision-making method for range-extended electric vehicles (REEVs). The method includes: collecting first vehicle status data and first external environment data; dynamically generating charging decision rules based on the first vehicle status data and the first external environment data; making decisions on candidate charging stations based on the charging decision rules to generate a recommended candidate charging station scheme; evaluating the candidate charging stations based on the recommended scheme to obtain a target charging station; and providing feedback on the target charging station to the user and generating a route map to the target charging station. This method provides vehicle D with the most suitable candidate charging station recommendation scheme from three charging stations, allowing the driver to choose the optimal solution based on the recommended scheme or a less optimal solution based on their preferences. Furthermore, it saves the driver's time, eliminating the need to search for nearby charging stations, research relevant information, and rely on experience to choose a suitable charging station. Therefore, the technical solution provided by this application can dynamically generate rules based on real-time environmental data and provide an optimal charging decision method through a multi-objective optimization algorithm, thereby improving user experience and energy efficiency.

[0026] To make the technical solution of this application clearer and easier to understand, the following describes a range-extended vehicle charging decision method provided by an embodiment of this application, in conjunction with the above application scenarios. Figure 2 As shown in the figure, this is a flowchart of a range-extended vehicle charging decision method provided in an embodiment of this application.

[0027] This range-extended vehicle charging decision method is applied to the vehicle's processing equipment, and the method includes: S201, The processing equipment collects the first vehicle status data and the first external environment data.

[0028] The processing device collects first vehicle status data and first external environment data through on-board sensors, GPS positioning system and cloud database. The first vehicle status data includes the vehicle's remaining battery power, vehicle speed, destination distance and vehicle location. The first external environment data includes weather information, traffic flow and road segment information.

[0029] The processing equipment provides a basis for vehicle D's charging decisions and driving plans on its journey to destination E, assisting in determining whether charging is necessary, when to charge, and which charging station to select, ensuring a smooth trip. The collection of initial vehicle status data and initial external environment data is crucial because the remaining battery power in the initial vehicle status data is essential for vehicle D to reach its destination or charging station; the driving speed, vehicle location, and distance to the destination in the initial vehicle status data affect the time to reach the charging station or destination and the energy consumption, which is key to determining the charging timing; furthermore, weather information in the initial external environment data affects energy consumption (e.g., air conditioning power consumption under high / low temperatures) and charging efficiency (extreme weather may affect the operation of charging piles), traffic flow determines vehicle travel time and energy consumption rate, and road segment information (e.g., congestion, gradient, etc.) is related to vehicle energy consumption and travel time. These environmental factors can alter vehicle power consumption and must be considered in conjunction with charging needs.

[0030] As can be seen, by understanding vehicle and environmental information, the processing equipment can rationally plan charging, avoiding breakdowns due to lack of power and ensuring a smooth arrival at the destination. Based on the collected data, it can select charging stations that are convenient (e.g., good road conditions, no congestion) and suitable for the vehicle's condition (e.g., fast charging compatibility, appropriate distance), providing convenience, saving time, and improving charging efficiency. Furthermore, it can adjust driving behavior (e.g., reasonable speed control) based on environmental and vehicle conditions, reducing unnecessary power consumption, extending range, and lowering the frequency of charging.

[0031] The processing device also updates the first vehicle status data and the first external environment data in real time, and transmits the updated first vehicle status data and the first external environment data to the processing device so that the processing device can adjust the charging decision rules in a timely and accurate manner based on the dynamically changing data, so that the charging decision rules can dynamically adapt to the current actual operating status of the vehicle and the external environmental conditions.

[0032] S202. The processing device dynamically generates charging decision rules based on the first vehicle status data and the first external environment data, makes decisions on candidate charging stations based on the charging decision rules, and generates a recommended scheme for candidate charging stations.

[0033] The processing device dynamically generates charging decision rules based on the first vehicle status data and the first external environment data; it then makes decisions on candidate charging stations based on these rules, generating a recommended charging station solution; specifically including: Acquire second vehicle status data and second external environment data, and perform data preprocessing on the second vehicle status data and the second external environment data. First, filter and remove outliers in the second vehicle status data and invalid information (such as incorrect weather codes and meaningless road segment markings) in the second external environment data. Then, fill in missing values. If the vehicle driving position information is missing, it can be re-acquired through the GPS positioning system or estimated and supplemented by combining information from surrounding base stations.

[0034] Furthermore, for the second external environment data, a unified conversion rule is established. For example, different expressions in weather information such as "sunny," "clear," etc., are uniformly mapped to preset codes (e.g., "01" represents sunny); descriptions of traffic flow such as "congested" and "busy" are converted to standardized codes like "03." All types of external environment data are standardized into a unified format (i.e., the first format, which can be customized to a coding system easily recognized by the rule engine). The second vehicle status data is also adjusted in format simultaneously to ensure compatibility with the second external environment data, resulting in processed second vehicle status data and second external environment data, laying a solid data foundation for generating charging decision rules. The second external environment data is uniformly processed as described above, and the resulting data format is named the first format. In this application, the first format can be the conversion of text information into numerical codes, thereby obtaining the first vehicle status data and the first external environment data.

[0035] The processing device sets a first parameter based on the obtained first vehicle status data and first external environment data. This first parameter includes a battery threshold and a preset distance threshold. Specifically, it includes determining the battery threshold that triggers a charging decision based on a preset safety redundancy coefficient, the user-defined preferred battery level, the vehicle's remaining battery level, and the destination distance. The calculation formula is: Battery Threshold = MAX(User-defined preferred battery level, (Minimum battery level required to reach the destination + Safety Redundancy Battery Level) / Total Battery Capacity), where the minimum battery level required to reach the destination = (Destination Distance / Vehicle Current Average Energy Consumption) × (1 + Environmental Energy Consumption Influence Factor), and the safety redundancy battery level = safety redundancy coefficient × total battery capacity. The vehicle's current average energy consumption is calculated in real-time by combining the historical changes in the vehicle's remaining battery level with the mileage traveled.

[0036] Based on traffic flow, road segment information, vehicle remaining battery power, vehicle speed, preset search radius coefficient, and user-defined preferred distance, a preset distance threshold for searching candidate charging stations is determined. The calculation formula is: Preset distance threshold = MIN(User-defined preferred distance, Real-time driving range × Search radius coefficient), where real-time driving range = Vehicle remaining battery power / (Estimated future energy consumption rate), and estimated future energy consumption rate = Vehicle current average energy consumption × (1 + Traffic congestion factor + Road segment slope factor). The vehicle current average energy consumption is obtained through vehicle speed, the traffic congestion factor is based on traffic flow, and the road segment slope factor is based on road segment information.

[0037] In this way, the first parameter is no longer a fixed value, but an intelligent variable that can be dynamically adjusted according to the vehicle's real-time status, external environment, and user habits, laying a solid foundation for the subsequent generation of charging decision rules.

[0038] The set first parameter is used to generate charging decision rules. In the process of dynamically generating charging decision rules based on the first parameter, the system first parses the first parameter and maps the parsed first parameter into condition variables that constitute the charging decision rules. Based on the condition variables, the system calls the matching rule template from the preset rule template library for instantiation to form the initial decision logic. The initial decision logic is matched and bound with the first vehicle status data and the first external environment data to generate charging decision rules.

[0039] In some embodiments, the system calculates the first parameters based on real-time data, including: a battery threshold of 25% and a preset distance threshold of 30 kilometers. Furthermore, real-time data collected on the first vehicle's status shows a remaining battery level of 24% and the vehicle is currently traveling on a highway; the first external environmental data shows a current temperature of -5°C.

[0040] The system first parses the first parameter mentioned above, mapping "battery threshold 25%" to the rule condition variable "whether charging is needed", and mapping "preset distance threshold 30 kilometers" to the rule condition variable "search range".

[0041] Based on these condition variables, the system calls the "Highway Low Temperature Environment Charging Decision" template from the pre-set rule template library. This template contains the following logical framework: when charging is required and the environment is on a highway, fast charging stations within a specified range should be searched first, and the impact of low temperature on charging efficiency should be considered.

[0042] The system substitutes specific parameters into the template for instantiation to form the initial decision logic: if charging is required and the road type is highway, the search range is set to 30 kilometers, and the charging station type preference is set to fast charging station.

[0043] Finally, the system matches and binds the initial decision logic with the first vehicle status data and the first external environment data. This involves connecting the abstract conditions and variables in the initial decision logic with the first vehicle status data and the first external environment data to generate specific executable instructions. The system detects that the current remaining battery power is 24%, lower than the 25% battery threshold, and the road type is indeed a highway with an ambient temperature of -5°C. Therefore, the final executable charging decision rule is generated: (1) Immediately trigger a charging alarm; (2) Search for available charging stations within a 30-kilometer radius; (3) Prioritize the selection of fast charging stations; (4) In the evaluation of charging stations, a negative compensation factor is introduced for the fast charging efficiency dimension due to the low temperature environment.

[0044] As can be seen from this embodiment, this application achieves dynamic generation of charging decision rules through steps such as parameter parsing, template instantiation, and data fusion. This enables the rules to adapt to specific vehicle states and external environmental conditions in real time, thereby improving the accuracy and practicality of charging decisions.

[0045] In some embodiments, the battery threshold and preset distance threshold can be adaptively adjusted based on first external environmental data. This process first performs an environmental risk level assessment: parsing the first external environmental data, for example, when weather information contains keywords such as 'heavy rain,' 'snow,' or 'high temperature,' and / or traffic flow data indicates that the current or predicted road segment is 'severely congested,' the system will determine that the current environment is at a high risk level. Such environments typically lead to increased vehicle energy consumption (e.g., activating windshield wipers, defogging / cooling the air conditioner, decreased battery efficiency at low temperatures, frequent start-stop operations in congested road segments, etc.), and the original threshold settings may be insufficient to ensure range safety.

[0046] Then, adaptive parameter adjustment is performed. This involves calling a pre-defined adjustment strategy mapping table. For example: High-risk scenarios: To ensure safety redundancy, the system will adjust the battery threshold from a base value (e.g., 20%) to a higher value (e.g., 25% or 30%), meaning that the vehicle will trigger a charging decision when the remaining battery is higher. At the same time, the preset distance threshold will be adjusted from a base value (e.g., 50 kilometers) to a shorter distance (e.g., 30 kilometers), meaning that the system will look for charging stations within a closer range, thereby advancing and shortening the triggering conditions for charging decisions to cope with potentially sudden increases in energy consumption.

[0047] Low-risk scenarios: When the environment is 'sunny' and 'open', the system determines it to be a low-risk level. At this time, the vehicle's energy consumption is stable and predictable. The system may adjust the battery threshold downward (e.g., from 20% to 15%) and the preset distance threshold upward (e.g., from 50 km to 70 km), thereby delaying and relaxing the triggering conditions for charging decisions. This helps users to drive longer distances continuously, reduce unnecessary charging times, and improve travel efficiency.

[0048] Through this dynamic compensation mechanism based on environmental risks, the system can improve the foresight and safety of charging decisions, effectively avoiding range crises caused by sudden environmental changes.

[0049] When the vehicle's remaining battery power is below the battery power threshold and the destination distance exceeds the preset distance threshold, a charging decision rule is triggered; based on the charging decision rule, multiple candidate charging stations are obtained.

[0050] In some embodiments, the battery threshold is set to 20kWh, and the preset distance threshold is two-thirds of the total distance. When car D is two-thirds of the distance from destination E and the remaining battery power of the vehicle is 20kWh, the charging decision rule is triggered, and three candidate charging stations A, B and C are obtained according to the charging decision rule.

[0051] In some embodiments, the first parameter further includes a time threshold. If the estimated time for the vehicle to reach its destination E is less than the time threshold and the vehicle has a remaining battery power of 20 kWh, a charging decision rule is triggered, and three candidate charging stations, A, B, and C, are obtained according to the charging decision rule.

[0052] The processing equipment also acquires historical charging records of the vehicle, trains a model based on these records, and uses the training results as optimization factors for the charging decision rules; it analyzes user charging behavior patterns using machine learning algorithms, and uses the analysis results as adjustment factors for the first parameter; it updates the first parameter based on the adjustment factors, obtaining the updated first parameter; and it dynamically updates the charging decision rules based on the updated first parameter and the optimization factors. Specifically, this includes: S1. Historical Charging Record Acquisition: Proactively collect complete past charging records of vehicles from local vehicle storage, cloud charging data platforms, and other channels. These records cover multiple dimensions of data, including the time of each charge (accurate to the specific moment, distinguishing different time attributes such as weekdays and holidays), initial battery level (the remaining battery level and corresponding percentage before charging), final battery level (the battery level reached after charging), charging duration (the duration from the start to the end of charging), selected charging station information (including the location and type of the charging station, such as fast charging station, slow charging station, and the operator), and the external environment at the time of charging (weather, traffic conditions of the road section, etc.), thus constructing a rich historical charging database.

[0053] S2. Model Training and Optimization Factor Generation: A professional machine learning model training process is employed, using the aforementioned diverse historical charging records as input data. Based on a big data analytics framework, suitable machine learning algorithms such as linear regression, decision trees, and deep learning neural networks are utilized to uncover hidden patterns within the data. For example, the charging time from the same initial charge to full charge is analyzed under different seasons and weather conditions; the correlation between power consumption rate and charging behavior is analyzed in different scenarios such as daily commutes and long-distance travel. Through iterative training and model validation, core patterns reflecting vehicle charging characteristics and adapting to actual usage scenarios are extracted. These validated training results are defined as optimization factors for charging decision rules. These optimization factors can be, for example, "the optimal starting charge threshold for the vehicle under specific conditions" or "the recommended charging time range for different trip types," used to optimize charging decision rules from the underlying logic.

[0054] S3. User Charging Behavior Pattern Analysis and Adjustment Factor Generation: Focusing on individual user charging behavior, this section leverages historical charging records and employs machine learning algorithms such as cluster analysis and behavioral sequence mining to deeply analyze user charging habits. For example, it identifies long-term user preferences for charging time (whether they habitually charge at fixed times each day or only charge when the battery level drops to a certain point), charging station selection tendencies (whether they prioritize slow charging stations near home or fast charging stations along the route to save time), and charging scenario associations (differences in charging decisions during commutes, weekends, and long-distance travel). These user behavioral characteristics extracted from the analysis are transformed into quantifiable adjustment factors that can be used to adjust decision parameters. Examples include "user commuter day charging timeliness factor (reflecting the urgency of replenishing battery on weekdays)" and "charging station type preference weight in long-distance travel scenarios," which serve as the basis for subsequent adjustments to the primary parameter.

[0055] S4. First Parameter Update: Based on the obtained adjustment factors, the pre-set first parameters (which can be understood as the basic and flexibly adjustable set of core parameters in the charging decision rules, such as the default battery warning threshold and the charging strategy trigger parameters corresponding to different distance ranges) are dynamically updated. If the adjustment factors show that "in winter low-temperature environments, the user's battery level drops 30% faster than in summer due to the rapid power consumption of the air conditioner," the battery warning trigger threshold parameter is lowered accordingly, allowing the vehicle to prompt charging earlier. If it is analyzed that "when traveling long distances, users prefer to choose fast charging stations within 5 kilometers of the route," the preset distance-related parameters are adjusted to adapt the charging station selection logic in the charging decision rules for long-distance scenarios to this preference. By adjusting the first parameters, the charging decision is made more in line with the user's actual needs.

[0056] S5. Dynamic Updates to Charging Decision Rules: By integrating the updated primary parameters with previously generated optimization factors, the entire charging decision rule system is systematically reshaped. Based on the impact model of different road congestion levels on power consumption within the optimization factors, and combined with the updated user power warning parameters for congested road sections, the decision logic for whether a vehicle needs to temporarily find a charging station while driving is reconstructed. Alternatively, based on the correlation model between charging station type and charging efficiency / cost within the optimization factors, and combined with the updated user charging station type preference parameters, the priority recommendation ranking rules for charging stations are adjusted. This ensures that the charging decision rules, from determining the charging timing and selecting charging stations to planning charging duration, not only align with the physical characteristics of the vehicle's battery and the influence of the external environment, but also deeply reflect the user's personalized charging habits, achieving dynamic optimization and upgrades.

[0057] In some embodiments, the processing device also supports users manually setting a first parameter, such as setting a power threshold and a preset distance according to user needs; specifically including: Users can customize battery warning thresholds based on their driving habits and trip plans. If a user frequently commutes short distances within the city and charging facilities are readily available, they can set the "low battery warning threshold" to 20%, triggering a charging reminder only when the vehicle's battery level drops to 20%. For planned long-distance intercity trips, to avoid battery anxiety during the journey, users can increase the "long-distance trip battery safety threshold" to 40% in advance; when the battery level approaches this threshold, the system will prioritize recommending charging stations along the route. Additionally, a "full charge target threshold" can be set. For example, for daily commutes, to save charging time, the system can be set to stop charging at 80%; for long-distance trips, it can be set to 100% full charge to ensure sufficient range.

[0058] For the charging station search and recommendation logic, users can customize distance-related parameters. If a user's new energy vehicle has a strong range and wants to reduce the number of charging trips, they can expand the "maximum recommended charging station distance range" from the default 10 kilometers to 20 kilometers, allowing the system to prioritize stations that are slightly farther away but offer a better charging experience (such as more fast charging stations and less queuing). If a user values ​​charging convenience more and doesn't want to take detours, they can set the "optimal charging station distance preference" to within 5 kilometers, prioritizing nearby stations and flexibly adapting to the distance needs of different travel scenarios.

[0059] Users can choose their charging station type preference. Specifically, users can set charging station type preference parameters based on their considerations such as charging speed, cost, and usage habits. If a user prioritizes charging efficiency and frequently needs rapid charging, they can increase the weight of fast charging stations, causing the rules engine to prioritize fast charging stations when recommending them, even if they are slightly farther away or more expensive. If a user commutes to a fixed area and there are slow charging stations near their home or workplace, they can increase the slow charging station preference coefficient to save on charging costs and take advantage of off-peak electricity rates, causing the system to recommend more slow charging stations. Users can also refine their preferences to specific operators' charging stations. For example, if a user is a member of a charging brand and enjoys member discounts, they can set that brand's charging stations to be prioritized. By flexibly configuring type preferences, charging decisions can be tailored to individual usage habits and cost control needs.

[0060] The processing equipment also dynamically generates specific charging decision rules by combining preset general rule templates with users' personalized needs; for example, the power threshold template: triggers charging when the remaining power is below a certain percentage; the time management template: reasonably allocates charging tasks according to the user's travel schedule and available time; the economy template: minimizes charging costs while meeting charging needs; and the safety template: ensures that the vehicle will not break down due to depleted power under any circumstances.

[0061] Personalized user needs refer to the generation of customized rules based on the specific needs of a particular user. Here are some typical scenarios: Preference-based needs: Users explicitly express a preference for a certain type of charging station (such as high-end facilities, free Wi-Fi, etc.); Example rule: Prioritize charging stations with rest areas and food services.

[0062] Efficiency-oriented needs: Users want to complete the charging task as quickly as possible and reduce waiting time; Example rule: Select the charging station with the fastest available parking space and give priority to fast charging piles.

[0063] Environmental needs: Users tend to use charging stations powered by green energy; Example rule: Only charging stations that use clean energy are recommended.

[0064] Based on the above, charging decision rules are generated to screen candidate charging stations and generate recommended solutions for them.

[0065] S203. The processing equipment evaluates the candidate charging stations according to the recommended scheme of the candidate charging stations to obtain the target charging station.

[0066] The processing equipment evaluates candidate charging stations based on recommended schemes to determine the target charging station; specifically, this includes: To evaluate candidate charging stations, a comprehensive scoring model encompassing multi-objective optimization was first constructed. This model mainly defines three core evaluation dimensions: travel time, charging cost, and service reliability.

[0067] The trip time dimension aims to minimize the user's overall time cost, and its evaluation comprehensively considers navigation distance, estimated travel time, and current queue waiting time. Among them, navigation distance refers to the distance from the vehicle's current location to the charging station; estimated travel time is dynamically calculated based on real-time traffic conditions (such as congestion and accidents); and current queue waiting time is obtained in real time through the charging station operation platform.

[0068] The charging cost dimension focuses on optimizing users' economic expenditures by comprehensively calculating the charging unit price, parking fees, and service fees. The charging unit price is the cost per kilowatt-hour, parking fees are additional costs that may be incurred during the charging period, and service fees are other fees that charging service providers may charge.

[0069] Service reliability is used to ensure a smooth charging process and user experience. This dimension comprehensively evaluates charging pile availability, historical user ratings, and operator reputation. Charging pile availability reflects the proportion of currently available charging piles at the station; historical user ratings are based on feedback from past users; and operator reputation represents the brand reputation and service guarantee capabilities of the charging station operator.

[0070] Because the factors have different units (e.g., distance in kilometers, time in minutes, cost in yuan), the system first standardizes the raw data for each factor, mapping it uniformly to a score range of [0,1] or [0,100]. Higher values ​​indicate better performance on that factor. For example, closer distances, shorter time, lower costs, and higher availability result in higher converted scores. Subsequently, the scores of multiple factors within the same dimension are aggregated to generate sub-scores for time consumption (S_time), cost (S_cost), and reliability (S_reliability).

[0071] The system incorporates weighting factors set by user preferences to weight and fuse the three sub-ratings, calculating a comprehensive score. These weighting factors allow the scoring model to be personalized to suit the needs of different users. The formula for calculating the comprehensive score can be expressed as: Score=W_time×S_time+W_cost×S_cost+W_reliability×S_reliability Where W_time is the first weight set by the user for the time consumption dimension, W_cost is the second weight set by the user for the cost dimension, and W_reliability is the third weight set by the user for the reliability dimension, and W_time+W_cost+W_reliability=1.

[0072] Ultimately, the system selects the candidate charging station with the highest overall score as the target charging station for recommendation.

[0073] In some embodiments, the filtered list of candidate charging stations is passed to the processing device in a structured format. This is typically done using JSON or a similar format to ensure data clarity and readability.

[0074] Step 1: Data Formatting Assume the shortlist of candidate charging stations after filtering is as follows: Station A: 20km away, fast charging, electricity price 0.8 yuan / kWh, no queue.

[0075] Bilibili: 35 km away, fast charging, electricity price 0.6 yuan / kWh, 20-minute queue required.

[0076] Station C: 40 km away, fast charging, electricity price 0.5 yuan / kWh, 30-minute queue required.

[0077] The formatted candidate charging stations are (in JSON format): [ {"id": "A", "distance": 20, "type": "fast", "price": 0.8, "wait_time": 0}, {"id": "B", "distance": 35, "type": "fast", "price": 0.6, "wait_time": 20}, {"id": "C", "distance": 40, "type": "fast", "price": 0.5, "wait_time": 30} ] Step 2: Define the optimization objective Heuristic algorithms require a clearly defined optimization objective. Common optimization objectives include: Time priority: Minimize total time (including navigation time and queuing time).

[0078] Cost priority: Minimize charging costs as much as possible.

[0079] Overall optimal: Finding a balance between time and cost.

[0080] Step 3: Input User Preferences Users can determine the focus of optimization by setting preference weights. For example: Time weighting: 70%; Cost weighting: 30%.

[0081] Step 4: Construct a scoring model Based on the optimization objectives and user preferences, a scoring model is constructed to calculate a weighted score for each candidate charging station. Assume the scoring model used by the system is as follows: [ Rating = (Time Weighting = 1 / T) + (Cost Weighting = 1 / C)] Where: (T): Total time (navigation time + queuing time); (C): Total cost (electricity price × amount of electricity required for charging).

[0082] Below is a calculation example, assuming a user needs to charge 20kWh, and the ratings for each charging station are as follows: Station A: Total time: 20 minutes (navigation time) + 0 minutes (queue time) = 20 minutes Total cost: 0.8 yuan / kWh × 20kWh = 16 yuan Rating: ((0.7 × 120) + (0.3 × 16) × approx. 0.049) Bilibili: Total time: 35 minutes (navigation time) + 20 minutes (queue time) = 55 minutes Total cost: 0.6 yuan / kWh × 20kWh = 12 yuan Rating: ((0.7 × 1.55) + (0.3 × 1.12) × approx. 0.032) Station C: Total time: 40 minutes (navigation time) + 30 minutes (queue time) = 70 minutes Total cost: 0.5 yuan / kWh × 20kWh = 10 yuan Rating: ((0.7 times 170) + (0.3 times 110) approx. 0.039) Step 5: Output target charging station Based on the results of the scoring model, the charging station with the highest score is selected as the target charging station, and the target charging station is used as the recommended solution.

[0083] In the calculation example above, Station A has the highest score (0.049), therefore Station A is recommended as the target charging station.

[0084] S204. The processing device feeds back the target charging station to the user and generates a route map to navigate to the target charging station.

[0085] The processing equipment also includes an in-vehicle touchscreen display, a mobile application, and voice prompts.

[0086] The in-vehicle touchscreen display shows recommended charging station information. Example: Considering the remaining battery power (25%), driving distance (100 km), and the queue at charging station A ahead, it is recommended that car D charge at charging station B, with an estimated charging time of 30 minutes. It also supports touch operations such as swiping and clicking for convenient user selection. A dedicated mobile application (supporting iOS and Android) is developed. The application interface includes the following functional modules: Rule Details: Displaying algorithm optimization rules, scoring formulas, etc.; Preference Settings: Allowing users to adjust time and cost weights; Feedback: Collecting user feedback on system performance, recommendation results, etc.

[0087] A mobile application that allows users to define preferences and view details of charging decision rules.

[0088] The voice prompt function is used to announce recommended charging station options via voice. Through the in-car navigation voice system, it reminds the user of the optimal charging solution after analyzing the current vehicle status, external environment, and user charging preferences. Example: Considering the remaining battery level (25%), driving distance (100 km), and the queue situation at charging station A ahead, we recommend charging at charging station B, which is expected to take 30 minutes.

[0089] Input method: Touchscreen operation. Users can select menu items or input data by clicking, swiping, etc. Suitable for in-vehicle displays and mobile applications.

[0090] Voice operation: Integrates voice recognition technology, allowing users to operate via voice commands. For example, users can say "set the time weight to 0.7" or "view the current rules".

[0091] Data synchronization: Data is synchronized between the in-vehicle display and the mobile application; user actions on either device are updated in real time on the other device, ensuring consistency.

[0092] Specifically, the range-extended vehicle charging decision-making method provided in this application also provides two-way interaction with users, allowing users to view rules, modify preferences, or provide feedback. This user-customized setting data is integrated into the voice reminder function, making the results of the algorithm decision more in line with the user's needs.

[0093] In some embodiments, a range-extended vehicle is set to travel from location F to destination E, with a current battery level of 20% and a distance of 100 kilometers from destination E. The specific implementation steps are as follows: 1. Data Collection: Current vehicle battery level: 20%; Distance to destination: 100 km; Weather conditions: Light rain; Charging station information along the way: Charging station A (30 km away, electricity price 0.8 yuan / kWh, 10-minute wait time), Charging station B (50 km away, electricity price 1.0 yuan / kWh, 5-minute wait time), Charging station C (70 km away, electricity price 0.9 yuan / kWh, 15-minute wait time).

[0094] 2. Rule generation: Based on the rule that the battery level is below 30% and the distance to the destination is more than 50 kilometers, it was determined that charging at the next charging station was necessary. Because of the light rain, the rule engine automatically lowered the battery threshold to 25%, further reducing energy consumption.

[0095] 3. Candidate charging station screening: Based on the rules, the following charging stations were selected that meet the criteria: C1, C2, and C3.

[0096] 4. Heuristic optimization: Calculating the weighted score: Assuming users prioritize time and cost, the score formula is: (Score = 0.6 times 1 / 2 distance + 0.3 times 1 / 2 electricity price + 0.1 times 1 / 2 queue time).

[0097] Charging station C1 rating: (0.6 times 130 + 0.3 times 10.8 + 0.1 times 10 = 0.02) Charging station C2 rating: (0.6 times 150 + 0.3 times 1.0 + 0.1 times 1.5 = 0.03) Charging station C3 rating: (0.6 times 170 + 0.3 times 10.9 + 0.1 times 115 = 0.025) Ultimately, C2, which received the highest rating, was selected as the recommended charging station.

[0098] 5. User Interaction: Feedback the final decision to the user, and after the user agrees, navigate to the C2 charging station.

[0099] Based on the above, the system collects first vehicle status data and first external environment data; sets first parameters based on the first vehicle status data and first external environment data; dynamically generates charging decision rules based on the first parameters; makes decisions on candidate charging stations based on the charging decision rules, generating a candidate charging station recommendation scheme; evaluates the candidate charging stations based on the candidate charging station recommendation scheme to obtain the target charging station; and feeds back the target charging station to the user and generates a route map to the target charging station. This system provides vehicle D with the most suitable candidate charging station recommendation scheme from three charging stations, allowing the driver in vehicle D to choose the optimal solution based on the candidate charging station recommendation scheme or a non-optimal solution based on their own preferences. Furthermore, it saves the driver's time, eliminating the need to search for nearby charging stations, research relevant information, and choose a suitable charging station based on experience. Therefore, the technical solution provided in this application can dynamically adjust rules based on real-time data to adapt to charging needs in different scenarios and avoid the limitations of fixed rules; it comprehensively considers multiple factors such as distance, electricity price, and queuing time through heuristic algorithms to ensure that users get the best charging experience; it reduces the time and cost for users to find charging stations and improves the overall user experience; it supports users to customize rule parameters and preference settings to meet personalized needs and improve user experience and energy utilization efficiency.

[0100] The above text combined Figures 1 to 2 The extended-range vehicle charging decision system provided in the embodiments of this application has been described in detail. The methods and devices provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0101] This application also provides a range-extended vehicle charging decision system, such as... Figure 3 As shown, this figure is a schematic diagram of a range-extended vehicle charging decision system provided in an embodiment of this application. The system includes: Data acquisition module 301 is used to acquire first vehicle status data and first external environment data; The rule engine module 302 is used to set a first parameter based on the first vehicle status data and the first external environment data; dynamically generate charging decision rules based on the first parameter; make decisions on candidate charging stations based on the charging decision rules; and generate a candidate charging station recommendation scheme. The heuristic algorithm module 303 is used to evaluate the candidate charging stations according to the candidate charging station recommendation scheme to obtain the target charging station; User interaction module 304 is used to provide feedback on the target charging station to the user and generate a route map to navigate to the target charging station.

[0102] In some possible implementations, the rule engine module 302 is specifically used to determine the power threshold that triggers a charging decision based on a preset safety redundancy coefficient, the user-set preferred power level, the vehicle's remaining power level, and the destination distance. Based on the traffic flow, the road segment information, the vehicle's remaining battery power, the vehicle's speed, the preset search radius coefficient, and the user-defined preferred distance, a preset distance threshold for searching candidate charging stations is determined.

[0103] In some possible implementations, the rule engine module 302 is specifically used to parse the first parameter and map the parsed first parameter into condition variables that constitute the charging decision rule; Based on the condition variables, a matching rule template is instantiated from a pre-set rule template library to form the initial decision logic; The initial decision logic is matched and bound with the first vehicle state data and the first external environment data to generate charging decision rules. In some possible implementations, the system further includes: The training module is used to acquire historical charging records of vehicles, train models based on these records, and use the training results as optimization factors for charging decision rules. It also analyzes user charging behavior patterns using machine learning algorithms and uses the analysis results as adjustment factors for the first parameter. The first parameter is updated based on the adjustment factors to obtain the updated first parameter. Finally, the charging decision rules are dynamically updated based on the updated first parameter and the optimization factors. In some possible implementations, the system further includes: The adjustment module is used to assess the risk level of the current environment to vehicle energy consumption based on the weather information and traffic flow. Based on the risk level, a preset parameter adjustment strategy is invoked to make compensatory adjustments to the power threshold and the preset distance threshold. In some possible implementations, the heuristic algorithm module 303 is specifically used to construct a comprehensive scoring model, which includes at least evaluation dimensions related to travel time, charging cost, and service reliability. Under the evaluation dimensions related to trip time, charging cost, and service reliability, sub-scores for time, cost, and reliability are determined. Based on the user's preset preference weights, the time consumption sub-score, the cost sub-score, and the reliability sub-score are weighted and fused to obtain a comprehensive score for each candidate charging station. The target charging station is determined based on the comprehensive score of each candidate charging station.

[0104] In some possible implementations, the system further includes: The settings module is used to set the power threshold, preset distance, and select the preferred type of charging station according to user needs.

[0105] This application also provides a computing device. For example... Figure 4 As shown in the figure, this is a schematic diagram of a computing device provided in an embodiment of this application. The computing device 400 includes a bus 401, a processor 402, a communication interface 403, and a memory 404. The processor 402, the memory 404, and the communication interface 403 communicate with each other via the bus 401.

[0106] Bus 401 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0107] Processor 402 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0108] Communication interface 403 is used for communication with external devices.

[0109] Memory 404 may include volatile memory, such as random access memory (RAM). Memory 404 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0110] The memory 404 stores executable code, and the processor 402 executes the executable code to perform the aforementioned range-extended vehicle charging decision method.

[0111] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-described range-extended vehicle charging decision method.

[0112] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0113] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0114] When the computer program product is executed by a computer, the computer performs any of the aforementioned methods of the range-extended vehicle charging decision method. The computer program product can be a software installation package; when any of the aforementioned methods of the range-extended vehicle charging decision method is required, the computer program product can be downloaded and executed on the computer.

[0115] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0116] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A charging decision method for range-extended electric vehicles, characterized in that, The method includes: Collect the first vehicle status data and the first external environment data; A first parameter is set based on the first vehicle status data and the first external environment data; wherein, the first parameter includes a battery threshold and a preset distance threshold; The charging decision rules are dynamically generated based on the first parameter; the candidate charging stations are decided based on the charging decision rules, and a recommended scheme for the candidate charging stations is generated. The candidate charging stations are evaluated according to the recommended scheme to obtain the target charging station; The target charging station is fed back to the user, and a route map is generated to navigate to the target charging station.

2. The method according to claim 1, characterized in that, The first vehicle status data includes the vehicle's remaining battery power, vehicle speed, destination distance, and vehicle location; the first external environment data includes traffic flow and road segment information. The step of setting the first parameter based on the first vehicle status data and the first external environment data includes: Based on the preset safety redundancy coefficient, the user's preferred battery level, the vehicle's remaining battery level, and the destination distance, a battery level threshold for triggering a charging decision is determined. Based on the traffic flow, the road segment information, the vehicle's remaining battery power, the vehicle's speed, the preset search radius coefficient, and the user-defined preferred distance, a preset distance threshold for searching candidate charging stations is determined.

3. The method according to claim 1, characterized in that, The step of dynamically generating charging decision rules based on the first parameter includes: The first parameter is parsed, and the parsed first parameter is mapped to condition variables that constitute the charging decision rule; Based on the condition variables, a matching rule template is instantiated from a pre-set rule template library to form the initial decision logic; The initial decision logic is matched and bound with the first vehicle state data and the first external environment data to generate charging decision rules.

4. The method according to claim 3, characterized in that, The method further includes: Obtain the vehicle's historical charging records, train the model based on the historical charging records, and use the training results as optimization factors for the charging decision rules. The user's charging behavior pattern is analyzed using machine learning algorithms, and the analysis results are used as the adjustment factor for the first parameter. The first parameter is updated according to the adjustment factor to obtain the updated first parameter; The charging decision rule is dynamically updated based on the updated first parameter and optimization factor.

5. The method according to claim 2, characterized in that, The first external environment data also includes weather information, and the method further includes: Based on the weather information and traffic flow, assess the risk level of the current environment to vehicle energy consumption; Based on the risk level, a preset parameter adjustment strategy is invoked to make compensatory adjustments to the power threshold and the preset distance threshold.

6. The method according to claim 1, characterized in that, The step of evaluating candidate charging stations according to the candidate charging station recommendation scheme to obtain the target charging station includes: Construct a comprehensive scoring model, which includes at least evaluation dimensions related to trip time, charging cost, and service reliability; Under the evaluation dimensions related to trip time, charging cost, and service reliability, sub-scores for time, cost, and reliability are determined. Based on the user's preset preference weights, the time consumption sub-score, the cost sub-score, and the reliability sub-score are weighted and fused to obtain a comprehensive score for each candidate charging station. The target charging station is determined based on the comprehensive score of each candidate charging station.

7. The method according to claim 1, characterized in that, The method further includes: Users can set power thresholds and preset distances based on their needs, and select their preferred charging station type.

8. A range-extended vehicle charging decision system, characterized in that, The system includes: The data acquisition module is used to collect the first vehicle status data and the first external environment data; The rule engine module is used to set a first parameter based on the first vehicle status data and the first external environment data; wherein, the first parameter includes a power threshold and a preset distance threshold; dynamically generate charging decision rules based on the first parameter; and make decisions on candidate charging stations based on the charging decision rules to generate a candidate charging station recommendation scheme. The heuristic algorithm module is used to evaluate candidate charging stations based on the candidate charging station recommendation scheme to obtain the target charging station; The user interaction module is used to provide feedback on the target charging station to the user and generate a route map to navigate to the target charging station.

9. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 7.

Images