Vehicle-mounted driving ability evaluation method and device, vehicle and medium

Abstract

The invention discloses a vehicle-mounted driving ability evaluation method and device, a vehicle and a medium, and relates to the technical field of driving safety. The method comprises the following steps: in response to the end of a travel, performing fusion analysis on multi-dimensional driving behavior data based on a plurality of predefined evaluation dimensions to generate a dimension score of each evaluation dimension; based on the dimension score of each evaluation dimension, calculating a comprehensive driving score of the journey, and outputting a visual evaluation report; and based on the visual evaluation report, executing integral incentive logic to update the driving ability integral data of the user. According to the scheme, the vehicle-mounted driving ability evaluation method capable of performing multi-dimensional fusion analysis, providing visual and visual feedback and being linked with the excitation system to form a closed loop is broken through and constructed, and the behavior level of a driver can be comprehensively, interactively and continuously improved.

Description

Technical Field

[0001] This disclosure relates to the field of driving safety technology, and in particular to a method, device, vehicle, and medium for assessing vehicle driving capabilities. Background Technology

[0002] Currently, in-vehicle driving ability assessment technologies mostly focus on monitoring and alerting for single driving behaviors or limited indicators, such as counting the number of times rapid acceleration or sudden braking occurs, or providing immediate warnings when speeding occurs. These methods often only make isolated judgments on localized operations and lack a multi-dimensional and systematic assessment of the driver's overall driving ability.

[0003] Furthermore, existing assessment feedback methods primarily rely on simple visual or auditory warnings, such as dashboard warning lights or voice prompts, lacking intuitive and visual representations. This one-way, static feedback format fails to effectively capture the driver's sustained attention and cannot help the driver understand the distribution of their driving behavior's strengths and weaknesses through intuitive comparisons, thus reducing user stickiness and willingness to use the driving assessment system.

[0004] Therefore, how to construct an in-vehicle driving ability assessment method that can perform multi-dimensional integrated analysis, provide intuitive and visual feedback, and link with the incentive system in a closed loop, so as to comprehensively, interactively, and continuously improve the level of driver behavior, has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] In view of the above problems, this disclosure provides a method, device, vehicle, and medium for assessing vehicle driving capability to overcome or at least partially solve the above problems. The technical solution is as follows: A method for assessing in-vehicle driving ability includes: real-time collection of multi-dimensional driving behavior data during vehicle operation; in response to the end of the trip, performing fusion analysis on the multi-dimensional driving behavior data based on multiple predefined assessment dimensions to generate dimensional scores for each assessment dimension; calculating a comprehensive driving score for the trip based on the dimensional scores for each assessment dimension and outputting a visual evaluation report; and executing an incentive logic based on the visual evaluation report to update the user's driving ability score data.

[0006] This disclosure provides a method for assessing in-vehicle driving ability. By collecting multi-dimensional driving behavior data in real time and performing a fusion analysis based on multiple predefined assessment dimensions after the trip, it generates an evaluation result including a comprehensive score and a visual report. This is linked to a points-based incentive logic to update the user's points, achieving a systematic and closed-loop assessment and guidance of driving ability. This method not only overcomes the limitations of past single-dimensional assessments by comprehensively and three-dimensionally reflecting the driver's overall driving level through the fusion analysis of multiple predefined assessment dimensions, but also transforms the analysis results into an intuitive visual evaluation report and connects with a points-based incentive logic. This links technical assessment with behavioral incentives, effectively solving the problems of one-sided assessment, abstract feedback, and disconnect from driving behavior optimization in existing technologies. It provides users with an integrated experience that spans trip assessment and long-term habit cultivation.

[0007] Optionally, the step of fusing and analyzing the multidimensional driving behavior data based on multiple predefined evaluation dimensions to generate dimensional scores for each evaluation dimension specifically includes: determining multiple behavioral evaluation items corresponding to each evaluation dimension based on a preset scoring logic corresponding to each evaluation dimension; extracting multiple behavioral evaluation data corresponding to the multidimensional driving behavior data based on the multiple behavioral evaluation items, and determining the scores of multiple evaluation items corresponding to the multiple behavioral evaluation data based on the scoring logic; and performing a weighted calculation on the scores of the multiple evaluation items corresponding to each evaluation dimension to obtain the dimensional scores for each evaluation dimension.

[0008] This embodiment defines the specific steps of multidimensional fusion analysis. By pre-setting scoring logic and multi-level weighted calculation, it enhances the granularity and objectivity of the assessment. This feature breaks down each assessment dimension into multiple specific behavioral assessment items and performs independent scoring and weighted summarization based on corresponding data extracted from multidimensional driving behavior data. This ensures that the final dimension score is not a general judgment but is based on specific and quantifiable behavioral data, thereby significantly improving the accuracy, interpretability, and credibility of the assessment results and laying a solid data foundation for the subsequent accurate generation of improvement suggestions.

[0009] Optionally, the step of calculating the comprehensive driving score for the current trip based on the dimensional scores of each evaluation dimension and outputting a visual evaluation report specifically includes: calculating the comprehensive driving score data according to the dimensional scores of each evaluation dimension and the predefined weight coefficients corresponding to each evaluation dimension; mapping the comprehensive driving score data to a predefined evaluation level range to generate a corresponding driving ability level; determining the weakest dimension of the current trip based on the dimensional scores of each evaluation dimension, and matching and generating personalized driving suggestion information for the weakest dimension in a preset improvement suggestion library; integrating the comprehensive driving score data, the driving ability level, the dimensional score data of each evaluation dimension, the scores of multiple evaluation items corresponding to each evaluation dimension, and the personalized driving suggestion information into a preset evaluation report template to generate the visual evaluation report.

[0010] This embodiment refines the generation logic of the visual evaluation report, enhancing its guiding value and user experience by integrating comprehensive scoring, level mapping, and personalized suggestions. This feature not only integrates multi-dimensional scores into easily understandable driving ability levels but also proactively identifies weaknesses in the current trip and generates targeted, personalized driving suggestions. The resulting visual evaluation report is not only a summary of driving skills but also a concrete guide for behavioral optimization, upgrading feedback from simply "informing about results" to "guiding action." This significantly enhances the report's practical utility and user engagement, directly driving targeted improvements in driving habits.

[0011] Optionally, the evaluation report template includes a driving ability radar chart, which is used to display the dimensional score data of each evaluation dimension in a graphical style. After outputting the visual evaluation report, the method further includes: responding to the user's interactive request to the graphical area corresponding to any evaluation dimension in the driving ability radar chart, obtaining the scores of multiple evaluation items corresponding to any evaluation dimension; and calling the secondary extended interface of the evaluation report template to display the scores of multiple evaluation items for any evaluation dimension.

[0012] This embodiment enhances the interactive depth and information transparency of the visual report by introducing an interactive driving ability radar chart and a secondary extended interface. The radar chart intuitively presents the multi-dimensional balance of driving ability in a highly condensed graphical format, while user interactions with specific dimensions can trigger the display of more detailed behavioral assessment scores for that dimension. This "overall score overview - details available" interactive design maintains a simple interface while meeting users' needs for in-depth understanding of their own driving details, improving the interactivity and exploratory nature of the assessment system, and making the assessment process more transparent and user-friendly.

[0013] Optionally, the step of executing the points incentive logic based on the visual evaluation report to update the user's driving ability points data specifically includes: querying a preset points reward and punishment mapping rule according to the comprehensive evaluation level contained in the visual evaluation report to determine the points change value corresponding to this trip; updating the user's accumulated historical driving ability points data based on the points change value to obtain updated driving ability points data; and updating the friend ranking list based on the updated driving ability points data; wherein, the user ranking information corresponding to the friend ranking list includes the current rank information and the current rank driving ability points data.

[0014] In this embodiment, a continuous cycle of positive incentives and social competition is constructed by dynamically linking evaluation levels with changes in points and the friend leaderboard. This feature instantly converts the evaluation results of a single trip into points, which cumulatively affect the user's dynamic ranking in the friend leaderboard. This design combines the improvement of driving skills with gamified point accumulation and social comparison, stimulating the user's ambition and sense of honor. It transforms the originally passive requirement of safe driving into an active, fun, and socially engaging goal pursuit, thereby forming a long-term intrinsic motivation that drives users to continuously optimize their driving behavior.

[0015] Optionally, after updating the user's currently accumulated driving ability points based on the points change value to obtain updated driving ability points, the method further includes: comparing the current rank driving ability points data with a preset rank level points range to determine whether rank upgrade or downgrade conditions are triggered; if triggered, generating a future trip evaluation task according to preset upgrade / downgrade evaluation rules to evaluate a preset number of future driving trips that meet the evaluation conditions; and determining whether to upgrade / downgrade based on the evaluation results of the preset number of driving trips.

[0016] This embodiment introduces a points-based rank promotion and demotion mechanism. By adding an evaluation step for promotion and demotion, it ensures the rigor and fairness of rank changes. This feature avoids frequent rank fluctuations caused by simple accumulation or deduction of points. Instead, after setting trigger conditions, it comprehensively judges the results of multiple consecutive trips, making rank promotion and demotion more reflective of the driver's stable driving level over a period of time, rather than the accidental performance of a single trip. This enhances the authority, fairness, and user acceptance of the rank system, and strengthens the robustness of the entire incentive system.

[0017] Optionally, after updating the friend ranking based on the updated driving ability score data, the method further includes: responding to the user's sharing instruction for the visual evaluation report or the friend ranking by calling a graphics compositing interface; using the graphics compositing interface to fuse key data elements in the visual evaluation report or the friend ranking with a preset sharing template layout to generate a static image or dynamic page for sharing; and responding to the user's selection operation on the sharing selection interface by uploading and publishing the static image or the dynamic page through the corresponding third-party social platform interface.

[0018] This embodiment provides a one-click social sharing function, conveniently extending personal driving achievements to social networks and expanding the influence and social value of the evaluation system. This feature can automatically synthesize key information from visual reports or leaderboards into easily shareable graphic and text content, supporting publication on mainstream social platforms. This not only satisfies users' social needs for self-expression and sharing achievements but also fosters positive interactions and word-of-mouth regarding safe driving within social circles, thereby popularizing the concept of safe driving on a larger scale and enhancing the social benefits of this technical solution and the interaction and stickiness among user groups.

[0019] An in-vehicle driving ability assessment device includes: a data acquisition module for real-time acquisition of multi-dimensional driving behavior data during vehicle operation; a response module for, upon completion of the current trip, fusing and analyzing the multi-dimensional driving behavior data based on multiple predefined assessment dimensions to generate dimensional scores for each assessment dimension; a calculation module for, calculating a comprehensive driving score for the current trip based on the dimensional scores for each assessment dimension, and outputting a visual evaluation report; and an integration module for, executing integration incentive logic based on the visual evaluation report to update the user's driving ability integration score data.

[0020] A vehicle includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform: real-time acquisition of multi-dimensional driving behavior data during vehicle operation; in response to the end of the current trip, performing fusion analysis on the multi-dimensional driving behavior data based on multiple predefined evaluation dimensions to generate dimensional scores for each evaluation dimension; calculating a comprehensive driving score for the current trip based on the dimensional scores for each evaluation dimension, and outputting a visual evaluation report; and executing an incentive logic based on the visual evaluation report to update the user's driving ability score data.

[0021] A computer-readable storage medium stores computer-executable instructions, the computer-executable instructions being configured to: collect multi-dimensional driving behavior data during vehicle operation in real time; in response to the end of the current trip, perform fusion analysis on the multi-dimensional driving behavior data based on multiple predefined evaluation dimensions to generate dimensional scores for each evaluation dimension; calculate a comprehensive driving score for the current trip based on the dimensional scores for each evaluation dimension, and output a visual evaluation report; and execute points incentive logic based on the visual evaluation report to update the user's driving ability points data. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating an embodiment of an on-board driving capability assessment method is shown. Figure 2 A schematic diagram of a visual evaluation report according to an embodiment of this disclosure is shown; Figure 3 A schematic diagram of the structure of an on-board driving ability assessment device according to an embodiment of this disclosure is shown; Figure 4 A schematic diagram of the structure of a vehicle according to an embodiment of the present disclosure is shown. Detailed Implementation

[0023] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0024] With the deep integration of vehicle intelligence and connectivity technologies, the functional focus of in-vehicle systems is gradually evolving from basic performance monitoring to driver behavior guidance and experience optimization. Against this backdrop, in-vehicle driving ability assessment, as a key technology for improving driving safety and cultivating good driving habits, is becoming increasingly important. However, existing mainstream assessment schemes mostly focus on isolated monitoring and simple scoring of basic vehicle control signals (such as rapid acceleration and deceleration), and their technical framework has obvious limitations: First, the assessment dimensions are highly singular, usually only focusing on a few mechanical indicators such as driving smoothness, and failing to systematically integrate multi-dimensional factors that affect driving safety and quality, such as safety awareness, rule compliance, road condition adaptation, emergency handling, and passenger experience. This results in a one-sided assessment profile that cannot truly reflect the driver's comprehensive ability level. Second, the feedback mechanism is non-visual and has low interactivity, relying mostly on warning lights or simple text prompts. It lacks intuitive and vivid multi-dimensional capability displays (such as radar charts) and fails to provide personalized improvement guidance based on weakness analysis. The human-computer interaction experience is rigid and its effectiveness is limited. Third, existing schemes generally lack the design to deeply integrate assessment results with long-term incentive mechanisms and social interaction functions. Their "assessment-feedback" link has a break, making it difficult to stimulate drivers' intrinsic motivation to continuously optimize driving behavior and unable to form a positive safe driving culture through social interaction.

[0025] Specifically, traditional solutions have the following technical shortcomings: 1. Fragmented Data Sources and Limited Evaluation Dimensions: Existing technologies typically acquire limited control signals (such as accelerator and brake opening) from the vehicle bus and make independent judgments based on preset thresholds. This approach fails to perform spatiotemporal alignment and fusion analysis of heterogeneous data from multiple sources, including driver monitoring systems, environmental perception sensors, and high-precision positioning, and it also fails to construct a comprehensive evaluation model covering operation, awareness, rules, and experience. For example, in complex urban road conditions, the system may only record one instance of sudden braking and deduct points, but it cannot correlate or determine whether the braking was due to following too closely (insufficient safety awareness) or avoiding a pedestrian suddenly crossing (appropriate risk prediction), leading to an evaluation conclusion that may deviate from actual driving ability.

[0026] 2. Static Feedback and Lack of Incentives: Mainstream systems simplify evaluation results into a static score or grade at the end of the trip, resulting in rigid and monotonous feedback. The systems lack the ability to generate targeted improvement suggestions based on multi-dimensional score differences, and they do not dynamically link scoring results with gamified points, rankings, or other incentive elements. For example, even if a driver repeatedly achieves the same total score, it's impossible to know their specific progress or regression in the dimensions of "safety awareness" and "riding experience," and they cannot obtain positive incentives for continuous optimization through point accumulation and leaderboard competition. This leads to a lack of effective link between evaluation behavior and habit improvement.

[0027] 3. Rigid Interaction Logic and Lack of Social Loop: The existing solution's interaction design is mainly based on one-way information output, preventing users from exploring the evaluation results in depth (such as clicking to view detailed deductions for a specific dimension). Furthermore, the evaluation results are confined to a single bike ride or trip, lacking convenient and user-friendly social sharing features. This fails to meet users' social needs for showcasing achievements and comparing themselves with others, making it difficult for the technical solution to generate a spread effect and maintain its appeal within the user community.

[0028] Therefore, this application provides a method for evaluating in-vehicle driving capabilities. Figure 1 This diagram illustrates a process flow for an in-vehicle driving capability assessment method provided in one or more embodiments of this specification. The method can be applied to different types of vehicles, and the process can be executed by computing devices in the relevant field (e.g., controllers installed in the vehicle, in-vehicle systems, or servers located in the cloud). Certain input parameters or intermediate results in the process can be manually adjusted to help improve accuracy.

[0029] The analysis method disclosed in this embodiment can be implemented using a terminal device or a server, and this application does not impose any special limitations on it. For ease of understanding and description, the following embodiments are all described in detail using a server as an example. It should be noted that the server can be a single device or a system composed of multiple devices, i.e., a distributed server, and this application does not impose any specific limitations on it.

[0030] like Figure 1 As shown, this disclosure provides a method for evaluating vehicle driving capabilities, including: Step 101: Collect multi-dimensional driving behavior data in real time during vehicle operation.

[0031] Firstly, it's understandable that "real-time acquisition" means that data acquisition is synchronized with the actual driving process of the vehicle. The data stream starts at the beginning of the trip and ends at the end, thus ensuring the timeliness and continuity of the information used for evaluation and avoiding evaluation biases that may result from using outdated or historical data. It's important to note that "real-time" here does not mean zero latency in a strict sense, but rather continuous or high-frequency sampling and recording of relevant signals within the processing capabilities of the onboard electronic system to capture the dynamic details of driving behavior.

[0032] In this embodiment, the "multidimensional driving behavior data" is a comprehensive dataset encompassing multi-source information such as vehicle status, driver behavior, external environment, and occupant interaction. Its "multidimensional" characteristic is reflected in the diversity of data sources and the breadth of driving behavior aspects reflected by the data.

[0033] For example, this data can be obtained primarily through, but not limited to, the following methods: First, by acquiring the vehicle's own dynamic and status signals from various electronic control units via the vehicle controller local area network bus. For instance, by reading the accelerator pedal opening and its rate of change, and the brake pedal opening and its rate of change from the vehicle controller or engine controller, in order to quantify the driver's acceleration and braking operation characteristics; by acquiring steering wheel angle signals from the electric power steering system, in order to analyze the smoothness and accuracy of steering operations; and by acquiring the status of light switches, turn signals, seat belt buckles, and defrosting / defogging functions from the body control module, in order to determine the driver's proper use of vehicle assistance functions.

[0034] Secondly, the driver's own status data is obtained through an integrated driver monitoring system. This system usually includes a built-in camera and infrared sensor facing the driver and runs a dedicated visual analysis algorithm. It can identify and output the driver's head posture angle (used to determine the direction of the gaze and the frequency of observation of the rearview mirror), eye status (such as the degree of eyelid closure and blinking frequency, used to monitor fatigue level), and specific behaviors (such as holding a phone, smoking, and taking the road out of sight for a long time). This data is a direct basis for assessing the driver's concentration and compliance.

[0035] Third, the vehicle acquires data on the relative relationship between the external environment and the vehicle through its environmental perception sensor suite. For example, forward-facing millimeter-wave radar, vision cameras, or lidar can be used to perceive vehicles, pedestrians, or other obstacles ahead, and calculate the relative distance, relative speed, and time difference between the vehicle and the target. Inertial measurement units can be used to measure the vehicle's acceleration in the longitudinal, lateral, and vertical directions, and this acceleration data is directly related to the ride's smoothness and comfort. By using a high-precision global positioning system combined with high-precision map data, not only can the vehicle's precise location and speed be obtained, but also the current road type (such as highways, urban roads, ramps), curvature, slope, and legal speed limits can be determined. In addition, surround-view cameras or dedicated vision modules can be used to identify traffic light status, lane line types (solid or dashed lines), etc., providing a basis for judging compliance with traffic rules.

[0036] Fourth, specific data can be obtained through other vehicle body sensors or system interfaces. For example, the seat weight sensor or dedicated interface signal can be used to determine whether the child safety seat is installed correctly; the multimedia volume setting value can be obtained through the in-vehicle infotainment system.

[0037] Understandably, the aforementioned multi-source data is typically tagged with a unified or alignable timestamp during collection and undergoes preliminary caching and preprocessing (such as format standardization and invalid value filtering) in the vehicle's domain controller or dedicated data acquisition module, forming a spatiotemporally synchronized multi-dimensional data sequence. For example, in a typical urban commuting scenario, when a vehicle is following another vehicle in congested traffic, the system not only continuously records every press and release of the brake pedal (reflecting basic operations), but the DMS system also analyzes whether the driver frequently checks the interior and exterior rearview mirrors to understand the surrounding traffic dynamics (reflecting safety awareness), the forward radar continuously calculates the real-time distance to the vehicle ahead (reflecting distance control), and the positioning and map data confirm that the vehicle is traveling on a solid line segment of an urban expressway (compliance with association rules). All of this data collectively constitutes a panoramic description of the following behavior, providing the possibility for subsequent fusion analysis and multi-dimensional evaluation.

[0038] Step 102: In response to the end of this trip, the multidimensional driving behavior data is fused and analyzed based on multiple predefined evaluation dimensions to generate dimensional scores for each evaluation dimension.

[0039] Understandably, the "response to the end of this trip" is used as the trigger condition for the analysis process. This condition can be determined in various ways, such as when the vehicle is detected to be in P gear for an extended period of time, the ignition switch is turned off, or the in-vehicle navigation system determines that the destination has been reached and a preset stationary delay has elapsed. In such cases, the system will automatically start the analysis engine for this step to ensure the timeliness of the evaluation.

[0040] In this embodiment, the "predefined multiple evaluation dimensions" constitute the theoretical framework for evaluating driving ability. For example, this embodiment defines an evaluation system comprising six core dimensions: basic operation, safety awareness, road condition adaptation, rule compliance, emergency handling, and passenger experience. Each dimension aims to characterize a specific and important aspect of driving ability. For instance, the "basic operation" dimension focuses on the driver's proficiency and standardization in operating basic control components such as vehicle acceleration, braking, and steering; while the "safety awareness" dimension emphasizes assessing the driver's ability to continuously observe the surrounding environment, anticipate risks, and proactively defend against them. It should be noted that the setting, naming, and number of dimensions are not fixed; their fundamental purpose is to systematically cover the key factors affecting driving safety and quality. The six-dimensional division in this embodiment is a preferred, not exclusive, implementation method.

[0041] In one specific embodiment of this disclosure, the step of fusing and analyzing the multidimensional driving behavior data based on predefined multiple evaluation dimensions to generate dimensional scores for each evaluation dimension specifically includes: determining multiple behavioral evaluation items corresponding to each evaluation dimension based on a preset scoring logic corresponding to each evaluation dimension; extracting multiple behavioral evaluation data corresponding to the multidimensional driving behavior data based on the multiple behavioral evaluation items, and determining the scores of multiple evaluation items corresponding to the multiple behavioral evaluation data based on the scoring logic; and performing a weighted calculation on the scores of the multiple evaluation items corresponding to each evaluation dimension to obtain the dimensional scores for each evaluation dimension.

[0042] Based on the above fusion analysis process, it can be understood that for each predefined evaluation dimension (such as "basic operation"), it is first necessary to determine the multiple specific "behavioral evaluation items" it includes based on the evaluation objectives of that dimension. For example, the "basic operation" dimension can be decomposed into multiple evaluation items such as "acceleration operation", "braking operation", "steering operation", "light usage", and "defogger function usage". Each behavioral evaluation item is associated with a pre-set, detailed "scoring logic".

[0043] Furthermore, the system extracts "behavioral evaluation data" corresponding to each behavioral evaluation item from the multidimensional driving behavior data cached in step 101. For example, for the "braking operation" evaluation item, it extracts the time series data of the "brake pedal position change rate" for the entire journey; for the "environmental observation" evaluation item under the "safety awareness" dimension, it extracts the "driver head posture angle" data and corresponding contextual data such as "vehicle gear" and "vehicle speed" provided by the DMS system. Then, the "scoring logic" for this evaluation item is applied to calculate these data. The scoring logic typically includes rules such as statistics, threshold comparison, and frequency analysis.

[0044] For example, the scoring logic for "braking operation" could be as follows: The number of times the "brake pedal position change rate exceeds a certain calibrated threshold" during the braking stroke is counted and defined as an "emergency braking" event; then, a specific evaluation item score (e.g., 10 points, 7 points, 4 points) is mapped to the preset range (e.g., 0-2 times, 3-5 times, more than 5 times) of the number of "emergency braking" events. As another example, the scoring logic for "environmental observation" might be more complex, requiring consideration of the current road type (provided by a high-precision map) and vehicle speed to determine whether the driver's frequency of observing the interior / exterior rearview mirrors conforms to the safety standard model for that scenario, and then a score is calculated based on the degree of conformity.

[0045] Furthermore, after obtaining the scores for all behavioral assessment items within an evaluation dimension, the system performs a weighted calculation according to the pre-assigned weights for each assessment item, and finally sums them to obtain the "dimensional score" for that dimension. For example, within the "basic operations" dimension, "acceleration operations," "braking operations," and "steering operations" may be assigned higher weights, while "light usage" may have a relatively lower weight, reflecting the different levels of importance of different operational items in basic driving skills. Through this hierarchical and weighted fusion analysis from specific behaviors to assessment items, and then to dimensions, the final "dimensional score" not only quantifies the driver's overall performance level in that dimension, but also has good interpretability and data support, as it can be traced back to specific deduction or bonus behaviors.

[0046] Step 103: Based on the dimensional scores of each evaluation dimension, calculate the comprehensive driving score for this trip and output a visual evaluation report.

[0047] Understandably, the purpose of this step is to transform the relatively independent "dimensional scores" into a comprehensive driving ability evaluation, and to provide feedback to the driver in the form of a highly visual, information-rich, and interactive "visual evaluation report," thereby completing a closed loop from data analysis to user cognition and behavioral guidance.

[0048] In a specific embodiment of this disclosure, the step of calculating the comprehensive driving score for the current trip based on the dimensional scores of each evaluation dimension and outputting a visual evaluation report specifically includes: calculating the comprehensive driving score data according to the dimensional scores of each evaluation dimension and the predefined weight coefficients corresponding to each evaluation dimension; mapping the comprehensive driving score data to a predefined evaluation level range to generate a corresponding driving ability level; determining the weakness dimension of the current trip based on the dimensional scores of each evaluation dimension, and matching and generating personalized driving suggestion information for the weakness dimension in a preset improvement suggestion library; integrating the comprehensive driving score data, the driving ability level, the dimensional score data of each evaluation dimension, the scores of multiple evaluation items corresponding to each evaluation dimension, and the personalized driving suggestion information into a preset evaluation report template to generate the visual evaluation report.

[0049] In one specific embodiment of this disclosure, the evaluation report template includes a driving ability radar chart, which is used to display the dimensional score data of each evaluation dimension in a graphical style. After outputting the visual evaluation report, the method further includes: responding to a user's interactive request to the graphical area corresponding to any evaluation dimension in the driving ability radar chart, obtaining the scores of multiple evaluation items corresponding to any evaluation dimension; and calling the secondary extended interface of the evaluation report template to display the scores of multiple evaluation items for any evaluation dimension.

[0050] Based on the scoring process described above, it can be understood that this comprehensive score is a single quantitative summary of the overall driving level during this trip. Its calculation method typically employs a weighted summation model, assigning a preset "weight coefficient" to each evaluation dimension based on its relative importance within the overall driving ability model. For example, considering that safety is the core of driving, the weights of "safety awareness" and "basic operation" dimensions might be set relatively high, such as 25% each; while "emergency handling," due to its low frequency of occurrence during regular trips, might have a relatively low weight, such as 5%. The system multiplies each dimension's "dimensional score" by its corresponding weight coefficient, then sums all the products to obtain the "comprehensive driving score." This score is a continuous numerical value, for example, ranging from 0 to 10 or 0 to 100. To help users more intuitively understand their own skill level, the system "maps" this value to a predefined evaluation level range, thereby generating a concise "driving ability level." Exemplary level divisions could be five levels: "S, A, B, C, D," or descriptive levels such as "Excellent, Good, Average, Pass, Needs Improvement." For example, an overall score of 9.2 might correspond to an "S" grade, while 6.5 might correspond to an "A" grade. This hierarchical representation makes it easier for users to quickly grasp their overall performance than simple numbers.

[0051] Furthermore, it can be understood that the "visualized evaluation report" output by the system is not merely displaying a score and grade, but rather constructing a comprehensive view containing multi-layered information. Specifically, one of the core contents of the report is a "driving ability radar chart." A radar chart is a polar coordinate graph that visualizes multi-dimensional data. In this embodiment, the six evaluation dimensions are evenly distributed along the six directions of a circle, with the scale on each dimension axis representing a score. The system plots the score values ​​of each dimension on the corresponding axis and connects these points to form a polygon. This graphical result makes it immediately clear whether the driver's abilities in each dimension are strong or weak, and whether the distribution is balanced. For example, a radar chart that is close to a regular hexagon indicates well-rounded driving ability, while a polygon that is severely concave inward visually indicates a significant weakness in a particular dimension. Another key task in generating the report is to provide "personalized driving suggestions." To this end, the system analyzes the scores of each dimension and identifies the "weak dimensions" with relatively low scores. Then, the system matches these suggestions with a "pre-set improvement suggestion library," which stores specific improvement suggestion texts for different dimensions and different score ranges. For example, if "rule compliance" is identified as a weakness, and the specific deductions mainly stem from "making and receiving calls on a handheld phone," the system may match and generate the following suggestion: "Avoid using a handheld phone while driving. It is recommended to use the in-vehicle Bluetooth system or answer the call after safely parking." If the score for the "riding experience" dimension is low and is related to "excessive longitudinal acceleration," the suggestion might be: "Please pay attention to smooth acceleration and deceleration, and reduce sudden acceleration and braking to improve riding comfort." Furthermore, it can be understood that the system integrates and renders information such as "comprehensive driving score," "driving ability level," an intuitive "driving ability radar chart," "dimensional scores for each evaluation dimension," and "personalized driving suggestions" according to a pre-designed "evaluation report template," generating a complete "visualized evaluation report." This report automatically pops up on the in-vehicle central control screen or the main interface of the synchronized mobile device application after the trip, such as... Figure 2 As shown.

[0052] For example, a driver who drives smoothly on highways but frequently brakes suddenly in urban areas might have a report showing an overall rating of B, with a significant dip in the "basic operation" dimension of the radar chart, accompanied by specific advice such as "when following other vehicles in the city, pay attention to anticipation, apply the brakes lightly in advance, and reduce the number of sudden brakings." On the other hand, a seasoned driver with balanced performance in all aspects might have a report showing a full radar chart and an S rating.

[0053] It's also understandable that the radar chart in the report template is not only for display but also supports interaction. When a user shows interest in and clicks on an area corresponding to a certain dimension on the radar chart, the system responds to the interaction request, retrieves and calls a secondary extended interface, and displays more detailed data for that dimension, such as the specific scores of each "behavioral assessment item" (e.g., "Braking Operation: 7 points," "Acceleration Operation: 9 points"). This allows users to drill down to understand the specific reasons for deductions or additions, greatly enhancing the report's transparency and user engagement. This "overview-detail" interactive design makes the visual report not just a results notification interface, but also an interactive tool that guides users to deeply understand their own driving behavior and reflect on safety practices.

[0054] Step 104: Based on the visualization evaluation report, execute the points incentive logic to update the user's driving ability points data.

[0055] In one specific embodiment of this disclosure, the step of executing the points incentive logic based on the visual evaluation report to update the user's driving ability points data specifically includes: querying a preset points reward and punishment mapping rule according to the comprehensive evaluation level contained in the visual evaluation report to determine the points change value corresponding to this trip; updating the user's accumulated historical driving ability points data based on the points change value to obtain updated driving ability points data; and updating the friend ranking list based on the updated driving ability points data; wherein, the user ranking information corresponding to the friend ranking list includes the current rank information and the current rank driving ability points data.

[0056] Based on the aforementioned points-based incentive system, it can be understood that "executing the points-based incentive logic" means that the system defines and maintains a set of rules that quantify driving performance into virtual value (points) and reward or punish accordingly. The execution of this points-based incentive logic begins with the extraction and application of key information from the visual evaluation report. The system first extracts the "comprehensive evaluation level" (e.g., S, A, B levels) contained in the report, and then queries a "preset points reward / punishment mapping rule." This mapping rule clearly specifies the "point change value" corresponding to different evaluation levels. An example rule could be: an "S" level rewards 10 points, an "A" level rewards 5 points, a "B" level has no increase or decrease, a "C" level deducts 5 points, and a "D" level deducts 10 points. This design directly transforms abstract driving ratings into concrete, accumulative, or consumable points, establishing a clear and immediate connection between driving behavior and virtual incentives. For example, a user who receives an "A" rating for a smooth and rule-abiding performance during a trip will immediately see their accumulated points increase by 5 points; while a user who receives a "C" rating for multiple sudden stops and distracted driving will have their points decrease accordingly.

[0057] Furthermore, the system will "update the user's accumulated historical driving ability points data based on the aforementioned point changes." This means that the system maintains a unique, long-term rolling total point value associated with each user's account. After each trip, the new point changes are added to this total value, resulting in "updated driving ability points data." This constantly changing point value becomes a core quantitative indicator for measuring a user's overall long-term driving performance. Understandably, to further enhance the social and competitive nature of the incentive, after the points are updated, the system will "update the friend leaderboard based on the updated driving ability points data."

[0058] For example, the system retrieves the current scores and ranks of other users within the user's social circle (such as a car enthusiast group or friend list) from the server, and then sorts them according to their scores to generate a dynamic "friends leaderboard." The "user ranking information" displayed on this leaderboard not only includes the ranking position, but more importantly, it includes the "current rank information and current rank driving ability score data" as specified in claim 5. For example, the leaderboard might display "1st place: Zhang San, rank 'Diamond Veteran Driver,' points 385"; "2nd place: Li Si, rank 'Gold Driver,' points 297." This display method allows users to not only compare the absolute values ​​of their scores, but also to intuitively see their relative position on the more concrete hierarchical ladder of "rank," thereby stimulating a stronger desire to surpass and a sense of honor.

[0059] It should be noted that there is a mapping relationship between points and ranks in this embodiment. For example, the system may preset multiple "rank level point ranges" such as "Iron Driver (0-100 points)," "Silver Driver (101-200 points)," and "Gold Driver (201-300 points)." The user's "updated driving ability point data" determines their rank. A typical application scenario is: a user who was originally at the bottom of the "Silver Driver" rank accumulates more than 200 points by obtaining "A" ratings several times in a row. The system will then automatically update their rank to "Gold Driver" and display it on their personal homepage and friend leaderboard. This "points-driven rank advancement" mechanism sets clear long-term goals for users, transforming the beneficial but somewhat tedious behavior of safe driving into a rewarding experience similar to leveling up in a game.

[0060] Understandably, if rank adjustments are immediately made solely based on whether the total score reaches a certain fixed threshold, it could lead to frequent changes in a user's rank due to one or two exceptionally good or bad runs. This would be detrimental to maintaining the authority of the rank system and the user's sense of value towards it, and might also fail to accurately reflect the user's steady-state driving ability. Therefore, this embodiment includes a buffered rank adjustment process based on triggering conditions and periodic evaluation.

[0061] In one specific embodiment of this disclosure, after updating the user's currently accumulated driving ability points based on the points change value to obtain updated driving ability points, the method further includes: comparing the current rank driving ability points data with a preset rank level points interval to determine whether rank upgrade or downgrade conditions are triggered; if triggered, generating a future trip evaluation task according to preset upgrade / downgrade evaluation rules to evaluate a preset number of future driving trips that meet the evaluation conditions; and determining whether to upgrade / downgrade based on the evaluation results of the preset number of driving trips.

[0062] Based on the aforementioned rank progression and demotion logic, it can be understood that after the system updates the user's driving ability points data based on the change in points, it will compare the user's current "rank driving ability points data" (i.e., the current total points) with each preset "rank level points interval." The purpose of this comparison is to "determine whether the rank upgrade or downgrade conditions have been triggered." For example, an upgrade condition might be that the current points value exceeds the upper limit threshold for the user's current rank; while a downgrade condition might be that the current points value falls below the current rank retention threshold. It should be noted that this trigger is merely a "qualification" or "warning," and does not represent an immediate rank upgrade or demotion operation.

[0063] If the system determines that upgrade or downgrade conditions have been triggered, it will not directly adjust the user's rank. Instead, it will "generate a future trip evaluation task according to preset upgrade / downgrade evaluation rules." The core idea of ​​these rules is to require the user to demonstrate their ability to reach the new rank or confirm their need for downgrade through multiple consecutive driving performances within a future observation period. Specifically, the system will generate an evaluation task that requires evaluating the user's "preset number of future driving trips that meet the evaluation conditions." Here, "meeting the evaluation conditions" can mean that the trip mileage is greater than a certain value (e.g., a single trip mileage greater than 5 kilometers) to ensure the validity of the evaluation; and the "preset number of trips" can be a fixed value, such as 10 trips. This means that from the moment the conditions are triggered, the user enters a temporary "observation period" or "buffer period," and every subsequent valid trip is related to the final upgrade / downgrade result.

[0064] After a user completes the preset number of driving trips, the system "determines whether to upgrade or downgrade a rank based on the evaluation results of the preset number of driving trips." This determination is typically based on a statistical analysis of the "comprehensive driving score" of these trips, such as calculating its average score. The system compares this average score with a preset benchmark score corresponding to the target rank. For example, for a user triggering an upgrade condition, their average score during the probationary period must reach the "A" or "S" level standard to be approved for promotion to a higher rank; while for a user triggering a downgrade condition, if their average score during the probationary period is still below the "C" level standard, they will be confirmed to be downgraded. If the average performance during the probationary period fails to meet the corresponding standard, the system determines that the upgrade or downgrade has failed, the user's rank remains unchanged, and their points may be reset to a safe value for the current rank (e.g., the midpoint of the point range for that rank), thus ending this buffer process.

[0065] Understandably, this design creates rich application scenarios and user psychological experiences. For example, a "Gold Driver" finally reaches the threshold for upgrading to "Diamond Driver" after hard work, and then enters a "promotion race" stage requiring 10 high-quality runs. During these 10 runs, they will pay more attention to all aspects of their driving performance than usual, because any mistake could lower their average score and lead to failure to advance. This simulates the "promotion race" mechanism in a game, greatly enhancing the challenge of the goal and the sense of accomplishment upon achievement. Conversely, a user on the verge of demotion will enter a "retention race" stage, which compels them to take every subsequent drive seriously and strive to improve their performance to avoid dropping in rank. This buffered evaluation mechanism extends the one-time score threshold judgment into a continuous behavioral guidance period with process management significance, making the rank system not only a result label but also a dynamic adjustment tool that drives users to maintain stable and good driving habits over a longer period. It effectively filters out accidental factors, making the final rank promotion or demotion decision more convincing and increasing user acceptance of the fairness and intelligence of the entire evaluation system.

[0066] In this embodiment, to further expand the social attributes and interactive value of the driving ability assessment system and meet users' deeper needs for sharing achievements, making comparisons, and promoting a safe driving culture, the system provides a convenient social sharing function as defined in claim 7 after updating scores and the leaderboard. It is understandable that users, upon receiving an excellent visual evaluation report or making progress on a friend's leaderboard, often want to share it with friends or fellow drivers. This embodiment uses technical means to seamlessly connect the system's internal evaluation data with external social platforms, making this sharing behavior extremely simple and expressive.

[0067] In one specific embodiment of this disclosure, after updating the friend ranking based on the updated driving ability score data, the method further includes: responding to a user's sharing instruction for the visual evaluation report or the friend ranking by calling a graphics compositing interface; using the graphics compositing interface to fuse key data elements in the visual evaluation report or the friend ranking with a preset sharing template layout to generate a static image or dynamic page for sharing; and responding to a user's selection operation on the sharing selection interface by uploading and publishing the static image or the dynamic page through the corresponding third-party social platform interface.

[0068] Based on the above sharing process, it can be understood that when a user becomes interested in and wishes to share the "Visual Evaluation Report" generated in step 103 or the "Friends Ranking" updated in step 104, a sharing command can be triggered. This is typically achieved by clicking a preset "Share" button on the report or ranking interface. After "responding to the user's sharing command for the Visual Evaluation Report or the Friends Ranking," the system does not directly capture the original screen but instead "calls the graphics compositing interface" to initiate a dedicated content generation process. This interface is responsible for artistically recombining and rendering the core data elements that need to be shared.

[0069] Furthermore, the system will "integrate key data elements from the visual evaluation report or the friend ranking list with a preset sharing template layout through the graphics synthesis interface." Based on the type of content to be shared, the system selects a suitable template and accurately fills the extracted key data into the predetermined positions of the template, ultimately "generating a static image or dynamic page for sharing." For example, a static image can be a long, informative, and well-designed image suitable for posting on platforms such as WeChat Moments and Weibo; while a dynamic page can be an interactive H5 page where viewers can click on a simplified radar chart to see more information.

[0070] Furthermore, upon responding to the user's selection on the sharing interface, the system will upload and publish the static image or dynamic page through the corresponding third-party social platform interface. For example, if the user chooses to share to WeChat Moments, the system will call the WeChat SDK's sharing interface to publish the generated image to the Moments editing interface. The user only needs to click "Publish" to complete the entire sharing process.

[0071] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide an in-vehicle driving ability assessment device, the structure of which is as follows: Figure 3 As shown.

[0072] The implementation of vehicle driving ability assessment provided in this disclosure is an exemplary structure of software modules. In some embodiments, the software modules in the vehicle driving ability assessment device may include: a data acquisition module 301, a response module 302, a calculation module 303, and an integration module 304.

[0073] The system includes: a data acquisition module 301 for real-time acquisition of multi-dimensional driving behavior data during vehicle operation; a response module 302 for performing fusion analysis on the multi-dimensional driving behavior data based on multiple predefined evaluation dimensions upon the end of the trip to generate dimensional scores for each evaluation dimension; a calculation module 303 for calculating the comprehensive driving score for the trip based on the dimensional scores of each evaluation dimension and outputting a visual evaluation report; and an points module 304 for executing points incentive logic based on the visual evaluation report to update the user's driving ability points data.

[0074] Regarding the apparatus in the above embodiments, the specific manner in which each unit performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0075] Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0076] For example, such as Figure 4 As shown, the vehicle includes a memory 401 and a processor 402. The memory 401 stores executable program code 4011, and the processor 402 is used to call and execute the executable program code 4011 to perform the on-board driving capability assessment method.

[0077] This embodiment can divide the vehicle into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0078] When each functional module is divided according to its corresponding function, the vehicle may include: Real-time collection of multi-dimensional driving behavior data during vehicle operation; In response to the end of this trip, the multidimensional driving behavior data is fused and analyzed based on multiple predefined evaluation dimensions to generate dimensional scores for each evaluation dimension; Based on the dimensional scores of each evaluation dimension, the overall driving score for this trip is calculated, and a visual evaluation report is output. Based on the aforementioned visual assessment report, the points incentive logic is executed to update the user's driving ability points data.

[0079] Some embodiments of this application provide corresponding to Figure 1 A computer-readable storage medium storing multi-dimensional driving behavior data collected in real time during vehicle operation; In response to the end of this trip, the multidimensional driving behavior data is fused and analyzed based on multiple predefined evaluation dimensions to generate dimensional scores for each evaluation dimension; Based on the dimensional scores of each evaluation dimension, the overall driving score for this trip is calculated, and a visual evaluation report is output. Based on the aforementioned visual assessment report, the points incentive logic is executed to update the user's driving ability points data.

[0080] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0081] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0082] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0087] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0088] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0089] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0090] The above description is merely an embodiment of this application and is not intended to limit the scope 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 the claims of this application.

Claims

1. A method for evaluating vehicle driving capability, characterized in that, The method includes: Real-time collection of multi-dimensional driving behavior data during vehicle operation; In response to the end of this trip, the multidimensional driving behavior data is fused and analyzed based on multiple predefined evaluation dimensions to generate dimensional scores for each evaluation dimension; Based on the dimensional scores of each evaluation dimension, the overall driving score for this trip is calculated, and a visual evaluation report is output. Based on the aforementioned visual assessment report, the points incentive logic is executed to update the user's driving ability points data.

2. The method for evaluating vehicle driving capability according to claim 1, characterized in that, The process involves fusing and analyzing the multidimensional driving behavior data based on multiple predefined evaluation dimensions to generate dimensional scores for each evaluation dimension, specifically including: Based on the preset scoring logic corresponding to each evaluation dimension, multiple behavioral evaluation items corresponding to each evaluation dimension are determined. Based on the multiple behavioral evaluation items, multiple corresponding behavioral evaluation data are extracted from the multidimensional driving behavior data, and the scores of multiple evaluation items corresponding to the multiple behavioral evaluation data are determined based on the scoring logic. The scores of the multiple evaluation items corresponding to each evaluation dimension are weighted and calculated to obtain the dimension score of each evaluation dimension.

3. The method for evaluating vehicle driving capability according to claim 1, characterized in that, Based on the dimensional scores of each evaluation dimension, a comprehensive driving score for this trip is calculated, and a visual evaluation report is output, specifically including: The comprehensive driving score data is calculated based on the dimensional scores of each evaluation dimension and the predefined weight coefficients corresponding to each evaluation dimension. The comprehensive driving score data is mapped to a predefined evaluation level range to generate a corresponding driving ability level. Based on the dimensional scores of each evaluation dimension, the shortcomings of this trip are determined, and personalized driving suggestions for the shortcomings are generated by matching them with the preset improvement suggestion library. The comprehensive driving score data, the driving ability level, the dimensional score data of each evaluation dimension, the scores of multiple evaluation items corresponding to each evaluation dimension, and the personalized driving suggestion information are integrated into a preset evaluation report template to generate the visual evaluation report.

4. The method for evaluating vehicle driving capability according to claim 3, characterized in that, The evaluation report template includes a driving ability radar chart, which is used to display the dimensional score data of each evaluation dimension in a graphical style. After outputting the visual evaluation report, the method further includes: In response to a user's interactive request to the graphical region corresponding to any evaluation dimension in the driving capability radar chart, the scores of multiple evaluation items corresponding to any evaluation dimension are obtained. The secondary extended interface of the evaluation report template is invoked to display the scores of multiple evaluation items for any one of the evaluation dimensions.

5. The method for evaluating vehicle driving capability according to claim 3, characterized in that, The step of executing the points incentive logic based on the visualized evaluation report to update the user's driving ability points data specifically includes: Based on the comprehensive evaluation level contained in the visualization evaluation report, query the preset points reward and punishment mapping rules to determine the points change value corresponding to this trip; The user's accumulated historical driving ability points are updated based on the points change value to obtain updated driving ability points data. The friend ranking is then updated based on the updated driving ability points data. The user ranking information corresponding to the friend ranking includes the current rank information and the current rank driving ability points data.

6. The method for evaluating vehicle driving capability according to claim 5, characterized in that, After updating the user's currently accumulated driving ability points based on the points change value to obtain updated driving ability points, the method further includes: The current driving ability score data is compared with the preset score range for each rank to determine whether the conditions for rank upgrade or downgrade have been triggered. If triggered, a future trip evaluation task will be generated according to the preset upgrade and downgrade evaluation rules to evaluate the preset driving trips that meet the evaluation conditions in the future. Based on the evaluation results of the preset driving trip, it is determined whether to upgrade or downgrade the rank.

7. The method for evaluating vehicle driving capability according to claim 5, characterized in that, After updating the friend ranking based on the updated driving ability points data, the method further includes: In response to the user's sharing instruction for the visual evaluation report or the friend ranking list, the graphics compositing interface is invoked; Through the graphics synthesis interface, key data elements in the visual evaluation report or the friend ranking are integrated with a preset sharing template layout to generate a static image or dynamic page for sharing. In response to the user's selection operation on the sharing selection interface, the static image or the dynamic page is uploaded and published through the corresponding third-party social platform interface.

8. A vehicle-mounted driving ability assessment device, characterized in that, The device includes: The data acquisition module is used to collect multi-dimensional driving behavior data in real time during vehicle operation; The response module is used to respond to the end of this trip by performing a fusion analysis on the multidimensional driving behavior data based on multiple predefined evaluation dimensions to generate a dimensional score for each evaluation dimension. The calculation module is used to calculate the comprehensive driving score for this trip based on the dimensional scores of each evaluation dimension, and output a visual evaluation report. The points module is used to execute points incentive logic based on the visual evaluation report to update the user's driving ability points data.

9. A vehicle, characterized in that, The vehicles include: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform a vehicle driving capability assessment method as described in any one of claims 1-7.

10. A computer storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, they implement a vehicle driving capability assessment method as described in any one of claims 1-7.

Images