A method, device, equipment and storage medium for identifying violent sorting behavior

Abstract

The embodiments of this specification provide a method, device, equipment and storage medium for identifying violent sorting behavior, which are applied to the field of behavior recognition technology. The method includes: obtaining recorded behavior data; determining whether the behavior data meets preset conditions; if the behavior data meets the preset conditions, uploading the behavior data to a server, so that the server determines whether the target sorter has violent sorting behavior based on the monitoring video and the behavior data within a preset time range. The accuracy of identifying violent sorting behavior can be improved by using the embodiments of this specification.

Description

Technical Field

[0001] The present application relates to the field of behavior recognition technology, and in particular to a method, device, equipment and storage medium for identifying violent sorting behavior. Background Art

[0002] With the rapid development of battery swapping business, when managing batteries in warehouses, due to the large amount of batteries, sorters may throw or trample on the batteries in the warehouse, which may endanger the safety of the batteries. In order to reduce the occurrence of such behaviors, it is becoming increasingly important to identify violent battery sorting behaviors.

[0003] In the prior art, the violent battery sorting behavior is mainly identified through video monitoring or machine vision. Among them, the video monitoring method is to install a camera in the sorter's work area, monitor the sorter's behavior, and manually determine whether it is a violent battery sorting behavior. The machine vision method is to convert the video frame into a picture, establish a spatial coordinate system with the location of the camera, identify the battery as the target to be measured, and then determine whether it is a violent battery sorting behavior based on the maximum movement distance of the target in the horizontal and vertical directions. However, since batteries are items that are handled with care, they are unlikely to leave the hands during the sorting process. This makes it easy for the battery to be blocked by the sorter's body, resulting in the loss of battery movement trajectory data, making it impossible to accurately identify whether the battery has been violently sorted using the above method.

[0004] Therefore, the industry is in urgent need of a technical solution that can solve the above technical problems. Summary of the invention

[0005] The embodiments of this specification provide a method, device, equipment and storage medium for identifying violent sorting behavior, which can quickly and accurately identify violent sorting behavior.

[0006] The method, device, equipment and storage medium for identifying violent sorting behavior provided in this specification are implemented in the following manner.

[0007] A method for identifying violent sorting behavior is applied to a wearable device, wherein the wearable device is worn on a designated part of a target sorter and is used to record the behavior data of the target sorter. The method comprises: obtaining the recorded behavior data; judging whether the behavior data meets a preset condition; and uploading the behavior data to a server when the behavior data meets the preset condition, so that the server determines whether the target sorter has violent sorting behavior based on a surveillance video within a preset time range and the behavior data.

[0008] A method for identifying violent sorting behavior is applied to a server, and the method comprises: receiving behavior data; wherein the behavior data is uploaded by a wearable device when it is determined that the recorded behavior data meets a preset condition; the wearable device is worn on a designated part of a target sorter to record the behavior data of the target sorter; a monitoring video within a preset time range is obtained; and based on the behavior data and the monitoring video, determining whether the target sorter has engaged in violent sorting behavior.

[0009] A device for identifying violent sorting behavior, comprising: an acquisition module, used for acquiring recorded behavior data of a target sorter; a judgment module, used for judging whether the behavior data meets a preset condition; and an upload module, used for uploading the behavior data to a server if the behavior data meets the preset condition, so that the server determines whether the target sorter has violent sorting behavior based on a surveillance video within a preset time range and the behavior data.

[0010] A device for identifying violent sorting behavior, comprising: a receiving module, used to receive behavior data; wherein the behavior data is uploaded by a wearable device when it is determined that the recorded behavior data meets a preset condition; the wearable device is worn on a designated part of a target sorter, and is used to record the behavior data of the target sorter; an acquisition module, used to acquire a monitoring video within a preset time range; and a determination module, used to determine whether the target sorter has violent sorting behavior based on the behavior data and the monitoring video.

[0011] A device for identifying violent sorting behavior includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the method embodiments in the embodiments of this specification are implemented.

[0012] A computer-readable storage medium stores computer instructions, which, when executed, implement the steps of any method embodiment in the embodiments of this specification.

[0013] This specification provides a method, device, equipment and storage medium for identifying violent sorting behavior. In some embodiments, the recorded behavior data of the target sorter can be obtained to determine whether the behavior data meets the preset conditions. If the behavior data meets the preset conditions, the behavior data is uploaded to the server so that the server can determine whether the target sorter has violent sorting behavior based on the monitoring video and behavior data within a preset time range. In this way, by combining the behavior data recorded by the wearable device with the monitoring video to identify violent sorting behavior, not only can the visual interface of violent sorting behavior be more clearly grasped, but also the accuracy of identifying violent sorting behavior can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of this specification, constitute a part of this specification, and do not constitute a limitation of this specification. In the drawings:

[0015] Figure 1 This is a scenario diagram of a method for identifying violent sorting behavior provided in this manual;

[0016] Figure 2 It is a flowchart of an embodiment of a method for identifying violent sorting behavior provided in this specification;

[0017] Figure 3 It is a flowchart of an embodiment of a method for identifying violent sorting behavior provided in this specification;

[0018] Figure 4 This is a flowchart of a method for identifying violent sorting behavior applied to a Bluetooth bracelet provided in this specification;

[0019] Figure 5 This is a flowchart of a method for identifying violent sorting behavior applied to a Bluetooth anklet provided in this specification;

[0020] Figure 6 This is a schematic diagram of the module structure of an embodiment of a device for identifying violent sorting behavior provided in this specification;

[0021] Figure 7 This is a schematic diagram of the module structure of an embodiment of a device for identifying violent sorting behavior provided in this specification;

[0022] Figure 8 This is a hardware structure block diagram of an embodiment of a server for identifying violent sorting behavior provided in this specification. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments in this specification, not all of the embodiments. Based on one or more embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the embodiments of this specification.

[0024] An implementation scheme provided in this specification can be applied to the system architecture of wearable device / server, wearable device / terminal device. The wearable device may include a communication module, which can be connected to a server, terminal device, etc. via Bluetooth or WiFi to achieve data transmission. The server may include a single computer device, or a server cluster composed of multiple servers, or a server structure of a distributed system. The terminal device may include a communication module, which can be connected to a wearable device via Bluetooth or WiFi to achieve data transmission. The terminal device may include a mobile terminal, such as a smart phone or a tablet computer. The server, wearable device, and terminal device described in the embodiments of this specification include different information processing parties that are logically divided.

[0025] In some embodiments, the wearable device can be powered by a relay when in sleep mode. A voice broadcast function can be set inside the wearable device. When the device successfully connects to the server or terminal device, the device will prompt "communication connection successful". When the work is completed and the communication is disconnected, it will prompt "communication connection disconnected".

[0026] In some embodiments, the wearable device may have two indicator lights. Among them, light 1 may indicate the power level. When the power is low or charging, light 1 will be always on. Light 2 may indicate that the storage space is almost exhausted. When the storage space is running low, light 2 will be always on, so that the user can be reminded to clean up the storage space in time.

[0027] In some embodiments, wearable devices can be worn on designated parts of the sorter to record the sorter's behavioral data, such as smart bracelets that can be worn on the sorter's wrists, and smart anklets that can be worn on the sorter's ankles. Among them, the wearable device may include internal sensors, such as various sensors for collecting behavioral data, such as force sensors, motion sensors, bioelectric sensors, etc. Force sensors can be used to collect information about the force on the sorter's wrist. Motion sensors can be used to collect motion trajectory information, acceleration information, coordinate information in a certain direction, etc. Bioelectric sensors can be used to collect bioelectric fluctuation information of muscles, etc.

[0028] In some embodiments, each wearable device has an identifier. The identifier of each wearable device can be pre-bound to the identifier of the corresponding sorter, so that the sorter and the wearable device can be one-to-one, and the wearable device cannot be paired randomly, so as to facilitate the corresponding analysis of data later. The above identifier can be composed of one or more of numbers, letters, characters, etc., and this specification does not limit this.

[0029] like Figure 1 As shown, Figure 1This is a scenario diagram of a method for identifying violent sorting behavior provided in this specification. The wearable device includes a Bluetooth module, which can communicate with the server to realize data transmission.

[0030] Specifically, when entering the work area, the sorter needs to wear a wearable device bound to his or her information and turn on the wearable device to ensure that the wearable device and the server can communicate.

[0031] Furthermore, the wearable device can collect behavioral data based on the various sensors included, and determine whether the collected behavioral data meets the preset conditions. If the preset conditions are met, the behavioral data can be marked as abnormal data. Then, the abnormal data can be uploaded to the server so that the server can obtain the monitoring video within the preset time range, and determine whether the target sorter has violent sorting behavior based on the abnormal data and the monitoring video. In this way, even if the battery movement trajectory data is missing due to the battery being blocked by the sorter's body during the sorting process, it can be quickly and accurately identified whether the battery has been violently sorted. Among them, the preset time range can be determined according to the actual scenario.

[0032] The following is an example of a specific application scenario to illustrate the implementation plan of this specification. Specifically, Figure 2 The flowchart of an embodiment of a method for identifying violent sorting behavior provided in this specification is shown in the following embodiments or drawings. Although this specification provides method operation steps or device structures as shown in the following embodiments or drawings, the method or device may include more or fewer operation steps or module units after partial combination based on routine or no creative labor.

[0033] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. The following embodiments are described from the perspective of wearable devices and do not limit the technical solutions in other application scenarios that can be expanded based on this specification. Among them, the wearable device can be worn on the designated part of the target sorter to record the behavior data of the target sorter. A specific implementation example is Figure 2 As shown, in an embodiment of a method for identifying violent sorting behavior provided by this specification, the method may include the following steps.

[0034] S20: Obtain recorded behavior data.

[0035] In some embodiments, the wearable device may include a smart bracelet and / or a smart anklet. The identifier of the smart bracelet and / or the identifier of the smart anklet corresponds to the identifier of the target sorter. The identifier of the smart bracelet, the identifier of the smart anklet, and the identifier of the target sorter may be composed of one or more of numbers, letters, symbols, etc., respectively, and this specification does not limit this. The target sorter may be any sorter.

[0036] It should be noted that in the embodiments of this specification, the smart bracelet is illustrated by taking a Bluetooth bracelet as an example, and the smart anklet is illustrated by taking a Bluetooth anklet as an example. Of course, the smart bracelet and the smart anklet are not limited to the above examples. Under the inspiration of the technical essence of this application, technicians in the relevant field may make other changes, but as long as the functions and effects achieved are the same or similar to those of this application, they should be covered within the protection scope of this application.

[0037] In some embodiments, the behavior data may include first behavior data recorded by a smart bracelet and / or second behavior data recorded by a smart anklet. The first behavior data may be data recorded by the smart bracelet when it detects that the wrist force information of the target sorter is greater than a first threshold, and the second behavior data may be data recorded by the smart anklet. The wrist force information may include the force that the wrist bears. The first threshold may be understood as the critical value at which the smart bracelet starts recording data.

[0038] In some implementation scenarios, when the target sorter is working, the smart bracelet is awakened and starts recording the first behavior data when it detects that the wrist force information of the target sorter is greater than the first threshold.

[0039] In some implementation scenarios, the first threshold value may represent the force exerted on the wrist when lifting the lightest target object, which may be adjusted according to the actual scenario requirements. The target object may be an object to be sorted, such as a battery, express delivery, or merchandise. It should be noted that in the embodiments of this specification, batteries are used as target objects for exemplary description, and other scenarios are similar and can be referenced to each other.

[0040] In some implementation scenarios, workers can be asked to simulate violent battery sorting to determine the first threshold. For example, a sorter can wear a Bluetooth bracelet and lift a battery, and record the wrist force recorded by the Bluetooth bracelet. Since the battery models are relatively fixed, the wrist force when lifting the lightest battery can be used as the first threshold.

[0041] After determining the first threshold, the first threshold can be stored in a preset memory. In this way, when the target sorter is working, the Bluetooth bracelet can compare the real-time monitored wrist force information of the sorter with the first threshold to determine whether to be awakened to start working. Among them, the preset memory can be the memory, cache, etc. of the Bluetooth bracelet, and can also be other memories connected to the Bluetooth bracelet. The awakening of the Bluetooth bracelet can be understood as starting to record behavioral data. The failure of the Bluetooth bracelet to be awakened can be understood as the Bluetooth bracelet being in a dormant state. It does not record behavioral data, but will monitor the wrist force information of the sorter.

[0042] Specifically, for example, in some implementation scenarios, after the sorter puts on the Bluetooth bracelet, the Bluetooth bracelet will not immediately record the behavior data. Only when the force sensor of the Bluetooth bracelet detects that the force information of the sorter's wrist is greater than the first threshold, the Bluetooth bracelet will be awakened and start working. After that, the motion sensor of the Bluetooth bracelet will record the sorter's behavior data in real time. Furthermore, the recorded behavior data is stored in a preset memory so that the processor in the Bluetooth bracelet can process the behavior data later. Among them, the sorter's wrist force information is greater than the first threshold, which means that the sorter has a battery in his hand at this time.

[0043] In some implementation scenarios, the target sorter can use the smart anklet to record the sorter's second behavior data in real time during the work process. For example, in some implementation scenarios, as long as the sorter wears the Bluetooth anklet, the motion sensor of the Bluetooth anklet can record the second behavior data in real time.

[0044] In some embodiments, the first behavior data may include at least one of the following: the motion trajectory information of the target sorter's hand within a preset time period, the acceleration information of the smart bracelet in the vertical direction within a preset time period, and the bioelectric fluctuation information of the muscles under the wrist of the target sorter within a preset time period. The second behavior data may include the coordinate information of the target sorter's feet in the vertical direction. Among them, the motion trajectory information of the target sorter's hand can represent the trajectory of the target sorter sorting batteries. The acceleration information of the smart bracelet in the vertical direction can also be understood as the acceleration information of the target sorter's hand in the vertical direction. The bioelectric fluctuation information of the muscles under the wrist of the target sorter can also be understood as the bioelectric change trend of the muscles under the wrist of the target sorter when the target sorter holds the battery. The coordinate information of the target sorter's feet in the vertical direction can be used to determine whether the target sorter has behaviors such as stepping on the battery. Of course, the second behavior data can also include the motion trajectory information of the target sorter's feet, the change amount of the target sorter's feet in the vertical direction, etc.

[0045] In some embodiments, the preset time period is a range from the first time to the second time. The first time is the time corresponding to when the smart bracelet detects that the target sorter's wrist force information is greater than the first threshold, and the second time is the time corresponding to when the smart bracelet detects that the target sorter's wrist force information is less than the first threshold for the first time after the first time. The target sorter always holds the battery in his hand during the preset time period.

[0046] For example, in some implementation scenarios, when the smart bracelet detects that the force information on the sorter's wrist is greater than the first threshold A, the corresponding time is t1 (indicating that the sorter has a battery in his hand). A certain period of time after t1, the smart bracelet detects that the force information on the sorter's wrist is less than A, and the corresponding time is t2 (indicating that the battery is put down). Then t1 to t2 represents the preset time period, and the time length corresponding to the preset time period is T = t2-t1. Among them, T can be a dynamically changing value. If the sorter works continuously, T will tend to increase.

[0047] In the embodiment of the present specification, the smart bracelet compares the monitored wrist force information of the sorter with the first threshold value, and records the behavioral data of the sorter from picking up the battery to putting it down, thereby reducing the recording of useless data and improving the subsequent data processing efficiency.

[0048] In the embodiments of this specification, the wearable device may be provided with a processor for acquiring and analyzing recorded behavior data.

[0049] S22: Determine whether the behavior data meets a preset condition.

[0050] In the embodiments of this specification, after obtaining the recorded behavior data, the wearable device can determine whether the behavior data meets the preset conditions. The preset conditions can be used to determine whether the behavior data is abnormal. If the behavior data is abnormal, it can indicate that the target sorter may have violent sorting behavior.

[0051] In some embodiments, the determining whether the behavior data satisfies a preset condition may include: determining whether the first behavior data satisfies a first preset condition; and / or determining whether the second behavior data satisfies a second preset condition.

[0052] In some embodiments, when the first behavior data includes the motion trajectory information of the target sorter's hand within a preset time period, the acceleration information of the smart bracelet in the vertical direction within the preset time period, and the bioelectric fluctuation information of the muscles under the wrist of the target sorter within the preset time period, the judgment of whether the first behavior data meets the first preset condition may include: judging whether the motion trajectory information of the target sorter's hand within the preset time period matches the preset motion trajectory information; if they match, determining the highest position of the target sorter's hand in the vertical direction within the preset time period; judging whether the acceleration of the smart bracelet in the vertical direction is the largest when the target sorter's hand is in the highest position in the vertical direction; when it is confirmed to be the largest, judging whether the bioelectric fluctuation information of the muscles under the wrist of the target sorter within the preset time period meets the preset change law; if so, determining that the first behavior data meets the first preset condition.

[0053] Among them, the preset motion trajectory information may include the motion trajectory of the smart bracelet when the target object is held and thrown upward. The target object may be an object to be sorted, such as a battery, express delivery, commodity, etc. For example, the motion trajectory of the Bluetooth bracelet when the battery is held and thrown upward may be all the way up to the highest point and then suddenly down. The preset change rule may include the bioelectric fluctuation trend of the muscles under the wrist when the target object is held and thrown upward. Among them, the bioelectricity can record the current change fluctuation trend when the target object is thrown out at the moment when the fingers are opened in the throwing state. It should be noted that when a person is throwing, the finger opening speed must be the largest. If it is normal to hold it lightly, the finger speed is in line with the law of uniform motion, and of course the bioelectric fluctuation is also in line with the law. If it is normal to hold it lightly, the motion trajectory of the smart bracelet will appear to be slowly downward, and it will generally be in an arched state. At the same time, the overall acceleration will be relatively stable, and there will be no large fluctuations. In addition, because the muscle memory is constant, if the sorter makes a throwing action, the bioelectricity must conform to the preset change law.

[0054] Specifically, for example, in some implementation scenarios, the staff can first simulate the action of throwing a battery upward, and then record the change of the movement trajectory of the Bluetooth bracelet in the state of throwing the battery upward and the bioelectric fluctuation trend C of the muscles under the wrist at this time, so as to obtain the preset movement trajectory information and the preset change law. Of course, the above is an exemplary description using the battery as the target object, and other scenarios are similar and can be referenced to each other, so I will not elaborate on this.

[0055] After obtaining the preset motion trajectory information and the preset change rule, the preset motion trajectory information and the preset change rule can be stored in the preset memory. In this way, after obtaining the recorded behavior data, the Bluetooth bracelet can determine whether the behavior data meets the preset conditions based on the stored preset motion trajectory information and the preset change rule.

[0056] In some implementation scenarios, if the motion trajectory information of the target sorter's hand in the preset time period is that it goes up to the highest point and then suddenly goes down, and the vertical acceleration of the Bluetooth bracelet is the largest when it reaches the highest point, and the bioelectric fluctuation information of the muscles under the wrist of the target sorter at this time meets the bioelectric fluctuation trend C, then it can be determined that the first behavior data meets the first preset condition. The first behavior data meeting the first preset condition may indicate that the target sorter may have violent sorting behavior, such as throwing batteries.

[0057] In some implementation scenarios, if one of the motion trajectory information of the target sorter's hand within the preset time period, the acceleration information of the smart bracelet in the vertical direction within the preset time period, and the bioelectric fluctuation information of the muscles under the wrist of the target sorter within the preset time period does not meet the corresponding condition, it can be determined that the first behavior data does not meet the first preset condition. The failure of the first behavior data to meet the first preset condition can indicate that the target sorter does not have violent sorting behavior, and no processing is required at this time.

[0058] In some embodiments, determining whether the second behavior data satisfies the second preset condition may include: comparing the coordinate information of the target sorter's feet in the vertical direction with a second threshold; and when the coordinate information is greater than the second threshold, determining that the second behavior data satisfies the second preset condition.

[0059] The second threshold value may represent the critical value of the smart foot ring when the sorter steps on the target object. Specifically, the critical value of the smart foot ring depends on the height of the target object. The target object may be an object to be sorted, such as a battery, express delivery, or merchandise.

[0060] For example, in some implementation scenarios, the height values ​​of batteries of different models can be counted and compared to obtain the lowest height value, which is then used as the critical value of the Bluetooth anklet when the sorter steps on the battery, that is, the second threshold.

[0061] After determining the second threshold, the second threshold can be stored in a preset memory. In this way, when the target sorter is working, the processor of the Bluetooth anklet can compare the recorded vertical coordinate information of the target sorter's feet with the second threshold in real time. Once the vertical coordinate information is greater than the second threshold, it can be determined that the second behavior data meets the second preset condition. The second behavior data meeting the second preset condition may indicate that the target sorter may have violent sorting behavior, such as stepping on batteries. Among them, the preset memory can be the memory, cache, etc. of the Bluetooth anklet, and can also be other memories connected to the Bluetooth anklet.

[0062] In some implementation scenarios, if the coordinate information of the target sorter's feet in the vertical direction is less than or equal to the second threshold, it can be determined that the second behavior data does not meet the second preset condition. The second behavior data not meeting the second preset condition can indicate that the target sorter does not engage in violent sorting behavior, and no processing is required at this time.

[0063] S24: When the behavior data meets a preset condition, the behavior data is uploaded to a server, so that the server determines whether the target sorter has violent sorting behavior based on the surveillance video and the behavior data within a preset time range.

[0064] In the embodiments of this specification, when the behavior data meets the preset conditions, the behavior data can be uploaded to the server so that the server can determine whether the target sorter has violent sorting behavior based on the monitoring video and behavior data within a preset time range.

[0065] In some embodiments, when the first behavior data meets the first preset condition, the smart bracelet can mark the behavior data at this moment as abnormal data and upload it to the server.

[0066] Specifically, for example, in some implementation scenarios, when the Bluetooth bracelet processor analyzes that within the time period T, the motion trajectory recorded by the Bluetooth bracelet motion sensor is that it goes up to the highest point and then suddenly goes down, and the acceleration in the vertical direction is the largest when reaching the highest point, and the bioelectric sensor records the bioelectricity generated by the muscles under the wrist within the time period T, which is consistent with the bioelectric fluctuation trend C in the throwing state. At this time, the Bluetooth bracelet can mark this behavior data as abnormal data and upload it to the server.

[0067] In some embodiments, when the second behavior data meets the second preset condition, the smart anklet can mark the behavior data at this moment as abnormal data and upload it to the server.

[0068] Specifically, for example, in some implementation scenarios, the staff wears a Bluetooth anklet, and the motion sensor of the Bluetooth anklet will record the coordinate information of the sorter's feet in the vertical direction in real time. At the same time, the Bluetooth anklet processor will compare the vertical coordinate information of the foot with the second threshold in real time. If the coordinate information recorded by the motion sensor is greater than the second threshold, it can be preliminarily determined that the sorter may have stepped on the battery. At this time, the Bluetooth anklet can mark this behavior data as abnormal data and upload it to the server.

[0069] In some embodiments, after receiving the behavior data (also referred to as abnormal data) uploaded by the smart bracelet and / or smart anklet, the server can obtain surveillance video within a preset time range, and then determine whether the sorter has engaged in violent sorting behavior based on the surveillance video and behavior data.

[0070] In some implementation scenarios, one or more cameras may be pre-installed in the sorter's work area to capture video of the sorting area, wherein each camera may upload the captured surveillance video to the server in real time.

[0071] In some implementation scenarios, when the server obtains the surveillance video within the preset time range, it can first determine the first time corresponding to the receiving behavior data, then determine the preset time range based on the first time, and finally obtain the surveillance video within the preset time range. Among them, the specified time period before and after the first time can be determined as the preset time range, which can be adjusted according to the actual scenario, and this specification does not limit this.

[0072] In some implementation scenarios, when a wearable device uploads behavior data, it can also upload the wearable device's identification, abnormal data triggering time, etc. In this way, after receiving the data, the server can accurately determine the preset time range based on the abnormal data triggering time, and then obtain the monitoring video corresponding to the wearable device within the preset time range, and determine whether the sorter has violent sorting behavior based on the behavior data and monitoring video.

[0073] In the embodiments of this specification, by uploading abnormal data triggering moment by wearable devices, the moment when abnormal behavior occurs in the surveillance video can be accurately located, reducing the workload of video analysis.

[0074] In some implementation scenarios, the smart bracelet and / or smart anklet marks the behavior data as abnormal data, reports it to the server, and can also remind the sorter by vibration so that he can standardize the sorting behavior.

[0075] The embodiments of this specification can be applied to the field of battery sorting, and can also be applied to other scenarios that require sorting, such as express sorting scenarios, two-wheeled vehicle sorting scenarios, etc.

[0076] In the embodiments of this specification, the behavior data recorded by the wearable device is combined with the surveillance video to identify the violent sorting behavior, which can not only more clearly grasp the visual interface of the violent sorting behavior, but also improve the accuracy of identifying the violent sorting behavior.

[0077] The embodiments of this specification will not cause a change in accuracy due to changes in scenes (such as changing the warehouse for sorting batteries), nor will it cause unrecognition due to batteries being blocked during the battery sorting process by staff.

[0078] In the embodiment of this specification, the behavior of the sorter is captured to determine whether it falls into the category of violent sorting behavior. As long as the wearable device detects that the sorter's behavior may be in violation of the rules, the device will vibrate to remind the sorter to regulate the behavior, and upload the behavior data mark at this moment as abnormal data to the server, so that the server can determine whether to store the violent sorting behavior in combination with the video of the abnormal time point taken by the camera. Since the wearable device is easy to wear, it will not delay the normal work of the sorter, and the recognition accuracy is high, so it can well protect the safety of assets.

[0079] The above embodiment describes the implementation of the method for identifying violent sorting behavior from the perspective of a wearable device. Based on the above embodiment description, this specification also provides a method for identifying violent sorting behavior described from the perspective of a server. Figure 3 This is a flow chart of an embodiment of a method for identifying violent sorting behavior provided in this specification. Specifically, in one embodiment, the method may include the following steps.

[0080] S30: receiving behavior data; wherein the behavior data is uploaded by the wearable device when it is determined that the recorded behavior data meets a preset condition; the wearable device is worn on a designated part of the target sorter to record the behavior data of the target sorter;

[0081] S32: Acquire surveillance video within a preset time range;

[0082] S34: Determine whether the target sorter has violent sorting behavior based on the behavior data and the surveillance video.

[0083] In some embodiments, the wearable device may include a smart bracelet and / or a smart anklet; the identification of the smart bracelet and / or the identification of the smart anklet corresponds to the identification of the target sorter.

[0084] In some embodiments, the behavior data may include first behavior data recorded by a smart bracelet and / or second behavior data recorded by a smart anklet; wherein, the first behavior data is data recorded by the smart bracelet when it detects that the wrist force information of the target sorter is greater than a first threshold, and the second behavior data is data recorded by the smart anklet.

[0085] In some embodiments, the wearable device can obtain recorded behavior data, determine whether the behavior data meets preset conditions, and upload the behavior data to the server if the behavior data meets the preset conditions. After receiving the behavior data, the server can obtain monitoring videos within a preset time range, and determine whether the target sorter has violent sorting behavior based on the behavior data and the monitoring videos.

[0086] In some embodiments, obtaining surveillance video within a preset time range may include: determining a first time corresponding to when the behavior data is received; based on the first time, determining a preset time range; and obtaining surveillance video within the preset time range.

[0087] It should be noted that the various embodiments of the above method are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. For relevant parts, refer to the partial description of the method embodiment.

[0088] From the above description, it can be seen that the embodiment of the present application identifies violent sorting behavior by combining the behavior data recorded by the wearable device with the surveillance video, which can not only more clearly grasp the visual interface of the violent sorting behavior, but also improve the accuracy of identifying the violent sorting behavior.

[0089] In order to further verify the practicality and feasibility of this method, this specification also provides specific examples of applying the above scheme. Figure 4 The figure is a flow chart of a method for identifying violent sorting behavior applied to a Bluetooth bracelet provided in this specification.

[0090] In specific implementation, when entering the work area, the sorter wears a Bluetooth bracelet bound to his or her information and turns on the Bluetooth bracelet to ensure that the Bluetooth bracelet and the server can communicate.

[0091] Then, the force sensor on the Bluetooth bracelet begins to monitor the force information of the sorter's wrist and compares it with the first threshold recorded in the memory. When the force information of the sorter's wrist is not greater than the first threshold, the Bluetooth bracelet can continue to monitor and compare it with the first threshold. When the force information of the sorter's wrist is greater than the first threshold, the Bluetooth bracelet is awakened, and thereafter, the motion sensor and bioelectric sensor of the Bluetooth bracelet begin to record the behavior data of the sorter in real time, and store the recorded behavior data in the memory. Further, the processor of the Bluetooth bracelet can determine whether the recorded behavior data meets the preset conditions. If the preset conditions are met, the behavior data is marked as abnormal data and uploaded to the server, so that the server can determine whether the target sorter has violent sorting behavior based on the monitoring video and abnormal data within the preset time range. Among them, the behavior data includes the motion trajectory information of the sorter's hand, the acceleration information of the Bluetooth bracelet in the vertical direction, and the bioelectric fluctuation information of the muscles under the sorter's wrist. If the movement trajectory information of the sorter's hand in the preset time period is that it goes up to the highest point and then suddenly goes down, and the vertical acceleration of the Bluetooth bracelet is the largest when it reaches the highest point, and the bioelectric fluctuation information of the muscles under the sorter's wrist at this time conforms to the bioelectric fluctuation trend, then it can be determined that the behavior data meets the preset conditions, otherwise it does not meet the preset conditions. When the preset conditions are not met, the processor of the Bluetooth bracelet can continue to determine whether the recorded behavior data meets the preset conditions. The Bluetooth bracelet can be powered by a relay during the process of determining whether the recorded behavior data meets the preset conditions.

[0092] like Figure 5 The figure is a flow chart of a method for identifying violent sorting behavior applied to a Bluetooth anklet provided in this specification.

[0093] In the specific implementation, when the sorter enters the work area, he wears a Bluetooth anklet bound to his own information and turns on the Bluetooth anklet to ensure that the Bluetooth anklet and the server can communicate.

[0094] Then, the force sensor on the Bluetooth anklet begins to record the coordinate information of the sorter's feet in the vertical direction in real time and stores it in the memory. Further, the processor of the Bluetooth anklet compares the recorded coordinate information of the sorter's feet in the vertical direction with the second threshold recorded in the memory. When the coordinate information of the sorter's feet in the vertical direction is greater than the second threshold, the processor of the Bluetooth anklet can mark the recorded behavior data as abnormal data and upload it to the server, so that the server can determine whether the target sorter has violent sorting behavior based on the monitoring video and abnormal data within a preset time range. Among them, when the coordinate information of the sorter's feet in the vertical direction is not greater than the second threshold, the processor of the Bluetooth anklet can continue to determine whether the recorded coordinate information of the sorter's feet in the vertical direction is greater than the second threshold. The Bluetooth anklet can be powered by a relay during the judgment process.

[0095] In addition, when the processor of the Bluetooth bracelet / footband marks the recorded behavior data as abnormal data and uploads it to the server, it can also remind the sorter by vibration so that he can standardize the sorting behavior.

[0096] Of course, the above is only an exemplary description, and the embodiments of this specification are not limited to the above examples. Under the inspiration of the technical essence of this application, technicians in the relevant field may also make other changes, but as long as the functions and effects achieved are the same or similar to those of this application, they should be included in the protection scope of this application. In addition, the "first" and "second" mentioned above are only for distinguishing different results and have no actual meaning.

[0097] In this specification, each embodiment of the above method is described in a progressive manner, and the same or similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. For relevant parts, refer to the partial description of the method embodiment.

[0098] Based on the above-mentioned method for identifying violent sorting behavior, an embodiment of this specification also provides a device for identifying violent sorting behavior. The device may include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiment of this specification and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiment of this specification is as described in the following embodiments. Since the implementation scheme and method of the device to solve the problem are similar, the implementation of the specific device in the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware of predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0099] Specifically, Figure 6 is a schematic diagram of a module structure of an embodiment of a device for identifying violent sorting behavior provided in this specification, such as Figure 6 As shown, a device for identifying violent sorting behavior provided in this specification may include: an acquisition module 610, a judgment module 612, and an upload module 614.

[0100] The acquisition module 610 can be used to acquire the recorded behavior data of the target sorter;

[0101] The judgment module 612 can be used to judge whether the behavior data meets the preset conditions;

[0102] The uploading module 614 can be used to upload the behavior data to the server when the behavior data meets the preset conditions, so that the server can determine whether the target sorter has violent sorting behavior based on the monitoring video and the behavior data within a preset time range.

[0103] It should be noted that the above-mentioned device may also include other implementation modes according to the description of the method embodiment. The specific implementation mode may refer to the description of the relevant method embodiment, which will not be described one by one here.

[0104] Figure 7 is a schematic diagram of the module structure of an embodiment of a device for identifying violent sorting behavior provided in this specification, such as Figure 7 As shown, a device for identifying violent sorting behavior provided in this specification may include: a receiving module 710, an acquiring module 712, and a determining module 714.

[0105] The receiving module 710 can be used to receive behavior data; wherein the behavior data is uploaded by the wearable device when it is determined that the recorded behavior data meets a preset condition; the wearable device is worn on a designated part of the target sorter to record the behavior data of the target sorter;

[0106] The acquisition module 712 can be used to acquire surveillance video within a preset time range;

[0107] The determination module 714 may be used to determine whether the target sorter has engaged in violent sorting behavior based on the behavior data and the surveillance video.

[0108] It should be noted that the above-mentioned device may also include other implementation modes according to the description of the method embodiment. The specific implementation mode may refer to the description of the relevant method embodiment, which will not be described one by one here.

[0109] The embodiments of this specification also provide a device for identifying violent sorting behavior, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the method embodiments in the embodiments of this specification can be implemented. For example, the following steps may be included: obtaining the recorded behavior data of the target sorter; determining whether the behavior data meets the preset conditions; if the behavior data meets the preset conditions, uploading the behavior data to the server, so that the server determines whether the target sorter has violent sorting behavior based on the surveillance video and the behavior data within the preset time range.

[0110] It should be noted that the above-mentioned device may also include other implementation modes according to the description of the method embodiment. The specific implementation mode may refer to the description of the relevant method embodiment, which will not be described one by one here.

[0111] The embodiment of this specification also provides a smart bracelet, including an internal sensor, a processor and a memory. Among them, the internal sensor may include a force sensor, a motion sensor, and a bioelectric sensor. The force sensor can be used to collect the force information of the sorter's wrist. The motion sensor can be used to collect motion trajectory information and acceleration information. The bioelectric sensor can be used to collect bioelectric fluctuation information of muscles. The memory can be used to store the behavior data, monitoring video and threshold data (such as the first threshold, the second threshold, etc.) recorded by the internal sensor. The processor can be used to obtain the recorded behavior data, determine whether the behavior data meets the preset conditions, and upload the behavior data to the server if the behavior data meets the preset conditions, so that the server can determine whether the target sorter has violent sorting behavior based on the monitoring video and behavior data within the preset time range.

[0112] The embodiments of this specification also provide a smart anklet, including an internal sensor, a processor and a memory. Among them, the internal sensor may include a motion sensor. The motion sensor can be used to collect coordinate information in a certain direction. The memory can be used to store the behavior data, monitoring video and threshold data (such as the first threshold, the second threshold, etc.) recorded by the internal sensor. The processor can be used to obtain the recorded behavior data, determine whether the behavior data meets the preset conditions, and upload the behavior data to the server when the behavior data meets the preset conditions, so that the server can determine whether the target sorter has violent sorting behavior based on the monitoring video and behavior data within a preset time range.

[0113] In some embodiments, the smart bracelet and the smart anklet may further include a relay and a vibrator. The relay may be used to power the smart bracelet and the smart anklet. The vibrator may remind the sorter by vibration.

[0114] It should be noted that the smart bracelet and smart anklet described above may also include other implementation methods according to the description of the method embodiment. The specific implementation methods can refer to the description of the relevant method embodiments, which will not be described one by one here.

[0115] The method embodiments provided in this specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 8 This is a hardware structure block diagram of an embodiment of a server for identifying violent sorting behavior provided in this specification. The server may be the apparatus for identifying violent sorting behavior or the device for identifying violent sorting behavior in the above-mentioned embodiment. Figure 8 As shown, the server 10 may include one or more (only one is shown in the figure) processors 100 (the processor 100 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 200 for storing data, and a transmission module 300 for communication functions. A person skilled in the art can understand that Figure 8 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 8 More or fewer components shown in the figure may also include other processing hardware, such as a database or multi-level cache, GPU, or other hardware with Figure 8 Different configurations shown.

[0116] The memory 200 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the method for identifying violent sorting behavior in the embodiment of this specification. The processor 100 executes various functional applications and data processing by running the software programs and modules stored in the memory 200. The memory 200 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 200 may further include a memory remotely arranged relative to the processor 100, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0117] The transmission module 300 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission module 300 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 300 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0118] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0119] The methods or devices described in the above embodiments provided in this specification can implement business logic through computer programs and record them on storage media, and the storage media can be read and executed by computers to achieve the effects of the solutions described in the embodiments of this specification. The storage medium may include a physical device for storing information, which is usually to digitize the information and then store it in a medium using electrical, magnetic or optical methods. The storage medium may include: devices that use electrical energy to store information, such as various types of memories, such as RAM, ROM, etc.; devices that use magnetic energy to store information, such as hard disks, floppy disks, magnetic tapes, magnetic core memories, bubble memories, and U disks; devices that use optical methods to store information, such as CDs or DVDs. Of course, there are other types of readable storage media, such as quantum memories, graphene memories, and so on.

[0120] The above-mentioned methods, devices, equipment and other embodiments for identifying violent sorting behaviors provided in this specification can be implemented by a processor in a computer executing corresponding program instructions, such as using the C++ language of the Windows operating system to implement it on a PC, or using a Linux system, or other methods such as using Android or iOS system programming languages ​​to implement it on a smart terminal, as well as based on the processing logic of a quantum computer.

[0121] It should be noted that the devices and equipment described in the specification may also include other implementation methods according to the description of the relevant method embodiments. The specific implementation methods can refer to the description of the corresponding method embodiments, which will not be described one by one here.

[0122] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0123] For the convenience of description, the above devices are described in various modules according to their functions. Of course, when implementing one or more of the present specification, the functions of some modules can be implemented in the same or more software and / or hardware, and the modules that implement the same function can also be implemented by a combination of multiple sub-modules or sub-units.

[0124] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices, apparatuses, etc. according to embodiments of the present invention. It should be understood that it can be implemented by computer program instructions, which can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the specified function. These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which is implemented in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0125] Those skilled in the art will appreciate that one or more embodiments of the present specification may be provided as a method, system or computer program product. Therefore, one or more embodiments of the present specification may be provided in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware.

[0126] The above is only an example of one or more embodiments of this specification and is not intended to limit one or more embodiments of this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application should be included in the scope of the claims.

Claims

1. A method for identifying violent sorting behavior, characterized in that: Applied to a wearable device, the wearable device is worn on a designated part of a target sorter to record the behavior data of the target sorter; the method comprises: Get recorded behavior data; Determining whether the behavior data meets a preset condition; When the behavior data meets the preset conditions, the behavior data is uploaded to the server, so that the server determines whether the target sorter has violent sorting behavior based on the surveillance video and the behavior data within a preset time range; The behavior data includes first behavior data recorded by the smart bracelet; the first behavior data includes movement trajectory information of the target sorter's hand within a preset time period, acceleration information of the smart bracelet in the vertical direction within a preset time period, and bioelectric fluctuation information of the muscles under the wrist of the target sorter within a preset time period; Determining whether the behavior data meets a preset condition includes: Determine whether the motion trajectory information of the target sorter's hand within a preset time period matches the preset motion trajectory information; In the case of a match, determining the highest vertical position of the target sorter's hand within a preset time period; Determine whether the vertical acceleration of the smart bracelet is the largest when the target sorter's hand is at the highest position in the vertical direction; When the maximum value is confirmed, it is determined whether the bioelectric fluctuation information of the muscles under the wrist of the target sorter in the preset time period meets the preset change law; If so, it is determined that the first behavior data meets the first preset condition.

2. The method according to claim 1, characterized in that The wearable device includes a smart bracelet and / or a smart anklet; the identification of the smart bracelet and / or the identification of the smart anklet corresponds to the identification of the target sorter; the behavior data includes second behavior data recorded by the smart anklet; wherein, the first behavior data is the data recorded by the smart bracelet when it monitors that the wrist force information of the target sorter is greater than a first threshold, and the second behavior data is the data recorded by the smart anklet.

3. The method according to claim 2, characterized in that The second behavior data includes coordinate information of the target sorter's feet in the vertical direction.

4. The method according to claim 3, characterized in that The determining whether the behavior data meets a preset condition includes: Determine whether the second behavior data satisfies a second preset condition.

5. The method according to claim 4, characterized in that The determining whether the second behavior data satisfies a second preset condition includes: comparing the vertical coordinate information of the feet of the target sorter with a second threshold; When the coordinate information is greater than a second threshold, it is determined that the second behavior data meets a second preset condition.

6. A method for identifying violent sorting behavior, characterized in that: Applied to a server, the method comprises: receiving behavior data; wherein the behavior data is uploaded by the wearable device when it is determined that the recorded behavior data meets a preset condition; the wearable device is worn on a designated part of the target sorter to record the behavior data of the target sorter; Get surveillance video within a preset time range; Determining whether the target sorter has engaged in violent sorting behavior based on the behavior data and the surveillance video; The behavior data includes first behavior data recorded by the smart bracelet; the first behavior data includes movement trajectory information of the target sorter's hand within a preset time period, acceleration information of the smart bracelet in the vertical direction within a preset time period, and bioelectric fluctuation information of the muscles under the wrist of the target sorter within a preset time period; When the wearable device determines that the recorded behavior data meets the preset conditions, it includes: Determine whether the motion trajectory information of the target sorter's hand within a preset time period matches the preset motion trajectory information; In the case of a match, determining the highest vertical position of the target sorter's hand within a preset time period; Determine whether the vertical acceleration of the smart bracelet is the largest when the target sorter's hand is at the highest position in the vertical direction; When the maximum value is confirmed, it is determined whether the bioelectric fluctuation information of the muscles under the wrist of the target sorter in the preset time period meets the preset change law; If so, it is determined that the first behavior data meets the first preset condition.

7. The method according to claim 6, characterized in that The wearable device includes a smart bracelet and / or a smart anklet; the identification of the smart bracelet and / or the identification of the smart anklet corresponds to the identification of the target sorter; The behavior data includes second behavior data recorded by the smart anklet; wherein, the first behavior data is data recorded by the smart anklet when the smart anklet monitors that the wrist force information of the target sorter is greater than a first threshold, and the second behavior data is data recorded by the smart anklet.

8. The method according to claim 6, characterized in that Get surveillance videos within a preset time range, including: Determine the first time corresponding to when the behavior data is received; Based on the first time, determining a preset time range; Get surveillance video within a preset time range.

9. A device for identifying violent sorting behavior, characterized in that: include: An acquisition module is used to acquire the recorded behavior data of the target sorter; A judgment module, used to judge whether the behavior data meets a preset condition; An uploading module, used for uploading the behavior data to a server when the behavior data meets a preset condition, so that the server can determine whether the target sorter has violent sorting behavior based on the monitoring video and the behavior data within a preset time range; The behavior data includes first behavior data recorded by the smart bracelet; The first behavior data includes the movement trajectory information of the target sorter's hand within a preset time period, the acceleration information of the smart bracelet in the vertical direction within a preset time period, and the bioelectric fluctuation information of the muscles under the wrist of the target sorter within a preset time period; The judgment module is used to: judge whether the motion trajectory information of the target sorter's hand within a preset time period matches the preset motion trajectory information; if they match, determine the highest position of the target sorter's hand in the vertical direction within the preset time period; judge whether the acceleration of the smart bracelet in the vertical direction is the largest when the target sorter's hand is at the highest position in the vertical direction; when it is confirmed to be the largest, judge whether the bioelectric fluctuation information of the muscles under the wrist of the target sorter within the preset time period meets the preset change law; if so, determine that the first behavior data meets the first preset condition.

10. A device for identifying violent sorting behavior, characterized in that: include: A receiving module, used for receiving behavior data; wherein the behavior data is uploaded by the wearable device when it is determined that the recorded behavior data meets a preset condition; the wearable device is worn on a designated part of the target sorter, and is used for recording the behavior data of the target sorter; An acquisition module is used to acquire surveillance videos within a preset time range; A determination module, used to determine whether the target sorter has violent sorting behavior based on the behavior data and the surveillance video; The behavior data includes first behavior data recorded by the smart bracelet; the first behavior data includes movement trajectory information of the target sorter's hand within a preset time period, acceleration information of the smart bracelet in the vertical direction within a preset time period, and bioelectric fluctuation information of the muscles under the wrist of the target sorter within a preset time period; When the wearable device determines that the recorded behavior data meets the preset conditions, it includes: Determine whether the motion trajectory information of the target sorter's hand within a preset time period matches the preset motion trajectory information; In the case of a match, determining the highest vertical position of the target sorter's hand within a preset time period; Determine whether the vertical acceleration of the smart bracelet is the largest when the target sorter's hand is at the highest position in the vertical direction; When the maximum value is confirmed, it is determined whether the bioelectric fluctuation information of the muscles under the wrist of the target sorter in the preset time period meets the preset change law; If so, it is determined that the first behavior data meets the first preset condition.

11. A device for identifying violent sorting behavior, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

12. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed, the steps of the method according to any one of claims 1 to 8 are implemented.

Images