Product use experience simulation method and system based on behavior analysis

Abstract

The invention discloses a product use experience simulation method and system based on behavior analysis, and belongs to the technical field of data processing, and the method comprises the steps: constructing an intelligent safety protection verification system covering a whole life cycle through a three-in-one technical path of data driving, scene simulation and dynamic optimization; the method comprises the following steps: firstly, carrying out user behavior feature mining based on multi-dimensional historical accident data, and constructing a misoperation feature library containing extreme scenes according to the user behavior feature mining; then, mapping the typical test scene to a virtual simulation environment by using a digital twinning technology; and finally, judging a protection response result based on a coincidence value threshold value, optimizing a sensor sampling frequency and protection trigger logic by adopting a dynamic parameter adjustment algorithm, and forming a closed-loop optimization mechanism through multi-round iterative verification, so that the test process is closer to the actual use condition, the pertinence and effectiveness of the test are improved, and the test efficiency is improved through iterative test and adjustment. The safety protection mechanism of the product is continuously optimized, and the safety of the product and the user experience are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a product usage experience simulation method and system based on behavior analysis. Background Art

[0002] With the continuous development of intelligent connected vehicles and active safety systems, vehicle safety protection mechanisms in various complex road environments have become critical to ensuring driving safety. By deeply analyzing user behavior data during use, we can identify potential types of misoperation and build a corresponding test scenario library. Mapping these scenarios into a digital twin simulation environment can realistically reproduce user operation behaviors and vehicle reactions, effectively evaluating and optimizing vehicle safety protection mechanisms.

[0003] For example, a product simulation optimization method announced in the invention patent with announcement number CN110502784B includes the following steps: obtaining a simulation source model of the product, uniformly sampling within the definition domain of the simulation source model to obtain sampling points; performing simulation analysis on the sampling points in the simulation source model to obtain response values corresponding to the sampling points; adding l1 norm penalty terms and l2 norm penalty terms on the basis of the least squares method according to the sampling points and the response values, and constructing a corresponding nearly sparse response surface model; wherein the nearly sparse response surface model uses orthogonal polynomials as basis functions, and the number of basis functions is a multiple of the number of sampling points; according to the nearly sparse response surface model, using an optimization algorithm to perform optimization, obtain the optimal point within the definition domain of the simulation source model and the optimal value corresponding to the optimal point; and optimizing and adjusting the design of the product according to the optimal point.

[0004] For example, the invention patent publication number CN112000863B discloses a method, apparatus, device, and medium for analyzing user behavior data, which involves big data, user models, and intelligent recommendation technologies. The specific implementation scheme includes: obtaining a user's continuous behavior sequence; extracting at least one user behavior pattern from the continuous behavior sequence; and determining the user's behavior pattern sequence based on the at least one behavior pattern, wherein the behavior pattern includes a combination of at least two consecutive behaviors; and clustering users based on each user's behavior pattern sequence to obtain multiple sets of users with different behavior patterns.

[0005] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: Existing safety testing relies heavily on physical experiments and static simulations, which pose challenges such as limited testing scenarios, incomplete data collection, and insufficient real-time feedback. Furthermore, user misuse and extreme environmental fluctuations during actual use also pose potential risks to vehicle safety systems. Summary of the Invention

[0006] In response to the deficiencies of the prior art, the present invention provides a product usage experience simulation method and system based on behavior analysis to solve the problems designed in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a product usage experience simulation method based on behavioral analysis, including obtaining historical accident data of each user's product usage experience, analyzing the historical accident data of each user's product usage experience, obtaining the type of misoperation of each user, screening and including each typical test scenario according to the type of misoperation of each user, and constructing a misoperation feature library.

[0008] Map each typical test scenario to the digital twin simulation environment, test the vehicle's safety protection mechanism, and monitor and analyze the key response parameters of the vehicle's safety protection mechanism to obtain the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario.

[0009] Based on the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario, the vehicle's safety protection response results in each typical test scenario are obtained. The vehicle's safety protection mechanism is adjusted according to the vehicle's safety protection response results, the adjusted vehicle's safety protection mechanism is verified, and feedback is provided in the digital twin simulation platform.

[0010] Furthermore, the historical accident data of each user's product usage experience is analyzed, and the specific process is: extracting the historical accident data of each user's product usage experience within a preset time period, including comparing the interface switching interval with the interface switching reference interval, the continuous false touch rate with the defined continuous false touch rate, and the single touch duration with the single touch reference duration, and introducing the influencing correction factor and coupling to obtain the error operation trigger value of each user, and the error operation trigger value of each user is used to evaluate the abnormality of the user's driving behavior.

[0011] Furthermore, the specific process of obtaining the error operation type of each user is as follows: extracting the error operation trigger value of each error operation user, and matching it with the error operation type corresponding to each interval of the error operation trigger value of each user stored in the database to obtain the error operation type of each error operation user.

[0012] Furthermore, the erroneous operation type of each user is screened and each typical test scenario is collected to construct an erroneous operation feature library. The specific process is: the erroneous operation type of each user includes a first type and a second type.

[0013] According to the first type and the second type of each user and matching with each set typical test scenario, each typical test scenario of the first type and the second type of each user is obtained, thereby constructing a misoperation feature library.

[0014] Furthermore, the key response parameters of the vehicle's safety protection mechanism are monitored and analyzed to obtain the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario. The specific process is: obtaining the vehicle's key safety protection response data in each typical test scenario, including the relative deviation between the duration of the response delay and the duration of the historical best response delay, the intervention trigger moment and the historical best intervention trigger moment, the maximum deceleration and the historical best maximum deceleration, and the duration of the execution action and the historical best duration of the execution action, and introducing an influencing correction factor and coupling to obtain the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario. The key response compliance values of the vehicle's safety protection mechanism in each typical test scenario are used to evaluate the effectiveness of the vehicle's safety protection system in simulating actual driving scenarios.

[0015] Furthermore, the safety protection response result of the vehicle in each typical test scenario is obtained according to the key response compliance value of the safety protection mechanism of the vehicle in each typical test scenario. The specific process is: according to the key response compliance value of the safety protection mechanism of the vehicle in each typical test scenario, and compared with the key response compliance threshold of the safety protection mechanism of the vehicle in each typical test scenario stored in the database, if the key response compliance value of the safety protection mechanism in a certain typical test scenario is less than or equal to the key response compliance threshold of the safety protection mechanism in the typical test scenario, the safety protection response result of the vehicle in the typical test scenario is recorded as abnormal; if the key response compliance value of the safety protection mechanism in a certain typical test scenario is higher than the key response compliance threshold of the safety protection mechanism in the typical test scenario, the safety protection response result of the vehicle in the typical test scenario is recorded as qualified, thereby obtaining the safety protection response result of the vehicle in each typical test scenario.

[0016] Furthermore, the vehicle's safety protection mechanism is adjusted according to the vehicle safety protection response result. The specific process is: if the vehicle safety protection response result is abnormal, the misoperation type of each user is simulated, and the triggering of the vehicle's safety protection mechanism is adjusted according to the misoperation type of each user, and the sampling frequency of the vehicle's key monitoring sensors is adjusted at the same time.

[0017] Furthermore, the safety protection mechanism of the adjusted vehicle is verified, and the specific process is: monitoring and obtaining the safety protection mechanism of the adjusted vehicle, obtaining the key safety protection response data of the vehicle in various typical test scenarios, and again obtaining the safety protection response results of the vehicle in various typical test scenarios. If the vehicle safety protection response result is abnormal, continue to adjust the vehicle's safety protection mechanism until the vehicle safety protection response result is qualified.

[0018] Furthermore, feedback is provided in the digital twin simulation platform. The specific process is: the key safety protection response data of the vehicle obtained by monitoring the adjusted safety protection mechanism in various typical test scenarios is synchronously updated to the misoperation feature library and the protection logic of the vehicle is updated.

[0019] The second aspect of the present invention also provides a system for simulating product usage experience based on behavioral analysis, including an error operation feature library construction module, which is used to obtain historical accident data of each user's product usage experience, analyze the historical accident data of each user's product usage experience, obtain the error operation type of each user, screen and include various typical test scenarios according to the error operation type of each user, and construct an error operation feature library.

[0020] The safety protection mechanism testing module is used to map various typical test scenarios into the digital twin simulation environment, test the vehicle's safety protection mechanism, and monitor and analyze the key response parameters of the vehicle's safety protection mechanism to obtain the key response compliance values of the vehicle's safety protection mechanism in various typical test scenarios.

[0021] The safety protection mechanism adjustment module is used to obtain the safety protection response results of the vehicle in various typical test scenarios based on the key response compliance values of the vehicle's safety protection mechanism in various typical test scenarios, adjust the vehicle's safety protection mechanism according to the vehicle's safety protection response results, verify the adjusted vehicle's safety protection mechanism, and provide feedback in the digital twin simulation platform.

[0022] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: The present invention has the following beneficial effects: (1) The product usage experience simulation method and system based on behavioral analysis provided by the present invention builds an intelligent safety protection verification system covering the entire life cycle through a three-in-one technical path of data-driven, scenario simulation, and dynamic optimization. First, user behavior characteristics are mined based on multi-dimensional historical accident data, and a misoperation feature library containing extreme scenarios is constructed based on this. Then, typical test scenarios are mapped to a virtual simulation environment using digital twin technology. Finally, the protection response results are determined based on the compliance value threshold, and a dynamic parameter adjustment algorithm is used to optimize the sensor sampling frequency and protection trigger logic. A closed-loop optimization mechanism is formed through multiple rounds of iterative verification, so that the test process is closer to actual usage, improving the pertinence and effectiveness of the test, and continuously optimizing the product's safety protection mechanism through iterative testing and adjustment, thereby improving product safety and user experience. (2) The present invention derives the misoperation trigger value for each user to assess the degree of abnormality in their driving behavior. Subsequently, these misoperation trigger values are matched with the misoperation types stored in the database to determine each user's misoperation type, enabling a deeper understanding of the user's behavior patterns and potential risks in actual operation. Accurately identifying the user's misoperation type facilitates subsequent targeted optimization of product design, improving safety and user experience.

[0023] (3) This invention uses in-depth analysis of historical accident data from user product usage experiences to assess the degree of abnormality in user driving behavior and identify user misoperation types, such as impatience and distraction. These misoperation types are matched with pre-set typical test scenarios to construct a misoperation feature library, providing a basis for testing safety protection mechanisms in a digital twin simulation environment.

[0024] (4) By obtaining the vehicle safety protection response results and adjusting the vehicle's safety protection mechanism, the present invention can improve the vehicle's safety protection mechanism in a targeted manner and reduce safety risks caused by improper user operation. At the same time, the application of digital twin simulation technology makes the testing and verification process more efficient, shortens the R&D cycle, and reduces costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 Schematic diagram of the method of the present invention; Figure 2 Schematic diagram of the system of the present invention. DETAILED DESCRIPTION

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0027] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "thickness", "top", "middle", "length", "inside", "around" and the like indicating orientation or positional relationship are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0028] See also Figure 1, an embodiment of the present invention provides a technical solution: a product usage experience simulation method based on behavioral analysis, including obtaining historical accident data of each user's product usage experience, analyzing the historical accident data of each user's product usage experience, obtaining the type of misoperation of each user, screening and including each typical test scenario according to the type of misoperation of each user, and constructing a misoperation feature library; mapping each typical test scenario to a digital twin simulation environment, testing the vehicle's safety protection mechanism, and monitoring and analyzing each key response parameter of the vehicle's safety protection mechanism to obtain the key response compliance value of the vehicle's safety protection mechanism in each typical test scenario.

[0029] It's important to note that the digital twin simulation environment consists of a physical layer, a virtual layer, and an environmental layer, corresponding to vehicle dynamics simulation, cockpit interface construction, and external environment data integration, respectively. A multidimensional simulation system encompassing these three layers has been constructed on the digital twin simulation platform. The physical layer uses MATLAB / Simulink models to simulate vehicle dynamics, while the virtual layer uses the Unity 3D engine to construct the cockpit interface. The environmental layer integrates real-time data from weather, road conditions, and traffic conditions.

[0030] It should be noted that the typical test scenarios include common misoperation scenarios, operation error scenarios in extreme environments, and emergency avoidance scenarios.

[0031] Based on the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario, the vehicle's safety protection response results in each typical test scenario are obtained. The vehicle's safety protection mechanism is adjusted according to the vehicle's safety protection response results, the adjusted vehicle's safety protection mechanism is verified, and feedback is provided in the digital twin simulation platform.

[0032] It's important to note that within the simulation environment, a virtual-reality mapping system is constructed through a physical layer (using MATLAB / Simulink models to reproduce vehicle dynamics), an interaction layer (building a virtual cockpit interface based on Unity 3D with pre-installed scripts for typical misoperations), and an environmental layer (integrating weather APIs and road sensor data to simulate extreme driving conditions). Multi-source data (including ECU signals and steering wheel angle data) is synchronized within milliseconds, creating a virtual-reality symbiotic testing environment capable of PBR material rendering.

[0033] Specifically, the historical accident data of each user's product usage experience is analyzed. The specific process is: extract the historical accident data of each user's product usage experience within a preset time period, including the interface switching interval and the interface switching reference interval, the continuous false touch rate and the defined continuous false touch rate, and the single touch duration and the single touch reference duration, and compare them, and then introduce the influencing correction factor and couple them to obtain the error operation trigger value of each user. The error operation trigger value of each user is used to evaluate the abnormality of the user's driving behavior.

[0034] It should be noted that the steering wheel angle mutation rate is collected in real time by the torque angle sensor of the electric power steering system (EPS), monitoring steering wheel angle changes at a sampling frequency of more than 100 times per second. The interface switching interval is based on the millisecond-level timestamp record of the capacitive touch chip, calculating the release-press time difference between two valid operations. The continuous false touch rate is determined through a comprehensive analysis of pressure sensing and contact area: when the touch pressure is lower than a preset threshold (unintentional press) and the contact area exceeds a preset area, it is recorded as a false touch event. In this embodiment, after counting all events determined to be false touches within a preset time period, the continuous false touch rate is calculated as the proportion of false touch events within the window to all touch events. The system response time relies on the precise clock synchronization of the time-sensitive network (TSN) to obtain the full link time from the detection of the target by the millimeter-wave radar to the completion of the pressure buildup of the wire control brake system.

[0035] It should be noted that the specific analysis conditions for each user's misoperation trigger value are as follows: ; Where, represents the misoperation trigger value of the jth user, represents the interface switching interval of the jth user, Indicates the interface switching reference interval, represents the continuous false touch rate of the jth user, Indicates the definition of continuous false touch rate, represents the single touch duration of the jth user, Indicates the set single touch reference duration, Indicates the correction factor corresponding to the set steering wheel angle mutation rate, Indicates the correction factor corresponding to the set interface switching interval. Indicates the correction factor corresponding to the set continuous false touch rate, Indicates the correction factor corresponding to the set single touch duration, j indicates the number of each user, , n represents the total number of users.

[0036] It should be noted that there is a close correlation between the interface switching interval, the continuous false touch rate, and the duration of a single touch, which together affect the stability and safety of driving behavior. The interface switching interval refers to the time interval between users switching between different interfaces during operation. Too frequent or too fast interface switching may cause user confusion and increase the possibility of incorrect operation.

[0037] In a specific embodiment, the correction factor corresponding to the interface switching interval also typically ranges from 0 to 1. The interface switching interval is monitored in real time. When a change in the time interval between user interface switching is detected, this interval value is entered into a pre-set mapping table, thereby obtaining the correction factor corresponding to the corresponding interface switching interval. This can help evaluate system response speed, optimize interface fluency, and ensure the coordination between real-time user operation and system performance. The correction factor corresponding to the continuous false touch rate is also obtained through a pre-set mapping table. During use, the false touch rate is entered into this mapping table, and the corresponding correction factor is quickly obtained. This helps analyze and adjust the sensitivity settings of the user interaction interface to reduce the frequency of false touches, thereby improving the user experience. Finally, the correction factor corresponding to the duration of a single touch is also dynamically obtained from a pre-set mapping table. By detecting the duration of a single touch in real time and comparing this time data with the standard value in the mapping table, the corresponding correction factor is obtained, which helps optimize the vehicle protection mechanism to improve response speed and safety.

[0038] Specifically, the error operation type of each user is obtained. The specific process is: extracting the error operation trigger value of each error operation user, and matching it with the error operation type corresponding to each interval of the error operation trigger value of each user stored in the database to obtain the error operation type of each error operation user.

[0039] It should be noted that when determining the error type of each user who made an error, the system extracts each user's error trigger value and matches it with the error trigger value range preset in the database to determine the corresponding error type. A larger error trigger value indicates a greater degree of deviation from the user's expected operation, potentially corresponding to a more serious or frequent error type. Therefore, a larger error trigger value generally matches the first type.

[0040] It should be noted that, from the perspective of real-time response, the initial use of two error categories for each user can simplify data matching and early warning mechanisms, thereby enabling rapid risk identification and intervention. This binary classification approach, based on statistical analysis and experimental validation of extensive historical data, is initially intended to achieve rapid system response and real-time monitoring. As data continues to accumulate and system performance gradually optimizes, the introduction of additional categories to more accurately reflect the specific types of driver errors could be considered in the future, thereby improving the system's assessment accuracy and safety assurance capabilities.

[0041] Specifically, we screen and collect typical test scenarios based on the types of misoperations of each user, and build a misoperation feature library. The specific process is as follows: The erroneous operation types of each user include a first type and a second type; According to the first type and the second type of each user and matching with each set typical test scenario, each typical test scenario of the first type and the second type of each user is obtained, thereby constructing a misoperation feature library.

[0042] It should be noted that mapping each typical test scenario into the digital twin simulation environment includes but is not limited to generating the following test scenarios for the first type of user: Scenario S1: In a low-temperature environment (-20°C), the user repeatedly accidentally touches the start button (≥5 times / minute) and the steering wheel angle changes at a rate greater than 30° / s.

[0043] Scenario S2: In a rainstorm (friction coefficient 0.25), the charging cable was not fully inserted (insertion depth <80%) and the current surge rate was >100A / s.

[0044] For the second type of users, the following test scenarios are generated: Scenario S3: In a high humidity (RH ≥ 90%) environment, the interface switching interval is less than 30 seconds, and the system recognition delay exceeds 300ms.

[0045] Scenario S4: The user accidentally touches the autonomous driving mode switch button in a low temperature (-10°C) and high-speed (≥100 km / h) scenario.

[0046] It should be noted that the specific process of constructing the misoperation feature library includes screening and collecting typical test scenarios that may cause safety risks during driving according to the type of misoperation of each user. For example, for "first type" users, typical scenarios include continuous sharp steering, sudden acceleration and sudden braking, etc.; while for "second type" users, they include frequent interface switching, unstable operation and other scenarios. After all the screened scenarios are classified, labeled and parameterized, they are constructed into a multi-dimensional misoperation feature library. This feature library records in detail the triggering conditions, key features and safety risk indicators of each typical scenario, providing accurate scenario parameters for subsequent digital twin simulation tests.

[0047] Specifically, the key response parameters of the vehicle's safety protection mechanism are monitored and analyzed to obtain the key response compliance values of the vehicle's safety protection mechanism in various typical test scenarios. The specific process is as follows: The key safety protection response data of the vehicle in each typical test scenario is obtained, including the relative deviation between the duration of the response delay and the historical best response delay, the intervention trigger moment and the historical best intervention trigger moment, the maximum deceleration and the historical best maximum deceleration, and the duration of the execution action and the historical best duration of the execution action. After introducing the influencing correction factor, coupling is performed to obtain the key response compliance value of the vehicle's safety protection mechanism in each typical test scenario. The key response compliance value of the vehicle's safety protection mechanism in each typical test scenario is used to evaluate the effectiveness of the vehicle's safety protection system in simulating actual driving scenarios.

[0048] It should be noted that the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario are analyzed under the following specific conditions: ; Where, Indicates the key response compliance value of the security protection mechanism under the i-th typical test scenario, Indicates the duration of the response delay in the i-th typical test scenario, Represents the duration of the best historical execution action stored in the database, represents the intervention triggering moment in the i-th typical test scenario, Indicates the historical best intervention triggering moment stored in the database, represents the maximum deceleration under the i-th typical test scenario, Indicates the historical best maximum deceleration stored in the database. represents the duration of the execution action in the i-th typical test scenario, Represents the duration of the best historical execution action stored in the database, Indicates the correction factor corresponding to the set response delay duration. Indicates the correction factor corresponding to the set intervention trigger moment, Indicates the correction factor corresponding to the set maximum deceleration. Indicates the correction factor corresponding to the duration of the set execution action, i represents the number of each typical test scenario, , m represents the total number of typical test scenarios.

[0049] It should be noted that the length of the response delay, the intervention triggering moment, the maximum deceleration and the duration of the execution action jointly affect the reliability and accuracy of the protection performance through dynamic coupling and compensation mechanisms. If the delay is too long (such as more than 0.5 seconds), even if the intervention triggering moment is in line with the theoretical optimal range (such as AEB should intervene 1.2 seconds before the collision), the actual intervention moment will be delayed due to the delay, forcing the system to increase the maximum deceleration (such as a sudden increase from 0.8g to 1.2g) to compensate for the compression of the time window, but this compensation may exceed the tire adhesion limit and cause braking slip or vehicle instability; conversely, if the intervention triggering moment is too early (such as AEB mistakenly triggered in a low-risk scenario), although it can reduce the pressure of the response delay, it may cause the duration of the execution action to be redundant (such as the braking lock time is too long), which not only increases energy loss, but may also interfere with the driver's operation continuity due to frequent braking. The maximum deceleration setting must be dynamically balanced with the duration of the maneuver. In high-speed collision avoidance scenarios, high deceleration (e.g., above 1.0g) applied for an inadequate duration (e.g., less than 2 seconds) may not adequately reduce the collision's kinetic energy. On the other hand, lower deceleration (e.g., 0.6g) applied for an extended duration (e.g., more than 3 seconds) may result in the vehicle sliding further, leading to missed opportunities for avoidance. For example, NIO's AEB system dynamically adjusts the deceleration gradient using a large AI model. With a response delay of 0.3 seconds, it maintains a maximum deceleration of 0.9g and a braking duration of 1.8 seconds, ensuring both deceleration efficiency and avoiding the risk of tire lock.

[0050] In a specific embodiment, the correction factor corresponding to the duration of the response delay and the correction factor corresponding to the intervention triggering moment generally range from 0 to 1. The correction factor corresponding to the duration of the response delay is determined by a pre-set mapping relationship. For example, by constructing a mapping relationship between the duration of the response delay and the correction factor, the duration of the response delay detected in real time is input into the mapping table, and the corresponding correction factor is quickly obtained. Similarly, the correction factor corresponding to the maximum deceleration and the correction factor corresponding to the duration of the execution action generally range from 0 to 1, and can also be determined in a similar manner. By establishing a mapping table between the maximum deceleration and the correction factor. After the maximum deceleration detected in real time is input into the mapping table, the correction factor corresponding to the maximum deceleration can be found; by establishing a mapping table between the duration of the execution action and the correction factor. After the duration of the execution action detected in real time is input into the mapping table, the correction factor corresponding to the duration of the execution action can be found.

[0051] It's important to note that response delay refers to the time interval between the vehicle safety system detecting an abnormality and initiating protective action (such as ESP or AEB intervention). This metric reflects the system's response speed. Intervention trigger timing refers to the moment when safety subsystems such as ESP or AEB actually begin intervention when a vehicle abnormality occurs (such as lateral instability or collision risk). This is compared with the preset standard trigger time to assess the accuracy of the intervention. Furthermore, the magnitude of the action performed, such as the maximum deceleration achieved by the vehicle during sudden braking, is also included. The duration of the action performed refers to the duration of protective measures (such as continuous braking or stability control) to assess the stability and continuity of the system throughout the accident response process. Comprehensive monitoring and analysis of these parameters allows for a comprehensive assessment of the vehicle's safety protection mechanism's response to abnormalities, providing a basis for subsequent strategy optimization.

[0052] It should be noted that by comparing the response delay with the historical best response delay, the intervention trigger time with the historical best intervention trigger time, the maximum deceleration with the historical best maximum deceleration, and the duration of the execution action with the historical best execution action duration, it is helpful to analyze the shortcomings of the current protection strategy in various scenarios.

[0053] Specifically, based on the key response compliance value of the vehicle's safety protection mechanism in each typical test scenario, the safety protection response result of the vehicle in each typical test scenario is obtained. The specific process is: based on the key response compliance value of the vehicle's safety protection mechanism in each typical test scenario, and compared with the key response compliance threshold of the vehicle's safety protection mechanism in each typical test scenario stored in the database, if the key response compliance value of the safety protection mechanism in a certain typical test scenario is less than or equal to the key response compliance threshold of the safety protection mechanism in the typical test scenario, the safety protection response result of the vehicle in the typical test scenario is recorded as abnormal; if the key response compliance value of the safety protection mechanism in a certain typical test scenario is higher than the key response compliance threshold of the safety protection mechanism in the typical test scenario, the safety protection response result of the vehicle in the typical test scenario is recorded as qualified, thereby obtaining the safety protection response result of the vehicle in each typical test scenario.

[0054] Specifically, the vehicle's safety protection mechanism is adjusted according to the vehicle's safety protection response results. The specific process is as follows: If the vehicle safety protection response result is abnormal, the misoperation type of each user is simulated, and the triggering of the vehicle's safety protection mechanism is adjusted according to the misoperation type of each user, and the sampling frequency of the vehicle's key monitoring sensors is adjusted at the same time.

[0055] It should be noted that key monitoring sensors include acceleration sensors. When the vehicle safety protection response result is abnormal, the basic sampling frequency of the acceleration sensor can be obtained and increased by a certain proportion, for example, by 20%, thereby shortening the time interval between data collection and processing.

[0056] It should be noted that the triggering of the vehicle's safety protection mechanism is adjusted according to the type of misoperation of each user. For impatient users, it is usually necessary to trigger the protection action in advance. The protection action usually includes automatic emergency braking, airbag deployment, lane keeping assist, blind spot monitoring intervention, adaptive cruise control adjustment, steering wheel vibration or seat vibration reminder, etc. For example, the response delay is shortened by 10% to 20% to trigger the protection action to cope with their rapidly changing driving conditions. For distracted users, the warning time is extended to 0.5 seconds, and the triggering of the protection action is delayed, for example, the response delay is delayed by 5% to 10% to trigger the protection action, so as to avoid unnecessary intervention caused by mistriggered. This allows the system to respond in time in an emergency and reduce improper triggering caused by misoperation.

[0057] Specifically, the safety protection mechanism of the adjusted vehicle is verified. The specific process is: monitor and obtain the safety protection mechanism of the adjusted vehicle, obtain the key safety protection response data of the vehicle in various typical test scenarios, and again obtain the safety protection response results of the vehicle in various typical test scenarios. If the vehicle safety protection response result is abnormal, continue to adjust the vehicle's safety protection mechanism until the vehicle safety protection response result is qualified.

[0058] It should be noted that the specific process of continuing to adjust the vehicle's safety protection mechanism includes using a preset gradient descent-based algorithm to generate a set of new control parameter candidate values (filter gain in the data fusion algorithm, proportional and integral parameters of the PID controller, and the braking force distribution ratio of each brake), and further simulating and testing these candidate parameters in a digital twin simulation environment, recording the key safety protection response data under each candidate scheme in real time, and recalculating the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario, and further obtaining the vehicle's safety protection response results in each typical test scenario. If the safety protection response result is still abnormal, the parameter search range is automatically narrowed. For example, the filter gain in the data fusion algorithm is increased in the original Based on the filter gain, for example, the filter gain may be increased by approximately 1% to 2% each time, and after several iterations, a total increase of 5% to 10% is ultimately achieved to improve the system's response speed to rapidly changing signals. Further control parameter adjustments are made, such as increasing the PID controller's proportional parameter by approximately 1% to 2% based on the original proportional gain, and achieving a total increase of 5% to 20% after several iterations. The integral parameter is reduced by approximately 2% to 5% based on the original integral parameter, and achieving a total increase of 10% to 30% after several iterations. The differential parameter is increased by approximately 1% to 2% based on the original differential parameter, and achieving a total increase of 5% to 15% after several iterations to improve the system's overshoot and steady-state error. Simulation testing is then repeated. This process is iterated and updated continuously until the vehicle safety protection response result is qualified.

[0059] Specifically, feedback is provided in the digital twin simulation platform. The specific process is: the key safety protection response data of the vehicle obtained by monitoring the adjusted safety protection mechanism in various typical test scenarios is synchronously updated to the misoperation feature library and the protection logic of the vehicle is updated.

[0060] It should be noted that feedback in the digital twin simulation platform includes verifying the adjusted safety protection mechanism in the digital twin environment, and encapsulating the updated protection strategy into a lightweight parameter package (such as a brake trigger threshold matrix in JSON format), which is pushed to the target vehicle electronic control unit (ECU) in batches through the OTA module.

[0061] like Figure 2 As shown, the second aspect of the present invention also provides a system for simulating product usage experience based on behavioral analysis, including a misoperation feature library construction module for obtaining historical accident data of each user's product usage experience, analyzing the historical accident data of each user's product usage experience, obtaining the misoperation type of each user, screening and including each typical test scenario according to the misoperation type of each user, and constructing a misoperation feature library.

[0062] The safety protection mechanism testing module is used to map various typical test scenarios into the digital twin simulation environment, test the vehicle's safety protection mechanism, and monitor and analyze the key response parameters of the vehicle's safety protection mechanism to obtain the key response compliance values of the vehicle's safety protection mechanism in various typical test scenarios.

[0063] The safety protection mechanism adjustment module is used to obtain the safety protection response results of the vehicle in various typical test scenarios based on the key response compliance values of the vehicle's safety protection mechanism in various typical test scenarios, adjust the vehicle's safety protection mechanism according to the vehicle's safety protection response results, verify the adjusted vehicle's safety protection mechanism, and provide feedback in the digital twin simulation platform.

[0064] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0066] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0068] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0069] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A product usage experience simulation method based on behavioral analysis, characterized in that: include: Obtain historical accident data from each user's product usage experience, analyze the historical accident data from each user's product usage experience, determine the type of misoperation for each user, screen and include typical test scenarios based on the type of misoperation for each user, and build a misoperation feature library; Map each typical test scenario to the digital twin simulation environment to test the vehicle's safety protection mechanism. Monitor and analyze the key response parameters of the vehicle's safety protection mechanism to obtain the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario. Based on the key response compliance values of the vehicle's safety protection mechanism in each typical test scenario, the vehicle's safety protection response results in each typical test scenario are obtained. The vehicle's safety protection mechanism is adjusted according to the vehicle's safety protection response results, the adjusted vehicle's safety protection mechanism is verified, and feedback is provided in the digital twin simulation platform.

2. The product usage experience simulation method based on behavior analysis according to claim 1, characterized in that: The specific process of analyzing the historical accident data of each user's product experience is as follows: Extract historical accident data of each user's product usage experience within a preset time period, including the interface switching interval and the interface switching reference interval, the continuous false touch rate and the defined continuous false touch rate, and the single touch duration and the single touch reference duration for comparison, and introduce an impact correction factor to obtain the introduction of the impact correction factor. After coupling, the misoperation trigger value of each user is obtained, and the misoperation trigger value of each user is used to evaluate the abnormality of the user's driving behavior.

3. The product usage experience simulation method based on behavior analysis according to claim 1, characterized in that: The specific process of obtaining the error operation type of each user is as follows: The error operation trigger value of each error operation user is extracted and matched with the error operation type corresponding to each interval of the error operation trigger value of each user stored in the database to obtain the error operation type of each error operation user.

4. The product usage experience simulation method based on behavior analysis according to claim 1, characterized in that: The specific process of screening and collecting typical test scenarios based on the misoperation types of each user to build a misoperation feature library is as follows: The erroneous operation types of each user include a first type and a second type; According to the first type and the second type of each user and matching with each set typical test scenario, each typical test scenario of the first type and the second type of each user is obtained, thereby constructing a misoperation feature library.

5. The product usage experience simulation method based on behavior analysis according to claim 1, characterized in that: The key response parameters of the vehicle's safety protection mechanism are monitored and analyzed to obtain the key response compliance values of the vehicle's safety protection mechanism in various typical test scenarios. The specific process is as follows: The key safety protection response data of the vehicle in each typical test scenario is obtained, including the relative deviation between the duration of the response delay and the historical best response delay, the intervention trigger moment and the historical best intervention trigger moment, the maximum deceleration and the historical best maximum deceleration, and the duration of the execution action and the historical best duration of the execution action. After introducing the influencing correction factor, coupling is performed to obtain the key response compliance value of the vehicle's safety protection mechanism in each typical test scenario. The key response compliance value of the vehicle's safety protection mechanism in each typical test scenario is used to evaluate the effectiveness of the vehicle's safety protection system in simulating actual driving scenarios.

6. The product usage experience simulation method based on behavior analysis according to claim 1, characterized in that: The safety protection response results of the vehicle in each typical test scenario are obtained according to the key response compliance values of the safety protection mechanism of the vehicle in each typical test scenario. The specific process is as follows: According to the key response compliance value of the vehicle's safety protection mechanism in each typical test scenario, it is compared with the key response compliance threshold of the vehicle's safety protection mechanism in each typical test scenario stored in the database. If the key response compliance value of the safety protection mechanism in a certain typical test scenario is less than or equal to the key response compliance threshold of the safety protection mechanism in the typical test scenario, the safety protection response result of the vehicle in the typical test scenario is recorded as abnormal; if the key response compliance value of the safety protection mechanism in a certain typical test scenario is higher than the key response compliance threshold of the safety protection mechanism in the typical test scenario, the safety protection response result of the vehicle in the typical test scenario is recorded as qualified, thereby obtaining the safety protection response results of the vehicle in each typical test scenario.

7. The product usage experience simulation method based on behavior analysis according to claim 1, characterized in that: The specific process of adjusting the vehicle's safety protection mechanism according to the vehicle safety protection response result is as follows: If the vehicle safety protection response result is abnormal, the misoperation type of each user is simulated, and the triggering of the vehicle's safety protection mechanism is adjusted according to the misoperation type of each user, and the sampling frequency of the vehicle's key monitoring sensors is adjusted at the same time.

8. The product usage experience simulation method based on behavior analysis according to claim 1, characterized in that: The specific process of verifying the safety protection mechanism of the adjusted vehicle is as follows: Monitor and obtain the safety protection mechanism of the adjusted vehicle, obtain the key safety protection response data of the vehicle in various typical test scenarios, and obtain the safety protection response results of the vehicle in various typical test scenarios again. If the vehicle safety protection response result is abnormal, continue to adjust the vehicle's safety protection mechanism until the vehicle safety protection response result is qualified.

9. The product usage experience simulation method based on behavior analysis according to claim 1, characterized in that: The specific process of providing feedback in the digital twin simulation platform is as follows: The safety protection mechanism of the monitored and adjusted vehicle will obtain the key safety protection response data of the vehicle in various typical test scenarios and synchronously update it to the misoperation feature library and push the updated vehicle protection logic.

10. A system using the product usage experience simulation method based on behavioral analysis according to any one of claims 1 to 9, comprising a misoperation feature library construction module for obtaining historical accident data of each user's product usage experience, analyzing the historical accident data of each user's product usage experience to obtain each user's misoperation type, screening and collecting typical test scenarios based on each user's misoperation type, and constructing a misoperation feature library; The safety protection mechanism testing module is used to map typical test scenarios into the digital twin simulation environment, test the vehicle's safety protection mechanism, and monitor and analyze the key response parameters of the vehicle's safety protection mechanism to obtain the key response compliance values of the vehicle's safety protection mechanism in various typical test scenarios; The safety protection mechanism adjustment module is used to obtain the safety protection response results of the vehicle in various typical test scenarios based on the key response compliance values of the vehicle's safety protection mechanism in various typical test scenarios, adjust the vehicle's safety protection mechanism according to the vehicle's safety protection response results, verify the adjusted vehicle's safety protection mechanism, and provide feedback in the digital twin simulation platform.

Images