TSN configuration method, system and terminal based on robot operation environment

Abstract

The invention relates to a TSN configuration method and system based on a robot operation environment and a terminal, and relates to the field of industrial internet, and the method comprises the steps: obtaining external environment parameters of a robot; analyzing the external environment parameters to determine an operation risk index of the robot; determining a switching operation mode of the robot according to the operation risk index and a preset index mode relationship; acquiring an actual operation mode and an actual TSN network architecture of the robot; judging whether the actual operation mode meets the requirement of switching the operation mode or not; if yes, the actual TSN network architecture is kept, and the external environment parameters of the robot continue to be obtained for cyclic analysis and judgment; and if not, reconfiguring the network architecture for the robot. The method and the device have the effect of improving the efficiency of network resource allocation.

Description

Technical Field

[0001] The present application relates to the technical field of industrial Internet, and in particular to a TSN configuration method, system and terminal based on a robot operating environment. Background Art

[0002] Time Sensitive Network (TSN) is a set of communication standards designed to achieve low-latency, deterministic, high-bandwidth transmission in Ethernet. These standards include time synchronization, traffic shaping, priority scheduling, reliable transmission, and network management.

[0003] In related technologies, robots usually involve multiple types of data streams, and the various types of data usually have different requirements for time sensitivity and bandwidth. For example, real-time control data requires low latency and high priority, visual sensor data requires large bandwidth, and status monitoring data is at a lower priority. Therefore, when configuring the TSN network for the robot, time synchronization, bandwidth reservation and traffic scheduling, VLAN division and priority setting will be performed in sequence to ensure that all robots are synchronized in the same time domain and ensure that high-priority data is transmitted within the specified time window.

[0004] Regarding the above-mentioned related technologies, when configuring the TSN network for the robot, although the different requirements for priority and bandwidth of different types of data are taken into consideration, priorities and specified transmission time windows are set for different types of data. However, the working environment of the robot is complex. Once a collision, slip or power outage occurs, the priority and bandwidth of the data required by the robot will change, resulting in the inability to reallocate network resources in a timely manner. There is still room for improvement. Summary of the invention

[0005] In order to improve the efficiency of network resource allocation, the present application provides a TSN configuration method, system and terminal based on a robot operating environment.

[0006] In the first aspect, the present application provides a TSN configuration method based on a robot operating environment, which adopts the following technical solutions: A TSN configuration method based on a robot operating environment, comprising: Get the robot's external environment parameters; Analyze external environmental parameters to determine the robot's operation risk index; Determine the robot's switching operation mode according to the operation risk index and the preset index mode relationship; Obtain the actual operation mode of the robot and the actual TSN network architecture; Determine whether the actual operation mode meets the requirements for switching the operation mode; If it meets the requirements, the actual TSN network architecture is maintained, and the robot's external environment parameters are continuously acquired for cyclic analysis and judgment; If not, reconfigure the network architecture for the robot.

[0007] By adopting the above technical solution, the robot's external environmental parameters are analyzed to determine the robot's operation risk index, and then the switching operation mode is determined according to the relationship between the operation risk index and the index mode. When it is determined that the switching operation mode is inconsistent with the actual operation mode, it indicates that the change in the robot's external environment has caused the robot's network resource configuration to change. Therefore, the network architecture of the robot is reconfigured, thereby improving the efficiency of network resource allocation.

[0008] Optionally, the step of analyzing the external environment parameters to determine the operation risk index of the robot includes: Analyze external environmental parameters to determine disaster parameter values, obstacle dynamic parameter values, and communication quality parameter values; Analyze the disaster parameter values ​​and preset disaster parameter thresholds to determine the disaster risk index; Analyze the obstacle dynamic parameter value and the preset safety dynamic parameter value to determine the obstacle hazard index; Analyze the communication quality parameter value and the preset error parameter threshold to determine the communication risk index; Get the risk index weight coefficient; The risk index weight coefficient, disaster hazard index, obstacle hazard index and communication hazard index are analyzed to determine the operational risk index.

[0009] By adopting the above technical scheme, the disaster risk index, obstacle risk index and communication risk index are obtained according to the analysis of disaster parameter values, obstacle dynamic parameter values ​​and communication quality parameter values ​​respectively, and then the disaster risk index, obstacle risk index and communication risk index are weighted and fused according to the risk index weight coefficient to obtain the operation risk index, so as to calculate the risk index according to the factors in the external environment that affect the operation of the robot, thereby improving the accuracy of the operation risk index.

[0010] Optionally, the steps of obtaining the risk index weight coefficient include: Obtain historical environmental parameters and historical weight coefficients; Controlling a preset environmental prediction model to make predictions based on historical environmental parameters to generate predicted environmental parameters; Get the environment transition probability matrix; Analyze the environmental transition probability matrix and predicted environmental parameters to determine the transition probability and predict the transition environment; Obtaining the environmental weight coefficient of the predicted transfer environment; The environmental weight coefficient, historical weight coefficient and transition probability are analyzed to determine the risk index weight coefficient.

[0011] By adopting the above technical scheme, the control environment prediction model generates predicted environment parameters according to historical environment parameters, and then identifies the transfer probability and predicts the transfer environment in the environment transfer probability matrix according to the predicted environment parameters and historical environment parameters, so as to calculate the risk index weight coefficient according to the environmental weight coefficient, historical weight coefficient and transfer probability of the predicted transfer environment, thereby ensuring the efficiency of determining the risk index weight coefficient.

[0012] Optionally, the step of analyzing the environmental weight coefficient, the historical weight coefficient and the transition probability to determine the risk index weight coefficient includes: Determine the probability amplification factor based on the relationship between the predicted transfer environment and the preset environmental coefficient; Analyze the transfer probability and the probability magnification factor to determine the magnification probability; The environmental weight coefficient, amplification probability and historical weight coefficient are analyzed to determine the risk index weight coefficient.

[0013] By adopting the above technical scheme, the probability amplification coefficient is determined according to the relationship between the predicted transfer environment and the environmental coefficient, and the transfer probability is amplified by the probability amplification coefficient to obtain the amplified probability, so as to obtain the risk index weight coefficient after analyzing and calculating the environmental weight coefficient and the historical weight coefficient with the amplified probability, and the risk index weight coefficient is calculated with the amplified transfer probability, which actively adapts to the prediction trend and improves the efficiency of determining the weight coefficient.

[0014] Optionally, steps to reconfigure the network architecture for the robot include: Determine the switching network architecture according to the switching operation mode and the preset mode architecture relationship; the switching network architecture includes a centralized architecture, a distributed edge architecture and an ad hoc network architecture; Reconfigure the network architecture for the robot according to the switched network architecture, and determine whether the switched network architecture is a self-organizing network architecture; If not, continue to obtain the robot's external environment parameters for cyclic analysis and judgment; If so, the robot is protected according to the operational risk index.

[0015] By adopting the above technical solution, the switching network architecture is determined according to the relationship between the switching operation mode and the mode architecture, and the network architecture of the robot is reconfigured according to the switching network architecture, thereby improving the efficiency of configuring the network architecture.

[0016] Optionally, the steps of performing data protection on the robot according to the operation risk index include: Determine whether the operation risk index meets the requirements of the preset protection index; If it does not meet the requirements, the robot's external environment parameters will continue to be acquired for cyclic analysis and judgment; If it meets the requirements, the compliance time of the operation risk index is obtained; Determine whether the compliance time exceeds the preset protection time; If it does not exceed, continue to obtain the matching time of the operation risk index for cyclic judgment; If exceeded, the preset fuse mechanism will be activated to protect the robot's data.

[0017] By adopting the above technical solution, when it is determined that the operation risk index meets the requirements of the protection index and the compliance time exceeds the protection time, the fuse mechanism is activated to protect the robot data, and a dual threshold is used to determine whether to protect the robot data, thereby avoiding instantaneous misjudgment and causing robot data loss, thereby improving the accuracy of robot data protection.

[0018] Optionally, the steps of activating a preset fuse mechanism to protect robot data include: Get the robot's real-time transmission data stream; Identify real-time transmission data streams to determine non-critical data streams and critical data streams; Stop the transmission of non-critical data streams and activate the preset encryption channel; Transmit critical data streams via encrypted channels.

[0019] By adopting the above technical solution, the transmission of non-critical data streams is terminated, thereby giving priority to the transmission of critical data streams, and activating encrypted channels to transmit critical data streams, thereby improving the efficiency and security of critical data stream transmission.

[0020] Optionally, the step of activating a preset encryption channel includes: Analyze key data streams to determine data type and data transfer speed; Determine an activation channel according to the data type and a preset data channel relationship; Analyze the data transmission speed and the preset effective bandwidth to determine the reserved bandwidth redundancy; The encrypted channel is activated according to the activated channel, and bandwidth is reserved according to the reserved bandwidth redundancy.

[0021] By adopting the above technical solution, the activation signal is determined according to the relationship between the data type and the data channel, so as to match the appropriate channel for the key data stream, which not only ensures the security of data transmission, but also does not occupy the remaining channels. The reserved bandwidth redundancy is determined according to the data transmission speed and the effective bandwidth, so that the encrypted channel reserves bandwidth with the reserved bandwidth redundancy. In the event of an abnormal situation, the channel still has sufficient bandwidth to ensure the quality of the transmitted data stream.

[0022] In the second aspect, the present application provides a TSN configuration system based on a robot operating environment, which adopts the following technical solutions: A TSN configuration system based on a robot operating environment, comprising: The acquisition module is used to obtain external environment parameters, actual operation mode and actual TSN network architecture; A memory, used to store a program of a TSN configuration method based on a robot operating environment as described in any one of the above items; The program in the memory can be loaded and executed by the processor and implement a TSN configuration method based on a robot operating environment as described in any one of the above items.

[0023] By adopting the above technical solution, the processor loads and executes a program of a TSN configuration method based on the robot operating environment stored in the memory, and the control acquisition module obtains a series of data related to the TSN configuration based on the robot operating environment, so as to determine the operation risk index of the robot after analyzing the external environment parameters of the robot, and then determine the switching operation mode according to the relationship between the operation risk index and the index mode. When it is determined that the switching operation mode is inconsistent with the actual operation mode, it indicates that the change of the external environment of the robot causes the change of the network resource configuration of the robot, so the network architecture of the robot is reconfigured, thereby improving the efficiency of network resource allocation.

[0024] In a third aspect, the present application provides a smart terminal, which adopts the following technical solution: An intelligent terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes a TSN configuration method based on a robot operating environment as described in any one of the above items.

[0025] By adopting the above technical solution, by operating the intelligent terminal, the processor loads and executes a program of a TSN configuration method based on the robot operating environment stored in the memory, thereby analyzing the external environmental parameters of the robot and determining the operation risk index of the robot, and then determining the switching operation mode according to the relationship between the operation risk index and the index mode. When it is determined that the switching operation mode is inconsistent with the actual operation mode, it indicates that the change in the external environment of the robot has caused the change in the network resource configuration of the robot, so the network architecture of the robot is reconfigured, thereby improving the efficiency of network resource allocation.

[0026] In summary, the present application includes at least one of the following beneficial technical effects: 1. The robot's operation risk index is determined by analyzing the robot's external environment parameters, and the switching operation mode is determined based on the relationship between the operation risk index and the index mode. When the switching operation mode is determined to be inconsistent with the actual operation mode, it indicates that the robot's external environment changes have caused the robot's network resource configuration to change. Therefore, the network architecture is reconfigured for the robot, thereby improving the efficiency of network resource allocation; 2. The disaster risk index, obstacle risk index and communication risk index are obtained by analyzing the disaster parameter value, obstacle dynamic parameter value and communication quality parameter value respectively, and then the disaster risk index, obstacle risk index and communication risk index are weighted and integrated according to the risk index weight coefficient to obtain the operation risk index, so as to calculate the risk index according to the factors in the external environment that affect the operation of the robot, thereby improving the accuracy of the operation risk index; 3. When it is determined that the operation risk index meets the requirements of the protection index and the compliance time exceeds the protection time, the fuse mechanism is activated to protect the robot data. A dual threshold is used to determine whether the robot data is protected, thereby avoiding instantaneous misjudgment and causing robot data loss, thereby improving the accuracy of robot data protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flowchart of a TSN configuration method based on a robot operating environment in an embodiment of the present application.

[0028] Figure 2 It is a flowchart of the steps of analyzing external environmental parameters to determine the operation risk index of the robot in an embodiment of the present application.

[0029] Figure 3 It is a flowchart of the steps of obtaining the risk index weight coefficient in an embodiment of the present application.

[0030] Figure 4 It is a flowchart of the steps of analyzing the environmental weight coefficient, the historical weight coefficient and the transition probability to determine the risk index weight coefficient in an embodiment of the present application.

[0031] Figure 5 It is a flowchart of the steps for reconfiguring the network architecture of the robot in an embodiment of the present application.

[0032] Figure 6 It is a flowchart of the steps of protecting robot data according to the operation risk index in an embodiment of the present application.

[0033] Figure 7 It is a flowchart of the steps of activating a preset fuse mechanism to protect the robot's data in an embodiment of the present application.

[0034] Figure 8It is a flowchart of the steps of activating a preset encrypted channel in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figures 1 to 8 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] The embodiment of the present application discloses a TSN configuration method based on the robot operating environment. After the sensor detects the external environment parameters of the robot, the external environment parameters are sent to the processing terminal. The processing terminal determines the operation risk index after analyzing the external environment parameters, and searches for the switching operation mode in the mapping table corresponding to the index mode relationship according to the operation risk index. When the processing terminal determines that the actual operation mode of the robot is consistent with the switching operation mode, the actual TSN network architecture is maintained. If they are inconsistent, the network architecture is reconfigured for the robot, so as to timely reallocate network resources for the robot according to changes in the external environment, thereby improving the efficiency of network resource allocation.

[0037] Reference Figure 1 The embodiment of the present application discloses a TSN configuration method based on a robot operating environment, comprising the following steps: Step S100: Acquire the external environment parameters of the robot.

[0038] Among them, external environmental parameters refer to data in the robot's operating environment, including disaster parameter values, obstacle dynamic parameter values ​​and communication quality parameter values. Disaster parameter values ​​include values ​​such as smoke concentration, temperature and radiation intensity, which are detected by relevant sensors such as temperature sensors and smoke sensors and sent to the processing terminal; obstacle dynamic parameter values ​​refer to the obstacle approach speed, which is measured in real time by the lidar and sent to the processing terminal; communication quality parameter values ​​refer to the bit error rate of the communication link, and the bit error rate is obtained by selecting test data to conduct actual test and comparison on the communication link.

[0039] Step S101: Analyze external environmental parameters to determine the operation risk index of the robot.

[0040] The operation risk index refers to the risk value caused by external environmental parameters to the robot during operation, which is determined by the processing terminal after analyzing the external environmental parameters. For specific methods, refer to Figure 2 steps.

[0041] Step S102: Determine the switching operation mode of the robot according to the operation risk index and a preset index mode relationship.

[0042] Among them, the index mode relationship refers to the corresponding relationship between the risk index and the operating mode. In the embodiment of the present application, there are three operating modes, including safety mode, warning mode and emergency mode. Among them, when the risk index is lower than 1, it corresponds to the safety mode, when the risk index is between 1 and 2, it corresponds to the warning mode, and when the risk index is greater than 2, it corresponds to the emergency mode. The operator matches the risk index and the operating mode one by one to form a mapping table.

[0043] The switching operation mode refers to an operation mode suitable for the current external environment parameters, which is obtained by the processing terminal by searching in a mapping table corresponding to the index mode relationship according to the operation risk index.

[0044] Step S103: Obtain the actual operation mode and actual TSN network architecture of the robot.

[0045] The actual operation mode refers to the current operation mode of the robot, which is obtained by the processing terminal identifying and calling the operation mode of the robot. The actual TSN network architecture refers to the current TSN architecture of the robot, which is obtained by the processing terminal identifying and calling the network architecture of the robot.

[0046] Step S104: Determine whether the actual operation mode meets the requirements for switching the operation mode.

[0047] The requirement for switching the operating mode refers to being consistent with the switching operating mode and is stored in the processing terminal by the operator.

[0048] The processing terminal determines whether the actual operation mode is consistent with the switched operation mode, thereby determining whether the network architecture needs to be reconfigured for the robot.

[0049] Step S1041: If it meets the requirements, the actual TSN network architecture is maintained, and the external environment parameters of the robot are continuously acquired for cyclic analysis and judgment.

[0050] Among them, if the processing terminal determines that the actual operation mode is consistent with the switched operation mode, it means that the operation mode of the robot has not changed, so there is no need to reconfigure the network architecture, so as to continue to maintain the actual TSN network architecture and continue to detect the external environmental parameters of the robot to continuously monitor the changes in the external environment of the robot.

[0051] Step S1042: If not, reconfigure the network architecture for the robot.

[0052] If the processing terminal determines that the actual operation mode is inconsistent with the switching operation mode, it indicates that the operation mode of the robot needs to be changed. At this time, the network architecture of the robot is reconfigured. The specific method is as follows Figure 5 steps, thereby triggering a responsive network scheduling strategy based on environmental changes, thereby improving the efficiency of network resource allocation.

[0053] Reference Figure 2 ,The steps of analyzing the external environment parameters to determine the robot's operation risk index include: Step S200: Analyze the external environment parameters to determine the disaster parameter value, the obstacle dynamic parameter value and the communication quality parameter value.

[0054] Among them, the disaster parameter value refers to the physical factors in the external environment that affect the operation of the robot, including values ​​such as smoke concentration, temperature and radiation intensity, which are detected by relevant sensors such as temperature sensors and smoke sensors and sent to the processing terminal; the obstacle dynamic parameter value refers to the obstacle approach speed, which is measured in real time by the lidar and sent to the processing terminal; the communication quality parameter value refers to the bit error rate of the communication link, which is obtained by selecting test data for actual test and comparison of the communication link. The three are identified and called by the processing terminal in the data packet corresponding to the external environment parameters.

[0055] Step S201: Analyze the disaster parameter value and the preset disaster parameter threshold to determine the disaster risk index.

[0056] The disaster parameter threshold refers to the safety threshold when a disaster occurs. For example, the smoke concentration threshold is set at 500ppm and is determined by the operator based on actual conditions.

[0057] The disaster risk index refers to the risk index caused by the disaster parameters to the robot, which is obtained by calculating the quotient between the disaster parameter value and the disaster parameter threshold by the processing terminal.

[0058] Step S202: Analyze the obstacle dynamic parameter value and the preset safety dynamic parameter value to determine the obstacle hazard index.

[0059] The safety dynamic parameter value refers to the maximum safe approach speed allowed by the robot, and 2m / s is taken as an example in the embodiment of the present application.

[0060] The obstacle hazard index refers to the risk index caused by dynamic obstacles to the robot, which is obtained by calculating the quotient between the obstacle dynamic parameter value and the safety dynamic parameter value by the processing terminal.

[0061] Step S203: Analyze the communication quality parameter value and the preset error parameter threshold to determine the communication risk index.

[0062] The bit error parameter threshold refers to the maximum bit error rate threshold tolerated by communication quality, and 0.0005 is taken as an example in the embodiment of the present application.

[0063] The communication risk index refers to the risk index caused by the communication quality to the operation of the robot, which is obtained by calculating the quotient between the communication quality parameter value and the error parameter threshold by the processing terminal.

[0064] Step S204: Obtain risk index weight coefficient.

[0065] Among them, the risk index weight coefficient refers to the weight of different risk indices in the total risk, including disaster weight coefficient, obstacle weight coefficient and communication weight coefficient. The specific acquisition method refers to Figure 3 steps.

[0066] Step S205: Analyze the risk index weight coefficient, disaster risk index, obstacle risk index and communication risk index to determine the operation risk index.

[0067] Among them, the operation risk index in this step is consistent with the operation risk index in step S101. The processing terminal calls the disaster weight coefficient, obstacle weight coefficient and communication weight coefficient in the risk index weight coefficient, so as to obtain the operation risk index by weighted summing the disaster weight coefficient, obstacle weight coefficient and communication weight coefficient with the disaster hazard index, obstacle hazard index and communication hazard index respectively.

[0068] Reference Figure 3 , the steps of obtaining the risk index weight coefficient include: Step S300: Obtain historical environmental parameters and historical weight coefficients.

[0069] Among them, the historical environmental parameters refer to the external environmental parameters of the robot before detecting the current external environmental parameters, which are detected by relevant sensors and sent to the processing terminal for backup and waiting for the processing terminal to call. The historical weight coefficient refers to the weight coefficient when the robot determined the risk index last time, which is backed up by the processing terminal for waiting to be called.

[0070] Step S301: Control a preset environment prediction model to make predictions based on historical environment parameters to generate predicted environment parameters.

[0071] Among them, the environmental prediction model refers to a model for predicting the environmental parameters at the next moment. In the embodiment of the present application, prediction is based on the long short-term memory network (LSTM), including an input layer, which abstracts historical environmental parameters into a dimensionally expandable feature vector, in which each component represents an environmental parameter; a hidden layer, which adopts a bidirectional LSTM layer (64 units) and an Attention mechanism; an output layer, a fully connected layer predicts the environmental parameters at the next moment.

[0072] The predicted environmental parameters refer to the predicted environmental parameters at the next moment, which are predicted by the processing terminal by inputting the historical environmental parameters into the environmental prediction model.

[0073] Step S302: Obtaining an environment transition probability matrix.

[0074] Among them, the environmental transition probability matrix refers to the transition probability matrix in the Markov decision process, which represents the probability of transitioning from one scene to another. It can be obtained through maximum likelihood estimation statistics. First, a series of scene sequences that change over time are recorded, and then the number of transitions from the first scene to the second scene is calculated. The number is divided by the total number to get the probability of a single scene transition. Finally, the probabilities of all scene transitions are sorted out to form an environmental transition probability matrix.

[0075] Step S303: Analyze the environment transition probability matrix and the predicted environment parameters to determine the transition probability and the predicted transition environment.

[0076] Among them, the predicted transfer environment refers to the predicted transfer scenario, which is obtained by the processing terminal according to the predicted environmental parameters in the scenario mapping table corresponding to the environmental parameters, including scenarios such as fire spread, communication interruption, and group obstacle avoidance.

[0077] The transition probability refers to the probability of a scene transition. First, the processing terminal calls the corresponding probability in the environment transition probability matrix according to the historical scenes and the transition scenes. Then, the Softmax function is used to convert the predicted environment parameters output by the environment prediction model into a probability distribution. Finally, the empirical smoothing coefficients corresponding to the probability matrix and the probability distribution are called, which are 0.3 and 0.7 respectively. The transition probability is obtained by weighted summation of the empirical smoothing coefficient, the probability matrix and the probability distribution.

[0078] Step S304: Obtain the environment weight coefficient of the predicted transfer environment.

[0079] Among them, the environmental weight coefficient refers to the disaster weight coefficient, obstacle weight coefficient and communication weight coefficient in the predicted environment, which are obtained by the processing terminal in the mapping table of environment and weight coefficient according to the predicted transfer environment. For example, in the fire spread scenario, the disaster weight coefficient is 0.7, the obstacle weight coefficient is 0.2, and the communication weight coefficient is 0.1; in the communication interruption scenario, the disaster weight coefficient is 0.3, the obstacle weight coefficient is 0.2, and the communication weight coefficient is 0.5, etc.

[0080] Step S305: Analyze the environmental weight coefficient, historical weight coefficient and transition probability to determine the risk index weight coefficient.

[0081] The risk index weight coefficient in this step is consistent with the risk index weight coefficient in step S204, and is calculated by the processing terminal according to the environmental weight coefficient, the historical weight coefficient and the transition probability. The specific method is referred to Figure 4 steps, thereby avoiding system oscillations caused by weight mutations through probability-weighted linear interpolation.

[0082] Reference Figure 4, the steps of analyzing the environmental weight coefficient, historical weight coefficient and transition probability to determine the risk index weight coefficient include: Step S400: Determine the probability amplification factor according to the relationship between the predicted transfer environment and the preset environment coefficient.

[0083] Among them, the environmental coefficient relationship refers to the correspondence between different environments and probability magnification coefficients. For example, the magnification coefficient of low-risk scenarios is smaller, and the magnification coefficient of emergency scenarios is larger. The operator forms a mapping table by matching the scenarios and probability magnification coefficients one by one.

[0084] The probability amplification factor refers to a factor used to amplify the transfer probability, and is obtained by searching the mapping table corresponding to the environmental coefficient relationship by the processing terminal according to the predicted transfer environment.

[0085] Step S401: Analyze the transition probability and the probability amplification factor to determine the amplified probability.

[0086] Among them, the amplified probability refers to the amplified transfer probability, the purpose of which is to enhance the influence of the prediction signal and solve the control lag problem caused by prediction uncertainty and execution delay in the dynamic environment. It is obtained by calculating the product of the transfer probability and the probability amplification coefficient by the processing terminal. When amplifying the transfer probability, it is truncated to 1 when it exceeds 1.

[0087] Step S402: Analyze the environmental weight coefficient, amplification probability and historical weight coefficient to determine the risk index weight coefficient.

[0088] Among them, the risk index weight coefficient in this step is consistent with the risk index weight coefficient in step S305. The processing terminal calculates the non-transfer probability based on the amplification probability and the total probability 1, and then calculates the product of the amplification probability and the environmental weight coefficient, and then calculates the product of the non-transfer probability and the historical weight coefficient. The two products are summed to obtain the risk index weight coefficient.

[0089] Reference Figure 5 ,The steps to reconfigure the network architecture for the robot include: Step S500: Determine the switching network architecture according to the switching operation mode and the preset mode architecture relationship; the switching network architecture includes a centralized architecture, a distributed edge architecture and a self-organizing network architecture.

[0090] Among them, the mode architecture relationship refers to the correspondence between the operating mode and the network architecture. For example, the security mode corresponds to the centralized architecture, the early warning mode corresponds to the distributed edge architecture, and the emergency mode corresponds to the self-organizing network architecture. The operator matches the operating mode and the network architecture one by one to form a mapping table.

[0091] The switching network architecture refers to the network architecture that needs to be switched to. It is found by the processing terminal in the mapping table corresponding to the mode architecture relationship according to the switching operation mode. It includes centralized architecture, distributed edge architecture and self-organizing network architecture. All three architectures can be used in combination with TSN technology. Among them, all computing, storage and decision-making functions of the centralized architecture are concentrated in a single or a small number of central nodes (such as data centers, servers), and edge devices are only responsible for lightweight tasks (such as sensor data uploading), thereby realizing resource scheduling, security policies, and data storage centralization to avoid synchronization conflicts. Unified policies, global monitoring and rapid response are required in the security mode, so a centralized architecture is selected; The distributed edge architecture moves computing, strategy, and decision-making capabilities down to edge nodes close to the data source (such as local servers, intelligent network management, and edge devices). The central node is only responsible for global coordination or complex tasks, reducing cloud dependence and data transmission time, and saving network resources. In the early warning mode, low-latency response, localized decision-making, and high reliability are required, such as natural disaster warning and equipment failure prediction. Therefore, a distributed edge architecture is selected; the self-organizing network architecture is a decentralized dynamic network architecture. Nodes autonomously form networks and dynamically adjust topology without relying on fixed infrastructure. In emergency modes, such as disaster relief, traditional networks may have been paralyzed, so a self-organizing network architecture is selected.

[0092] Step S501: reconfigure the network architecture for the robot according to the switched network architecture, and determine whether the switched network architecture is an ad hoc network architecture.

[0093] Among them, after determining to switch the network architecture, the network architecture is automatically reconfigured for the robot according to the switched network architecture. For example, when switching from a centralized architecture to a distributed edge architecture, the decision engine triggers the switch, distributes the computing tasks to the edge nodes, Kubernetes schedules the service instances to the edge, and the SDN controller updates the traffic routing. When switching to the self-organizing network architecture, the nodes automatically form a Mesh network, and the AODV protocol is used to maintain the routing. The edge nodes take over the local decision-making, and the data is temporarily stored and synchronized after recovery. After switching the network architecture, it is determined whether the switched network architecture is a self-organizing network architecture, so as to improve data support for the subsequent determination of whether data protection for the robot is required.

[0094] Step S5011: If not, continue to obtain the robot's external environment parameters for cyclic analysis and judgment.

[0095] Among them, if the processing terminal determines that the switched network architecture is not a self-organizing network architecture, it means that the emergency mode has not appeared. At this time, there is no need to protect the robot's data. Therefore, the robot's external environmental parameters continue to be detected, thereby continuously monitoring changes in the robot's operating environment.

[0096] Step S5012: If yes, data protection is performed on the robot according to the operation risk index.

[0097] If the processing terminal determines that the switched network architecture is an ad hoc network architecture, it means that the robot is in an extreme environment and is likely to cause damage to the robot's data. Therefore, the robot data is protected according to the operation risk index. The specific method is as follows: Figure 6 steps to ensure the data security of the robot.

[0098] Reference Figure 6 ,The steps of protecting robot data according to the operation risk index include: Step S600: Determine whether the operation risk index meets the requirements of the preset protection index.

[0099] The protection index refers to the minimum risk index for data protection. The specific value is determined by the operator based on actual conditions. The protection index requirement is not lower than the protection index.

[0100] By processing the terminal to determine whether the operation risk index is not lower than the protection index, it is determined whether the robot's environment is extreme, which provides data support for subsequent determination of whether the robot's data needs to be protected.

[0101] Step S601: If not, continue to obtain the robot's external environment parameters for cyclic analysis and judgment.

[0102] Among them, if the processing terminal determines that the operation risk index is lower than the protection index, it means that even if the robot is in emergency mode, the risk has not reached the level that requires data protection. Therefore, the external environmental parameters of the robot continue to be tested, so as to continue to pay attention to changes in the external environment of the robot.

[0103] Step S602: If it is in compliance, the compliance time of the operation risk index is obtained.

[0104] Among them, if the processing terminal determines that the operation risk index is not lower than the protection index, it means that the robot is in an extreme environment and data protection is required. Therefore, the compliance time of the operation risk index is detected to provide data support for the subsequent determination of whether an instantaneous misjudgment occurs.

[0105] The compliance time refers to the time when the operation risk index exceeds the protection index, which is obtained by the timer.

[0106] Step S603: Determine whether the compliance time exceeds the preset protection time.

[0107] Among them, the protection time refers to the minimum time that the operation risk index exceeds the protection time, and 2 seconds is taken as an example in the embodiment of the present application.

[0108] The processing terminal determines whether the compliance time exceeds the protection time, thereby determining whether an instantaneous misjudgment occurs in the data protection of the robot.

[0109] Step S6031: If it does not exceed, continue to obtain the matching time of the operation risk index for cyclic judgment.

[0110] Among them, if the processing terminal determines that the compliance time does not exceed the protection time, it means that the data protection of the robot is an instantaneous misjudgment, so the compliance time of the operation risk index continues to be detected, thereby continuously monitoring the operation risk status of the robot.

[0111] Step S6032: If exceeded, the preset fuse mechanism is activated to protect the robot's data.

[0112] If the processing terminal determines that the compliance time exceeds the protection time, it indicates that the data protection of the robot is not an instantaneous misjudgment, so the fuse mechanism is activated to protect the robot data. For specific methods, refer to Figure 7 steps.

[0113] The fuse mechanism refers to a method of terminating the transmission of non-critical data streams of the robot and retaining the transmission of critical data streams, which is stored in the processing terminal by the operator.

[0114] Reference Figure 7 , the steps to activate the preset fuse mechanism to protect the robot's data include: Step S700: Acquire the real-time transmission data stream of the robot.

[0115] The real-time transmission data stream refers to the data stream being transmitted by the robot, and the network monitoring tool captures and displays all traffic of the network adapter.

[0116] Step S701: Identify the real-time transmission data stream to determine the non-critical data stream and the critical data stream.

[0117] Among them, non-critical data streams refer to data with less impact under the current external environment, and critical data streams refer to data that directly affects the operation and safety of the robot. For example, in early warning or emergency modes, log files, performance statistics, non-urgent software update requests, etc. are non-critical data streams, and control instructions (such as move commands, stop instructions), real-time sensor data, and status feedback information are critical data, which are obtained by the processing terminal by identifying and classifying the real-time transmission data streams according to the external environment.

[0118] Step S702: suspend the transmission of non-critical data streams and activate the preset encryption channel.

[0119] Among them, after determining the non-critical data flow and the critical data flow, the non-critical data flow transmission is terminated, thereby reducing the external data transmission volume, reducing the risk of external attacks, and activating the encryption channel. The specific method is referred to Figure 8 The encrypted channel is a transmission channel that protects communication data by using encryption technology.

[0120] Step S703: Transmit the key data stream via an encrypted channel.

[0121] Among them, after the encrypted channel is activated, the key data stream is transmitted through the encrypted channel, thereby ensuring the normal transmission of the robot's key data and data security.

[0122] Reference Figure 8 , the steps of activating the preset encryption channel include: Step S800: Analyze the key data stream to determine the data type and data transmission speed.

[0123] Among them, data type refers to the type of key data flow, including control instructions, sensor data, and status information. Data transmission speed refers to the amount of data transmitted per unit time, which is determined by the processing terminal after analyzing the key data flow.

[0124] Step S801: determining an activated channel according to a data type and a preset data channel relationship.

[0125] Among them, the data channel relationship refers to the correspondence between different types of data and encrypted channels. Different types of data are divided into different levels. The higher the level of data, the higher the encryption level of the channel. The operator matches the data type with the encrypted channel one by one to form a mapping table.

[0126] The activated channel refers to an encrypted channel that needs to be activated, which is found by the processing terminal in a mapping table corresponding to the data channel relationship according to the data type.

[0127] Step S802: Analyze the data transmission speed and the preset effective bandwidth to determine the reserved bandwidth redundancy.

[0128] Among them, effective bandwidth refers to the total available bandwidth of the channel, which is determined by the operator based on the actual situation of the encrypted channel. Reserved bandwidth redundancy refers to the proportion of additional bandwidth reserved to ensure transmission quality. The processing terminal calculates the quotient of data transmission speed and effective bandwidth, and then subtracts the quotient from the total proportion to obtain the reserved bandwidth redundancy.

[0129] Step S803: activating the encrypted channel according to the activated channel, and reserving bandwidth according to the reserved bandwidth redundancy.

[0130] Among them, after determining the activation channel and reserved bandwidth redundancy, the corresponding encrypted channel is activated according to the activation channel, and bandwidth is reserved for the encrypted channel according to the reserved bandwidth redundancy, so that when the network conditions are poor or there is an unexpected increase in traffic, there is still enough bandwidth to ensure the transmission quality of critical data.

[0131] Based on the same inventive concept, the embodiment of the present application provides a TSN configuration system based on a robot operating environment, including: An acquisition module is used to obtain external environment parameters, actual operation mode, actual TSN network architecture, risk index weight coefficient, historical environment parameters, historical weight coefficient, environment transfer probability matrix, environment weight coefficient, compliance time and real-time transmission data stream; A memory for storing a program of a TSN configuration method based on a robot operating environment; The program in the processor memory can be loaded and executed by the processor to implement a TSN configuration method based on the robot operating environment.

[0132] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0133] An embodiment of the present application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute a TSN configuration method based on a robot operating environment.

[0134] Computer storage media include, for example, USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks, and other media that can store program codes.

[0135] Based on the same inventive concept, an embodiment of the present application provides an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute a TSN configuration method based on a robot operating environment.

[0136] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0137] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A TSN configuration method based on a robot operating environment, characterized in that: include: Get the robot's external environment parameters; Analyze external environmental parameters to determine the robot's operation risk index; Determine the robot's switching operation mode according to the operation risk index and the preset index mode relationship; Obtain the actual operation mode of the robot and the actual TSN network architecture; Determine whether the actual operation mode meets the requirements for switching the operation mode; If it meets the requirements, the actual TSN network architecture is maintained, and the robot's external environment parameters are continuously acquired for cyclic analysis and judgment; If not, reconfigure the network architecture for the robot.

2. A TSN configuration method based on a robot operating environment according to claim 1, characterized in that: The steps of analyzing the external environment parameters to determine the robot's operation risk index include: Analyze external environmental parameters to determine disaster parameter values, obstacle dynamic parameter values, and communication quality parameter values; Analyze the disaster parameter values ​​and preset disaster parameter thresholds to determine the disaster risk index; Analyze the obstacle dynamic parameter value and the preset safety dynamic parameter value to determine the obstacle hazard index; Analyze the communication quality parameter value and the preset error parameter threshold to determine the communication risk index; Get the risk index weight coefficient; The risk index weight coefficient, disaster hazard index, obstacle hazard index and communication hazard index are analyzed to determine the operational risk index.

3. A TSN configuration method based on a robot operating environment according to claim 2, characterized in that: The steps to obtain the risk index weight coefficient include: Obtain historical environmental parameters and historical weight coefficients; Controlling a preset environmental prediction model to make predictions based on historical environmental parameters to generate predicted environmental parameters; Get the environment transition probability matrix; Analyze the environmental transition probability matrix and predicted environmental parameters to determine the transition probability and predict the transition environment; Obtaining the environmental weight coefficient of the predicted transfer environment; The environmental weight coefficient, historical weight coefficient and transition probability are analyzed to determine the risk index weight coefficient.

4. A TSN configuration method based on a robot operating environment according to claim 3, characterized in that: The steps of analyzing the environmental weight coefficient, the historical weight coefficient and the transition probability to determine the risk index weight coefficient include: Determine the probability amplification factor based on the relationship between the predicted transfer environment and the preset environmental coefficient; Analyze the transfer probability and the probability magnification factor to determine the magnification probability; The environmental weight coefficient, amplification probability and historical weight coefficient are analyzed to determine the risk index weight coefficient.

5. A TSN configuration method based on a robot operating environment according to claim 1, characterized in that: The steps to reconfigure the network architecture for the robot include: Determine the switching network architecture according to the switching operation mode and the preset mode architecture relationship; the switching network architecture includes a centralized architecture, a distributed edge architecture and an ad hoc network architecture; Reconfigure the network architecture for the robot according to the switched network architecture, and determine whether the switched network architecture is a self-organizing network architecture; If not, continue to obtain the robot's external environment parameters for cyclic analysis and judgment; If so, the robot is protected according to the operational risk index.

6. A TSN configuration method based on a robot operating environment according to claim 5, characterized in that: The steps for protecting robot data based on the operational risk index include: Determine whether the operation risk index meets the requirements of the preset protection index; If it does not meet the requirements, the robot's external environment parameters will continue to be acquired for cyclic analysis and judgment; If it meets the requirements, the compliance time of the operation risk index is obtained; Determine whether the compliance time exceeds the preset protection time; If it does not exceed, continue to obtain the matching time of the operation risk index for cyclic judgment; If exceeded, the preset fuse mechanism will be activated to protect the robot's data.

7. A TSN configuration method based on a robot operating environment according to claim 6, characterized in that: The steps to activate the preset fuse mechanism to protect the robot's data include: Get the real-time transmission data stream of the robot; Identify real-time transmission data streams to determine non-critical data streams and critical data streams; Stop the transmission of non-critical data streams and activate the preset encryption channel; Transmit critical data streams via encrypted channels.

8. A TSN configuration method based on a robot operating environment according to claim 7, characterized in that: The steps to activate the preset encryption channel include: Analyze key data streams to determine data type and data transfer speed; Determine an activation channel according to the data type and a preset data channel relationship; Analyze the data transmission speed and the preset effective bandwidth to determine the reserved bandwidth redundancy; The encrypted channel is activated according to the activated channel, and bandwidth is reserved according to the reserved bandwidth redundancy.

9. A TSN configuration system based on a robot operating environment, characterized in that: include: The acquisition module is used to obtain external environment parameters, actual operation mode and actual TSN network architecture; A memory, used to store a program of a TSN configuration method based on a robot operating environment according to any one of claims 1 to 8; The program in the memory can be loaded and executed by the processor and implement a TSN configuration method based on a robot operating environment as described in any one of claims 1 to 8.

10. An intelligent terminal, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and executes a TSN configuration method based on a robot operating environment as described in any one of claims 1 to 8.

Images