Figure action accurate identification method suitable for VR practical training of basic library station

Abstract

The invention discloses a figure action accurate identification method suitable for VR practical training of a basic library station, relates to the technical field of basic library station detection, and solves the technical problem that in the prior art, scene differentiation cannot be carried out to identify and detect the action track of a practical training person. Taking the safety scene as an operation environment of a modeling scene, performing action recognition evaluation on the practical training personnel, and inferring the feasibility of action execution of the practical training personnel through operation recognition evaluation of each link in the safety scene; and taking the risk scene as an operation environment of a modeling scene, carrying out practical training personnel coping action identification evaluation when any equipment in a region operates abnormally, and deducing whether the practical training personnel coping measures for each link in the basic library station meet actual requirements or not.

Description

Technical Field

[0001] The present invention relates to the technical field of grassroots warehouse station detection, and in particular to a method for accurately recognizing human actions suitable for VR training of grassroots warehouse stations. Background Art

[0002] At grassroots depots in the energy, chemical and other industries, daily operations involve a large number of high-risk operational processes, such as oil loading and unloading, chemical storage and transshipment, etc. Traditional training methods rely more on theoretical explanations and on-site demonstrations. It is difficult for trainees to fully absorb complex knowledge within a limited time, and practical exercises in real scenarios, once operational errors are made, can easily lead to safety accidents and cause immeasurable losses.

[0003] However, in the existing technology, it is impossible to perform modeling control during training at the grassroots warehouse station, that is, it is impossible to fit the operation logic setting after modeling, which reduces the training efficiency. In addition, it is impossible to identify the trainees' misjudgment of actions, resulting in the inability to identify and collect action screening, affecting the accuracy of the training results. At the same time, it is impossible to differentiate the scenes to identify and detect the trainees' action trajectories, and the feasibility of action execution at the grassroots warehouse station cannot be effectively inferred.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to solve the above-mentioned problems and to propose a method for accurately recognizing human actions suitable for VR training at grassroots libraries and stations.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A method for accurately identifying human actions suitable for VR training at grassroots libraries and stations. The specific process of the method for accurately identifying human actions is as follows: S1. VR modeling of grassroots depots and stations. 3D modeling of the areas and equipment within the grassroots depots and stations. In the modeling stage, the equipment in the area is scaled in proportion to the actual working scene. After the modeling is completed, the construction coordination area is finely modeled, and the coordination operation logic of the equipment in each area is matched to ensure that the personnel undergoing VR training can perform actions in accordance with the actual scene; S2, action misjudgment identification, after completing the modeling, according to the actual modeling scene, the trainees should take actions according to the scene, and the action misjudgment identification of the trainees is performed; S3, safety scenario action recognition evaluation, after the trainee's action is accurately recognized, the safety scenario is used as the operating environment of the modeling scenario to conduct action recognition evaluation on the trainee. Through the operation recognition evaluation of each link in the safety scenario, the feasibility of the trainee's action execution is inferred; S4. Risk scenario action recognition assessment: using risk scenarios as the operating environment for modeling scenarios, conduct action recognition assessments on the responses of trainees when any equipment in the area operates abnormally, and infer whether the response measures of trainees at each link within the grassroots warehouses and stations meet actual needs.

[0007] As a preferred embodiment of the present invention, the VR modeling process of the grassroots warehouse station is as follows: Modeling and layout planning are carried out according to the actual layout of each area in the grassroots depot, and the equipment in each area of ​​the grassroots depot is simulated to restore the appearance and internal structure of the equipment; The operation logic of each area in the grassroots warehouse station under the actual scenario is obtained, and the operation actions of the adjacent areas are set as operation sub-logic, and the operation sub-logic constructs the entire operation logic according to the operation process of the grassroots warehouse station; the preset operation logic of the equipment is constructed according to the process execution sequence of each area in the grassroots warehouse station, and the operation sub-logic in the actual scenario is compared. If there is a logical deviation between the actual preset operation logic and the actual operation sub-logic, the logic of the mutual coordination of the equipment of the actual operation sub-logic is analyzed. If there is no deviation in the mutual coordination, the current actual operation sub-logic is marked as the production sub-logic, and the actual preset operation logic is marked as the ideal logic.

[0008] As a preferred implementation mode of the present invention, the execution time is set to different cycle progress in the VR modeling scenario, and the actual operation logic of the trainees is monitored. If the current cycle progress is in the stage of rushing to meet the deadline, that is, the remaining progress time is lower than the preset time of the remaining workload, the trainees actively change the operation logic, that is, it is inferred that the trainees' logical operation is qualified. On the contrary, if the trainees still use the ideal logic, it is inferred that the sequential personnel logic transformation is inefficient; if the current cycle progress is in the stage of early completion, the trainees only execute the ideal logic, that is, it is inferred that the trainees' logical operation is theoretical; the trainees' training is summarized according to the logic execution type, and displayed through the human-computer interaction terminal after the training.

[0009] As a preferred embodiment of the present invention, the action misjudgment identification process is as follows: In the simulation modeling scenario, the trainees' execution actions are detected, the displacement of the trainees' limb joints is monitored by sensors, and the trainees' limb movements are marked as execution actions. First, the corresponding operation logic is obtained according to the trainees' location, and the operation sub-logic is obtained according to the equipment that the trainees need to operate at the current moment; Analyze whether the current operation sub-logic receives the execution instruction; If yes, the current trainee is in the stage of receiving instructions. The trainee's action execution time and instruction receiving time are collected, and the execution delay is obtained according to the time comparison. If the current execution delay is within the delay range, and the body movement execution has no reset track, the corresponding execution action is marked as a logical action; otherwise, if the current execution delay is not within the delay range, or the body movement execution has a reset track, the corresponding execution action is marked as a non-logical action. If no, the trainee is currently in the no-instruction stage, and the trainee's real-time body position is collected. If the real-time body position moves, and the moving direction is not in the direction of the location of the running equipment of the process to be executed in the area, the trainee's current body movement is regarded as a superfluous instinctive movement; if the moving direction of the real-time body position is in the direction of the equipment in the area, and the body position enters the area where the equipment is located, the trainee's current body movement is regarded as an execution deviation action; Unnecessary instinctive actions and illogical actions are uniformly marked as recorded unrecognized actions; execution deviation actions and logical actions are uniformly marked as recorded recognized actions, and the action types of trainees are identified and collected.

[0010] As a preferred embodiment of the present invention, the safety scene action recognition and evaluation process is as follows: Set the simulation modeling scene for trainees to be a safe scene, that is, the equipment in each area of ​​the simulation modeling scene cooperates with each other properly or the equipment operating parameters in the area are within the rated range of the equipment; Collect execution buffer data and buffer impact data; If the execution buffer data exceeds the action buffer duration threshold, or the buffer impact data exceeds the speed reciprocating floating span threshold, the correct execution action process of the current operation logic is compared with the parameters of the real-time execution action, and the abnormalities are marked. After the training of the trainees is completed, it will be displayed through the human-computer interaction terminal after the training is completed; If the execution buffer data does not exceed the action buffer duration threshold, and the buffer impact data does not exceed the speed reciprocating floating span threshold, the correct execution action process of the current operation logic and the parameters of the real-time execution action are compared and collected, and displayed through the human-computer interaction terminal after the trainees complete the training.

[0011] As a preferred embodiment of the present invention, the execution buffer data is the action buffer duration of the adjacent record recognition action execution moments of the trainee in the safety scenario; the buffer impact data is the reciprocating floating span of the execution speed of the current record recognition action after the trainee generates the action buffer duration during the training stage.

[0012] After the training, the trainees will correct the execution actions in the safety scenarios. For example, if the execution actions are marked as abnormal, they will make rectifications. If the execution actions are normal but the execution parameters are lower than the parameters of the correct execution actions, they will summarize the execution actions and adjust the execution actions.

[0013] As a preferred embodiment of the present invention, the risk scenario action recognition and evaluation process is as follows: The simulation modeling scenario for trainees is set as a risk scenario, that is, the equipment in each area of ​​the simulation modeling scenario fails to cooperate with each other or the equipment operating parameters in the area are not within the rated range of the equipment, and the risk scenario is divided into a safe transition risk stage and a post-transition risk continuation stage; Collect risk impact information and risk persistence information; If the risk impact information exceeds the change amount threshold, or the risk persistence information exceeds the decline rate threshold, the current execution sub-logic will be marked as abnormal, and displayed through the human-computer interaction terminal after the trainees have completed the training; If the risk impact information does not exceed the change amount threshold, and the risk persistence information does not exceed the decline rate threshold, it is judged that the trainee's execution action is normal under the risk scenario, and the current execution sub-logic is marked as normal. After the trainee's training is completed, it is displayed through the human-computer interaction terminal after the training is completed.

[0014] As a preferred implementation of the present invention, the risk impact information is the change amount of the action trajectory corresponding to the operation sub-logic currently executed by the trainee in the safety transition risk stage; The risk continuity information refers to the execution logic of the trainees during the risk continuity stage after the transformation, involving the rate of decrease in the qualified and coordinated operation of equipment in the area.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. In the present invention, 3D modeling is performed on the area within the grassroots warehouse station and the equipment within the area. In the modeling stage, the equipment in the area is scaled in proportion to the actual working scene, and the detection accuracy of VR training is improved by restoration. At the same time, after the modeling is completed, the construction coordination area is finely modeled, and the coordination operation logic of the equipment in each area is matched, ensuring that the personnel conducting VR training can perform actions in accordance with the actual scene, which effectively improves the training efficiency; After completing the modeling, according to the actual modeling scenario, the trainees should take actions according to the scenario, and the trainees’ actions will be identified and recognized, that is, the trainees’ execution actions will be detected to avoid invalid actions being identified during the training stage, thereby reducing the proportion of parameter trainees’ action recognition detection, causing the trainees to perform actions unrelated to the grassroots warehouse station operations, affecting the training results.

[0016] 2. In the present invention, after the trainee's action is accurately identified, the safety scene is used as the operating environment of the modeling scene to perform action recognition evaluation on the trainee. Through the operation recognition evaluation of each link in the safety scene, the feasibility of the trainee's action execution is inferred, so as to infer the qualified efficiency of the trainee's action execution in the safety scene, ensure the trainee's operational maturity in each area link, and be able to conduct action evaluation in time through training and rectify abnormal actions in each link; Taking the risk scenario as the operating environment of the modeling scenario, the trainees' response actions are identified and evaluated when any equipment in the area operates abnormally, and it is inferred whether the trainees' response measures for each link in the grassroots warehouse and station meet the actual needs, so as to avoid the trainees' inability to respond in a timely and accurate manner when the operating environment is abnormal. The risk scenario simulation can effectively detect the trainees' actions, and can also monitor and optimize the processing methods under the current risk scenario in real time, so as to reduce the impact of the actual operation risks of the grassroots warehouses and stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 A flow chart of the overall method of the present invention; Figure 2 A flowchart of the method for VR modeling of a grassroots library station in the present invention; Figure 3 The figure is a flow chart of the method for identifying action misjudgment in the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] See also Figure 1 As shown in the figure, a method for accurate character action recognition suitable for VR training in grassroots libraries and stations is provided. The specific process of the method for accurate action recognition is as follows: S1. VR modeling of grassroots warehouses and stations. 3D modeling of the areas and equipment within the grassroots warehouses and stations. In the modeling stage, the equipment in the area is scaled in proportion to the actual working scene. The detection accuracy of VR training is improved through restoration. At the same time, after the modeling is completed, the construction coordination area is finely modeled, and the coordination operation logic of the equipment in each area is matched to ensure that the personnel conducting VR training can perform actions in accordance with the actual scene, which effectively improves the training efficiency. S2, action misjudgment identification. After completing the modeling, according to the actual modeling scenario, the trainees should make actions according to the scenario, and the trainees are identified for action misjudgment, that is, the trainees are detected for execution actions to avoid invalid actions being identified during the training stage, thereby reducing the proportion of parameter trainees' action recognition detection, causing the trainees to make actions irrelevant to the operation of the grassroots warehouse station, affecting the training results; S3, safety scene action recognition evaluation, after the trainee's action is accurately recognized, the safety scene is used as the operating environment of the modeling scene to conduct action recognition evaluation on the trainee. Through the operation recognition evaluation of each link in the safety scene, the feasibility of the trainee's action execution is inferred, so as to infer the qualified efficiency of the trainee's action execution in the safety scene, ensure the trainee's operational maturity in each area, and be able to conduct action evaluation in time through training and rectify abnormal actions in each link; S4. Risk scenario action recognition assessment. Risk scenarios are used as the operating environment for modeling scenarios. When any equipment in the area operates abnormally, trainees’ response actions are evaluated. This is to infer whether the trainees’ response measures for each link in the grassroots depots and stations meet actual needs, to avoid trainees’ inability to respond in a timely and accurate manner in abnormal operating environments. Risk scenario simulation can effectively detect trainees’ actions, and can also monitor and optimize the processing methods under the current risk scenarios in real time, so as to reduce the impact of actual operating risks on grassroots depots and stations.

[0022] See also Figure 2 As shown in the figure, the VR modeling process of S1 grassroots warehouse station is as follows: Modeling and layout planning are carried out according to the actual layout of each area in the grassroots depot, and the equipment in each area of ​​the grassroots depot is simulated to restore the equipment appearance and internal structure. Areas include the oil tank area, loading and unloading platform, pump room, and power distribution room in the actual grassroots depot; equipment includes oil storage tanks, oil pumps, valve groups and other equipment; The operation logic of each area in the grassroots warehouse station under the actual scenario is obtained, and the operation actions of the adjacent areas are set as the operation sub-logic, and the operation sub-logic constructs the entire operation logic according to the operation process of the grassroots warehouse station; the preset operation logic of the equipment is constructed according to the process execution order of each area in the grassroots warehouse station, and the operation sub-logic in the actual scenario is compared. If there is a logical deviation between the actual preset operation logic and the actual operation sub-logic, the logic of the mutual coordination of the equipment of the actual operation sub-logic is analyzed. If there is no deviation in the mutual coordination, the current actual operation sub-logic is marked as the production sub-logic, and the actual preset operation logic is marked as the ideal logic; it needs to be explained that the mutual coordination logic of each equipment in the grassroots warehouse station will be subject to the limitations of the actual site or cost during actual execution, and logical scheduling will occur. For example, the loading and unloading platform may load and unload raw materials of multiple execution processes at the same time to reduce the time cost or input cost of loading and unloading; the operation logic is represented by the corresponding coordinated operation of each equipment used in coordination with each other in the area; In the VR modeling scenario, the execution time is set to different cycle progress, and the actual operation logic of the trainees is monitored. If the current cycle progress is in the stage of rushing to meet the deadline, that is, the remaining progress time is lower than the preset time of the remaining workload, the trainees will actively change the operation logic, that is, it is inferred that the trainees' logical operation is qualified. On the contrary, if the trainees still use the ideal logic, it is inferred that the timing personnel's logic transformation is inefficient; if the current cycle progress is in the stage of early completion, the trainees will only execute the ideal logic, that is, it is inferred that the trainees' logical operation is theoretical; the trainees' training is summarized according to the logic execution type, and displayed through the human-computer interaction terminal after the training.

[0023] See also Figure 3 As shown in the figure, the S2 action misjudgment identification process is as follows: In the simulation modeling scenario, the trainee's execution action is detected, the displacement of the trainee's limb joints is monitored according to the sensor, and the trainee's limb action is marked as an execution action. First, the corresponding operation logic is obtained according to the trainee's location, and the operation sub-logic is obtained according to the equipment that the trainee needs to run at the current moment; it is analyzed whether the current operation sub-logic receives the execution instruction. If yes, the current trainee is in the instruction stage, and the execution time of the trainee's execution action and the instruction reception time are collected, and the execution delay is obtained according to the time comparison. If the current execution delay is within the delay range, and the limb action execution has no reset trajectory, that is, the limb action execution generates a trajectory that moves and then returns to the position before the movement, it is called a reset trajectory, and the corresponding execution action is marked as a logical action; on the contrary, if the current execution delay is not within the delay range, or the limb action execution has a reset trajectory, the corresponding execution action is marked as a non-logical action; If no, the trainee is currently in the no-command stage, and the trainee's real-time body position is collected. If the real-time body position moves, and the moving direction is not in the direction of the location of the running equipment of the process to be executed in the area, the trainee's current body movement is regarded as a redundant instinctive movement; such as the trainee's active area inspection and other actions; If the real-time limb position moves in the direction of the device in the area, and the limb position enters the area where the device is located, the trainee's current limb movement will be regarded as an execution deviation movement; Unnecessary instinctive actions and illogical actions are uniformly marked as recorded unrecognized actions; execution deviation actions and logical actions are uniformly marked as recorded recognized actions, and the action types of trainees are identified and collected.

[0024] The S3 safety scenario action recognition evaluation process is as follows: The simulation modeling scenario of the trainee is set as a safe scenario, that is, the equipment in each area of ​​the simulation modeling scenario cooperates with each other properly or the equipment operating parameters in the area are within the rated range of the equipment, and the action buffer duration of the adjacent record recognition action execution moment of the trainee in the safe scenario is obtained. At the same time, the execution speed reciprocating floating span of the current record recognition action after the action buffer duration is generated during the training stage of the trainee is collected, and the action buffer duration of the adjacent record recognition action execution moment of the trainee in the safe scenario and the execution speed reciprocating floating span of the current record recognition action after the action buffer duration is generated during the training stage of the trainee are marked as execution buffer data and buffer influence data, respectively, and compared with the action buffer duration threshold and the speed reciprocating floating span threshold, respectively: If the action buffering time of the adjacent record recognition action execution time of the trainee in the safety scenario exceeds the action buffering time threshold, or the reciprocating floating span of the execution speed of the current record recognition action after the action buffering time is generated during the training stage of the trainee exceeds the reciprocating floating span threshold, it is inferred that the real-time operation logic execution action of the trainee in the current safety scenario is unqualified, and the correct execution action process of the current operation logic is compared and collected with the parameters of the real-time execution action and anomalies are marked, such as action trajectory, position, speed and other parameters are collected together, and displayed through the human-computer interaction terminal after the trainee's training is completed; If the action buffer duration of the adjacent record recognition action execution time of the trainee in the safety scenario does not exceed the action buffer duration threshold, and the execution speed reciprocating floating span of the current record recognition action after the trainee generates the action buffer duration during the training stage does not exceed the speed reciprocating floating span threshold, it is inferred that the real-time operation logic execution action of the trainee in the current safety scenario is qualified, and the correct execution action process of the current operation logic is compared and collected with the parameters of the real-time execution action, and after the trainee's training is completed, it is displayed through the human-computer interaction terminal after the training is completed; After the training, the trainees will correct the execution actions in the safety scenarios. For example, if the execution actions are marked as abnormal, they will make rectifications. If the execution actions are normal but the execution parameters are lower than the parameters of the correct execution actions, they will summarize the execution actions and adjust the execution actions.

[0025] The S4 risk scenario action recognition and assessment process is as follows: The simulation modeling scenario of the trainees is set as a risk scenario, that is, the equipment in each area of ​​the simulation modeling scenario does not cooperate with each other properly or the equipment operating parameters in the area are not within the rated range of the equipment. The risk scenario is divided into a safety transition risk stage and a post-transition risk continuation stage. The change amount of the action trajectory corresponding to the operation sub-logic currently executed by the trainees in the safety transition risk stage is collected, where the action trajectory is represented by the execution trajectory of the equipment in the area, such as the execution sequence and click frequency of each button on the operating console corresponding to the body movement trajectory of the trainees, and the change amount is represented by the change distance of the body movement trajectory executed by the execution sub-logic; The execution logic of the trainees in the risk continuation stage after the acquisition transformation involves the rate of decline of the qualified rate of equipment in the area. It should be explained that the qualified equipment operation means that the equipment operation is qualified during the equipment coordination process and the efficiency of the equipment coordination is qualified during the equipment coordination process. On the contrary, if the equipment is not qualified for coordination, it means that any of the above parameters is not satisfied. The change amount of the action trajectory corresponding to the operation sub-logic currently executed by the trainee in the safety transition risk stage and the rate of decrease of the qualified rate of equipment in the area involved in the execution logic of the trainee in the risk continuation stage after the transition are marked as risk impact information and risk continuation information, respectively, and compared with the change amount threshold and the rate of decrease threshold respectively: If the change amount of the action trajectory corresponding to the operation sub-logic currently executed by the trainee in the safety transition risk stage exceeds the change amount threshold, or the qualified rate of the qualified coordinated operation of the equipment in the area involved in the execution logic of the trainee in the risk continuation stage after the transition exceeds the decline rate threshold, it is judged that the trainee's execution action in the risk scenario is abnormal, and the current execution sub-logic is marked as abnormal, and after the trainee's training is completed, it is displayed through the human-computer interaction terminal after the training is completed; If the change in the action trajectory corresponding to the operation sub-logic currently executed by the trainee in the safety transition risk stage does not exceed the change threshold, and the rate of decrease in the qualified rate of equipment in the area involved in the trainee's execution logic in the post-transition risk continuation stage does not exceed the rate of decrease threshold, then it is judged that the trainee's execution of the action is normal under the risk scenario, and the current execution sub-logic is marked as normal, and after the trainee's training is completed, it is displayed through the human-computer interaction terminal after the training is completed.

[0026] When the present invention is in use, the grassroots warehouse station VR modeling is carried out, and the area within the grassroots warehouse station and the equipment within the area are 3D modeled. In the modeling stage, the equipment in the area is scaled in proportion to the actual working scene. At the same time, according to the completion of the modeling, the construction coordination area is finely modeled, and the coordination operation logic of the equipment in each area is fitted to ensure that the personnel conducting VR training can perform actions in accordance with the actual scene; action misjudgment identification is carried out, after the modeling is completed, according to the actual modeling scene, the trainees take actions in response to the scene, and the action misjudgment identification is carried out on the trainees; safety scene action recognition evaluation is carried out, after the trainees' actions are accurately identified, the safety scene is used as the operating environment of the modeling scene, and the trainees are evaluated for action recognition; risk scene action recognition evaluation is carried out, using the risk scene as the operating environment of the modeling scene, and the trainees are evaluated for action recognition when any equipment in the area operates abnormally.

[0027] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for accurately identifying human actions suitable for VR training at grassroots warehouses and stations, characterized in that: The specific action accurate recognition method process is as follows: S1. VR modeling of grassroots depots and stations. 3D modeling of the areas and equipment within the grassroots depots and stations. In the modeling stage, the equipment in the area is scaled in proportion to the actual working scene. After the modeling is completed, the construction coordination area is finely modeled, and the coordination operation logic of the equipment in each area is matched to ensure that the personnel undergoing VR training can perform actions in accordance with the actual scene; S2, action misjudgment identification, after completing the modeling, according to the actual modeling scene, the trainees should take actions according to the scene, and the action misjudgment identification of the trainees is performed; S3, safety scenario action recognition evaluation, after the trainee's action is accurately recognized, the safety scenario is used as the operating environment of the modeling scenario to conduct action recognition evaluation on the trainee. Through the operation recognition evaluation of each link in the safety scenario, the feasibility of the trainee's action execution is inferred; S4. Risk scenario action recognition assessment: using risk scenarios as the operating environment for modeling scenarios, conduct action recognition assessments on the responses of trainees when any equipment in the area operates abnormally, and infer whether the response measures of trainees at each link within the grassroots warehouses and stations meet actual needs.

2. According to claim 1, a method for accurately identifying human actions suitable for VR training at grassroots libraries and stations, characterized in that: The VR modeling process of the grassroots warehouse station is as follows: Modeling and layout planning are carried out according to the actual layout of each area in the grassroots depot, and the equipment in each area of ​​the grassroots depot is simulated to restore the appearance and internal structure of the equipment; The operation logic of each area in the grassroots depot in the actual scenario is obtained, and the operation actions of the adjacent areas are set as operation sub-logic, and the operation sub-logic constructs the entire operation logic according to the operation process of the grassroots depot; The preset operation logic of the equipment is constructed according to the process execution order of each area in the grassroots warehouse station, and the operation sub-logic in the actual scenario is compared. If there is a logical deviation between the actual preset operation logic and the actual operation sub-logic, the logic of the mutual coordination of the equipment in the actual operation sub-logic is analyzed. If there is no deviation in the mutual coordination, the current actual operation sub-logic is marked as the production sub-logic, and the actual preset operation logic is marked as the ideal logic.

3. According to claim 2, a method for accurate character motion recognition suitable for VR training at grassroots warehouses and stations, characterized in that: In the VR modeling scenario, the execution time is set to different cycle progress, and the actual operation logic of the trainees is monitored. If the current cycle progress is in the stage of rushing to meet the deadline, that is, the remaining progress time is lower than the preset time of the remaining workload, the trainees will actively change the operation logic, that is, it is inferred that the trainees' logical operation is qualified. On the contrary, if the trainees still use the ideal logic, it is inferred that the timing personnel's logic transformation is inefficient; if the current cycle progress is in the stage of early completion, the trainees will only execute the ideal logic, that is, it is inferred that the trainees' logical operation is theoretical; the trainees' training is summarized according to the logic execution type, and displayed through the human-computer interaction terminal after the training.

4. According to claim 1, a method for accurate character motion recognition suitable for VR training at grassroots warehouses and stations, characterized in that: The process of action misjudgment identification is as follows: In the simulation modeling scenario, the trainees' execution actions are detected, the displacement of the trainees' limb joints is monitored by sensors, and the trainees' limb movements are marked as execution actions. First, the corresponding operation logic is obtained according to the trainees' location, and the operation sub-logic is obtained according to the equipment that the trainees need to operate at the current moment; Analyze whether the current operation sub-logic receives the execution instruction; If yes, the current trainee is in the stage of receiving instructions. The trainee's action execution time and instruction receiving time are collected, and the execution delay is obtained according to the time comparison. If the current execution delay is within the delay range, and the body movement execution has no reset track, the corresponding execution action is marked as a logical action; otherwise, if the current execution delay is not within the delay range, or the body movement execution has a reset track, the corresponding execution action is marked as a non-logical action. If no, the trainee is currently in the no-instruction stage, and the trainee's real-time body position is collected. If the real-time body position moves, and the moving direction is not in the direction of the location of the running equipment of the process to be executed in the area, the trainee's current body movement is regarded as a superfluous instinctive movement; if the moving direction of the real-time body position is in the direction of the equipment in the area, and the body position enters the area where the equipment is located, the trainee's current body movement is regarded as an execution deviation action; Unnecessary instinctive actions and illogical actions are uniformly marked as recorded unrecognized actions; execution deviation actions and logical actions are uniformly marked as recorded recognized actions, and the action types of trainees are identified and collected.

5. According to claim 1, a method for accurately identifying human actions suitable for VR training at grassroots warehouses and stations, characterized in that: The safety scene action recognition evaluation process is as follows: Set the simulation modeling scene for trainees to be a safe scene, that is, the equipment in each area of ​​the simulation modeling scene cooperates with each other properly or the equipment operating parameters in the area are within the rated range of the equipment; Collect execution buffer data and buffer impact data; If the execution buffer data exceeds the action buffer duration threshold, or the buffer impact data exceeds the speed reciprocating floating span threshold, the correct execution action process of the current operation logic is compared with the parameters of the real-time execution action, and the abnormalities are marked. After the training of the trainees is completed, it will be displayed through the human-computer interaction terminal after the training is completed; If the execution buffer data does not exceed the action buffer duration threshold, and the buffer impact data does not exceed the speed reciprocating floating span threshold, the correct execution action process of the current operation logic and the parameters of the real-time execution action are compared and collected, and displayed through the human-computer interaction terminal after the trainees complete the training.

6. According to claim 5, a method for accurately identifying human actions suitable for VR training at grassroots warehouses and stations, characterized in that: The execution buffer data is the action buffer duration of the adjacent record recognition action execution time of the trainee in the safety scenario; the buffer impact data is the reciprocating floating span of the execution speed of the current record recognition action after the trainee generates the action buffer duration; After the training, the trainees will correct the execution actions in the safety scenarios. For example, if the execution actions are marked as abnormal, they will make rectifications. If the execution actions are normal but the execution parameters are lower than the parameters of the correct execution actions, they will summarize the execution actions and adjust the execution actions.

7. According to claim 1, a method for accurately identifying human actions suitable for VR training at grassroots warehouses and stations, characterized in that: The risk scenario action recognition and assessment process is as follows: The simulation modeling scenario for trainees is set as a risk scenario, that is, the equipment in each area of ​​the simulation modeling scenario fails to cooperate with each other or the equipment operating parameters in the area are not within the rated range of the equipment, and the risk scenario is divided into a safe transition risk stage and a post-transition risk continuation stage; Collect risk impact information and risk persistence information; If the risk impact information exceeds the change amount threshold, or the risk persistence information exceeds the decline rate threshold, the current execution sub-logic will be marked as abnormal, and displayed through the human-computer interaction terminal after the trainees have completed the training; If the risk impact information does not exceed the change amount threshold, and the risk persistence information does not exceed the decline rate threshold, it is judged that the trainee's execution action is normal under the risk scenario, and the current execution sub-logic is marked as normal. After the trainee's training is completed, it is displayed through the human-computer interaction terminal after the training is completed.

8. According to claim 7, a method for accurate character motion recognition suitable for VR training at grassroots warehouses and stations, characterized in that: The risk impact information is the change in the action trajectory corresponding to the operation sub-logic currently executed by the trainee during the safety transition risk stage; The risk continuity information refers to the execution logic of the trainees during the risk continuity stage after the transformation, involving the rate of decrease in the qualified and coordinated operation of equipment in the area.

Images