EDCA Parameter Adjustment Method, Device, Equipment and Storage Medium

Abstract

The present invention relates to the technical field of intelligent devices, and discloses an EDCA parameter adjustment method, device, equipment and storage medium. The method includes: obtaining scene information collected by an intelligent device, and determining the current scene according to the scene information; when the current scene is a preset scene, determining the total number of people in the current scene; when the total number of people is greater than a preset quantity threshold, determining the key point positions of each person; determining the category of the current scene according to the key point positions, and adjusting the EDCA parameters according to the category of the current scene; by the above method, after determining the current scene, it is judged whether the current scene is a preset scene, if so, it is further judged whether the total number of people in the current scene is greater than a preset quantity threshold, if so, the EDCA parameters are adjusted according to the category of the current scene, so as to realize the adaptive adjustment of the EDCA parameters based on different types of scenes, meet the network requirements of different places, and improve the user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent devices, and in particular to an EDCA parameter adjustment method, device, equipment and storage medium. Background Art

[0002] With the continuous development of augmented reality (AR) technology, real-time and efficient data transmission requires high-quality networks as support, and high-quality networks are inseparable from EDCA parameters. However, the current method of adjusting EDCA parameters is relatively conservative and cannot be adaptively adjusted according to specific scenarios, especially in places with large indoor traffic and high network bandwidth requirements, such as restaurants, libraries, shopping malls, hospitals, and stations. Different places have different requirements for network services. Therefore, how to achieve adaptive adjustment of EDCA parameters based on different types of scenarios is a technical problem that needs to be solved urgently.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide an EDCA parameter adjustment method, apparatus, device and storage medium, aiming to solve the technical problem of how to adaptively adjust EDCA parameters based on different types of scenarios.

[0005] To achieve the above object, the present invention provides an EDCA parameter adjustment method, the EDCA parameter adjustment method comprising the following steps:

[0006] Acquire scene information collected by the smart device, and determine the current scene based on the scene information;

[0007] When the current scene is a preset scene, determining the total number of people in the current scene;

[0008] When the total number of people is greater than a preset number threshold, determining the key point position of each person;

[0009] The category of the current scene is determined according to the key point position, and the EDCA parameters are adjusted according to the category of the current scene.

[0010] Optionally, when the current scene is a preset scene, determining the total number of people in the current scene includes:

[0011] When the current scene is a preset scene, acquiring surveillance video data, image data captured by a smart device, and public image data in the current scene;

[0012] Generate a target image dataset based on the monitored video data, captured image data, and public image data;

[0013] Detect the target image dataset through a target image detection algorithm to obtain the human body bounding boxes of each person;

[0014] Determine the total number of people in the current scene based on the human body bounding boxes of each person.

[0015] Optionally, when the total number of people is greater than a preset quantity threshold, determining the key point positions of each person includes:

[0016] When the total number of people is greater than a preset quantity threshold, obtain the images within the human body bounding boxes of each person;

[0017] Identify the images within the human body bounding boxes of each person through a target pose estimation algorithm to obtain the pose data of each person;

[0018] Obtain the key point positions of each person based on the pose data of each person.

[0019] Optionally, determining the category of the current scene based on the key point positions and adjusting the EDCA parameters according to the category of the current scene includes:

[0020] Obtain the coordinates of each key point based on the key point positions;

[0021] Calculate the relative distances and relative angles between each key point based on the coordinates of each key point;

[0022] Identify the relative distances and relative angles through a target depth behavior recognition model to obtain the behavior data of each person;

[0023] Determine the category of the current scene through a scene recognition vision algorithm based on the behavior data of each person and the total number of people in the current scene;

[0024] Adjust the EDCA parameters according to the category of the current scene.

[0025] Optionally, adjusting the EDCA parameters according to the category of the current scene includes:

[0026] Determine the adjustment priority of the EDCA parameters according to the category of the current scene, and the category of the current scene includes scene categories that focus on video stream transmission performance and conventional data transmission performance, scene categories that focus on silent data transmission performance and background stream transmission performance, scene categories that focus on navigation performance and video stream transmission performance, scene categories that focus on call performance and conventional data transmission performance, and scene categories that focus on navigation performance, call performance, and conventional data transmission performance;

[0027] Reduce or increase the value of the parameter whose priority is to be adjusted.

[0028] Optionally, after adjusting the EDCA parameters according to the category of the current scenario, the method further includes:

[0029] Establish a network connection according to the adjusted EDCA parameters;

[0030] Obtain the data to be transmitted in the current scenario;

[0031] Transmit the data to be transmitted through the connected network.

[0032] Optionally, after obtaining the scenario information collected by the intelligent device and determining the current scenario according to the scenario information, the method further includes:

[0033] When the current scenario is not a preset scenario, or the total number of people is less than or equal to a preset quantity threshold, or the category of the current scenario is a target scenario category, establish a network connection through default EDCA parameters;

[0034] Transmit the data to be transmitted through the default connected network.

[0035] In addition, to achieve the above object, the present invention further provides an EDCA parameter adjustment device, where the EDCA parameter adjustment device includes:

[0036] An acquisition module, configured to acquire scenario information collected by an intelligent device and determine the current scenario according to the scenario information;

[0037] A determination module, configured to determine the total number of people in the current scenario when the current scenario is a preset scenario;

[0038] The determination module is further configured to determine the key point positions of each person when the total number of people is greater than a preset quantity threshold;

[0039] An adjustment module, configured to determine the category of the current scenario according to the key point positions and adjust the EDCA parameters according to the category of the current scenario.

[0040] In addition, to achieve the above object, the present invention further provides an EDCA parameter adjustment device, where the EDCA parameter adjustment device includes: a memory, a processor, and an EDCA parameter adjustment program stored on the memory and executable on the processor, and the EDCA parameter adjustment program is configured to implement the EDCA parameter adjustment method as described above.

[0041] In addition, to achieve the above object, the present invention also provides a storage medium, on which an EDCA parameter adjustment program is stored. When the EDCA parameter adjustment program is executed by a processor, the EDCA parameter adjustment method described above is implemented.

[0042] The EDCA parameter adjustment method proposed by the present invention obtains the scene information collected by an intelligent device, and determines the current scene according to the scene information; when the current scene is a preset scene, determines the total number of people in the current scene; when the total number of people is greater than a preset quantity threshold, determines the key point positions of each person; determines the category of the current scene according to the key point positions, and adjusts the EDCA parameters according to the category of the current scene; in the above manner, after determining the current scene, it is judged whether the current scene is a preset scene, if so, it is further judged whether the total number of people in the current scene is greater than the preset quantity threshold, if so, the EDCA parameters are adjusted according to the category of the current scene, so as to be able to adaptively adjust the EDCA parameters based on different types of scenes to meet the network requirements of different places and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a schematic structural diagram of an EDCA parameter adjustment device in the hardware operating environment related to the solution of the embodiment of the present invention;

[0044] Figure 2 is a schematic flowchart of the first embodiment of the EDCA parameter adjustment method of the present invention;

[0045] Figure 3 is a schematic diagram of scene recognition in an embodiment of the EDCA parameter adjustment method of the present invention;

[0046] Figure 4 is a schematic flowchart of the second embodiment of the EDCA parameter adjustment method of the present invention;

[0047] Figure 5 is a schematic overall flowchart of an embodiment of the EDCA parameter adjustment method of the present invention;

[0048] Figure 6 is a schematic diagram of functional modules of the first embodiment of the EDCA parameter adjustment device of the present invention.

[0049] The implementation, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] Refer to Figure 1 ,Figure 1 The figure is a schematic structural diagram of an EDCA parameter adjustment device for the hardware operating environment involved in the solution of the embodiment of the present invention.

[0052] As Figure 1 shown, the EDCA parameter adjustment device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless-fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0053] Those skilled in the art can understand that Figure 1 the structure shown in

[0054] does not constitute a limitation on the EDCA parameter adjustment device, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. Figure 1 As shown, in the memory 1005 as a storage medium, there may be included an operating system, a network communication module, a user interface module, and an EDCA parameter adjustment program.

[0055] In Figure 1 the EDCA parameter adjustment device shown, the network interface 1004 is mainly used for data communication with a network integrated platform workstation; the user interface 1003 is mainly used for data interaction with users; the processor 1001 and the memory 1005 in the EDCA parameter adjustment device of the present invention may be provided in the EDCA parameter adjustment device. The EDCA parameter adjustment device calls the EDCA parameter adjustment program stored in the memory 1005 through the processor 1001 and executes the EDCA parameter adjustment method provided by the embodiment of the present invention.

[0056] Based on the above hardware structure, an embodiment of the EDCA parameter adjustment method of the present invention is proposed.

[0057] Referring to Figure 2 ,Figure 2 This is a schematic flowchart of the first embodiment of the EDCA parameter adjustment method of the present invention.

[0058] In the first embodiment, the EDCA parameter adjustment method includes the following steps:

[0059] Step S10: Obtain the scene information collected by the intelligent device, and determine the current scene according to the scene information.

[0060] It should be noted that the execution subject of this embodiment is an EDCA parameter adjustment device, and it can also be other devices that can achieve the same or similar functions, such as a parameter adjustment controller, etc. This embodiment does not limit this. In this embodiment, a parameter adjustment controller is used as an example for illustration.

[0061] It should be understood that the scene information refers to the relevant information used to determine the current scene. This scene information can be obtained by extracting features from the information collected by each module in the intelligent device. The scene information includes but is not limited to magnetic field information, angular velocity, and acceleration. The magnetic field information can be obtained by extracting features from the information collected by the magnetometer. The angular velocity can be obtained by extracting features from the information collected by the gyroscope. The acceleration can be obtained by extracting features from the information collected by the accelerometer. After obtaining the scene information collected by the intelligent device, the scene information is input into a pre-trained support vector machine (SVM) scene recognition model, and then the current scene is recognized by the pre-trained SVM scene recognition model.

[0062] Further, after step S10, it further includes: when the current scene is not a preset scene, or the total number of people is less than or equal to a preset quantity threshold, or the category of the current scene is a target scene category, perform network connection through default EDCA parameters; transmit the data to be transmitted through the default connected network.

[0063] It can be understood that when it is determined that any one of the conditions that the current scene is not a preset scene, or the total number of people is less than or equal to a preset quantity threshold, or the category of the current scene is a target scene category is satisfied, it indicates that there is no need to adjust the EDCA parameters. The target scene category refers to all other scene categories except for the scene categories that focus on video stream transmission performance and conventional data transmission performance, the scene categories that focus on silent data transmission performance and background stream transmission performance, the scene categories that focus on navigation performance and video stream transmission performance, the scene categories that focus on call performance and conventional data transmission performance, and the scene categories that focus on navigation performance, call performance, and conventional data transmission performance. At this time, network connection is directly performed using default EDCA parameters, and then the data to be transmitted is transmitted through the default connected network.

[0064] Step S20: When the current scene is a preset scene, determine the total number of people in the current scene.

[0065] It can be understood that the preset scene can be an outdoor scene. After obtaining the current scene, it is judged whether the current scene is a preset scene. If so, the total number of people in the current scene is determined.

[0066] Further, step S20 includes: when the current scene is a preset scene, obtain the surveillance video data, the image data captured by intelligent devices, and the public image data in the current scene; generate a target image dataset according to the surveillance video data, the captured image data, and the public image data; detect the target image dataset through a target image detection algorithm to obtain the human body bounding boxes of each person; determine the total number of people in the current scene according to the human body bounding boxes of each person.

[0067] It should be understood that the target image dataset refers to a dataset composed of the surveillance video data, the image data captured by intelligent devices, and the public image data in the current scene. The intelligent device can be an AR glasses. The public image data refers to the human image data collected by public devices. Then, through the target image detection algorithm, the human body bounding boxes (bounding box) of each person are detected according to the target image dataset, and then the total number of people in the current scene is determined according to the human body bounding boxes of each person. The target image detection algorithm can be the YOLOv5 detection algorithm.

[0068] Step S30: When the total number of people is greater than a preset quantity threshold, determine the key point positions of each person.

[0069] It should be understood that after determining the total number of people in the current scene, it is necessary to judge whether the total number of people is greater than the preset quantity threshold. If so, determine the key point positions of each person in the corresponding place in the current scene. The key point positions include but are not limited to the head position, the shoulder position, and the wrist position, etc.

[0070] Further, step S30 includes: when the total number of people is greater than a preset quantity threshold, obtain the images within the human body bounding boxes of each person; identify the images within the human body bounding boxes of each person through a target pose estimation algorithm to obtain the pose data of each person; obtain the key point positions of each person according to the pose data of each person.

[0071] It can be understood that the target pose estimation algorithm refers to an algorithm used to estimate the pose of a person in an image. The target pose estimation algorithm can be the OpenPose pose estimation algorithm. When it is determined that the total number of people is greater than the preset quantity threshold, it indicates that there are more people in the current scene, that is, the EDCA parameters need to be adjusted. Before adjusting the EDCA parameters, it is necessary to determine the key point positions of each person. Specifically, the target pose estimation algorithm is used to identify the image within the human body bounding box of each person, and then the key point positions of each person are obtained through the recognized pose data of each person.

[0072] Step S40: Determine the category of the current scene according to the key point positions, and adjust the EDCA parameters according to the category of the current scene.

[0073] It can be understood that the EDCA parameters refer to the parameters used for network connection. The priorities of the EDCA parameters are divided into four types, specifically Video (VI), Voice (VO), Best Effort (BE), and Background Traffic (BK). And the parameters of each priority level include the minimum contention window (CWmin), the maximum contention window (CWmax), the arbitration inter-frame spacing (AIFS), and the transmission opportunity (TXOP). After determining the key point positions of each person, determine the category of the previous scene according to the key point positions, and then adjust the EDCA parameters according to the category of the current scene. If the categories of the current scenes are different, the numerical values of the parameters of the priority levels of the EDCA parameters are also different.

[0074] Furthermore, step S40 includes: obtaining the coordinates of each key point according to the key point positions; calculating the relative distances and relative angles between the key points according to the coordinates of each key point; identifying the relative distances and relative angles through the target depth behavior recognition model to obtain the behavior data of each person; determining the category of the current scene through the scene recognition vision algorithm according to the behavior data of each person and the total number of people in the current scene; adjusting the EDCA parameters according to the category of the current scene.

[0075] It should be understood that after determining the positions of the key points, the coordinates of each key point are obtained according to the position points of the key points in the three-dimensional rectangular coordinate system. Then, the relative distances and relative angles between every two key points are calculated according to the coordinates of each key point. The relative distance can be calculated by the distance formula between two points, and the relative angle can be determined by the angle between the line connecting the two points and the coordinate axes. Then, the target depth behavior recognition model identifies each person's behavior data according to the relative distance and relative angle. The target depth behavior recognition model can be a long short-term memory (LSTM) deep learning model.

[0076] It can be understood that the scene recognition vision algorithm refers to the algorithm used to recognize the scene category. After recognizing each person's behavior data, combining the total number of people in the current scene and using the scene recognition vision algorithm to determine the category of the current scene, refer to Figure 3 , Figure 3 is a schematic diagram of scene recognition. Specifically, after generating the target image dataset based on the surveillance video data, the captured image data, and the public image data, the target image detection algorithm is used to recognize the target image dataset, and the human positions are marked and the total number of people is counted according to the recognition results. Then, the target pose estimation algorithm is used to recognize the image of a single human position, and the key point positions of each person are marked according to the recognition results. Then, the target depth behavior recognition model is used to recognize each person's behavior data. Finally, the scene recognition vision algorithm is used to recognize each person's behavior data and the total number of people in the current scene, and the category of the current scene is marked according to the recognition results.

[0077] Further, after step S40, it further includes: performing network connection according to the adjusted EDCA parameters; obtaining the data to be transmitted in the current scene; and transmitting the data to be transmitted through the connected network.

[0078] It should be understood that the data to be transmitted refers to the data that needs to be transmitted through the network. After adjusting the EDCA parameters, network connection is performed according to the adjusted EDCA parameters, and then the data to be transmitted is transmitted through the connected network, so as to optimize the network connection of the intelligent device, improve the efficiency and reliability of network transmission, and thus improve the user experience.

[0079] In this embodiment, the scene information collected by the intelligent device is obtained, and the current scene is determined according to the scene information; when the current scene is a preset scene, the total number of people in the current scene is determined; when the total number of people is greater than the preset quantity threshold, the key point positions of each person are determined; according to the key point positions, the category of the current scene is determined, and the EDCA parameters are adjusted according to the category of the current scene; in the above manner, after determining the current scene, it is judged whether the current scene is a preset scene, if so, it is further judged whether the total number of people in the current scene is greater than the preset quantity threshold, if so, the EDCA parameters are adjusted according to the category of the current scene, so that the EDCA parameters can be adaptively adjusted based on different types of scenes to meet the network requirements of different places and improve the user experience.

[0080] In one embodiment, as Figure 4 described, based on the first embodiment, a second embodiment of the EDCA parameter adjustment method of the present invention is proposed. The step S40 includes:

[0081] Step S401: Determine the adjustment priority of the EDCA parameters according to the category of the current scene. The category of the current scene includes the scene categories that focus on video stream transmission performance and conventional data transmission performance, the scene categories that focus on silent data transmission performance and background stream transmission performance, the scene categories that focus on navigation performance and video stream transmission performance, the scene categories that focus on call performance and conventional data transmission performance, and the scene categories that focus on navigation performance, call performance, and conventional data transmission performance.

[0082] It should be understood that the adjustment priorities of the EDCA parameters include but are not limited to VI, VO, BE, and BK. For example, when the category of the current scene is the scene category that focuses on video stream transmission performance and conventional data transmission performance, the adjustment priorities are VI and BE; when the category of the current scene is the scene category that focuses on silent data transmission performance and background stream transmission performance, the adjustment priorities are BE and BK. The scene category that focuses on video stream transmission performance and conventional data transmission performance can be the restaurant scene category, the scene category that focuses on silent data transmission performance and background stream transmission performance can be the library scene category, the scene category that focuses on navigation performance and video stream transmission performance can be the shopping mall scene category, the scene category that focuses on call performance and conventional data transmission performance can be the hospital scene category, and the scene category that focuses on navigation performance, call performance, and conventional data transmission performance can be the station scene category.

[0083] Step S402: Increase or decrease the value of the parameter with the adjustment priority.

[0084] It is understandable that after obtaining the to-be-adjusted priority of the EDCA parameters, the numerical values of the parameters with the to-be-adjusted priority are decreased or increased. Specifically: when the type of the current scenario is a scenario category that emphasizes video stream transmission performance and regular data transmission performance, the numerical values of CWmin, CWmax, and AIFS of VI are decreased, the numerical values of CWmin, CWmax, and AIFS of BE are decreased, and the numerical values of TXOP of VI and BE are increased. When the type of the current scenario is a scenario category that emphasizes silent data transmission performance and background stream transmission performance, the numerical values of CWmin, CWmax, and AIFS of BE are decreased, the numerical values of CWmin, CWmax, and AIFS of BK are decreased, and the numerical values of TXOP of BE and BK are increased. When the type of the current scenario is a scenario category that emphasizes navigation performance and video stream transmission performance, the numerical values of CWmin, CWmax, and AIFS of VI are decreased, the numerical values of CWmin, CWmax, and AIFS of BE are decreased, the numerical values of CWmin, CWmax, and AIFS of BK are decreased, and the numerical values of TXOP of VI, BE, and BK are increased. When the type of the current scenario is a scenario category that emphasizes call performance and regular data transmission performance, the numerical values of CWmin, CWmax, and AIFS of VO are decreased, the numerical values of CWmin, CWmax, and AIFS of BE are decreased, and the numerical values of TXOP of VO and BE are increased. When the type of the current scenario is a scenario category that emphasizes navigation performance, call performance, and regular data transmission performance, the numerical values of CWmin, CWmax, and AIFS of VI are decreased, the numerical values of CWmin, CWmax, and AIFS of VO are decreased, the numerical values of CWmin, CWmax, and AIFS of BE are decreased, the numerical values of TXOP of VI, VO, and BE are increased, the numerical values of CWmin, CWmax, and AIFS of VI are decreased, the numerical values of CWmin, CWmax, and AIFS of BE are decreased, the numerical values of CWmin, CWmax, and AIFS of BK are decreased, and the numerical values of TXOP of VI, BE, and BK are increased.

[0085] Reference Figure 5 , Figure 5It is a schematic diagram of the overall process. Specifically: after collecting the scene information jointly by the magnetometer, gyroscope, and accelerometer in the intelligent device, the current scene is identified through a pre-trained SVM scene recognition model, and then it is determined whether the current scene is a preset scene. If not, the network connection is directly made with the default EDCA parameters. If so, the total number of people in the current scene is identified based on the surveillance video data, the captured image data, and the public image data, and then it is determined whether the total number of people is greater than the preset quantity threshold. If not, the network connection is directly made with the default EDCA parameters. If so, the scene recognition vision algorithm identifies the behavior data of each person and the total number of people in the current scene to determine the category of the current scene, and then determines the adjustment priority of the EDCA parameters according to the category of the current scene, and then adjusts the value of the parameter with the adjustment priority, and then makes the network connection according to the adjusted EDCA parameters, and then transmits the data to be transmitted through the connected network.

[0086] In this embodiment, the adjustment priority of the EDCA parameters is determined according to the category of the current scene; the value of the parameter with the adjustment priority is decreased or increased; in the above manner, after determining the category of the current scene, the adjustment priority of the EDCA parameters is determined according to the scene category to which the category of the current scene belongs, and then the value of the parameter with the adjustment priority is decreased or increased, so as to effectively improve the accuracy of adjusting the EDCA parameters.

[0087] In addition, an embodiment of the present invention also proposes a storage medium, on which an EDCA parameter adjustment program is stored. When the EDCA parameter adjustment program is executed by a processor, the steps of the EDCA parameter adjustment method described above are implemented.

[0088] Since this storage medium adopts all the technical solutions of the above all embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be elaborated one by one here.

[0089] In addition, with reference to Figure 6 , an embodiment of the present invention also proposes an EDCA parameter adjustment device, which includes:

[0090] An acquisition module 10, configured to acquire the scene information collected by the intelligent device and determine the current scene according to the scene information.

[0091] A determination module 20, configured to determine the total number of people in the current scene when the current scene is a preset scene.

[0092] The determination module 20 is further configured to determine the key point positions of each person when the total number of people is greater than the preset quantity threshold.

[0093] An adjustment module 30 is configured to determine the category of the current scene according to the key point positions, and adjust the EDCA parameters according to the category of the current scene.

[0094] In this embodiment, the scene information collected by the intelligent device is obtained, and the current scene is determined according to the scene information; when the current scene is a preset scene, the total number of people in the current scene is determined; when the total number of people is greater than the preset quantity threshold, the key point positions of each person are determined; the category of the current scene is determined according to the key point positions, and the EDCA parameters are adjusted according to the category of the current scene. In the above manner, after determining the current scene, it is judged whether the current scene is a preset scene. If so, it is further judged whether the total number of people in the current scene is greater than the preset quantity threshold. If so, the EDCA parameters are adjusted according to the category of the current scene, so that the EDCA parameters can be adaptively adjusted based on different types of scenes to meet the network requirements of different places and improve the user experience.

[0095] It should be noted that the above-described workflow is only illustrative and does not limit the protection scope of the present invention. In actual applications, those skilled in the art can select some or all of them according to actual needs to achieve the purpose of the solution of this embodiment, and no limitation is made here.

[0096] In addition, for the technical details not described in detail in this embodiment, reference can be made to the EDCA parameter adjustment method provided in any embodiment of the present invention, which will not be elaborated here.

[0097] In one embodiment, the determination module 20 is further configured to, when the current scene is a preset scene, obtain the surveillance video data, the image data captured by the intelligent device, and the public image data in the current scene; generate a target image data set according to the surveillance video data, the captured image data, and the public image data; detect the target image data set through a target image detection algorithm to obtain the human body bounding boxes of each person; determine the total number of people in the current scene according to the human body bounding boxes of each person.

[0098] In one embodiment, the determination module 20 is further configured to, when the total number of people is greater than the preset quantity threshold, obtain the images within the human body bounding boxes of each person; identify the images within the human body bounding boxes of each person through a target pose estimation algorithm to obtain the pose data of each person; obtain the key point positions of each person according to the pose data of each person.

[0099] In one embodiment, the adjustment module 30 is further configured to obtain the coordinates of each key point according to the positions of the key points; calculate the relative distances and relative angles between the key points according to the coordinates of each key point; identify the relative distances and relative angles through a target depth behavior recognition model to obtain each person's behavior data; determine the category of the current scene according to each person's behavior data and the total number of people in the current scene through a scene recognition vision algorithm; and adjust the EDCA parameters according to the category of the current scene.

[0100] In one embodiment, the adjustment module 30 is further configured to determine the adjustment priority of the EDCA parameters according to the category of the current scene, where the category of the current scene includes a scene category that emphasizes video stream transmission performance and conventional data transmission performance, a scene category that emphasizes silent data transmission performance and background stream transmission performance, a scene category that emphasizes navigation performance and video stream transmission performance, a scene category that emphasizes call performance and conventional data transmission performance, and a scene category that emphasizes navigation performance, call performance, and conventional data transmission performance; and decrease or increase the value of the parameter with the adjustment priority.

[0101] In one embodiment, the adjustment module 30 is further configured to perform network connection through default EDCA parameters when the current scene is not a preset scene, or the total number of people is less than or equal to a preset quantity threshold, or the category of the current scene is a target scene category; and transmit the data to be transmitted through the default connected network.

[0102] In one embodiment, the adjustment module 30 is further configured to perform network connection according to the adjusted EDCA parameters; obtain the data to be transmitted in the current scene; and transmit the data to be transmitted through the connected network.

[0103] Other embodiments or implementation methods of the EDCA parameter adjustment device of the present invention may refer to the above method embodiments, and will not be repeated here.

[0104] In addition, it should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or system including the element.

[0105] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0106] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a Read Only Memory (ROM) / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, an integrated platform workstation, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0107] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. An EDCA parameter adjustment method, characterized in that The EDCA parameter adjustment method includes the following steps: Obtain the scene information collected by the intelligent device, and determine the current scene according to the scene information; When the current scene is a preset scene, determine the total number of people in the current scene; When the total number of people is greater than a preset quantity threshold, determine the key point positions of each person; Determine the category of the current scene according to the key point positions, and adjust the EDCA parameters according to the category of the current scene.

2. The EDCA parameter adjustment method according to claim 1, characterized in that The step of determining the total number of people in the current scene when the current scene is a preset scene includes: When the current scene is a preset scene, obtain the surveillance video data, the image data captured by the intelligent device, and the public image data in the current scene; Generate a target image dataset according to the surveillance video data, the captured image data, and the public image data; Detect the target image dataset through a target image detection algorithm to obtain the human body bounding boxes of each person; Determine the total number of people in the current scene according to the human body bounding boxes of each person.

3. The EDCA parameter adjustment method according to claim 1, wherein The step of determining the key point positions of each person when the total number of people is greater than a preset quantity threshold includes: When the total number of people is greater than a preset quantity threshold, obtain the images within the human body bounding boxes of each person; Identify the images within the human body bounding boxes of each person through a target pose estimation algorithm to obtain the pose data of each person; Obtain the key point positions of each person according to the pose data of each person.

4. The EDCA parameter adjustment method according to claim 1, wherein The step of determining the category of the current scene according to the key point positions and adjusting the EDCA parameters according to the category of the current scene includes: Obtain the coordinates of each key point according to the key point positions; Calculate the relative distances and relative angles between the key points according to the coordinates of each key point; Identify the relative distances and relative angles through a target depth behavior recognition model to obtain the behavior data of each person; Determine the category of the current scene through a scene recognition vision algorithm according to the behavior data of each person and the total number of people in the current scene; Adjust the EDCA parameters according to the category of the current scene.

5. The EDCA parameter adjustment method according to claim 1, wherein The step of adjusting the EDCA parameters according to the category of the current scene includes: Determine the adjustment priority of the EDCA parameters according to the category of the current scene. The categories of the current scene include the scene categories that focus on video stream transmission performance and conventional data transmission performance, the scene categories that focus on silent data transmission performance and background stream transmission performance, the scene categories that focus on navigation performance and video stream transmission performance, the scene categories that focus on call performance and conventional data transmission performance, and the scene categories that focus on navigation performance, call performance, and conventional data transmission performance; Increase or decrease the values of the parameters with the adjustment priority.

6. The EDCA parameter adjustment method according to claim 1, wherein After adjusting the EDCA parameters according to the category of the current scene, it further includes: Establish a network connection according to the adjusted EDCA parameters; Obtain the data to be transmitted in the current scene; Transmit the data to be transmitted through the connected network.

7. The EDCA parameter adjustment method according to claim 1, wherein After obtaining the scene information collected by the intelligent device and determining the current scene according to the scene information, it further includes: When the current scenario is not a preset scenario, or the total number of people is less than or equal to a preset quantity threshold, or the category of the current scenario is a target scenario category, network connection is performed using default EDCA parameters; The data to be transmitted is transmitted through the default-connected network.

8. An EDCA parameter adjustment device, characterized in that, The EDCA parameter adjustment device includes: An acquisition module, configured to acquire the scenario information collected by the intelligent device and determine the current scenario according to the scenario information; A determination module, configured to determine the total number of people in the current scenario when the current scenario is a preset scenario; The determination module is further configured to determine the key point positions of each person when the total number of people is greater than a preset quantity threshold; An adjustment module, configured to determine the category of the current scenario according to the key point positions and adjust the EDCA parameters according to the category of the current scenario.

9. An EDCA parameter adjustment device, characterized in that The EDCA parameter adjustment device includes: a memory, a processor, and an EDCA parameter adjustment program stored on the memory and executable on the processor, and the EDCA parameter adjustment program is configured to implement the EDCA parameter adjustment method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, An EDCA parameter adjustment program is stored on the storage medium, and when the EDCA parameter adjustment program is executed by a processor, the EDCA parameter adjustment method according to any one of claims 1 to 7 is implemented.

Images