A standardized dynamic information intelligent detection system

Abstract

This invention relates to the field of data detection, and more particularly to a standardized dynamic information intelligent detection system. The invention controls a modeling object to execute predetermined instructions in a modeling space to acquire the modeling object's motion trajectory; compares the modeling trajectory with actual motion trajectory samples to determine the trajectory deviation value; evaluates the modeling deviation characterization value based on the joint motion deviation characteristics of the modeling object to determine the deviation category of the modeling object; calls instruction execution data to detect and analyze the modeling object; responds to the detection and analysis, adjusts the point cloud density of the corresponding active joints based on the modeling sensitivity characterization coefficient for secondary modeling; controls the modeling object to execute predetermined instructions again, acquires the instruction execution delay characteristics, analyzes whether the modeling object meets the delay error condition, and determines whether to adjust the network link bandwidth. This invention can collect relevant standardized data in a standardized manner, evaluate the instruction execution effect in a standardized manner, discover potential problems, and improve execution efficiency.

Description

Technical Field

[0001] This invention relates to the field of data detection, and in particular to a standardized dynamic information intelligent detection system. Background Technology

[0002] In the field of data detection, the accuracy and real-time performance of dynamic modeling and command execution have become core indicators for measuring system performance. Especially in scenarios such as robotic arm control, robot motion simulation, and dynamic monitoring of industrial equipment, issues such as command response deviation and data transmission delay of the modeled object directly affect production efficiency and operational safety.

[0003] However, current dynamic modeling and detection systems generally lack a standardized benchmark data support system. Most solutions rely solely on a single trajectory sample as a comparison benchmark, failing to establish a standard dataset covering multiple dimensions such as joint motion parameters of the modeled object and command execution timing. This results in a lack of a unified reference for evaluating operational behavior deviations. Therefore, it is necessary to construct personalized standard data storage and retrieval mechanisms for different modeled objects to improve the accuracy of operational effect evaluation and precisely locate the boundary between modeling errors and inherent equipment errors.

[0004] Furthermore, existing systems lack the ability to respond to dynamic scenarios. Most systems only focus on the trajectory deviation of the modeled object, neglecting the linkage analysis of dynamic data such as instruction transmission delay and execution delay. In industrial automated production lines, transmission delay may cause the modeled object and the actual equipment to move out of sync, leading to production accidents. However, existing solutions lack detailed detection of delay characteristics and cannot specifically optimize network transmission or equipment response mechanisms, resulting in insufficient completeness and practicality of dynamic detection.

[0005] Against this backdrop, we will build an intelligent detection system that integrates standardized data support and adapts to dynamic scene changes. Through multi-module collaboration, we can achieve accurate evaluation of the execution effect of modeling object instructions and timely early warning of potential problems, thereby improving the execution efficiency and safety redundancy of dynamic modeling.

[0006] Chinese Patent Application Publication No. CN120471138A discloses a dynamic intelligent target detection system and method based on a reasoning-training paradigm. The system includes: a real-time learning module that uses a YOLOX model to perform real-time reasoning on input data, while simultaneously monitoring the model's reasoning results and triggering online learning as needed; a parameter fusion engine that trains the model requiring online learning, uses a gradient importance ranking algorithm to approximate parameter sensitivity based on the Hessian matrix, employs a difference-aware aggregation protocol, filters gradients from abnormal nodes using cosine similarity, and uses progressive knowledge fusion to achieve smooth parameter transitions through momentum updates; a multi-level verification subsystem that automatically verifies the trained model; and a resource-aware controller that dynamically adjusts resource allocation and gradient sparsity transmission by acquiring real-time hardware resource information. This invention can significantly improve the real-time performance, accuracy, and environmental adaptability of target detection, ensuring efficient model operation on different hardware platforms. Summary of the Invention

[0007] To address these issues, this invention provides a standardized dynamic information intelligent detection system to overcome the shortcomings of existing technologies. These technologies lack a standardized benchmark data system covering multiple dimensions, rely solely on single trajectory sample comparisons, making it difficult to accurately assess operational deviations and inherent errors in modeling and equipment. Furthermore, they do not integrate dynamic data analysis, lack detailed detection of delay features, and cannot specifically optimize network or equipment response mechanisms, resulting in incomplete dynamic detection.

[0008] To achieve the above objectives, the present invention provides a standardized dynamic information intelligent detection system, comprising: A standard data storage module is used to store the actual motion trajectory samples of the modeling object executing predetermined instructions, as well as the instruction execution data of the modeling object; The standard analysis module is used to control the modeling object to execute the predetermined instructions in the modeling space in order to obtain the modeling motion trajectory of the modeling object; The standard deviation evaluation module is connected to the standard data storage module and the standard analysis module respectively. It is used to compare the modeled motion trajectory with the actual motion trajectory sample, determine the trajectory deviation value, and evaluate the modeling deviation characterization value in combination with the joint motion deviation characteristics corresponding to the modeling object, so as to determine the deviation category of the modeling object. A standard detection module, connected to the standard deviation evaluation module, is used to call the instruction execution data based on the deviation category of the modeling object, and to perform detection and analysis on the modeling object, including... The cumulative rotation angle deviation and degrees of freedom of the movable joints of the modeling object are obtained, and the modeling sensitivity characterization coefficient of the modeling object is calculated to determine whether the execution of the instruction corresponding to the modeling object meets the execution error benchmark. A standard adjustment module, which is connected to the standard detection module, responds to the judgment result of the standard detection module and adjusts the point cloud density of the corresponding active joint for secondary modeling based on the modeling sensitivity characterization coefficient; A standard transmission module, connected to the standard adjustment module, is used to control the modeling object to execute the predetermined instruction again, obtain the delay characteristics of the instruction execution, analyze whether the modeling object meets the delay error condition, and determine whether to adjust the network link bandwidth. The joint motion deviation characteristics include the number of increases in the number of movements of the active joint and the amount of extension of the motion path, and the delay characteristics include the amount of transmission delay and the amount of execution delay.

[0009] Furthermore, the standard deviation evaluation module is used to evaluate the modeling deviation characterization value, including: The ratio of the trajectory deviation value to the trajectory deviation value threshold is used as the first modeling deviation feature; The sum of the ratio of the increase in the number of movements of the active joint to the threshold for the increase in the number of movements and the ratio of the extension of the movement path to the threshold for the extension is used as the second modeling bias feature. The first modeling deviation feature and the second modeling deviation feature are weighted and summed to obtain the modeling deviation characterization value.

[0010] Furthermore, the standard deviation evaluation module is used to determine the deviation category of the modeling object, including: If the modeling deviation characterization value of the modeling object is greater than or equal to the modeling deviation characterization threshold, then the deviation category of the modeling object is determined to be the high deviation category.

[0011] Furthermore, the standard detection module is used to call the instruction execution data based on the deviation category of the modeling object, and to perform detection and analysis on the modeling object, including: If the deviation category of the modeling object is a high deviation category, then the instruction is invoked to execute the data and perform detection and analysis on the modeling object.

[0012] Furthermore, the standard detection module is used to calculate the modeling sensitivity characterization coefficient of the modeling object, including: The ratio of the cumulative rotational angle deviation of the movable joint to the cumulative rotational angle deviation threshold is used as the first modeling sensitivity feature; The ratio of the threshold of the degrees of freedom of the movable joint to the degrees of freedom of the movable joint is used as the second modeling sensitivity feature; The sum of the first modeling sensitivity feature and the second modeling sensitivity feature is used as the modeling sensitivity characterization coefficient.

[0013] Furthermore, the standard detection module is used to determine whether the execution of the instructions corresponding to the modeled object conforms to the execution error benchmark, including: If the modeling sensitivity coefficient of the modeling object is greater than or equal to the modeling sensitivity coefficient threshold, then the execution of the instruction corresponding to the modeling object is determined to be inconsistent with the execution error benchmark.

[0014] Furthermore, the standard adjustment module responds to the determination result of the standard detection module, including: If the determination result is that the execution of the instruction corresponding to the modeling object does not meet the modeling sensitivity benchmark, then the point cloud density of the corresponding active joint is adjusted based on the modeling sensitivity characterization coefficient for secondary modeling.

[0015] Furthermore, the standard adjustment module is used to adjust the point cloud density of the corresponding active joint based on the modeling sensitivity representation coefficient, including: Increase the point cloud density, and the amount of increase in point cloud density is positively correlated with the modeling sensitivity characterization coefficient.

[0016] Furthermore, the standard transmission module is used to analyze whether the modeling object satisfies the delay error condition, including: If the transmission delay of the instruction execution corresponding to the modeling object is less than the transmission delay threshold and the execution delay is less than the execution delay threshold, then the modeling object is determined to meet the delay error condition.

[0017] Furthermore, the standard transmission module is used to determine whether to adjust the network link bandwidth, including: If the modeling object does not meet the delay error condition, then it is determined that the network link bandwidth should be adjusted.

[0018] Compared with existing technologies, this invention sets up a standard data storage module to store actual motion trajectory samples of the modeling object executing predetermined instructions and instruction execution data of the modeling object; a standard analysis module to control the modeling object to execute predetermined instructions in the modeling space to obtain the modeling motion trajectory of the modeling object; a standard deviation evaluation module to compare the modeling motion trajectory with the actual motion trajectory samples, determine the trajectory deviation value, and evaluate the modeling deviation characterization value in combination with the joint motion deviation characteristics of the modeling object to determine the deviation category of the modeling object; a standard detection module to call the instruction execution data to detect and analyze the modeling object according to the deviation category of the modeling object; a standard adjustment module, in response to the judgment result of the standard detection module, adjusts the point cloud density of the corresponding active joints for secondary modeling based on the modeling sensitivity characterization coefficient; and a standard transmission module to control the modeling object to execute the predetermined instructions again, obtain the delay characteristics of instruction execution, analyze whether the modeling object meets the delay error condition, and determine whether to adjust the network link bandwidth. This invention can accurately evaluate the instruction execution effect of the modeling object, promptly discover potential problems, and improve the execution efficiency of dynamic modeling.

[0019] In particular, this invention includes a standard deviation evaluation module. Based on comparing the modeled motion trajectory with actual motion trajectory samples to assess the overall trajectory deviation, it comprehensively analyzes and evaluates the accuracy of the modeled object by considering deviations arising from the detailed motion of the modeled object's joints. By analyzing the increase in the number of joint movements, it determines whether any joint of the modeled object exhibits unnecessary additional movement. The degree of deviation in command execution can be assessed based on the extension of the joint's motion path. Therefore, this application uses trajectory deviation values ​​combined with joint motion deviation characteristics to evaluate the modeling deviation representation value, thus characterizing the degree of deviation in command execution and providing data support for subsequently determining the deviation category of the modeled object. Through the analysis of the above characteristics, deviation problems that occur in the modeled object under complex and changing motion scenarios can be promptly identified and addressed, ensuring that the modeled object operates stably and accurately under various conditions.

[0020] In particular, this invention includes a standard detection module to detect and analyze deviations generated by the execution of commands by the modeling object. It analyzes the cumulative deviation of the rotation angle of movable joints, assessing the frequency and duration of these deviations and their impact on the accuracy and smoothness of command execution. Consideration of the degrees of freedom of movable joints allows for a more comprehensive analysis of their motion capabilities and limitations, quantifying the degree of interference of the aforementioned two factors on deviations. Therefore, this invention calculates the modeling sensitivity coefficient of the modeling object based on the cumulative deviation of the rotation angle of its movable joints and the degrees of freedom of those joints. This coefficient characterizes the modeling object's responsiveness to commands and its own motion sensitivity, providing data support for determining whether the execution of commands by the modeling object meets the execution error benchmark. This invention can accurately evaluate the command execution effect of the modeling object, promptly identify potential problems, and improve the execution efficiency of dynamic modeling.

[0021] In particular, this invention sets up a standard transmission module to evaluate the impact of data on the execution instructions of the modeled object, based on accurate secondary modeling in advance. It clearly distinguishes between transmission latency and execution latency. Transmission latency reflects the time spent on data transmission over the network, while execution latency reflects the time required for the modeled object's internal processing and instruction execution. By analyzing these two characteristics, the impact of both network transmission and the modeled object's own processing on instruction execution can be quantified from two dimensions. Stable network transmission and timely instruction execution reduce the probability of system failures or anomalies, providing accurate direction for subsequent problem-solving. Therefore, this invention analyzes latency characteristics to determine whether the modeled object after secondary modeling meets latency error conditions, and also supports subsequent decisions on adjusting network link bandwidth, effectively reducing transmission latency and making the modeled object's actions smoother and more accurate, avoiding incoordination or errors caused by latency. This invention can meet the real-time response requirements of the modeled object, accurately evaluate the instruction execution effect of the modeled object, promptly identify potential problems, and improve the execution efficiency of dynamic modeling. Attached Figure Description

[0022] Figure 1 A functional block diagram of a standardized dynamic information intelligent detection system according to an embodiment of the invention; Figure 2 A logic diagram for determining the deviation category of a modeling object in an embodiment of the invention; Figure 3 A logic diagram for determining whether the execution of instructions corresponding to a modeling object conforms to the execution error benchmark in an embodiment of the invention; Figure 4 This is a logic diagram for analyzing whether the modeling object meets the delay error condition in an embodiment of the invention. Detailed Implementation

[0023] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0024] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0025] It should be noted that in the description of this invention, terms such as "upper" indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. This is merely for ease of description and does not indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0026] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral connection; it can refer to a mechanical connection or an electrical connection. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0027] Please see Figure 1 The diagram shown is a functional block diagram of the standardized dynamic information intelligent detection system according to an embodiment of the present invention. The standardized dynamic information intelligent detection system according to an embodiment of the present invention includes: A standard data storage module is used to store the actual motion trajectory samples of the modeling object executing predetermined instructions, as well as the instruction execution data of the modeling object; The standard analysis module is used to control the modeling object to execute the predetermined instructions in the modeling space in order to obtain the modeling motion trajectory of the modeling object; The standard deviation evaluation module is connected to the standard data storage module and the standard analysis module respectively. It is used to compare the modeled motion trajectory with the actual motion trajectory sample, determine the trajectory deviation value, and evaluate the modeling deviation characterization value in combination with the joint motion deviation characteristics corresponding to the modeling object, so as to determine the deviation category of the modeling object. A standard detection module, connected to the standard deviation evaluation module, is used to call the instruction execution data based on the deviation category of the modeling object, and to perform detection and analysis on the modeling object, including... The cumulative rotation angle deviation and degrees of freedom of the movable joints of the modeling object are obtained, and the modeling sensitivity characterization coefficient of the modeling object is calculated to determine whether the execution of the instruction corresponding to the modeling object meets the execution error benchmark. A standard adjustment module, which is connected to the standard detection module, responds to the judgment result of the standard detection module and adjusts the point cloud density of the corresponding active joint for secondary modeling based on the modeling sensitivity characterization coefficient; A standard transmission module, connected to the standard adjustment module, is used to control the modeling object to execute the predetermined instruction again, obtain the delay characteristics of the instruction execution, analyze whether the modeling object meets the delay error condition, and determine whether to adjust the network link bandwidth. The joint motion deviation characteristics include the number of increases in the number of movements of the active joint and the amount of extension of the motion path, and the delay characteristics include the amount of transmission delay and the amount of execution delay.

[0028] Specifically, the instruction execution data includes trajectory deviation values, joint motion deviation characteristics, cumulative rotation angle deviation of movable joints, degrees of freedom of movable joints, point cloud density, and delay characteristics of modeling operations.

[0029] Specifically, a modeling object is composed of several joints. The modeling object is formed by the mutual assembly of the joints. For example, the supporting joint is used to maintain the structural stability of the modeling object, while the movable joint connects adjacent parts. Through operations such as rotation, the relative movement and cooperation of adjacent parts are realized, and the modeling object executes the instructions, making the modeling object dynamic.

[0030] Specifically, there are no restrictions on the specific structure of the standard data storage module, standard analysis module, standard deviation evaluation module, standard detection module, standard adjustment module, and standard transmission module. Each module or its units can be composed of logic components or combinations of logic components. Logic components include field-programmable processors, computers, or microprocessors in computers.

[0031] Specifically, the standard deviation evaluation module is used to evaluate the modeling deviation characterization value, including, The ratio of the trajectory deviation value to the trajectory deviation value threshold is used as the first modeling deviation feature; The sum of the ratio of the increase in the number of movements of the active joint to the threshold for the increase in the number of movements and the ratio of the extension of the movement path to the threshold for the extension is used as the second modeling bias feature. The first modeling deviation feature and the second modeling deviation feature are weighted and summed to obtain the modeling deviation characterization value.

[0032] Specifically, the method for determining the trajectory deviation value is not limited. It can be achieved by controlling the modeling object and the entity corresponding to the modeling object to execute the same instruction. Correspondingly, the same instruction corresponds to the same motion path. At the same time, detection equipment is used, for example, tracking markers are set on the entity, and multiple cameras of the optical tracking system capture the tracking markers to track the actual motion trajectory of the entity in real time to reconstruct the actual motion trajectory. The actual motion trajectory is superimposed and compared with the modeling motion trajectory of the modeling object. The position deviation is determined by analyzing the difference between the two motion trajectories. Then, the root mean square error is calculated to reflect the overall degree of deviation between the positions corresponding to the modeling motion trajectory and the positions corresponding to the actual motion trajectory. Therefore, in this embodiment, the root mean square error is used to determine the trajectory deviation value. The larger the root mean square error, the greater the degree of deviation between the modeling motion trajectory and the actual motion trajectory. This will not be elaborated further.

[0033] Specifically, during the actual execution of control commands by the modeled object, compared to the trajectory deviation value determined by the modeled motion trajectory and the actual motion trajectory sample, the features directly presented by the modeled object itself can more intuitively and clearly represent the severity of the difference in the execution commands by the modeled object. Therefore, in implementation, joint motion deviation features are given priority, that is, the number of times the active joint moves and the amount of extension of the motion path. Thus, the second modeling deviation feature calculated based on the joint motion deviation features is given a slightly higher weight. Therefore, when performing weighted summation, the weight of the first modeling deviation feature is set to 0.4, and the weight of the second modeling deviation feature is set to 0.6. In this embodiment, the purpose of setting the trajectory deviation threshold, the motion increase threshold, and the extension threshold is to characterize the situation where the deviation between the modeling object and its corresponding entity object is large during the execution of instructions. Historical data related to the modeling object executing several control instructions is obtained. Historical data of trajectory deviation values, historical data of the motion increase of active joints, and historical data of the extension of the motion path are called to calculate the mean trajectory deviation, the mean motion increase, and the mean extension, respectively, and these are used as the baseline values ​​under normal conditions. Based on the purpose of setting the above three thresholds, the trajectory deviation threshold is determined as the product of the mean trajectory deviation and the deviation coefficient; the motion increase threshold is determined as the product of the mean motion increase and the increase deviation coefficient; and the extension threshold is determined as the product of the mean extension and the extension offset coefficient. The deviation coefficient is selected within the interval [1.05, 1.1], preferably 1.05 in practice; the increase deviation coefficient is selected within the interval [1.1, 1.15], preferably 1.1 in practice; and the extension offset coefficient is selected within the interval [1.15, 1.2], preferably 1.15 in practice.

[0034] Specifically, this invention includes a standard deviation evaluation module. Based on comparing the modeled motion trajectory with actual motion trajectory samples to assess the overall trajectory deviation, it comprehensively analyzes and evaluates the accuracy of the modeled object by considering deviations arising from the detailed motion of the modeled object's joints. By analyzing the number of increases in joint motion, it determines whether any joint of the modeled object exhibits unnecessary additional motion. For example, if a particular joint shows a significant increase in motion, it may indicate inaccuracies in the modeling of that joint. The extension of the joint's motion path can assess the degree of deviation in command execution. Therefore, this application uses trajectory deviation values ​​combined with joint motion deviation characteristics to evaluate the modeling deviation representation value, thus characterizing the degree of deviation in command execution and providing data support for subsequently determining the deviation category of the modeled object. Through the analysis of these characteristics, deviation problems arising in complex and ever-changing motion scenarios can be promptly identified and addressed, ensuring that the modeled object operates stably and accurately under various conditions.

[0035] Specifically, please refer to Figure 2 As shown, this is a logic diagram for determining the deviation category of a modeling object according to an embodiment of the present invention. The standard deviation evaluation module is used to determine the deviation category of the modeling object, including: If the modeling deviation characterization value of the modeling object is greater than or equal to the modeling deviation characterization threshold, then the deviation category of the modeling object is determined to be the high deviation category.

[0036] The modeling deviation characterization threshold is predetermined. The modeling deviation characterization value calculated when the trajectory deviation value is equal to the trajectory deviation value threshold, the number of motion increases of the active joint is equal to the number of motion increases threshold, and the extension amount of the motion path is equal to the extension amount threshold is determined as the modeling deviation characterization threshold.

[0037] Specifically, the standard detection module is used to call the instruction execution data based on the deviation category of the modeling object, and to perform detection and analysis on the modeling object, including, If the deviation category of the modeling object is a high deviation category, then the instruction is invoked to execute the data and perform detection and analysis on the modeling object.

[0038] Specifically, the standard detection module is used to calculate the modeling sensitivity representation coefficient of the modeling object, including, The ratio of the cumulative rotational angle deviation of the movable joint to the cumulative rotational angle deviation threshold is used as the first modeling sensitivity feature; The ratio of the threshold of the degrees of freedom of the movable joint to the degrees of freedom of the movable joint is used as the second modeling sensitivity feature; The sum of the first modeling sensitivity feature and the second modeling sensitivity feature is used as the modeling sensitivity characterization coefficient.

[0039] In this embodiment, the purpose of setting the cumulative rotation angle deviation threshold and the degree of freedom threshold of the movable joint is to characterize the poor sensitivity of the modeling object during the execution of instructions. Historical data related to the modeling object executing several control instructions is obtained, and historical data of the cumulative rotation angle deviation and degree of freedom of the movable joint are called to calculate the average cumulative rotation angle deviation and the average degree of freedom of the movable joint, which are then used as the baseline values ​​under normal conditions. Based on the purpose of setting the above two thresholds, the cumulative rotation angle deviation threshold is determined as the product of the average cumulative rotation angle deviation and the cumulative deviation coefficient, and the degree of freedom threshold of the movable joint is determined as the product of the average degree of freedom of the movable joint and the free offset coefficient. The cumulative deviation coefficient is selected within the interval [1.1, 1.15], preferably 1.1 in practice, and the free offset coefficient is selected within the interval [0.9, 0.95], preferably 0.9 in practice.

[0040] It is understandable that the modeling object is composed of multiple movable joints connected in series. Each movable joint has a certain error within a reasonable range when rotating at an angle. When the modeling object executes a command action, the angle error of the first joint will be transmitted to the next joint and added to the error of the second joint itself, and so on, accumulating the error. When the accumulation reaches a certain level, it will affect the execution accuracy of the modeling object. Therefore, in this embodiment, the cumulative amount of rotation angle deviation of the movable joints is considered to affect the execution command of the modeling object. The modeling object can be a robotic arm or a robot or other dynamically moving objects, which will not be elaborated further.

[0041] Specifically, the degrees of freedom of a movable joint refers to the number of directions in which several movable joints of a modeling object can move independently. Since the modeling object moves in coordination and synchronization with each other during the execution of instructions, the control system needs to process more information and perform more calculations, which increases the control cycle and response time and affects the sensitivity of the modeling object.

[0042] Specifically, this invention sets up a standard detection module to detect and analyze the deviations generated by the execution of commands by the modeled object, analyze the cumulative amount of rotation angle deviation of the movable joint, and assess the frequency of the continuous rotation angle deviation. If the cumulative amount of rotation angle deviation of a certain movable joint is large, it indicates that the movable joint has continuously experienced angle deviations in multiple command executions, affecting the accuracy and smoothness of the modeled object's execution of commands. Considering the degrees of freedom of the movable joints can more comprehensively analyze the motion capabilities and limitations of the movable joints, so as to quantify the degree of interference of the above two factors on the deviation. Therefore, this invention calculates the modeling sensitivity coefficient of the modeling object based on the cumulative rotation angle deviation of its movable joints and the degrees of freedom of the movable joints. This coefficient characterizes the modeling object's responsiveness to commands and its own motion sensitivity, providing data support for determining whether the execution of commands corresponding to the modeling object meets the execution error benchmark. This invention can accurately evaluate the command execution effect of the modeling object, promptly identify potential problems, and improve the execution efficiency of dynamic modeling.

[0043] Specifically, please refer to Figure 3 As shown, this is a logic diagram for determining whether the execution of instructions corresponding to the modeling object meets the execution error benchmark. The standard detection module is used to determine whether the execution of instructions corresponding to the modeling object meets the execution error benchmark, including: If the modeling sensitivity coefficient of the modeling object is greater than or equal to the modeling sensitivity coefficient threshold, then the execution of the instruction corresponding to the modeling object is determined to be inconsistent with the execution error benchmark. If the modeling sensitivity coefficient of the modeling object is less than the modeling sensitivity coefficient threshold, then the execution of the instruction corresponding to the modeling object is determined to meet the execution error benchmark.

[0044] The modeling sensitivity characterization coefficient threshold is predetermined. The modeling sensitivity characterization coefficient calculated when the cumulative amount of rotation angle deviation of the movable joint is equal to the cumulative amount of rotation angle deviation threshold, and the threshold of the movable joint degrees of freedom is equal to the movable joint degrees of freedom, is determined as the modeling sensitivity characterization coefficient threshold.

[0045] Specifically, the standard adjustment module responds to the determination result of the standard detection module, including, If the determination result is that the execution of the instruction corresponding to the modeling object does not meet the modeling sensitivity benchmark, then the point cloud density of the corresponding active joint is adjusted based on the modeling sensitivity characterization coefficient for secondary modeling.

[0046] Specifically, the standard adjustment module is used to adjust the point cloud density of the corresponding active joint based on the modeling sensitivity representation coefficient, including: Increase the point cloud density, and the amount of increase in point cloud density is positively correlated with the modeling sensitivity characterization coefficient.

[0047] In this embodiment, optionally, The modeling sensitivity coefficient is compared with the preset first modeling sensitivity coefficient comparison threshold and the second modeling sensitivity coefficient comparison threshold. When the modeling sensitivity coefficient is greater than the second modeling sensitivity coefficient comparison threshold, the increase in point cloud density is determined as the first increase, which is set to be 1.8 times the current point cloud density. When the modeling sensitivity coefficient is greater than or equal to the first modeling sensitivity coefficient comparison threshold and less than or equal to the second modeling sensitivity coefficient comparison threshold, the increase in point cloud density is determined to be the second increase, which is set to be 1.55 times the current point cloud density. When the modeling sensitivity coefficient is less than the first modeling sensitivity coefficient comparison threshold, the increase in point cloud density is determined to be the third increase, which is set to be 1.3 times the current point cloud density. The first modeling sensitivity coefficient comparison threshold is 1.1 times the modeling sensitivity coefficient threshold, and the second modeling sensitivity coefficient comparison threshold is 1.3 times the modeling sensitivity coefficient threshold.

[0048] It is understandable that the purpose of setting the increase is to make the point cloud density adapt to the flexibility and accuracy of the instructions executed by the modeling object. Therefore, the increase in point cloud density can also be adjusted by those skilled in the art under different circumstances, which will not be elaborated here.

[0049] Specifically, please refer to Figure 4 As shown, this is a logic decision diagram for analyzing whether the modeling object meets the delay error condition according to an embodiment of the present invention. The standard transmission module is used to analyze whether the modeling object meets the delay error condition, including: If the transmission delay of the instruction execution corresponding to the modeling object is less than the transmission delay threshold and the execution delay is less than the execution delay threshold, then the modeling object is determined to meet the delay error condition.

[0050] In this embodiment, the purpose of setting the transmission delay threshold is to characterize the situation where the modeling object responds to the predetermined instruction with a large delay due to the slow data transmission. The purpose of setting the execution delay threshold is to characterize the situation where the instruction execution is relatively delayed due to the error of the modeling model of the modeling object. Historical data related to the execution of several control commands by the modeling object is obtained. Historical data of transmission delay and execution delay are called, and the mean of transmission delay and the mean of execution delay are calculated respectively. These are used as the baseline values ​​under normal conditions. Based on the purpose of setting the above two thresholds, the transmission delay threshold is determined as the product of the mean of transmission delay and the transmission deviation coefficient, and the execution delay threshold is determined as the product of the mean of execution delay and the execution offset coefficient. The transmission deviation coefficient is selected in the interval [1.1, 1.15], preferably 1.1 in practice, and the execution offset coefficient is selected in the interval [1.15, 1.2], preferably 1.15 in practice.

[0051] Specifically, the standard transmission module is used to determine whether to adjust the network link bandwidth, including, If the modeling object does not meet the delay error condition, then it is determined to adjust the network link bandwidth, including increasing the allocation of network link bandwidth.

[0052] Specifically, this invention sets up a standard transmission module to evaluate the impact of data on the execution instructions of the modeled object, based on accurate secondary modeling in advance. It also clearly distinguishes between transmission latency and execution latency. Transmission latency reflects the time spent on data transmission over the network, while execution latency reflects the time required for the modeled object to process and execute instructions internally. By analyzing these two characteristics, the impact of network transmission and the modeled object's own processing on instruction execution can be quantified from two dimensions. Stable network transmission and timely instruction execution can reduce the probability of system failures or anomalies, providing accurate direction for subsequent problem-solving. Therefore, this invention analyzes delay characteristics to determine whether the modeled object after secondary modeling meets the delay error condition, and also provides support for subsequent determination of whether to adjust network link bandwidth, effectively reducing transmission delay and making the modeled object's movements smoother and more accurate. It avoids incoordination or errors caused by delay. For example, in robot modeling and command control, reducing delay enables the robot to respond to control commands more quickly and accurately, improving its operational precision and efficiency. This invention can meet the real-time response requirements of the modeled object, accurately evaluate the command execution effect of the modeled object, promptly identify potential problems, and improve the execution efficiency of dynamic modeling.

[0053] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A standardized dynamic information intelligent detection system, characterized in that, include: A standard data storage module is used to store the actual motion trajectory samples of the modeling object executing predetermined instructions, as well as the instruction execution data of the modeling object; The standard analysis module is used to control the modeling object to execute the predetermined instructions in the modeling space in order to obtain the modeling motion trajectory of the modeling object; The standard deviation evaluation module is used to compare the modeled motion trajectory with the actual motion trajectory sample, determine the trajectory deviation value, and evaluate the modeling deviation characterization value in combination with the joint motion deviation characteristics corresponding to the modeling object, so as to determine the deviation category of the modeling object. The standard detection module is used to call the instruction execution data based on the deviation category of the modeling object, and to perform detection and analysis on the modeling object, including: The cumulative rotation angle deviation and degrees of freedom of the movable joints of the modeling object are obtained, and the modeling sensitivity characterization coefficient of the modeling object is calculated to determine whether the execution of the instruction corresponding to the modeling object meets the execution error benchmark. The standard adjustment module, in response to the judgment result of the standard detection module, adjusts the point cloud density of the corresponding active joint for secondary modeling based on the modeling sensitivity characterization coefficient; A standard transmission module is used to control the modeling object to execute the predetermined instruction again, obtain the delay characteristics of the instruction execution, analyze whether the modeling object meets the delay error condition, and determine whether to adjust the network link bandwidth. The joint motion deviation characteristics include the number of increases in the number of movements of the active joint and the amount of extension of the motion path, and the delay characteristics include the amount of transmission delay and the amount of execution delay.

2. The standardized dynamic information intelligent detection system according to claim 1, characterized in that, The standard deviation evaluation module is used to evaluate the modeling deviation characterization value, including: The ratio of the trajectory deviation value to the trajectory deviation value threshold is used as the first modeling deviation feature; The sum of the ratio of the increase in the number of movements of the active joint to the threshold for the increase in the number of movements and the ratio of the extension of the movement path to the threshold for the extension is used as the second modeling bias feature. The first modeling deviation feature and the second modeling deviation feature are weighted and summed to obtain the modeling deviation characterization value.

3. The standardized dynamic information intelligent detection system according to claim 2, characterized in that, The standard deviation evaluation module is used to determine the deviation category of the modeling object, including: If the modeling deviation characterization value of the modeling object is greater than or equal to the modeling deviation characterization threshold, then the deviation category of the modeling object is determined to be the high deviation category.

4. The standardized dynamic information intelligent detection system according to claim 3, characterized in that, The standard detection module is used to call the instruction execution data according to the deviation category of the modeling object, and to perform detection and analysis on the modeling object, including: If the deviation category of the modeling object is a high deviation category, then the instruction is invoked to execute the data and perform detection and analysis on the modeling object.

5. The standardized dynamic information intelligent detection system according to claim 1, characterized in that, The standard detection module is used to calculate the modeling sensitivity coefficient of the modeling object, including: The ratio of the cumulative rotational angle deviation of the movable joint to the cumulative rotational angle deviation threshold is used as the first modeling sensitivity feature; The ratio of the threshold of the degrees of freedom of the movable joint to the degrees of freedom of the movable joint is used as the second modeling sensitivity feature; The sum of the first modeling sensitivity feature and the second modeling sensitivity feature is used as the modeling sensitivity characterization coefficient.

6. The standardized dynamic information intelligent detection system according to claim 5, characterized in that, The standard detection module is used to determine whether the execution of the instructions corresponding to the modeled object conforms to the execution error benchmark, including: If the modeling sensitivity coefficient of the modeling object is greater than or equal to the modeling sensitivity coefficient threshold, then the execution of the instruction corresponding to the modeling object is determined to be inconsistent with the execution error benchmark.

7. The standardized dynamic information intelligent detection system according to claim 6, characterized in that, The standard adjustment module responds to the determination result of the standard detection module, including: If the determination result is that the execution of the instruction corresponding to the modeling object does not meet the modeling sensitivity benchmark, then the point cloud density of the corresponding active joint is adjusted based on the modeling sensitivity characterization coefficient for secondary modeling.

8. The standardized dynamic information intelligent detection system according to claim 5, characterized in that, The standard adjustment module is used to adjust the point cloud density of the corresponding active joint based on the modeling sensitivity coefficient, including: Increase the point cloud density, and the amount of increase in point cloud density is positively correlated with the modeling sensitivity characterization coefficient.

9. The standardized dynamic information intelligent detection system according to claim 1, characterized in that, The standard transmission module is used to analyze whether the modeling object meets the delay error condition, including: If the transmission delay of the instruction execution corresponding to the modeling object is less than the transmission delay threshold and the execution delay is less than the execution delay threshold, then the modeling object is determined to meet the delay error condition.

10. The standardized dynamic information intelligent detection system according to claim 9, characterized in that, The standard transmission module is used to determine whether to adjust the network link bandwidth, including: If the modeling object does not meet the delay error condition, then it is determined that the network link bandwidth should be adjusted.

Images