Patrol route intelligent planning method and system based on component distribution completion

Abstract

The invention discloses an intelligent routing inspection route planning method and system based on component distribution completion, relates to the technical field of intelligent route planning, and aims to solve the problem that task efficiency and coverage rate are reduced. A virtual routing inspection scene is constructed by acquiring routing inspection area information, and a user sets and receives an interaction instruction when entering simulated routing inspection; detecting response time and a routing inspection path of a completion instruction; judging an interaction state according to a path offset rate and the response time, and screening and marking a user; calling an initial route to detect stress point distribution and driving simulation speed; analyzing a user route refining degree; the adaptive force index is generated in combination with the interactive intention trend and the route refining degree, the route corresponding to the adaptive force grade is called, the route is dynamically adjusted according to the user component operation difference, the routing inspection coverage rate and execution efficiency are improved, routing inspection dead angles and redundant paths are reduced, and therefore efficient routing inspection of the routing inspection area is achieved.

Description

Technical Field

[0001] This invention relates to the field of intelligent route planning technology, and more specifically, to a method and system for intelligent route planning based on component distribution completion. Background Technology

[0002] With the widespread application of intelligent inspection equipment such as drones and mobile robots, inspection route planning technology has developed rapidly in fields such as power line inspection, industrial equipment testing, and smart city management. Most existing inspection route planning methods rely on preset waypoints, fixed paths, or simple obstacle avoidance algorithms to ensure that inspection equipment can complete its tasks in designated areas.

[0003] The existing technology has the following shortcomings: Currently, traditional routes are mostly set unilaterally by maintenance personnel, failing to dynamically optimize based on the operational characteristics, response speed, and interaction status of inspection personnel. Existing solutions fail to refine and adjust routes according to individual differences, easily leading to blind spots or redundant paths in inspections, resulting in reduced task efficiency and coverage, and discrepancies between route planning results and actual needs. Therefore, an intelligent route planning method and system based on component distribution completion is proposed.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an intelligent planning method and system for inspection routes based on component distribution completion, which solves the problems mentioned in the background art by using user interaction feature quantitative analysis, component distribution modeling and adaptability index generation technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent planning method for inspection routes based on component distribution completion, comprising the following steps: Step S1: Obtain inspection area information, construct virtual inspection scenario. When the user enters the simulated inspection, set interaction commands and display them through the interactive interface. Detect the response time of the user to complete the interaction commands and the inspection task path. Calculate the path offset rate based on the inspection task path and judge the user's interaction status in combination with the response time. Step S2: Based on the user's interaction status, filter and mark the user, call the initial inspection route, detect the distribution of force points of the marked user in the initial inspection route and the driving simulation speed of the simulation device, and analyze the refinement of the user's initial route by combining the distribution of force points and the driving simulation speed. Step S3: Set the monitoring time, collect the behavioral data of marked users, analyze the interaction intent trend based on the behavioral data of marked users, and generate an adaptability index by combining the refinement of the initial path; Step S4: Use the adaptability index to mark the user's adaptability level and retrieve the inspection route corresponding to the marked user's adaptability level.

[0007] In a preferred embodiment, in step S1, the information database is accessed to obtain inspection area information, which includes the parameters of each component of the inspection tool and the location of the inspection area. The model is created using the parameters of each component of the inspection tool, and then combined with the location of the inspection area to enter the virtual inspection scene. When a user enters the simulated inspection, the simulated cockpit system sets a set of interactive commands; After receiving interactive instructions through the interactive interface, users complete the corresponding tasks in the virtual inspection scenario. The time interval required from receiving the instruction to completing the instruction is recorded by a high-precision sensor and used as the response time.

[0008] In a preferred embodiment, in step S1, during the user's execution of the interactive command, the user's inspection task path is tracked and compared in real time. The inspection task path refers to the operation trajectory performed by the user in the simulated cockpit. The system collects and records the position and time sequence of each task operation point of the user through high-precision sensors, draws the user's inspection task path, and calculates the difference measure between the user's inspection task path and the standard operation path as the path offset rate. The response time and path offset rate are standardized and then used as input features into the logistic regression model. Combined with weight coefficients, the probability value of the user's interaction state being efficient is calculated. The probability value of a user's interaction state being efficient is compared with a preset state judgment threshold. If the probability value of a user's interaction state being efficient is greater than or equal to the state judgment threshold, then the user's interaction state is determined to be efficient; if the probability value of a user's interaction state being efficient is less than the state judgment threshold, then the user's interaction state is determined to be inefficient.

[0009] In a preferred embodiment, in step S2, the user interaction status is determined and categorized to filter out users with different inspection experience and to carry out targeted processing, and users with efficient interaction status are filtered out and marked. The initial inspection route is invoked, and the pressure values ​​of each pressure point on the user's seat are collected and marked by the force sensor array. Each pressure value represents the magnitude of the force exerted by the user at a specific location on the seat surface. Multiple pressure values ​​form a force sequence as the distribution of the user's pressure points. The driving simulation speed of the simulator is monitored and recorded during the initial inspection route according to the preset recording frequency. The driving simulation speed is the speed at which the simulator travels when the user drives it.

[0010] In a preferred embodiment, in step S2, the standard deviation of the force point distribution and the average gradient difference based on the change in driving simulation speed are calculated to obtain the change in vehicle acceleration. After standardizing the standard deviation of the force point distribution and the acceleration change of the driving simulation speed, the user's initial route refinement level is evaluated by weighted fusion method.

[0011] In a preferred embodiment, in step S3, a preset monitoring time is evenly divided into multiple sampling times, and the behavioral data of the marked user is collected, including throttle pressure value, brake pressure value, and the coordinates of the grip center of the hand on the steering wheel surface. The pedal switching frequency and grip stability coefficient are calculated based on the behavioral data of the marked user. Collect and mark user behavior data based on the preset initial inspection route; The throttle pressure value and brake pressure value at each sampling time are obtained by pressure sensors installed under the accelerator pedal and brake pedal respectively. The pressure change is obtained by taking the absolute value of the difference between the throttle pressure value and the brake pressure value at the same sampling time. If the pressure change exceeds the preset pressure change threshold, the corresponding sampling time is marked as the switching time. The number of switching times within the monitoring time is counted as the pedal switching frequency, and the ratio of the pedal switching frequency to the monitoring time is used as the pedal switching frequency.

[0012] In a preferred embodiment, in step S3, the tactile sensor collects the coordinates of the user's hand grip center on the steering wheel surface, and takes the average of the left and right hand grip center coordinates as the grip center coordinates at the sampling time. The grip center coordinates at the sampling time refer to the midpoint of the line connecting the left and right hand grip center coordinates. The coordinates of the grip center at the initial sampling time are used as the reference coordinates. The positional distance between the reference coordinates and the grip center coordinates at each sampling time is calculated using Euclidean distance. The average value of the positional distances is used as the grip stability coefficient. After standardizing the pedal switching frequency and grip stability coefficient, the adaptive index is calculated by inputting them into the hyperbolic tangent function.

[0013] In a preferred embodiment, in step S4, a first adaptation index threshold and a second adaptation index threshold are preset, and the first adaptation index threshold is greater than the second adaptation index threshold. The first adaptation index threshold is compared with the adaptation index to determine the user's adaptation level. If the adaptability index exceeds the first adaptability index threshold, the user's adaptability level is determined to be the enhanced adaptability level. If the adaptability index is between the first adaptability index threshold and the second adaptability index threshold, then the user's adaptability level is determined to be the normal adaptability level. If the adaptability index is lower than the second adaptability index threshold, the user's adaptability level is judged to be the primary adaptability level.

[0014] In a preferred embodiment, in step S4, the inspection route corresponding to the user's adaptability level is retrieved through the scenario management module of the simulated driving system.

[0015] The intelligent inspection route planning system based on component distribution completion includes an interactive detection module, a refinement and evaluation module, an intent analysis module, and a route matching module. The functions of each module are as follows: The interaction detection module is used to set interaction commands. Users receive interaction commands through the interaction interface. The module detects the response time of the user to complete the interaction command and the inspection task path. The path offset rate is calculated based on the inspection task path, and the user's interaction status is determined in combination with the response time. The refinement evaluation module filters and marks users based on their interaction status, calls the initial inspection route, detects the distribution of force points and the driving simulation speed of the simulated vehicle for the marked users in the initial inspection route, and analyzes the refinement level of the initial route by combining the distribution of force points and the driving simulation speed, and marks the users accordingly. The intent analysis module sets the monitoring time, collects behavioral data of marked users, analyzes the interaction intent trend based on the behavioral data of marked users, and generates an adaptability index by combining the initial route refinement level. The route matching module uses the adaptability index to determine the adaptability level of the marked user and retrieves the inspection route corresponding to the adaptability level of the marked user.

[0016] The technical effects and advantages of this invention are as follows: This invention acquires inspection area information and constructs a virtual inspection scenario. When a user enters the simulated inspection, interactive commands are set, and the user receives these commands through an interactive interface. The response time of the user completing the interactive commands and the inspection task commands are detected. The path offset rate is calculated based on the inspection task path, and the user's interaction status is determined by the response time. Users are then filtered and marked based on their interaction status. An initial inspection route is invoked, and the distribution of force points and the driving simulation speed of the simulated vehicle for the marked user within the initial inspection route are detected. The refinement level of the user's initial route is analyzed by combining the distribution of force points and the driving simulation speed. A monitoring time is set, and behavioral data of the marked users is collected. The interaction intent trend is analyzed based on the behavioral data of the marked users. An adaptability index is generated based on the refinement level of the initial route. An inspection route corresponding to the adaptability level of the marked user is retrieved. The inspection route is dynamically adjusted according to the differences in the operation of the inspection vehicle components by different inspection users, thereby achieving efficient inspection of the inspection area, reducing inspection blind spots and redundant paths, and improving inspection coverage and execution efficiency. Attached Figure Description

[0017] Figure 1 This is a flowchart of the intelligent planning method for inspection routes based on component distribution completion according to the present invention.

[0018] Figure 2 This is a schematic diagram of the intelligent inspection route planning system based on component distribution completion according to the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] This invention acquires inspection area information and constructs a virtual inspection scenario. When a user enters the simulated inspection, interactive commands are set, and the user receives these commands through an interactive interface. The system detects the response time of the user's interaction commands and the inspection task commands, calculates the path offset rate based on the inspection task path, and judges the user's interaction status based on the response time. Users are then filtered and marked based on their interaction status, and an initial inspection route is invoked. The distribution of force points and the driving simulation speed of the simulated vehicle are detected in the marked user's initial inspection route. The refinement level of the user's initial route is analyzed by combining the distribution of force points and the driving simulation speed. A monitoring time is set, and behavioral data of the marked users is collected. The interaction intent trend is analyzed based on the behavioral data of the marked users, and an adaptability index is generated based on the refinement level of the initial route. The inspection route corresponding to the adaptability level of the marked user is retrieved, and the inspection route is dynamically adjusted according to the differences in the operation of the inspection vehicle components by different inspection users, thereby achieving efficient inspection of the inspection area.

[0021] Example 1: Intelligent planning method for inspection routes based on component distribution completion, such as... Figure 1 As shown, it includes the following steps: Step S1: Obtain inspection area information, construct virtual inspection scenario. When the user enters the simulated inspection, set interaction commands and display them through the interactive interface. Detect the response time of the user to complete the interaction commands and the inspection task path. Calculate the path offset rate based on the inspection task path and judge the user's interaction status in combination with the response time. Step S2: Based on the user's interaction status, filter and mark the user, call the initial inspection route, detect the distribution of force points of the marked user in the initial inspection route and the driving simulation speed of the simulation device, and analyze the refinement of the user's initial route by combining the distribution of force points and the driving simulation speed. Step S3: Set the monitoring time, collect the behavioral data of marked users, analyze the interaction intent trend based on the behavioral data of marked users, and generate an adaptability index by combining the refinement of the initial path; Step S4: Use the adaptability index to mark the user's adaptability level and retrieve the inspection route corresponding to the marked user's adaptability level.

[0022] The specific implementation is as follows: In step S1, the information database is accessed to obtain the inspection area information, which includes the parameters of each component of the inspection tool and the location of the inspection area. The model is created using the parameters of each component of the inspection tool, and then combined with the location of the inspection area to enter the virtual inspection scene. When a user enters the simulated inspection, the simulated cockpit system sets a set of interactive commands, which are a set of predefined operation steps, including steering wheel operation, pedal control, and instrument panel viewing.

[0023] After receiving interactive instructions through the interactive interface, users complete the corresponding tasks in the virtual inspection scenario. The system records the time interval required from receiving the instruction to completing it through a high-precision sensor. This time interval is used as the response time. The shorter the response time, the faster the user reacts to the interactive instructions, and the more efficient the user's interaction.

[0024] During the user's execution of interactive commands, the system tracks and compares the user's inspection task path in real time. The inspection task path refers to the user's operational trajectory within the simulated cockpit. The system uses high-precision sensors to collect and record the position and time sequence of each user's task operation point, thus drawing the user's inspection task path. Simultaneously, the system retrieves the standard operation path, which is the user's operational trajectory under ideal conditions set by the system based on pre-defined driving task standards, and includes a set of standard operation points.

[0025] It should be noted that an information database is a system used to store, manage, and retrieve information. In this example, it is used to retrieve information about the inspection area. A high-precision sensor is a sensor that can provide very small errors and high-resolution output within its measurement range, accurately capturing and quantifying changes in physical or chemical quantities such as temperature, pressure, and displacement.

[0026] The difference between the user's inspection task path and the standard operation path is calculated as the path offset rate. The specific calculation formula is as follows: ; in, This is the path offset rate. Let i be the location of the user's operation at the i-th time point. Let be the standard operating position at time point i, and n be the total number of steps in the inspection task path. The smaller the path offset rate, the higher the matching degree between the inspection task path and the standard operating path, and the more efficient the user interaction. The larger the path offset rate, the greater the operational deviation between the inspection task path and the standard operating path, and the less efficient the user interaction.

[0027] The response time and path offset rate are standardized and then used as input features to the logistic regression model. Combined with the weight coefficients, the probability value of the user's interaction state is calculated by the Sigmoid function, and a binary classification is performed by setting a threshold.

[0028] Specifically, the calculation formula for the logistic regression model is as follows: ; in, The probability value for the user's interaction state is efficient. For bias terms, and These are the weighting coefficients corresponding to response time and path offset, respectively. For response time.

[0029] It should be noted that logistic regression is a statistical and machine learning model widely used in binary classification problems to predict a binary outcome, that is, to predict the probability of an event occurring; the sigmoid function is an activation function used in machine learning and statistics that maps any real number to between 0 and 1; the weight coefficients in the logistic regression model are obtained by training and optimizing historical data using the maximum likelihood estimation method. The maximum likelihood estimation method ensures that, given the observed data, the parameter values ​​maximize the probability of the observed data occurring. Standardization methods include, but are not limited to, standard linear transformation based on interval scaling, statistical Z-Score standardization, or normalization based on nonlinear mapping functions. The application methods of standardization will not be elaborated here.

[0030] The probability value of a user's interaction state being efficient is compared with a preset state judgment threshold. If the probability value of a user's interaction state being efficient is greater than or equal to the state judgment threshold, then the user's interaction state is determined to be efficient; if the probability value of a user's interaction state being efficient is less than the state judgment threshold, then the user's interaction state is determined to be inefficient.

[0031] It should be noted that the state determination threshold is a probability threshold set by the model when classifying user interaction states. It is used to convert the probability value output by the model into a specific classification result. During the training of the logistic regression model, the best binary classification effect is found through cross-validation as the state determination threshold. For example, if the probability value of the user interaction state calculated by the logistic regression model as efficient is 0.75, and the preset state determination threshold is 0.7, then the user interaction state is determined to be efficient.

[0032] In step S2, the user interaction status is determined and categorized to filter out users with different inspection experience and to carry out targeted processing. Users with efficient interaction status are selected and marked, and the initial inspection route is called for further analysis.

[0033] The initial inspection route setting includes the basic environment and task settings of the simulated driving, ensuring that it can reflect the user's basic behavior patterns in the initial driving environment. The specific parameters of the initial inspection route, including but not limited to driving conditions, vehicle type, road curves, etc., are uniformly loaded through system preset parameters.

[0034] During the initial inspection route, the pressure values ​​of each force point on the user's seat are collected and marked by a force sensor array. Each pressure value represents the magnitude of the force exerted by the user at a specific location on the seat surface. Multiple pressure values ​​form a force sequence as the distribution of the user's force points.

[0035] It should be noted that a force sensor array is a structure composed of multiple pressure sensors arranged in a two-dimensional or one-dimensional array. It is used to detect and record the pressure distribution on the surface of an object or a specific area. By collecting pressure data from each pressure sensor point, the force situation of the entire surface is formed.

[0036] The driving simulation speed of the simulator is monitored and recorded during the initial inspection route according to the preset recording frequency. The driving simulation speed is the speed at which the simulator travels when the user drives it.

[0037] The standard deviation of the stress point distribution is calculated to measure the uniformity of the stress point distribution and the degree of pressure fluctuation. The formula for calculating the standard deviation of the stress point distribution is as follows: ; in, The standard deviation of the force distribution is given. Let i be the pressure value in the force distribution. denoted as the mean pressure value among the force points, and n is the total number of pressure values ​​among the force points.

[0038] The standard deviation of the stress point distribution reflects the dispersion of the pressure distribution at the stress points. The smaller the value, the more uniform the stress point distribution, the stronger the user's balance control ability, and the higher the user's refinement of the initial route. Conversely, the larger the value, the more uneven the stress point pressure distribution, the greater the user's balance control problem, and the lower the refinement of the initial route.

[0039] The average gradient difference is calculated based on the speed change in the driving simulation to obtain the change in vehicle acceleration, thereby assessing the user's balance in vehicle control. The formula for calculating the change in acceleration is: ; in, The change in acceleration and These represent the simulated driving speeds at two consecutive moments, where m is the total number of simulated driving speeds collected. When the simulator is stationary, i.e. and At this point in time, the velocity difference is not included in the statistics to avoid misjudging acceleration fluctuations from a stationary state.

[0040] The change in acceleration is used to quantify the fluctuation of speed in driving simulation, reflecting the user's ability to accelerate and decelerate at different speed stages. The smaller the change in acceleration, the more smoothly the user controls the vehicle and the stronger the balance control ability; the larger the change in acceleration, the worse the user's control ability during driving and the weaker the balance control ability.

[0041] After standardizing the standard deviation of the force point distribution and the acceleration change of the driving simulation speed, the user's initial route refinement level is evaluated using a weighted fusion method. The calculation formula is as follows: ; in, To ensure the initial route is refined to the required level, , and For the weighting coefficients, satisfying The standard deviation of the force distribution and the degree of influence of acceleration change on the final result are used to adjust the user's initial route refinement level. The lower the user's initial route refinement level, the stronger the user's balance control ability. The higher the user's initial route refinement level, the weaker the user's balance control ability.

[0042] It should be noted that weighting coefficients refer to the coefficients assigned to different parameters in weighted fusion, aiming to adjust the contribution of each parameter to the final evaluation result. These coefficients are determined through optimization algorithms. For example, after standardizing the standard deviation of the force point distribution and the acceleration change of the driving simulation speed, we obtain values ​​of 0.8 and 0.6 respectively, and then set the weighting coefficients accordingly. It is 0.7. If the value is 0.3, then the initial route refinement level can be calculated as follows: .

[0043] In step S3, the monitoring time is preset and evenly divided into multiple sampling times. The behavioral data of the marked user is collected, including throttle pressure value, brake pressure value, and the coordinates of the grip center of the hand on the steering wheel surface. The pedal switching frequency and grip stability coefficient are calculated based on the behavioral data of the marked user. Behavioral data of marked users are collected based on a preset initial inspection route to evaluate the marked users' perception, reaction and operating rhythm to basic simulated driving tasks; The preset initial inspection route refers to a driving simulation environment with low-complexity traffic elements and simple road conditions set up by professionals, which is used to collect and label user behavior data based on control variables.

[0044] The throttle pressure value and brake pressure value at each sampling time are obtained by pressure sensors installed under the accelerator pedal and brake pedal respectively. The pressure change is obtained by taking the absolute value of the difference between the throttle pressure value and the brake pressure value at the same sampling time. If the pressure change exceeds the preset pressure change threshold, the corresponding sampling time is marked as the switching time, the number of switching times within the monitoring time is counted as the pedal switching frequency, and the ratio of the pedal switching frequency to the monitoring time is used as the pedal switching frequency. The pedal switching frequency reflects the rhythm of state switching and changes in control strategy of the marked user during the simulated driving process. In the preset primary driving scenario, the higher the pedal switching frequency, the more frequently the marked user adjusts the accelerator and brake control, and the higher the trend of their interaction intention. The lower the pedal switching frequency, the more stable the marked user's operation, and the lower the trend of their interaction intention. The system uses tactile sensors to collect and mark the coordinates of the user's hand grip center on the steering wheel surface. The average value of the left and right hand grip center coordinates is taken as the grip center coordinate at the sampling time. The grip center coordinate at the sampling time refers to the midpoint of the line connecting the left and right hand grip center coordinates, reflecting the user's overall control center of gravity. The coordinates of the grip center at the initial sampling time are used as the reference coordinates. The positional distance between the reference coordinates and the grip center coordinates at each sampling time is calculated using Euclidean distance. ,in, As the reference coordinates, Let be the coordinates of the grip center at the i-th sampling time. Let be the position distance at the i-th sampling time; the average of the position distances is used as the grip stability coefficient. The larger the grip stability coefficient, the less stable the user's hand operation and the less stable their interaction intention; the smaller the grip stability coefficient, the more stable the user's hand operation and the clearer and more consistent their interaction intention. After standardizing the pedal switching frequency and grip stability coefficient, they are mapped to the 0 to 1 range. The difference between the standardized pedal switching frequency and grip stability coefficient is used to obtain the interaction intention trend. Interaction intent trend is used to reflect the interaction stability and scene adaptability of the marked user. Based on the complementary relationship between pedal switching frequency and grip stability coefficient in terms of the interaction dynamics and operation stability of the marked user, the difference between them reflects the user's interaction intent trend. Substituting the interaction intent trend and the initial route refinement level into the hyperbolic tangent function, the fitness index is calculated: ,in, For interactive intent trends, To determine the level of refinement of the initial route, , These are preset influence weights corresponding to the interaction intent trend and the initial route refinement level, with values ​​ranging from 0 to 1. For adaptability index; The greater the refinement of the initial route, the more unstable the balance rhythm of the marked user, the lower the adaptability index, and the greater the interaction intention trend, indicating that the marked user's interaction actions are more active and the adaptability index is higher. in, The function has nonlinear compression properties, which can enhance the discrimination sensitivity at the critical point. accomplish The function's value range is normalized from [-1,1] to [0,1]; the preset influence weights are set by professionals to determine the impact of interaction intent trends and the degree of initial route refinement on the adaptability index. It should be noted that the preset monitoring time is the time limit for collecting behavioral data of the marked user. After the analysis of the initial route refinement is completed, it is set based on the preset initial inspection route. For example, the preset monitoring time is 60 seconds and is evenly divided into 60 sampling moments. The pressure sensor is a sensor device used to sense the pressure applied by the pedaling action in real time. The preset pressure change threshold is a threshold set by professionals based on the statistical results and experience of a large number of pressure changes under the same preset initial inspection route. It is used to distinguish the pressure change boundary value of whether the marked user has performed a pedal switching operation. The tactile sensor is an electronic device that can sense and measure physical contact information. It is used to detect the coordinates of the marked user's hands holding the device in real time. Euclidean distance is a standard measurement method for measuring the straight-line distance between two points in space. In this example, it is used to calculate the position distance of the marked user's hand grip center coordinates relative to the reference coordinates at different sampling moments.

[0045] In step S4, a first adaptation index threshold and a second adaptation index threshold are preset, and the first adaptation index threshold is greater than the second adaptation index threshold. The first adaptation index threshold is compared with the adaptation index to determine the user's adaptation level. If the adaptability index exceeds the first adaptability index threshold, the user's adaptability level is determined to be the enhanced adaptability level. If the adaptability index is between the first adaptability index threshold and the second adaptability index threshold, then the user's adaptability level is determined to be the normal adaptability level. If the adaptability index is lower than the second adaptability index threshold, the user's adaptability level is judged to be the primary adaptability level. The scene management module of the driving simulator retrieves the inspection route corresponding to the user's adaptability level. The scenario management module of the simulated driving system is a functional component used to call up inspection routes and render driving scenes in real time according to the user's adaptability level. The inspection routes are divided into multiple inspection levels by professionals in the field based on the complexity of the inspection tasks and the degree of interactive challenges, and are matched with the user's adaptability level. This will not be analyzed in detail here.

[0046] It should be noted that the preset first and second adaptation index thresholds are used as the basis for judging the user's adaptability index classification. Professionals can obtain the values ​​based on the analysis of historical adaptability index samples or set them based on actual application needs. For example, the mean and standard deviation of the historical adaptability index samples can be calculated, the sum of the mean and standard deviation can be used to obtain the first adaptation index threshold, and the difference between the mean and standard deviation can be used to obtain the second adaptation index threshold.

[0047] Example 2: Intelligent inspection route planning system based on component distribution completion, such as... Figure 2 As shown, it includes an interaction detection module, a refinement evaluation module, an intent analysis module, and a route matching module. The functions of each module are as follows: The interaction detection module is used to set interaction commands. Users receive interaction commands through the interaction interface. The module detects the response time of the user to complete the interaction command and the inspection task path. The path offset rate is calculated based on the inspection task path, and the user's interaction status is determined in combination with the response time. The refinement evaluation module filters and marks users based on their interaction status, calls the initial inspection route, detects the distribution of force points and the driving simulation speed of the simulated vehicle for the marked users in the initial inspection route, and analyzes the refinement level of the initial route by combining the distribution of force points and the driving simulation speed, and marks the users accordingly. The intent analysis module sets the monitoring time, collects behavioral data of marked users, analyzes the interaction intent trend based on the behavioral data of marked users, and generates an adaptability index by combining the initial route refinement level. The route matching module uses the adaptability index to determine the adaptability level of the marked user and retrieves the inspection route corresponding to the adaptability level of the marked user.

[0048] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0049] Furthermore, 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.

[0050] In this document, the singular forms “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that terms such as “comprising / including” or “having” specify the presence of the stated features, integrals, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, integrals, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0051] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0052] The above description of the disclosed embodiments will enable those skilled in the art to make or use various modifications to these embodiments. It will be readily apparent to those skilled in the art that the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent planning method for inspection routes based on component distribution completion, characterized in that: Includes the following steps: Step S1: Obtain inspection area information, construct virtual inspection scenario. When the user enters the simulated inspection, set interaction commands and display them through the interactive interface. Detect the response time of the user to complete the interaction commands and the inspection task path. Calculate the path offset rate based on the inspection task path and judge the user's interaction status in combination with the response time. Step S2: Based on the user's interaction status, filter and mark the user, call the initial inspection route, detect the distribution of force points of the marked user in the initial inspection route and the driving simulation speed of the simulation device, and analyze the refinement of the user's initial route by combining the distribution of force points and the driving simulation speed. Step S3: Set the monitoring time, collect the behavioral data of marked users, analyze the interaction intent trend based on the behavioral data of marked users, and generate an adaptability index by combining the refinement of the initial path; Step S4: Use the adaptability index to mark the user's adaptability level and retrieve the inspection route corresponding to the marked user's adaptability level.

2. The intelligent inspection route planning method based on component distribution completion according to claim 1, characterized in that: In step S1, the information database is accessed to obtain the inspection area information, which includes the parameters of each component of the inspection tool and the location of the inspection area. The model is created using the parameters of each component of the inspection tool, and then combined with the location of the inspection area to enter the virtual inspection scene. When a user enters the simulated inspection, the simulated cockpit system sets a set of interactive commands; After receiving interactive instructions through the interactive interface, users complete the corresponding tasks in the virtual inspection scenario. The time interval required from receiving the instruction to completing the instruction is recorded by a high-precision sensor and used as the response time.

3. The intelligent inspection route planning method based on component distribution completion according to claim 2, characterized in that: In step S1, during the user's execution of interactive instructions, the system tracks and compares the user's inspection task path in real time. The inspection task path refers to the operation trajectory performed by the user in the simulated cockpit. The system collects and records the position and time sequence of each task operation point of the user through high-precision sensors, draws the user's inspection task path, and calculates the difference between the user's inspection task path and the standard operation path as the path offset rate. The response time and path offset rate are standardized and then used as input features into the logistic regression model. Combined with weight coefficients, the probability value of the user's interaction state being efficient is calculated. The probability value of the user's interaction state being efficient is compared with the preset state judgment threshold. If the probability value of the user's interaction state being efficient is greater than or equal to the state judgment threshold, then the user's interaction state is determined to be efficient. If the probability value of a user's interaction state being efficient is less than the state determination threshold, then the user's interaction state is determined to be inefficient.

4. The intelligent inspection route planning method based on component distribution completion according to claim 1, characterized in that: In step S2, the user interaction status is determined and categorized to filter out users with different inspection experience and to carry out targeted processing. Users with efficient interaction status are filtered out and marked. The initial inspection route is invoked, and the pressure values ​​of each pressure point on the user's seat are collected and marked by the force sensor array. Each pressure value represents the magnitude of the force exerted by the user at a specific location on the seat surface. Multiple pressure values ​​form a force sequence as the distribution of the user's pressure points. The driving simulation speed of the simulator is monitored and recorded during the initial inspection route according to the preset recording frequency. The driving simulation speed is the speed at which the simulator travels when the user drives it.

5. The intelligent planning method for inspection routes based on component distribution completion according to claim 4, characterized in that: In step S2, the standard deviation of the force distribution is calculated and the average gradient difference is calculated based on the change in driving simulation speed to obtain the change in vehicle acceleration. After standardizing the standard deviation of the force point distribution and the acceleration change of the driving simulation speed, the user's initial route refinement level is evaluated by weighted fusion method.

6. The intelligent inspection route planning method based on component distribution completion according to claim 1, characterized in that: In step S3, the monitoring time is preset and evenly divided into multiple sampling times. The behavioral data of the marked user is collected, including throttle pressure value, brake pressure value, and the coordinates of the grip center of the hand on the steering wheel surface. The pedal switching frequency and grip stability coefficient are calculated based on the behavioral data of the marked user. Collect and mark user behavior data based on the preset initial inspection route; The throttle pressure value and brake pressure value at each sampling time are obtained by pressure sensors installed under the accelerator pedal and brake pedal respectively. The pressure change is obtained by taking the absolute value of the difference between the throttle pressure value and the brake pressure value at the same sampling time. If the pressure change exceeds the preset pressure change threshold, the corresponding sampling time is marked as the switching time. The number of switching times within the monitoring time is counted as the pedal switching frequency, and the ratio of the pedal switching frequency to the monitoring time is used as the pedal switching frequency.

7. The intelligent inspection route planning method based on component distribution completion according to claim 6, characterized in that: In step S3, the tactile sensor collects and marks the center coordinates of the user's hand grip on the steering wheel surface. The average value of the center coordinates of the left and right hands grip is taken as the center coordinates of the grip at the sampling time. The center coordinates of the grip at the sampling time refer to the midpoint of the line connecting the center coordinates of the left and right hands grip. The coordinates of the grip center at the initial sampling time are used as the reference coordinates. The positional distance between the reference coordinates and the grip center coordinates at each sampling time is calculated using Euclidean distance. The average value of the positional distances is used as the grip stability coefficient. After standardizing the pedal switching frequency and grip stability coefficient, the adaptive index is calculated by inputting them into the hyperbolic tangent function.

8. The intelligent inspection route planning method based on component distribution completion according to claim 1, characterized in that: In step S4, a first adaptation index threshold and a second adaptation index threshold are preset, and the first adaptation index threshold is greater than the second adaptation index threshold. The first adaptation index threshold is compared with the adaptation index to determine the user's adaptation level. If the adaptability index exceeds the first adaptability index threshold, the user's adaptability level is determined to be the enhanced adaptability level. If the adaptability index is between the first adaptability index threshold and the second adaptability index threshold, then the user's adaptability level is determined to be the normal adaptability level. If the adaptability index is lower than the second adaptability index threshold, the user's adaptability level is judged to be the primary adaptability level.

9. The intelligent planning method for inspection routes based on component distribution completion according to claim 8, characterized in that: In step S4, the inspection route corresponding to the user's adaptability level is retrieved through the scenario management module of the simulated driving system.

10. An intelligent inspection route planning system based on component distribution completion, used to implement the intelligent inspection route planning method based on component distribution completion as described in any one of claims 1-9, characterized in that: It includes an interaction detection module, a refinement evaluation module, an intent analysis module, and a route matching module. The functions of each module are as follows: The interaction detection module is used to set interaction commands. Users receive interaction commands through the interaction interface. The module detects the response time of the user to complete the interaction command and the inspection task path. The path offset rate is calculated based on the inspection task path, and the user's interaction status is determined in combination with the response time. The refinement evaluation module filters and marks users based on their interaction status, calls the initial inspection route, detects the distribution of force points and the driving simulation speed of the simulated vehicle for the marked users in the initial inspection route, and analyzes the refinement level of the initial route by combining the distribution of force points and the driving simulation speed, and marks the users accordingly. The intent analysis module sets the monitoring time, collects behavioral data of marked users, analyzes the interaction intent trend based on the behavioral data of marked users, and generates an adaptability index by combining the initial route refinement level. The route matching module uses the adaptability index to determine the adaptability level of the marked user and retrieves the inspection route corresponding to the adaptability level of the marked user.

Images