Traffic jam charging scheduling method and system

Abstract

The invention provides a traffic jam charging scheduling method and system, and relates to the technical field of traffic jam charging scheduling. Vehicle operation information, real-time traffic information, charging station related information and charging preference information set by a driver are comprehensively evaluated; the energy consumption of the vehicle in a specific traffic environment, the actual service capability of the charging station and the personalized charging efficiency of the vehicle are comprehensively evaluated, a target charging station and a charging route are determined, the reasonability of the target charging station and the charging route is locally judged according to vehicle-mounted local sensing data and navigation information, and the charging efficiency of the vehicle is improved. And obtaining a local judgment result. And when the local judgment result is different from the decision consideration factor, selection information made by the driver based on the difference information can be obtained, and a subsequent scheduling strategy is adjusted. And the accuracy, the effectiveness and the user experience of charging scheduling in the traffic jam area are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of traffic congestion charging scheduling technology, and more specifically, to a traffic congestion charging scheduling method and system. Background Technology

[0002] With the increasing number of electric vehicles in cities, an intelligent charging dispatch system has emerged to ensure that vehicles do not break down due to insufficient battery power. This system collects information such as the vehicle's real-time location, remaining battery power, and estimated power consumption, and combines this with real-time traffic data. When a vehicle's battery level falls below a preset threshold, it automatically plans a route to the optimal charging station. Under normal traffic conditions, this system functions effectively, preventing vehicles from running out of power and ensuring smooth traffic flow. However, in certain urban areas and during specific time periods, such as rush hour, traffic congestion becomes severe and prolonged, posing new challenges to existing charging dispatch systems.

[0003] Specifically, in scenarios where specific urban areas face persistent, structural traffic congestion, and where periodic surges in charging demand occur around charging stations, existing charging dispatch systems often plan charging routes based solely on the basic availability and geographical distance of charging stations. They fail to adequately consider factors such as the limited actual power supply capacity of charging stations, dynamic operational strategies (e.g., electricity pricing or service priority), and the individual battery health and charging characteristics of electric vehicles. For example, the system might guide a vehicle to a physically empty charging station that actually requires a long queue, or the station might be unable to provide high-power charging due to grid capacity limitations, resulting in charging times far exceeding expectations. Furthermore, the system fails to acquire and integrate real-time information on dynamic electricity pricing or service restrictions for specific vehicle types, potentially leading to high charging costs or the inability to charge on time for drivers.

[0004] Furthermore, existing systems typically employ a generic, ideal-state-based charging model when estimating charging time, failing to adequately consider the actual battery health status of each electric vehicle, its current battery temperature, and the dynamic adjustment capabilities of its battery management system to charging power. This leads to severely inaccurate estimations of charging completion time, further extending waiting times already caused by queuing due to insufficient actual charging power. This completely disrupts drivers' travel plans and significantly reduces the turnover efficiency of charging stations. This information asymmetry greatly diminishes the accuracy and effectiveness of the scheduling system's decisions in complex and ever-changing real-world scenarios, ultimately resulting in low overall utilization efficiency of charging resources and failing to truly alleviate the charging problems in urban traffic congestion areas. Summary of the Invention

[0005] This application provides a method and system for charging scheduling during traffic congestion, aiming to address the problems of inaccurate charging time prediction, high charging costs, and low charging efficiency caused by the failure to fully consider the actual power supply capacity of charging stations, dynamic operation strategies, individual battery health conditions of electric vehicles, and differences in charging characteristics under normalized, structural traffic congestion and surges in charging demand in urban electric vehicle charging scheduling scenarios. On the one hand, this application provides a traffic congestion charging scheduling method, including: Based on the acquired vehicle operation information, real-time traffic information, charging station information and driver-set charging preference information, a comprehensive evaluation is conducted on the vehicle's energy consumption in a specific traffic environment, the actual service capacity of the charging station and the vehicle's personalized charging efficiency to obtain the first evaluation result. Based on the first assessment results, the target charging station and charging route are determined according to the decision-making considerations. Based on the vehicle's local perception data and navigation information, the rationality of the target charging station and the charging route is locally determined, and a local determination result is obtained. When there is a difference between the local judgment result and the decision consideration factors, the driver's selection information based on the difference information is obtained, and the subsequent scheduling strategy is adjusted according to the selection information.

[0006] Optionally, after the step of making a local judgment on the rationality of the target charging station and the charging route based on onboard local perception data and navigation information, and obtaining a local judgment result, the following steps are included: When there is a difference between the local judgment result and the decision consideration factors, the driver's facial expression, eye movement trajectory, head posture and steering wheel grip data are analyzed to obtain a second assessment result of the driver's current cognitive load and emotional state. Adjust the information presentation strategy based on the second evaluation results.

[0007] Optionally, the step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, the key differences between the decision-making considerations and the local judgment result are extracted and highlighted. The estimated time, estimated power consumption and congestion level of the target charging station and the charging route are compared and displayed in a graphical manner, and decision-making assistance prompts are provided to the driver.

[0008] Optionally, the step of analyzing the driver's facial expressions, eye movements, head posture, and steering wheel grip data to obtain a second assessment result of the driver's current cognitive load and emotional state when there is a difference between the local judgment result and the decision consideration factors includes: An infrared camera is used to capture an image of the driver's face to obtain an infrared image, and a visible light camera is used to capture an image of the driver's face to obtain a visible light image; The infrared image and the visible light image are fused to obtain a fused image; The driver's key facial feature points in the fused image are identified. Based on the driver's key facial feature points, facial expression, eye movement trajectory, head posture, and steering wheel grip data, the driver's current cognitive load and emotional state are assessed to obtain a second assessment result.

[0009] Optionally, the step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, slow down the information broadcasting speed, extend the display time of key information, give priority to voice broadcasting and concise visual cues, and use reassuring and encouraging language; When the second assessment result indicates that the driver is in a state of low cognitive load or relaxation, speed up the information broadcasting, shorten the display time of non-critical information, provide detailed text information and interactive options, and use neutral and objective language; Adjust the visual elements of the information presentation based on the complexity of the vehicle's current driving environment and the driver's preference for the way information is presented.

[0010] Optionally, the step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, the driver's physiological response data is continuously monitored, including heart rate, skin conductivity, and driving behavior data, including accelerator pedal depth, brake pedal pressure, and steering wheel angle rate. Based on the physiological response data and the driving behavior data, calculate the driver's instantaneous stress index and decision-making reaction time; The intensity of information presentation is dynamically adjusted based on the instantaneous stress index and the decision-making reaction time.

[0011] Optionally, the step of dynamically adjusting the intensity of information presentation based on the instantaneous stress index and the decision reaction time includes: When the instantaneous stress index increases, reduce the visual brightness or volume of the information presentation, prioritize the presentation of core decision options and their direct consequences, and reduce background information; When the decision-making response time is prolonged, the number of times key information is repeatedly broadcast should be increased.

[0012] Optionally, the vehicle operation information includes the vehicle's real-time location information, battery status information, and motion information; the real-time traffic information includes real-time traffic congestion information and road topology; and the charging station-related information includes real-time charging station occupancy information, charging station power supply capacity information, and charging station layout information.

[0013] Optionally, the step of making a local judgment on the rationality of the target charging station and the charging route based on onboard local perception data and navigation information, and obtaining a local judgment result, specifically includes: Based on the real-time location information, the vehicle-mounted camera is used to identify the entrance area of ​​the target charging station to detect the number of vehicles queuing in real time and the occupancy status of charging piles; millimeter-wave radar is used to perceive the real-time traffic flow density and vehicle speed distribution of the road ahead; traffic condition information broadcast by surrounding vehicles and queuing information shared by the target charging station are received; and lidar and ultrasonic sensors are used to scan the surrounding environment of the target charging station to assess its actual physical accessibility. Based on the acquired real-time location and motion information, road topology and charging station layout information, real-time number of queuing vehicles and charging pile occupancy status, real-time traffic flow density and vehicle speed distribution, traffic condition information and queuing information shared by the target charging station, as well as the actual physical accessibility of the target charging station, a preset path evaluation algorithm is used to generate a local judgment result on the rationality of the target charging station and the charging route. The path evaluation algorithm is configured to identify micro-situations such as internal lane congestion, temporary occupation of charging piles, or mismatched sizes, and to correct the local judgment result based on the identified micro-situations.

[0014] On the other hand, this application provides a traffic congestion charging dispatch system, which includes: The comprehensive evaluation module is used to comprehensively evaluate the energy consumption of the vehicle in a specific traffic environment, the actual service capacity of the charging station, and the personalized charging efficiency of the vehicle based on the acquired vehicle operation information, real-time traffic information, charging station information, and the charging preference information set by the driver, and obtain the first evaluation result. The scheduling decision module is used to determine the target charging station and charging route based on the first evaluation result and decision consideration factors. The local judgment module is used to make a local judgment on the rationality of the target charging station and the charging route based on the vehicle's local perception data and navigation information, and obtain a local judgment result. The difference display and selection module is used to obtain the driver's selection information based on the difference information when there is a difference between the local judgment result and the decision consideration factors, and to adjust the subsequent scheduling strategy according to the selection information.

[0015] This application discloses a traffic congestion charging scheduling method and system. By comprehensively evaluating vehicle operation information, real-time traffic information, charging station information, and driver-set charging preferences, it comprehensively assesses the vehicle's energy consumption under specific traffic conditions, the actual service capacity of charging stations, and the vehicle's personalized charging efficiency, obtaining a first evaluation result. Based on this, target charging stations and charging routes are determined according to decision-making considerations. More importantly, this application introduces onboard local perception data and navigation information to locally judge the rationality of target charging stations and charging routes, obtaining a local judgment result. When there is a discrepancy between the local judgment result and the decision-making considerations, it can obtain the driver's choice information based on the discrepancy information and adjust subsequent scheduling strategies accordingly. This application can more accurately predict vehicle energy consumption and charging station service capacity, avoiding guiding vehicles to charging stations that are physically idle but actually require long queues or have limited charging power. Meanwhile, the local judgment mechanism can identify micro-level conditions such as queuing vehicles, charging pile occupancy status, and real-time traffic flow density at the charging station entrance area in real time, and correct the scheduling results. This avoids serious inaccuracies in charging time estimation caused by information asymmetry, as well as the dilemma faced by drivers facing high charging costs or inability to charge in a timely manner. In addition, the introduction of driver selection information allows the scheduling strategy to be adjusted according to the actual needs and preferences of drivers, improving flexibility and user satisfaction. In summary, this application, through a closed-loop scheduling mechanism of refined evaluation, localized judgment, and driver participation, significantly improves the accuracy, effectiveness, and user experience of charging scheduling in traffic-congested areas, effectively alleviating the charging problem in urban traffic-congested areas. Attached Figure Description

[0016] To illustrate this application more clearly, the accompanying drawings used in the embodiments will be briefly described below. Obviously, those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0017] Figure 1 The diagram above illustrates a flowchart of a traffic congestion charging scheduling method. Figure 2 The diagram above illustrates a schematic of a traffic congestion charging scheduling system.

[0018] Attached label: 100, Traffic congestion charging dispatch system; 10, Comprehensive evaluation module; 20, Dispatch decision module; 30, Local judgment module; 40, Difference display and selection module. Detailed Implementation

[0019] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0021] Traditionally, when facing persistent, structural traffic congestion in specific urban areas, as well as periodic surges in charging demand around charging stations, route planning is often based solely on the basic availability and geographical distance of charging stations. This approach fails to adequately consider the limited actual power supply capacity of charging stations, dynamic operational strategies, and differences in the individual battery health and charging characteristics of electric vehicles. This leads to inaccurate charging time estimates, resulting in drivers facing high charging costs or the inability to charge on time. Ultimately, this results in low overall utilization efficiency of charging resources and fails to effectively alleviate the charging problems in urban traffic-congested areas.

[0022] like Figure 1 The diagram illustrates a flowchart of a traffic congestion charging scheduling method. This application proposes a traffic congestion charging scheduling method, comprising: S10, based on the acquired vehicle operation information, real-time traffic information, charging station information and driver-set charging preference information, comprehensively evaluates the vehicle's energy consumption in a specific traffic environment, the actual service capacity of the charging station and the vehicle's personalized charging efficiency, and obtains the first evaluation result. Vehicle operation information refers to various real-time data collected by the vehicle during operation, such as real-time location information, battery status information (e.g., remaining charge, battery temperature, health status), and motion information (e.g., speed, acceleration). Real-time traffic information covers current road conditions, including real-time traffic congestion information and road topology. Charging station information includes real-time occupancy information, power supply capacity information, layout information, and dynamic operation strategies (e.g., electricity price, service priority). Driver-defined charging preferences refer to the driver's personalized needs regarding charging time, charging costs, and charging station brands.

[0023] S20, Based on the first evaluation result, determine the target charging station and charging route according to the decision-making considerations; Among them, decision-making considerations refer to various indicators that need to be comprehensively considered when determining target charging stations and charging routes, such as estimated charging time, estimated cost, route congestion level, and charging station service quality.

[0024] S30, based on the vehicle's local perception data and navigation information, make a local judgment on the rationality of the target charging station and the charging route, and obtain a local judgment result; S40, when there is a difference between the local judgment result and the decision consideration factors, obtain the selection information made by the driver based on the difference information, and adjust the subsequent scheduling strategy according to the selection information.

[0025] Among them, vehicle-mounted local perception data refers to environmental data acquired in real time by the vehicle's own sensors (such as cameras, radar, ultrasonic sensors, etc.), while navigation information is provided by the vehicle-mounted navigation system.

[0026] The traffic congestion charging scheduling method of this application first comprehensively evaluates the energy consumption of vehicles in specific traffic environments, the actual service capacity of charging stations, and the personalized charging efficiency of vehicles based on the acquired vehicle operation information, real-time traffic information, charging station information, and charging preference information set by drivers, and obtains a first evaluation result.

[0027] Specifically, vehicle operation information can be obtained from onboard sensors, vehicle bus systems, or mobile devices connected to the vehicle. For example, real-time vehicle location information can be obtained through a GPS module; battery status information can be obtained through a battery management system (BMS); and motion information can be obtained through the vehicle's inertial measurement unit (IMU) or wheel speed sensors. Real-time traffic information can be obtained from traffic management department data platforms, third-party map service providers, or through vehicle-to-everything (V2X) communication. Charging station information can be obtained from the charging station operator's back-end system, charging service platform, or through the charging station's own sensor network. Driver-set charging preferences can be entered through the in-vehicle infotainment system's human-machine interface or set through the driver's smartphone application.

[0028] After obtaining the above information, the vehicle's energy consumption under specific traffic conditions will be assessed. For example, calculations can be performed using a pre-defined energy consumption model based on factors such as the vehicle's real-time speed, acceleration, road conditions, gradient, vehicle model, and load. The actual service capacity assessment of charging stations will consider the number of charging piles, real-time occupancy, power supply capacity, queuing situation, and the charging station's operational strategies (such as whether there are discounts or restrictions for specific vehicle models). Personalized charging efficiency assessments will combine factors such as the vehicle's battery health, current temperature, battery management system characteristics, and charging pile power to predict the actual charging speed. These assessment results are comprehensively analyzed to form the first assessment result, which fully reflects the vehicle's charging needs and potential charging service quality under the current circumstances.

[0029] Subsequently, based on the initial assessment results, target charging stations and charging routes are determined according to decision-making considerations. These considerations may include estimated charging time, estimated charging cost, route congestion level, charging station service quality rating, and driver preferences. For example, a multi-objective optimization algorithm can be used to balance objectives such as shortest charging time, lowest cost, and least congestion while satisfying driver charging preferences, selecting the optimal target charging station from multiple alternative charging stations and planning the corresponding charging route.

[0030] After determining the target charging station and charging route, the system uses onboard local perception data and navigation information to locally assess the feasibility of the target charging station and route, obtaining a local assessment result. The local assessment module can use onboard cameras to identify the entrance area of ​​the target charging station to detect the real-time number of vehicles in queue and the occupancy status of charging piles; use millimeter-wave radar to perceive the real-time traffic flow density and vehicle speed distribution on the road ahead; receive traffic condition information broadcast by surrounding vehicles and queuing information shared by the target charging station; and use lidar and ultrasonic sensors to scan the surrounding environment of the target charging station to assess its actual physical accessibility. Navigation information provides real-time map data, traffic updates, and route guidance. Through this local data, the previously planned charging station and route can be further verified, for example, to determine if the charging station is temporarily closed, if the charging piles are occupied by other vehicles, or if there are sudden congestion or construction issues along the route.

[0031] When local assessments differ from the factors considered in the decision-making process, the system acquires information about the driver's choices based on these discrepancies and adjusts subsequent dispatch strategies accordingly. For example, if local assessments reveal that queuing at the target charging station is significantly longer than expected, or that the planned route is severely congested, this discrepancy information will be presented to the driver. The driver can then choose to accept the original technical solution, select an alternative technical solution, or manually adjust their charging preferences. Based on the driver's choice, the system will adjust subsequent dispatch strategies accordingly, such as replanning charging stations and routes, or adjusting the way information is presented.

[0032] The traffic congestion charging scheduling method proposed in this application achieves accurate prediction of vehicle energy consumption, charging station service capacity, and personalized charging efficiency by introducing comprehensive evaluation of multi-source information, overcoming the limitations of relying solely on basic availability and geographical distance. Through a local judgment mechanism, the rationality of the scheduling technical solution can be verified in real time, effectively responding to emergencies and micro-level changes. More importantly, when there is a discrepancy between the local judgment result and the decision-making considerations, the method can obtain the driver's choice information based on the discrepancy and adjust subsequent scheduling strategies accordingly. This integrates the driver's real-time feedback and subjective intentions into the scheduling decision, significantly improving the adaptability and user satisfaction of the scheduling technical solution. This human-machine collaborative scheduling approach not only improves the utilization efficiency of charging resources but also greatly alleviates the problem of electric vehicle charging in urban traffic congestion areas, providing drivers with a more intelligent, efficient, and personalized charging experience.

[0033] In some embodiments, after the step of making a local judgment on the rationality of the target charging station and the charging route based on onboard local perception data and navigation information, and obtaining a local judgment result, the following steps are included: When there is a difference between the local judgment result and the decision consideration factors, the driver's facial expression, eye movement trajectory, head posture and steering wheel grip data are analyzed to obtain a second assessment result of the driver's current cognitive load and emotional state. Adjust the information presentation strategy based on the second evaluation results.

[0034] Among these data, the driver's facial expressions can be captured by the in-vehicle camera and analyzed through image recognition, such as identifying emotions like joy, anger, and anxiety; eye movement can reflect the driver's focus and degree of distraction, such as the frequency, direction, and fixation point of eye movements; head posture can indicate the driver's fatigue or distraction, such as head tilt angle and rotation frequency; and steering wheel grip data can indirectly reflect the driver's level of tension or operational stability. Combining these data allows for a relatively accurate assessment of the driver's current cognitive load and emotional state. Furthermore, based on the second assessment results, information presentation strategies can be dynamically adjusted. Information presentation strategies refer to the way and content of information is delivered to the driver, such as the speed of information delivery, display duration, visual elements, and language style. By adjusting these strategies, information can be made more suitable for the driver's current state, thereby improving information reception efficiency and decision-making quality.

[0035] By employing the aforementioned technical solutions and assessing the driver's cognitive load and emotional state in real time, inappropriate information can be avoided when the driver is under high pressure or distracted, thereby effectively reducing the driver's cognitive burden and psychological stress. This personalized and contextualized information presentation not only improves the driver's understanding and acceptance of dispatch suggestions but also reduces the risk of erroneous decisions due to information overload or misunderstanding.

[0036] For example, suppose a vehicle is traveling on a congested section of a highway, and an initial assessment recommends a target charging station and charging route. However, onboard local perception data and navigation information show that there is a long queue at the entrance of the target charging station, and the estimated arrival time is significantly extended due to a sudden accident ahead, which is a clear difference from the initial decision-making considerations. At this point, instead of immediately presenting the driver with all the detailed differences and asking them to choose, the system first captures an image of the driver's face using an infrared camera, analyzes their facial expressions, and monitors their eye movements, head posture, and steering wheel grip. If the second assessment indicates that the driver is currently under high cognitive load (e.g., tense facial expression, frequent and irregular eye movements, and heavy steering wheel grip), the information presentation strategy will be automatically adjusted. Specifically, it might prioritize a concise voice announcement in a reassuring tone, informing the driver that "there may be a queue at the charging station ahead, and we are reassessing the best technical option for you," while highlighting only the key differences on the display screen, such as the estimated long queue time, rather than presenting all the complex traffic and charging station data at once. Once the driver's condition has eased somewhat or initial simplified suggestions have been provided, more detailed information or alternative technical solutions can be gradually offered to guide the driver to make a decision in a relatively relaxed state.

[0037] In some embodiments, the step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, the key differences between the decision-making considerations and the local judgment result are extracted and highlighted. The estimated time, estimated power consumption and congestion level of the target charging station and the charging route are compared and displayed in a graphical manner, and decision-making assistance prompts are provided to the driver.

[0038] Specifically, when a driver is detected to be under high cognitive load or anxiety, the system proactively analyzes and identifies the core differences between the initial recommendation (based on decision-making considerations) and the actual situation as determined by the vehicle's local perception data and navigation information (local judgment results). This allows for the extraction and highlighting of these key differences. For example, if the initially recommended charging station is based on its theoretical availability, but the local judgment results indicate a large number of vehicles queuing at the station's entrance, then the "real-time number of vehicles queuing" becomes the key difference, which will be presented to the driver in a prominent manner (e.g., highlighted, flashing, or emphasized via voice).

[0039] Furthermore, graphically comparing and displaying the estimated travel time, estimated battery consumption, and congestion levels of the target charging station and the charging route can be understood as transforming complex numerical information into intuitive and easy-to-understand visual charts. For example, bar charts, pie charts, or color-coded maps can be used to clearly compare and display the differences between the original recommended technical solution and the actual situation revealed by the local judgment in terms of estimated arrival time, estimated battery consumption, and traffic congestion levels along the route. This graphical display aims to help drivers quickly understand the information in a short time, avoiding the increased cognitive burden of reading large amounts of text or numbers.

[0040] In addition to presenting information about differences, the system proactively offers concise and clear suggestions or options to assist drivers in making decisions, providing decision-making support prompts. These prompts could include suggestions such as "choose an alternative charging station," "wait 10 minutes before setting off to avoid peak hours," or "consider taking an alternate route to avoid congested areas," aiming to directly guide drivers to their next steps and reduce their decision-making hesitation under pressure.

[0041] Through the above technical solutions, when drivers are under high cognitive load or anxiety, the information presentation method can be optimized in a targeted manner to avoid information overload. This can not only significantly reduce the driver's cognitive burden and decision-making pressure, improving their decision-making efficiency and safety in complex traffic environments, but also enhance the intelligence and humanization of human-computer interaction, thereby improving the driving experience.

[0042] In some embodiments, the step of analyzing the driver's facial expressions, eye movements, head posture, and steering wheel grip data to obtain a second assessment result of the driver's current cognitive load and emotional state when there is a difference between the local judgment result and the decision consideration factors includes: An infrared camera is used to capture an image of the driver's face to obtain an infrared image, and a visible light camera is used to capture an image of the driver's face to obtain a visible light image; The infrared image and the visible light image are fused to obtain a fused image; The driver's key facial feature points in the fused image are identified. Based on the driver's key facial feature points, facial expression, eye movement trajectory, head posture, and steering wheel grip data, the driver's current cognitive load and emotional state are assessed to obtain a second assessment result.

[0043] The infrared camera is configured to capture driver facial images in environments with insufficient or no visible light, overcoming the impact of lighting conditions on image quality. The visible light camera, on the other hand, acquires high-resolution driver facial images under normal lighting conditions. The fusion of the infrared and visible light images can be understood as integrating image data from different spectra to generate a fused image containing richer and more comprehensive facial information, and exhibiting greater robustness to changes in lighting. Fusion techniques can employ various methods, such as pixel-level fusion, feature-level fusion, or decision-level fusion, for example, through weighted averaging, wavelet transform, or deep learning networks.

[0044] Furthermore, key facial feature points refer to points on the face with significant geometric or textural features, such as the outlines of the eyes, eyebrows, nose, and mouth. These feature points can be identified and tracked using image processing algorithms (such as ASM, AAM, or deep learning models). Driver facial expressions can be identified by analyzing the relative positions and shape changes of these key feature points, as well as the movement patterns of facial muscles. For example, facial expressions can be classified into emotional states such as happiness, anger, and anxiety using expression recognition algorithms. The eye movement trajectory can be obtained using eye-tracking devices or image-based eye-tracking algorithms, reflecting the driver's focus of attention, scanning path, and pupil size changes—information closely related to cognitive load. Head posture can be obtained using head-tracking sensors or vision-based head posture estimation algorithms, indicating the driver's head orientation, tilt angle, etc. These posture changes are often associated with the driver's attention and emotional state. Steering wheel grip force data can be obtained using force sensors installed on the steering wheel; changes in grip force can serve as a physiological indicator of the driver's tension or stress level.

[0045] Through the aforementioned technical solution, this application significantly improves the accuracy and robustness of assessing driver cognitive load and emotional state. Specifically, by utilizing infrared and visible light image fusion technology, clear and complete driver facial information is obtained under various lighting conditions, effectively avoiding difficulties in facial feature recognition caused by insufficient or excessive light. Simultaneously, a comprehensive assessment combining multi-dimensional data such as facial expressions, eye movement trajectories, head posture, and steering wheel grip strength results in a more comprehensive and refined judgment of the driver's internal state, enabling more accurate identification of whether the driver is under high cognitive load or anxiety. This provides a more reliable basis for subsequently adjusting information presentation strategies based on the second assessment results, thereby enhancing the intelligence level of human-computer interaction and driving safety.

[0046] In some embodiments, the step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, slow down the information broadcasting speed, extend the display time of key information, give priority to voice broadcasting and concise visual cues, and use reassuring and encouraging language; When the second assessment result indicates that the driver is in a state of low cognitive load or relaxation, speed up the information broadcasting, shorten the display time of non-critical information, provide detailed text information and interactive options, and use neutral and objective language; Adjust the visual elements of the information presentation based on the complexity of the vehicle's current driving environment and the driver's preference for the way information is presented.

[0047] Specifically, when the second assessment indicates that the driver is under high cognitive load or anxiety, a series of measures are configured to reduce driver stress and ensure effective reception of critical information. For example, the information broadcasting speed will be significantly slowed down to give the driver ample time to process the information; the display time of critical information will be extended to ensure the driver has sufficient opportunity to read and understand it. Furthermore, to reduce visual interference and improve information reception efficiency, voice broadcasting will be prioritized, supplemented by concise and intuitive visual cues. In terms of language selection, reassuring and encouraging wording will be used to alleviate the driver's tension.

[0048] Conversely, when the second assessment indicates that the driver is in a state of low cognitive load or relaxation, the system is configured to provide richer and more efficient information. In this case, the information delivery speed is increased, and the display time for non-critical information is shortened to improve overall information delivery efficiency. Detailed textual information and interactive options are provided, allowing the driver to actively explore and obtain more details. Simultaneously, the information delivery uses neutral and objective language to maintain professionalism and accuracy.

[0049] Furthermore, the visual elements used to present information are dynamically adjusted to adapt to the complexity of the vehicle's current driving environment and the driver's preferences for information presentation. For example, in complex traffic environments, visual elements may be simplified to reduce distractions, while in simpler environments, richer visual information can be provided. Driver preferences, such as their choice of font size, color scheme, or layout, are also taken into account to provide a more personalized user experience.

[0050] Through the aforementioned technical solution, this application can dynamically and intelligently adjust information presentation strategies based on the driver's real-time cognitive load and emotional state, thereby significantly improving the adaptability and effectiveness of human-computer interaction. This not only effectively reduces the driver's cognitive burden and psychological pressure in complex traffic environments or situations with differing decision-making processes, avoiding decision-making errors or emotional fluctuations caused by inappropriate information presentation, but also provides a richer and more efficient information interaction experience when the driver is in a good state. Therefore, this application achieves a more humanized and personalized charging dispatch information service, greatly optimizing the driver's driving experience and decision-making efficiency, and improving the safety and comfort of charging dispatch in congested traffic environments.

[0051] For example, suppose a vehicle is driving during peak urban hours. The onboard local judgment module detects a large number of vehicles queuing at the entrance of the intended target charging station, and the charging pile occupancy rate is far higher than expected, significantly differing from the decision-making factors determined by the scheduling decision module. At this point, a local judgment result is generated. By analyzing the driver's facial expressions, eye movements, head posture, and steering wheel grip data, a second assessment result is obtained, indicating that the driver is in a state of high cognitive load and mild anxiety. Based on this second assessment result, the information presentation strategy is immediately adjusted. The voice broadcast speed is slowed down; for example, the message "There are too many vehicles queuing at the charging station ahead; we recommend choosing an alternative charging station" is broadcast at a slower, clearer pace. Simultaneously, the screen will extend the display of key differences, such as showing the estimated queuing time of the original target charging station and the estimated queuing time of the alternative charging station in a concise graphical comparison, and providing a reassuring prompt: "Don't worry, we have found a better alternative technology to ensure your charging needs." Conversely, if the vehicle is traveling in a suburban area with good traffic conditions, and local judgments differ from decision-making factors, but the second assessment indicates the driver is in a low cognitive load and relaxed state, the information broadcast speed will be accelerated, for example, quickly announcing "Road construction ahead, detour recommended, estimated to add only 5 minutes to the journey." The display time for non-critical information on the screen will be shortened, and detailed text information will be provided, such as a detailed map of the detour route and details of multiple alternative charging stations, with interactive options for the driver to choose from. The information broadcast will use neutral and objective language, such as "Road construction detected ahead, we suggest you consider alternative route A or B." Furthermore, if the vehicle is currently driving in complex conditions (such as rain, snow, or at night), even if the driver's cognitive load is low, the visual elements of the information presentation may be adjusted. For example, the screen brightness may be reduced to decrease glare, or key text and icons may be enlarged to ensure that the information remains clearly visible in adverse conditions. If the driver prefers voice interaction in the settings, the priority and level of detail of the voice prompts will be further enhanced.

[0052] In some embodiments, the step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, the driver's physiological response data is continuously monitored, including heart rate, skin conductivity, and driving behavior data, including accelerator pedal depth, brake pedal pressure, and steering wheel angle rate. Based on the physiological response data and the driving behavior data, calculate the driver's instantaneous stress index and decision-making reaction time; The intensity of information presentation is dynamically adjusted based on the instantaneous stress index and the decision-making reaction time.

[0053] Specifically, when the second assessment indicates that the driver is in a state of high cognitive load or anxiety, the system is configured to continuously acquire the driver's physiological response data and driving behavior data. Physiological response data can be understood as indicators reflecting changes in the driver's internal physical state; for example, heart rate refers to the number of heartbeats per unit time, and skin conductivity refers to changes in the electrical conductivity of the skin surface. These data can directly or indirectly reflect the driver's level of tension, excitement, or relaxation. Driving behavior data refers to the behavioral patterns generated by the driver when operating the vehicle; for example, accelerator pedal depth reflects the driver's intention and force to accelerate the vehicle, brake pedal pressure reflects the driver's intention and force to decelerate the vehicle, and steering wheel angle rate reflects the precision and urgency of the driver's control over the vehicle's direction. This data can be collected in real time using onboard sensors (such as heart rate monitors, skin conductivity sensors, pedal sensors, steering wheel angle sensors, etc.).

[0054] Furthermore, based on the acquired physiological response data and driving behavior data, the system is configured to calculate the driver's instantaneous stress index and decision-making reaction time. The instantaneous stress index can be understood as a quantitative indicator comprehensively reflecting the driver's current psychological stress level. Its calculation can be weighted by combining heart rate variability, fluctuations in skin conductivity, and abnormal driving behavior patterns (such as frequent acceleration / braking, excessive steering wheel corrections, etc.). Decision-making reaction time can be understood as the time required for the driver to make a corresponding decision or operation after receiving an information prompt, such as the time interval from information presentation to the driver selecting an option or performing a driving action. The calculation of these indicators aims to provide a more refined and real-time assessment of the driver's immediate state.

[0055] Therefore, based on the calculated instantaneous stress index and decision-making reaction time, the intensity of information presentation is dynamically adjusted. The intensity of information presentation can be understood as the degree to which information stimulates the driver's senses in visual, auditory, and other dimensions, such as the brightness, contrast, and flicker frequency of visual information, and the volume, speech rate, and repetition frequency of auditory information. Dynamic adjustment means that this adjustment is continuous and real-time, rather than a one-off event. Its purpose is to optimize information delivery and help drivers receive and process information more effectively in complex environments by adjusting the intensity of information presentation when driver stress increases or decision-making reaction time lengthens. This could involve reducing the intensity of non-critical information to reduce interference, or increasing the intensity of critical information to ensure its effective perception.

[0056] Through the aforementioned technical solution, this application achieves a more refined and real-time perception of the driver's state, thereby making the adjustment of information presentation strategies more targeted and adaptive. Specifically, by continuously monitoring physiological reaction data and driving behavior data, and calculating the instantaneous stress index and decision-making reaction time, it can dynamically and accurately match the driver's current cognitive load and emotional state, avoiding providing too much or overly complex information when the driver is under excessive stress, and also avoiding insufficient information presentation when the driver needs more assistance. This significantly reduces the driver's cognitive load in traffic congestion and decision-making discrepancies, improves the driver's efficiency in receiving key information and the accuracy of decision-making, thereby enhancing driving safety and user experience. This dynamic adjustment of information presentation intensity enables more intelligent interaction with the driver, effectively alleviating the driver's anxiety in complex traffic environments and ensuring the effective transmission of charging dispatch information.

[0057] For example, suppose an electric vehicle is driving during peak urban hours. Based on the initial assessment, a target charging station and charging route are recommended. However, the onboard local decision-making module detects temporary construction at the entrance of the target charging station, reducing its actual accessibility, which differs from the factors considered in the decision. At this point, the driver faces the choice of whether to accept the recommended alternative technology.

[0058] By analyzing the driver's facial expressions and eye movements, a preliminary assessment is made that the driver is in a state of moderate cognitive load (second assessment result). Based on the aforementioned technical solution, continuous monitoring of the driver's physiological response data and driving behavior data will be further initiated. For example, heart rate and skin conductivity data will be acquired in real time using heart rate and skin conductivity sensors integrated into the steering wheel. Simultaneously, driving behavior data such as accelerator pedal depth, brake pedal pressure, and steering wheel angle rate will be acquired via the vehicle bus.

[0059] Suppose that after a few seconds of driver hesitation, the driver's heart rate begins to rise, skin conductivity fluctuates, and steering wheel turning rate becomes irregular, while accelerator pedal depth and brake pedal pressure also show uncertainty. Based on this data, it is calculated that the driver's instantaneous stress index is rising rapidly, and decision-making reaction time is significantly prolonged.

[0060] Based on these dynamically changing indicators, the intensity of information presentation is adjusted immediately. For example, the brightness of non-critical background information on the in-vehicle screen may be reduced, while core decision-making information such as estimated charging time, estimated battery consumption, and congestion levels are highlighted in larger fonts and brighter colors. Key decision options are repeated in a slower, clearer voice, such as "Please choose: Option A (detour for 5 minutes, charging station available), or Option B (wait 10 minutes, charging station may be available)." If the driver's stress level continues to rise and decision-making reaction time does not decrease, the background volume may be further reduced, and decision-making assistance prompts may be provided in a more reassuring tone, such as "Please stay calm, we will provide you with the best option." Through this dynamic, real-time intensity adjustment, key information is delivered in the most effective way when the driver needs help most, is most easily distracted, or is anxious, thereby helping the driver make wiser and safer decisions.

[0061] In some embodiments, the step of dynamically adjusting the intensity of information presentation based on the instantaneous stress index and the decision reaction time includes: When the instantaneous stress index increases, reduce the visual brightness or volume of the information presentation, prioritize the presentation of core decision options and their direct consequences, and reduce background information; When the decision-making response time is prolonged, the number of times key information is repeatedly broadcast should be increased.

[0062] Specifically, the driver stress level, calculated through continuous monitoring of physiological response data (such as heart rate and skin conductivity) and driving behavior data (such as accelerator pedal depth, brake pedal pressure, and steering wheel angle rate), shows an upward trend. When an immediate increase in the stress index is detected, the visual brightness or volume of the information presentation is proactively reduced to minimize additional sensory stimulation for the driver, avoid information overload, and thus help the driver better concentrate under high-pressure situations. Simultaneously, core decision options and their direct consequences are prioritized, for example, only displaying key information such as "whether to select an alternative charging station" and "estimated arrival time after selecting an alternative charging station," while reducing background information not directly related to the current decision, such as detailed road topology maps or non-emergency traffic updates, to further reduce the driver's cognitive load, enabling them to quickly grasp key information and make a judgment.

[0063] Extended decision-making reaction time can be understood as the time required for a driver to make a clear choice or take action after receiving the provided decision-making assistance information, exceeding a preset normal threshold. When an extended decision-making reaction time is detected, the number of times key information is repeated is increased. The purpose is to ensure that the driver can fully receive and understand the core decision-making information, avoiding decision delays or errors due to information omissions or misunderstandings.

[0064] Through the aforementioned technical solution, this application can make more refined and adaptive adjustments to the information presentation strategy based on the driver's real-time physiological and behavioral state. This not only effectively alleviates the driver's stress under high cognitive load or anxiety, avoiding information overload, but also significantly improves the driver's decision-making efficiency and accuracy in complex traffic environments by ensuring the effective transmission and understanding of key information. Therefore, this application can provide drivers with more humane and safer charging dispatch assistance, thereby further ensuring driving safety.

[0065] For example, suppose an electric vehicle is en route to a designated charging station when it encounters a serious traffic accident ahead, causing severe traffic congestion. By continuously monitoring the driver's physiological response data, such as heart rate and skin conductivity, as well as driving behavior data, such as steering wheel angle rate and accelerator pedal depth, the system calculates a significant increase in the driver's immediate stress index. In this situation, the system will immediately respond by automatically reducing the visual brightness of the navigation screen and lowering the volume of the voice announcements to minimize additional stimulation to the driver. Simultaneously, the navigation interface will quickly switch, highlighting only two core decision options: continue to the original charging station, with an estimated arrival time extended by 45 minutes and potentially insufficient battery power; or choose the nearest alternative charging station, with an estimated arrival time extended by only 15 minutes, but requiring a detour. All non-essential background traffic information, such as minor road conditions or entertainment information, is temporarily hidden. If a driver shows significant hesitation after receiving these core decision options, such as failing to make a choice within 10 seconds, resulting in a prolonged decision-making reaction time, the two core decision options and their key consequences will be immediately repeated, for example, "Please note that the original charging station is expected to be delayed by 45 minutes, and the battery may be insufficient. The alternative charging station is expected to be delayed by 15 minutes. Please choose as soon as possible." This dynamically adjusted information presentation method effectively helps drivers concentrate on the most critical decisions under high-pressure and information-processing difficulties, thereby improving decision-making efficiency and safety.

[0066] In some embodiments, the vehicle operation information includes the vehicle's real-time location information, battery status information, and motion information; the real-time traffic information includes real-time traffic congestion information and road topology; and the charging station related information includes real-time charging station occupancy information, charging station power supply capacity information, and charging station layout information.

[0067] Specifically, vehicle operation information refers to data related to the vehicle's own state and behavior. Real-time location information can be obtained by the onboard Global Positioning System (GPS) module to accurately determine the vehicle's geographical coordinates within the road network. Battery status information includes the battery's current charge level, health status, number of charging cycles, and estimated driving range; this data is crucial for assessing the vehicle's energy consumption and charging needs. Motion information includes the vehicle's speed, acceleration, direction, and driving trajectory; this data helps predict the vehicle's energy consumption patterns in specific traffic environments.

[0068] Real-time traffic information refers to data reflecting the current state of the road network. Real-time traffic congestion information can originate from real-time data from traffic management departments, third-party map service providers, or be obtained through vehicle-mounted sensors (such as millimeter-wave radar and cameras) that perceive and analyze surrounding traffic flow. This information is used to assess road efficiency and estimated travel time. Road topology refers to the structural information of the road network, including road connections, number of lanes, speed limits, and gradients. This information plays a fundamental role in planning charging routes and predicting energy consumption.

[0069] Charging station related information refers to data related to charging facilities and their service capabilities. Real-time charging station occupancy information can be provided by the charging station operator or obtained through local sensing when vehicles arrive at the station (such as cameras identifying queuing vehicles), used to understand the availability of charging piles. Charging station power supply capacity information refers to the maximum charging power the charging station can provide, the type of charging pile (such as fast charging, slow charging), and the number of vehicles that can be served simultaneously. This information directly affects vehicle charging efficiency and waiting time. Charging station layout information includes the charging station's geographical location, entrance direction, internal driveway design, and surrounding environment. This information is crucial for assessing the actual accessibility and convenience of the charging station.

[0070] Through the aforementioned technical solution, this application provides more comprehensive, accurate, and detailed data input for traffic congestion charging scheduling methods, significantly improving the accuracy of assessments of vehicle energy consumption, charging station service capacity, and personalized charging efficiency. Specifically, the clear definition of vehicle operation information, real-time traffic information, and charging station-related information enables scheduling decisions to be based on more realistic and detailed data, effectively avoiding assessment biases and scheduling errors caused by ambiguous or missing information. Therefore, the technical solution of this application ensures that the identified target charging stations and charging routes are more consistent with actual conditions, improving the reliability of charging scheduling and user satisfaction, thereby optimizing the charging experience for vehicles in traffic congestion environments.

[0071] In some embodiments, the step of making a local judgment on the rationality of the target charging station and the charging route based on vehicle-mounted local perception data and navigation information, and obtaining a local judgment result, specifically includes: Based on the real-time location information, the vehicle-mounted camera is used to identify the entrance area of ​​the target charging station to detect the number of vehicles queuing in real time and the occupancy status of charging piles; millimeter-wave radar is used to perceive the real-time traffic flow density and vehicle speed distribution of the road ahead; traffic condition information broadcast by surrounding vehicles and queuing information shared by the target charging station are received; and lidar and ultrasonic sensors are used to scan the surrounding environment of the target charging station to assess its actual physical accessibility. Based on the acquired real-time location and motion information, road topology and charging station layout information, real-time number of queuing vehicles and charging pile occupancy status, real-time traffic flow density and vehicle speed distribution, traffic condition information and queuing information shared by the target charging station, as well as the actual physical accessibility of the target charging station, a preset path evaluation algorithm is used to generate a local judgment result on the rationality of the target charging station and the charging route. The path evaluation algorithm is configured to identify micro-situations such as internal lane congestion, temporary occupation of charging piles, or mismatched sizes, and to correct the local judgment result based on the identified micro-situations.

[0072] The path evaluation algorithm is configured to identify micro-situations such as internal lane congestion, temporary occupation of charging piles, or mismatched sizes, and to correct local judgment results based on the identified micro-situations.

[0073] Among them, the vehicle-mounted camera can be understood as a visual sensor installed on the vehicle. Its purpose is to acquire image information of the entrance area of ​​the target charging station, and to identify the number of vehicles queuing in real time and the occupancy status of charging piles through image processing technology, thereby providing intuitive on-site data.

[0074] Millimeter-wave radar is a sensor that uses millimeter-wave electromagnetic waves for detection. Its purpose is to sense the real-time traffic flow density and vehicle speed distribution on the road in front of the vehicle, providing accurate data for assessing the real-time congestion of the charging route.

[0075] Traffic information broadcast by surrounding vehicles and queuing information shared by the target charging station refer to real-time data obtained through vehicle-to-everything (V2X) technology or charging station management systems. Their purpose is to supplement the deficiencies of local sensor data and provide more macroscopic and comprehensive traffic and charging station status information.

[0076] A route evaluation algorithm is a pre-defined computational model or program designed to comprehensively analyze multi-source data and quantitatively assess the feasibility of target charging stations and charging routes. This algorithm is specifically configured to identify "micro-situations" such as "internal lane congestion, temporary occupancy of charging piles, or size mismatch," which refer to localized problems within or near the charging station that may affect charging efficiency or accessibility. For example, "internal lane congestion" might refer to localized congestion caused by inefficient vehicle scheduling within the charging station; "temporary occupancy of charging piles" might mean that a charging pile, although displayed as available, is occupied by a non-charging vehicle; and "size mismatch" might mean that the charging pile or parking space is not the appropriate size for the current vehicle. Based on the identification of these micro-situations, the route evaluation algorithm can correct initial local judgments to better reflect actual conditions.

[0077] It is precisely because of this rich and detailed perception data that the path evaluation algorithm can identify micro-level situations that are difficult to detect using traditional methods, such as internal lane congestion, temporary occupancy of charging stations, or mismatched dimensions. By identifying these micro-level situations, the algorithm can correct its initial local judgment. For example, even if the charging station system shows that there are available charging stations, if the camera detects a long queue at the entrance or the lidar detects that parking spaces are blocked by obstacles, the algorithm will correct its judgment and consider that the charging station is not the optimal choice at present. This correction mechanism makes the local judgment more closely reflect the actual situation when the vehicle arrives, thereby significantly improving the accuracy and reliability of the scheduling strategy.

[0078] Through the above technical solution, this application can significantly improve the accuracy and robustness of local judgment in the traffic congestion charging scheduling method. Compared with relying solely on general vehicle perception data and navigation information for judgment, this technical solution integrates multi-source data such as vehicle cameras, millimeter-wave radar, lidar, ultrasonic sensors, and external broadcast information to achieve refined perception of the real-time queuing situation of the target charging station, the occupancy status of charging piles, the surrounding physical accessibility, and the micro-traffic flow density of the charging route. As a result, the path evaluation algorithm can identify and correct judgment biases caused by micro-congestion, temporary occupancy of charging piles, or incompatible sizes, thereby avoiding the predicament of vehicles arriving at the target charging station only to find that they cannot charge or have difficulty charging. This refined local judgment not only improves the practicality and reliability of the charging scheduling strategy and reduces the anxiety and uncertainty of drivers due to inaccurate information, but also further optimizes the driver's charging experience, ensuring that the scheduling strategy can adapt to the complex and ever-changing actual traffic and charging environment.

[0079] For example, suppose an electric vehicle is driving on a city road, and a target charging station and a charging route are recommended based on the initial assessment. When the vehicle approaches the target charging station, the local decision-making module begins to operate.

[0080] Specifically, the vehicle's onboard camera captures real-time images of the target charging station's entrance area, identifying three vehicles queuing to enter. It also detects that two charging piles, while appearing available in the charging station system, are actually being temporarily occupied by non-charging vehicles. Simultaneously, millimeter-wave radar continuously monitors traffic flow ahead, detecting a sudden increase in traffic density and a significant decrease in vehicle speed 500 meters from the charging station, indicating localized congestion. LiDAR and ultrasonic sensors scan the charging station's interior, finding that a parking space next to an available charging pile is partially blocked by a construction fence, making it difficult for vehicles to park smoothly.

[0081] This multi-source sensing data, along with the vehicle's real-time location, attitude, and motion information, as well as road topology and charging station layout information, is input into a pre-defined path evaluation algorithm. The algorithm first generates a local judgment based on the preliminary data, potentially indicating that the target charging station and route are reasonable. However, because the algorithm is configured to identify micro-contexts, it will recognize micro-contexts such as "large number of vehicles queuing at the entrance," "charging stations being temporarily occupied," "partial congestion in internal lanes," and "incorrectly sized (obstructed) charging station parking spaces." Based on these identified micro-contexts, the path evaluation algorithm will revise its local judgment, changing it from "reasonable" to "unreasonable" or "posing a serious risk."

[0082] This presents drivers with the discrepancies between their local assessment and the factors they considered in their decision-making. For example, it might inform drivers that "there are long queues at the target charging station entrance, and some charging piles are occupied; we suggest choosing a different charging station or waiting." Drivers can make more informed choices based on this detailed information, avoiding the frustration of arriving at a charging station only to find they cannot charge, thus improving the effectiveness of charging dispatch and user satisfaction.

[0083] This application also proposes a traffic congestion charging scheduling system, such as... Figure 2 As shown, a traffic congestion charging dispatch system 100 includes: The comprehensive evaluation module 10 is used to comprehensively evaluate the energy consumption of the vehicle in a specific traffic environment, the actual service capacity of the charging station, and the personalized charging efficiency of the vehicle based on the acquired vehicle operation information, real-time traffic information, charging station related information, and the charging preference information set by the driver, and obtain the first evaluation result. The scheduling decision module 20 is used to determine the target charging station and charging route based on the first evaluation result and decision consideration factors. The local judgment module 30 is used to make a local judgment on the rationality of the target charging station and the charging route based on the vehicle local perception data and navigation information, and obtain a local judgment result. The difference display and selection module 40 is used to obtain the selection information made by the driver based on the difference information when there is a difference between the local judgment result and the decision consideration factors, and to adjust the subsequent scheduling strategy according to the selection information.

[0084] Through its modular design, the system enables comprehensive assessment of vehicle charging needs, intelligent scheduling decisions, real-time local verification, and user-friendly interactive adjustments. This effectively addresses the challenges of electric vehicle charging in congested urban areas, improving the utilization efficiency of charging resources and enhancing the charging experience for drivers.

[0085] The traffic congestion charging dispatch system proposed in this application represents a significant advancement over existing technologies. Traditional systems, when faced with complex urban traffic congestion and surges in charging demand, often suffer from inaccurate dispatch solutions due to incomplete information acquisition and simplistic decision-making models. This application's system, by introducing a comprehensive evaluation module, comprehensively considers vehicle energy consumption under specific traffic conditions, the actual service capacity of charging stations, and the personalized charging efficiency of vehicles. This overcomes the limitations of existing systems that rely solely on basic availability and geographical distance, significantly improving the accuracy of charging time prediction.

[0086] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for scheduling charging during traffic congestion, characterized in that, include: Based on the acquired vehicle operation information, real-time traffic information, charging station information and driver-set charging preference information, a comprehensive evaluation is conducted on the vehicle's energy consumption in a specific traffic environment, the actual service capacity of the charging station and the vehicle's personalized charging efficiency to obtain the first evaluation result. Based on the first assessment results, the target charging station and charging route are determined according to the decision-making considerations. Based on the vehicle's local perception data and navigation information, the rationality of the target charging station and the charging route is locally determined, and a local determination result is obtained. When there is a difference between the local judgment result and the decision consideration factors, the driver's selection information based on the difference information is obtained, and the subsequent scheduling strategy is adjusted according to the selection information.

2. The traffic congestion charging scheduling method of claim 1, wherein, After the step of making a local judgment on the rationality of the target charging station and the charging route based on the vehicle's local perception data and navigation information, and obtaining the local judgment result, the following steps are included: When there is a difference between the local judgment result and the decision consideration factors, the driver's facial expression, eye movement trajectory, head posture and steering wheel grip data are analyzed to obtain a second assessment result of the driver's current cognitive load and emotional state. Adjust the information presentation strategy based on the second evaluation results.

3. The traffic congestion charging scheduling method of claim 2, wherein, The step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, the key differences between the decision-making considerations and the local judgment result are extracted and highlighted. The estimated time, estimated power consumption and congestion level of the target charging station and the charging route are compared and displayed in a graphical manner, and decision-making assistance prompts are provided to the driver.

4. The traffic congestion charging scheduling method of claim 2, wherein, When there is a difference between the local judgment result and the decision consideration factors, the step of analyzing the driver's facial expression, eye movement trajectory, head posture, and steering wheel grip data to obtain the second assessment result of the driver's current cognitive load and emotional state includes: An infrared camera is used to capture an image of the driver's face to obtain an infrared image, and a visible light camera is used to capture an image of the driver's face to obtain a visible light image; The infrared image and the visible light image are fused to obtain a fused image; The driver's key facial feature points in the fused image are identified. Based on the driver's key facial feature points, facial expression, eye movement trajectory, head posture, and steering wheel grip data, the driver's current cognitive load and emotional state are assessed to obtain a second assessment result.

5. The traffic congestion charging scheduling method of claim 2, wherein, The step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, slow down the information broadcasting speed, extend the display time of key information, give priority to voice broadcasting and concise visual cues, and use reassuring and encouraging language; When the second assessment result indicates that the driver is in a state of low cognitive load or relaxation, speed up the information broadcasting, shorten the display time of non-critical information, provide detailed text information and interactive options, and use neutral and objective language; Adjust the visual elements of the information presentation based on the complexity of the vehicle's current driving environment and the driver's preference for the way information is presented.

6. The traffic congestion charging dispatching method of claim 2, wherein, The step of adjusting the information presentation strategy based on the second evaluation result includes: When the second assessment result shows that the driver is in a state of high cognitive load or anxiety, the driver's physiological response data is continuously monitored, including heart rate, skin conductivity, and driving behavior data, including accelerator pedal depth, brake pedal pressure, and steering wheel angle rate. Based on the physiological response data and the driving behavior data, calculate the driver's instantaneous stress index and decision-making reaction time; The intensity of information presentation is dynamically adjusted based on the instantaneous stress index and the decision-making reaction time.

7. The traffic congestion charging scheduling method of claim 6, wherein, The step of dynamically adjusting the intensity of information presentation based on the instantaneous stress index and the decision-making reaction time includes: When the instantaneous stress index increases, reduce the visual brightness or volume of the information presentation, prioritize the presentation of core decision options and their direct consequences, and reduce background information; When the decision-making response time is prolonged, the number of times key information is repeatedly broadcast should be increased.

8. The traffic congestion charging scheduling method of any one of claims 1-7, wherein, The vehicle operation information includes the vehicle's real-time location information, battery status information, and motion information; the real-time traffic information includes real-time traffic congestion information and road topology; the charging station related information includes real-time charging station occupancy information, charging station power supply capacity information, and charging station layout information.

9. The traffic congestion charging scheduling method of claim 8, wherein, The step of making a local judgment on the rationality of the target charging station and the charging route based on vehicle-mounted local perception data and navigation information, and obtaining the local judgment result, specifically includes: Based on the real-time location information, the vehicle-mounted camera is used to identify the entrance area of ​​the target charging station to detect the number of vehicles queuing in real time and the occupancy status of charging piles; millimeter-wave radar is used to perceive the real-time traffic flow density and vehicle speed distribution of the road ahead; traffic condition information broadcast by surrounding vehicles and queuing information shared by the target charging station are received; and lidar and ultrasonic sensors are used to scan the surrounding environment of the target charging station to assess its actual physical accessibility. Based on the acquired real-time location and motion information, road topology and charging station layout information, real-time number of queuing vehicles and charging pile occupancy status, real-time traffic flow density and vehicle speed distribution, traffic condition information and queuing information shared by the target charging station, as well as the actual physical accessibility of the target charging station, a preset path evaluation algorithm is used to generate a local judgment result on the rationality of the target charging station and the charging route. The path evaluation algorithm is configured to identify micro-situations such as internal lane congestion, temporary occupation of charging piles, or mismatched sizes, and to correct the local judgment result based on the identified micro-situations.

10. A traffic congestion charging dispatch system, characterized in that, The system includes: The comprehensive evaluation module is used to comprehensively evaluate the energy consumption of the vehicle in a specific traffic environment, the actual service capacity of the charging station, and the personalized charging efficiency of the vehicle based on the acquired vehicle operation information, real-time traffic information, charging station information, and the charging preference information set by the driver, and obtain the first evaluation result. The scheduling decision module is used to determine the target charging station and charging route based on the first evaluation result and decision consideration factors. The local judgment module is used to make a local judgment on the rationality of the target charging station and the charging route based on the vehicle's local perception data and navigation information, and obtain a local judgment result. The difference display and selection module is used to obtain the driver's selection information based on the difference information when there is a difference between the local judgment result and the decision consideration factors, and to adjust the subsequent scheduling strategy according to the selection information.

Images