Task cooperative processing method, device and equipment for recording and broadcasting host and camera

Abstract

The invention discloses a method, a device and equipment for cooperatively processing tasks by a recording and broadcasting host and a camera, and a storage medium. Wherein. The method comprises the steps that an AI analysis general task of a docking platform is received, and the AI analysis general task comprises at least one platform subtask; matching with a first relation corresponding table to obtain cameras corresponding to each platform sub-task in the AI analysis total task, the first relation corresponding table being an association list of all platform sub-tasks and the corresponding cameras; packaging the platform subtasks responsible for each camera and distributing the platform subtasks to the corresponding cameras; receiving AI analysis data returned by each camera; and summarizing all AI analysis data to a docking platform. The recording and broadcasting host and the camera are coordinated in a distributed computing power coordination mode, so that the stability and the reliability of the system are improved, and the overall hardware cost is effectively reduced by optimizing resource configuration.

Description

Technical Field

[0001] The present invention relates to the technical field of video recording and broadcasting, and more specifically, to a method, device, equipment and storage medium for collaborative processing of tasks by a recording and broadcasting host and a camera. Background Art

[0002] By using a multi-camera high-quality recording and broadcasting system to fully record the teaching process and conduct standardized AI analysis of teacher and student classroom behavior, teachers can receive timely feedback in daily teaching, which is of great significance for promoting teacher professional development and improving overall teaching quality.

[0003] In traditional recording and broadcasting systems, cameras are used to capture all-round images of the classroom in real time, such as teacher panorama, teacher close-up, student panorama, student close-up, blackboard close-up, etc., and transmit these all-round images to the recording and broadcasting host, which will handle all AI analysis tasks (or additional computing power boxes). However, in addition to handling AI analysis tasks, the recording and broadcasting host is also responsible for scheduling tasks such as automatic image switching and processing of various video streams. This undoubtedly places extremely high demands on the computing power performance of the recording and broadcasting host, increases the risk of failure, and also pushes up the overall hardware cost. Summary of the invention

[0004] In order to solve the technical problem of improving the stability and reliability of the system and reducing the overall performance requirements of the hardware, the present invention provides a method, device, equipment and storage medium for collaborative processing of tasks by a recording and broadcasting host and a camera. The technical solution adopted by the present invention is as follows.

[0005] In a first aspect, the present invention provides a method for a recording and broadcasting host and a camera to collaboratively process a task, comprising:

[0006] Receive an AI analysis task of the docked platform, wherein the AI ​​analysis task includes at least one platform subtask;

[0007] Matching with the first relationship correspondence table to obtain the camera corresponding to each platform subtask in the AI ​​analysis task, wherein the first relationship correspondence table is an association list of all platform subtasks and corresponding cameras;

[0008] Package the platform subtasks that each camera is responsible for and assign them to the corresponding cameras;

[0009] Receive AI analysis data returned by each camera;

[0010] Aggregate all AI analysis data to the docking platform.

[0011] In one embodiment, it further includes:

[0012] Determine the triggered temporary tasks based on the received AI analysis data;

[0013] When a temporary task is triggered, matching is performed with the second relationship correspondence table to obtain the camera corresponding to each temporary subtask in the triggered temporary task, wherein the second relationship correspondence table is an association list of all temporary subtasks and corresponding cameras;

[0014] The temporary subtasks that each camera is responsible for are packaged and distributed to the corresponding camera, and the camera is instructed to execute the temporary subtasks first.

[0015] In one embodiment, the process of determining the triggered temporary task based on the received AI analysis data includes:

[0016] The scene results are obtained based on the AI ​​analysis data set returned by each camera;

[0017] Determine the triggered temporary tasks based on the scenario results.

[0018] In one embodiment, it further includes:

[0019] Determine whether the temporary task is completed based on the received AI analysis data;

[0020] When the temporary task ends, the corresponding camera is notified to stop executing the temporary subtask and continue to execute the original docking platform subtask.

[0021] In one embodiment, it further includes:

[0022] Determine the camera type required for each platform subtask;

[0023] Mark each camera with its corresponding camera type;

[0024] According to the camera type marked by each camera and the camera type required by each platform subtask, the platform subtask is associated with the corresponding camera, and a first relationship correspondence table is generated.

[0025] In one embodiment, it further includes:

[0026] Determine the type of camera required for each temporary subtask;

[0027] Mark each camera with its corresponding camera type;

[0028] According to the camera type marked by each camera and the camera type required by each temporary subtask, the temporary subtask is associated with the corresponding camera, and a second relationship correspondence table is generated.

[0029] In a second aspect, the present invention provides a device for collaboratively processing tasks between a recording and broadcasting host and a camera, comprising:

[0030] A first receiving module, configured to receive an AI analysis task of a docked platform, wherein the AI ​​analysis task includes at least one platform subtask;

[0031] A first matching module, used for matching with a first relationship correspondence table to obtain the camera corresponding to each platform subtask in the AI ​​analysis task, wherein the first relationship correspondence table is an association list of all platform subtasks and corresponding cameras;

[0032] The first allocation module is used to package the platform subtasks that each camera is responsible for and allocate them to the corresponding camera;

[0033] The second receiving module is used to receive AI analysis data returned by each camera;

[0034] The summary and sending module is used to summarize all AI analysis data to the docking platform.

[0035] In one embodiment, it further includes:

[0036] The analysis module is used to determine the triggered temporary tasks based on the received AI analysis data;

[0037] A second matching module is used to match with the second relationship correspondence table when a temporary task is triggered, and obtain the camera corresponding to each temporary subtask in the triggered temporary task, wherein the second relationship correspondence table is an association list of all temporary subtasks and corresponding cameras;

[0038] The second allocation module is used to package the temporary subtasks that each camera is responsible for and allocate them to the corresponding camera, and instruct the camera to execute the temporary subtasks first.

[0039] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned methods when executing the program.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method of any of the above-mentioned embodiments.

[0041] In the present invention, a distributed computing power collaboration method is adopted to share part of the AI ​​analysis tasks by utilizing the hardware performance of the camera, thereby reducing the burden on the recording and broadcasting host, while the recording and broadcasting host focuses on unified scheduling, processing multi-screen video streams and AI analysis data, etc. This distributed computing power collaboration not only improves the stability and reliability of the system, but also effectively reduces the overall hardware cost by optimizing resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the overall flow of an implementation method of Example 1 of the present invention.

[0043] Figure 2 This is a diagram of an applicable application environment of the first embodiment of the present invention.

[0044] Figure 3 This is a schematic diagram of the first relationship correspondence of the first embodiment of the present invention.

[0045] Figure 4 It is a schematic diagram of the overall structure of an implementation method of Example 21 of the present invention. DETAILED DESCRIPTION

[0046] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0047] It should be noted that the terms "first\second\..." involved in the embodiments of the present invention are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\..." can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\..." can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0048] Embodiment 1

[0049] See also Figure 1 , Figure 1 A flowchart of a method for collaboratively processing tasks between a recording and broadcasting host and a camera provided in Embodiment 1 of the present invention, the method comprising step S110, step S120, step S130, step S140 and step S150. It should be noted that step S110, step S120, step S130, step S140 and step S150 are merely reference numerals for clarifying the embodiment and the appendix. Figure 1The corresponding relationship does not limit the order of the steps in this embodiment.

[0050] Step S110, receiving an AI analysis task of the docked platform, wherein the AI ​​analysis task includes at least one platform subtask;

[0051] Step S120, matching with the first relationship correspondence table to obtain the camera corresponding to each platform subtask in the AI ​​analysis task, wherein the first relationship correspondence table is an association list of all platform subtasks and corresponding cameras;

[0052] Step S130, packaging the platform subtasks that each camera is responsible for and distributing them to the corresponding camera;

[0053] Step S140, receiving AI analysis data returned by each camera;

[0054] Step S150, aggregate all AI analysis data to the docking platform.

[0055] like Figure 2 As shown, Figure 2 This is an application environment diagram applicable to this method, including: a business platform, a recording and broadcasting host, and various cameras. The business platform is used to interact with users, issue AI analysis tasks according to user operations, receive video content and the results of AI analysis tasks, and present the video content analysis results. In addition to shooting video images, the camera in this method can also perform a separate AI analysis on its own video images to obtain analysis results. The recording and broadcasting host is used to distribute AI analysis tasks to each camera, and receive and summarize the AI ​​analysis results of each camera. This method is used in the recording and broadcasting host. As mentioned earlier, in addition to shooting and transmitting video images, the camera also performs a separate AI analysis on its own video images to obtain and transmit analysis results, but this method is mainly for scheduling the AI ​​analysis part, so the following description also focuses on the AI ​​analysis part, and the conventional image transmission part is not elaborated.

[0056] The business platform initiates an AI analysis task, such as recording and analyzing the teaching and learning situation of a class. This analysis task is the AI ​​analysis general task. The AI ​​analysis general task covers a variety of tasks, for example, including sub-tasks related to teachers, such as teachers' teaching quality, teaching posture and emotion, interactive feedback, PPT and blackboard analysis, classroom management and other dimensions; and sub-tasks related to student learning situation analysis, such as students' head-up rate, concentration, participation, standing and raising hands, classroom atmosphere and observation of individual students. In step S110, the general analysis task sent by the docked business platform is received.

[0057] In step S120, after receiving the total AI analysis task, the recording and broadcasting host breaks it down into multiple subtasks and assigns them to the corresponding cameras. For example, individual student observation tasks such as student expressions, student hand raising, student response, and student table lying behavior recognition in each group (or area) are split and summarized by the recording and broadcasting host and assigned to the student close-up camera.

[0058] like Figure 3 As shown, Figure 3 This is a schematic diagram of the first relationship correspondence. In the figure, the subtask set {Task_1~Task_n} is associated with the camera set {Camera_1~Camera_m} to generate a relationship correspondence table (Note: 1 subtask is executed by ≥1 camera). For example, the total AI analysis task includes subtasks Task_2, Task_3, Task_6 and Task_n (i.e. Figure 3 The gray background part in the middle), then in step S120, the above subtasks are matched with the corresponding cameras in the table to obtain the cameras corresponding to the subtasks in the AI ​​analysis task, such as Task_2, the corresponding camera is Camera_1; for Task_3, the corresponding camera is Camera_2; for Task_6, the corresponding cameras are Camera_1 and Camera_2; for Task_n, the corresponding camera is Camera_m.

[0059] Step S130 packages the subtasks that each camera is responsible for and distributes them to the corresponding camera according to the task matching result of step S120, for example:

[0060] Camera_1: {Task_2, Task_6};

[0061] Camera_2: {Task_3, Task_6};

[0062] Camera_m:{Task_n}.

[0063] After receiving the task, each camera starts to execute the subtask. For example, after receiving the subtask of individual observation, the camera will shoot according to the preset cruise path and identify the expressions, hand raising, answering, lying on the table and other behaviors of students in each group (or area). Then, the AI ​​analysis data is transmitted back to the recording and broadcasting host in real time, and the recording and broadcasting host receives the AI ​​analysis data returned by each camera according to the platform subtask it is responsible for.

[0064] In step S150, the recording and broadcasting host centrally processes all AI analysis data, and then connects with the business platform to display the analysis results and provide data support for teaching evaluation and improvement.

[0065] In this method, a distributed computing power collaboration method is adopted to share part of the AI ​​analysis tasks by utilizing the hardware performance of the camera, thereby reducing the burden on the recording and broadcasting host, while the recording and broadcasting host focuses on unified scheduling, processing multi-screen video streams and AI analysis data, etc. This distributed computing power collaboration not only improves the stability and reliability of the system, but also effectively reduces the overall hardware cost by optimizing resource allocation.

[0066] In one implementation, the method for the recording and broadcasting host and the camera to collaboratively process tasks further includes: step S210, step S220, and step S230.

[0067] Step S210, determining the triggered temporary task according to the received AI analysis data;

[0068] Step S220, when a temporary task is triggered, matching is performed with the second relationship correspondence table to obtain the camera corresponding to each temporary subtask in the triggered temporary task, wherein the second relationship correspondence table is an association list of all temporary subtasks and corresponding cameras;

[0069] Step S230: Pack the temporary subtasks that each camera is responsible for and distribute them to the corresponding camera, and instruct the camera to execute the temporary subtasks first.

[0070] In this implementation, the recording and broadcasting host flexibly schedules tasks based on the AI ​​analysis data transmitted back by each camera in real time. For example, the student panoramic camera is responsible for identifying and analyzing the global situation of the student area. Once it recognizes that a student is standing to answer, it will send the identification result and location information to the recording and broadcasting host. The recording and broadcasting host then sends a new analysis instruction to the student close-up camera, requiring it to take close-up photos and perform individual analysis on students in specific locations. The student close-up camera then pauses the current task, focuses on close-up photography and analysis of the designated students, and transmits the results back to the recording and broadcasting host in real time. Then, the recording and broadcasting host continues to flexibly adjust tasks based on the real-time data returned by each camera.

[0071] Specifically, each camera executes the currently assigned platform subtask and returns the analysis data Data_1 to Data_m to the recording and broadcasting host in real time. In step S210, the recording and broadcasting host confirms whether there is a triggered temporary person according to the returned data set {Data_1 to Data_m}, and if so, what is the currently triggered temporary task, for example {T-Task_1 to T-Task_x}.

[0072] When a temporary task is triggered, as in the previous step S120, the second relationship table is matched to obtain the cameras {Camera_1 to Camera_m} corresponding to each temporary subtask in the triggered temporary task. Then, as in step S130, the temporary subtasks for each camera are packaged and assigned to the corresponding camera.

[0073] Cameras without temporary subtasks are allowed to continue to execute the originally assigned platform subtasks; cameras with temporary subtasks are required to give priority to running temporary subtasks when temporary tasks are assigned. The cameras continue to execute the originally assigned platform subtasks until the task is completed or the recording and broadcasting host notifies the cancellation of the task.

[0074] At the same time, receive the AI ​​analysis data returned by each camera according to the temporary subtask it is responsible for. It should be noted here that the AI ​​analysis data returned by each camera received in step S140 includes both the AI ​​analysis data returned by the platform subtask and the AI ​​analysis data returned by the temporary subtask; in addition, the basis for judging the triggered temporary task in step S210 also includes both the AI ​​analysis data returned by the platform subtask and the AI ​​analysis data returned by the temporary subtask. It should be pointed out here that it is possible that some temporary subtasks do not need to return AI analysis data, so step S140 does not need to receive the data of this part of the temporary subtask.

[0075] In one implementation, the process of step S210 includes: step S211 and step S212.

[0076] Step S211, obtaining a scene result according to the AI ​​analysis data set returned by each camera;

[0077] Step S212, determining the triggered temporary task according to the scenario result.

[0078] In this embodiment, the relationship between the AI ​​analysis data set and different scenes is defined in advance, and the relationship between different scenes and each temporary task is defined. Then, based on the AI ​​analysis data set returned by each camera, the different scene conditions represented by it are obtained, so as to determine the triggered temporary task.

[0079] In one implementation, the method for the recording and broadcasting host and the camera to collaboratively process tasks further includes: step S240 and step S250.

[0080] Step S240, judging whether the temporary task is completed according to the received AI analysis data;

[0081] Step S250: When the temporary task ends, the corresponding camera is notified to stop executing the temporary subtask and continue to execute the original docking platform subtask.

[0082] As mentioned above, some temporary tasks can be terminated automatically, while some temporary tasks need to be determined based on the returned AI analysis data to determine whether they need to be terminated. This implementation is optimized for the latter situation. In this implementation, when it is determined that a temporary task is to be terminated based on the received AI analysis data, the corresponding camera is notified to stop the temporary task and the camera continues to execute the originally assigned platform subtask.

[0083] In one implementation, the method for the recording and broadcasting host and the camera to collaboratively process tasks further includes: step S310, step S320, and step S330.

[0084] Step S310, determining the camera type required for each platform subtask;

[0085] Step S320, marking each camera with its corresponding camera type;

[0086] Step S330 , according to the camera type marked by each camera and the camera type required by each platform subtask, the platform subtask is associated with the corresponding camera, and a first relationship correspondence table is generated.

[0087] This embodiment is a process of how to generate the first relationship correspondence table. In step S310, all subtasks related to the camera are defined as: Task_1~Task_n, and Figure 3 In this way, the camera type required for each platform subtask is determined. In step S320, all cameras are defined as: Camera_1~Camera_m, and then the properties of each camera are defined according to the actual scene, for example, Camera_1 is the teacher's panoramic camera, Camera_2 is the teacher's close-up camera, Camera_3 is the student's panoramic camera... Finally, in step S330, the subtask set {Task_1~Task_n} is associated with the camera set {Camera_1~Camera_m} to generate a relationship correspondence table (Note: 1 subtask is executed by ≥1 camera).

[0088] In one implementation, the method for the recording and broadcasting host and the camera to collaboratively process tasks further includes: step S410, step S420, and step S430.

[0089] Step S410, determining the camera type required for each temporary subtask;

[0090] Step S420, marking each camera with its corresponding camera type;

[0091] Step S430 , according to the camera type marked by each camera and the camera type required by each temporary subtask, associate the temporary subtask with the corresponding camera, and generate a second relationship correspondence table.

[0092] This implementation method is the process of how to generate the second relationship correspondence table. Receive the analysis data Data_1~Data_m returned by the camera in real time. Step S410 defines multiple temporary subtasks according to the different scene conditions represented by the data sets returned by each camera. All temporary subtasks are defined as: T-Task_1~T-Task_x, and then the camera type required for each platform subtask is determined. In step S420, all camera positions are defined as: Camera_1~Camera_m, and then the properties of each camera are defined according to the actual scene. For example, Camera_1 is a teacher's panoramic camera, Camera_2 is a teacher's close-up camera, Camera_3 is a student's panoramic camera... Finally, in step S430, the temporary task set {T-Task_1~T-Task_x} is associated with the camera set {Camera_1~Camera_m} to generate a second relationship correspondence table.

[0093] Embodiment 2

[0094] Corresponding to the method of embodiment 1, as Figure 4 As shown, the present invention also provides a device 4 for collaboratively processing tasks between a recording and broadcasting host and a camera, comprising: a first receiving module 410, a first matching module 420, a first allocation 430, a second receiving module 440 and a summary sending module 450.

[0095] A first receiving module 410 is used to receive an AI analysis task of a docked platform, wherein the AI ​​analysis task includes at least one platform subtask;

[0096] A first matching module 420 is used to match with a first relationship correspondence table to obtain the camera corresponding to each platform subtask in the AI ​​analysis task, wherein the first relationship correspondence table is an association list of all platform subtasks and corresponding cameras;

[0097] A first allocation module 430 is used to package the platform subtasks that each camera is responsible for and allocate them to the corresponding camera;

[0098] The second receiving module 440 is used to receive AI analysis data returned by each camera;

[0099] The aggregation and sending module 450 is used to aggregate all AI analysis data to the docking platform.

[0100] In one embodiment, the device for the recording and broadcasting host and the camera to collaboratively process tasks further includes:

[0101] The analysis module is used to determine the triggered temporary tasks based on the received AI analysis data;

[0102] A second matching module is used to match with the second relationship correspondence table when a temporary task is triggered, and obtain the camera corresponding to each temporary subtask in the triggered temporary task, wherein the second relationship correspondence table is an association list of all temporary subtasks and corresponding cameras;

[0103] The second allocation module is used to package the temporary subtasks that each camera is responsible for and allocate them to the corresponding camera, and instruct the camera to execute the temporary subtasks first.

[0104] In one embodiment, the analysis module performs the process of determining the triggered temporary task based on the received AI analysis data, including:

[0105] The scene results are obtained based on the AI ​​analysis data set returned by each camera;

[0106] Determine the triggered temporary tasks based on the scenario results.

[0107] In one embodiment, the analysis module is also used to determine whether the temporary task is completed based on the received AI analysis data; when the temporary task is completed, notify the corresponding camera to stop executing the temporary subtask and continue to execute the original docking platform subtask.

[0108] In one embodiment, the device for the recording and broadcasting host and the camera to collaboratively process tasks further includes:

[0109] The first relationship correspondence table generation module is used to determine the camera type required for each platform subtask; mark each camera with its corresponding camera type; according to the camera type marked by each camera and the camera type required for each platform subtask, associate the platform subtask with the corresponding camera, and generate a first relationship correspondence table.

[0110] In one embodiment, the device for the recording and broadcasting host and the camera to collaboratively process tasks further includes:

[0111] The second relationship correspondence table generation module is used to determine the camera type required for each temporary subtask; mark each camera with its corresponding camera type; according to the camera type marked by each camera and the camera type required for each temporary subtask, associate the temporary subtask with the corresponding camera, and generate a second relationship correspondence table.

[0112] In this device, a distributed computing power collaboration method is adopted to share part of the AI ​​analysis tasks by utilizing the hardware performance of the camera, thereby reducing the burden on the recording and broadcasting host, while the recording and broadcasting host focuses on unified scheduling, processing multi-screen video streams and AI analysis data, etc. This distributed computing power collaboration not only improves the stability and reliability of the system, but also effectively reduces the overall hardware cost by optimizing resource allocation.

[0113] Embodiment 3

[0114] An embodiment of the present invention further provides a storage medium on which computer instructions are stored. When the instructions are executed by a processor, the method for collaboratively processing tasks between a recording and broadcasting host and a camera in any of the above embodiments is implemented.

[0115] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, random access memories (RAM), read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0116] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, RAM, ROM, magnetic disks or optical disks.

[0117] Corresponding to the above-mentioned computer storage medium, in one embodiment, a computer device is also provided, which includes a memory, an encoder, and a computer program stored in the memory and executable on the encoder, wherein when the encoder executes the program, any one of the hand-raising behaviors described in the above-mentioned embodiments is detected.

[0118] The above-mentioned computer equipment adopts a distributed computing power collaboration method, and uses the camera hardware performance to share part of the AI ​​analysis tasks, thereby reducing the burden on the recording and broadcasting host, while the recording and broadcasting host focuses on unified scheduling, processing multi-screen video streams and AI analysis data, etc. This distributed computing power collaboration not only improves the stability and reliability of the system, but also effectively reduces the overall hardware cost by optimizing resource allocation.

[0119] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0120] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for collaboratively processing tasks between a recording and broadcasting host and a camera, characterized in that: include: Receive an AI analysis task of the docked platform, wherein the AI ​​analysis task includes at least one platform subtask; Matching with the first relationship correspondence table to obtain the camera corresponding to each platform subtask in the AI ​​analysis task, wherein the first relationship correspondence table is an association list of all platform subtasks and corresponding cameras; Package the platform subtasks that each camera is responsible for and assign them to the corresponding cameras; Receive AI analysis data returned by each camera; Aggregate all AI analysis data to the docking platform.

2. The method for collaboratively processing tasks between a recording and broadcasting host and a camera according to claim 1, characterized in that: Also includes: Determine the triggered temporary tasks based on the received AI analysis data; When a temporary task is triggered, matching is performed with the second relationship correspondence table to obtain the camera corresponding to each temporary subtask in the triggered temporary task, wherein the second relationship correspondence table is an association list of all temporary subtasks and corresponding cameras; The temporary subtasks that each camera is responsible for are packaged and distributed to the corresponding camera, and the camera is instructed to execute the temporary subtasks first.

3. The method for collaboratively processing tasks between a recording and broadcasting host and a camera according to claim 2, characterized in that: The process of determining the triggered temporary task based on the received AI analysis data includes: The scene results are obtained based on the AI ​​analysis data set returned by each camera; Determine the triggered temporary tasks based on the scenario results.

4. The method for collaboratively processing tasks between a recording and broadcasting host and a camera according to claim 2, characterized in that: Also includes: Determine whether the temporary task is completed based on the received AI analysis data; When the temporary task ends, the corresponding camera is notified to stop executing the temporary subtask and continue to execute the original docking platform subtask.

5. The method for collaboratively processing tasks between a recording and broadcasting host and a camera according to any one of claims 1 to 4, characterized in that: Also includes: Determine the camera type required for each platform subtask; Mark each camera with its corresponding camera type; According to the camera type marked by each camera and the camera type required by each platform subtask, the platform subtask is associated with the corresponding camera, and a first relationship correspondence table is generated.

6. The method for collaboratively processing tasks by a recording and broadcasting host and a camera according to any one of claims 1 to 4, characterized in that: Also includes: Determine the type of camera required for each temporary subtask; Mark each camera with its corresponding camera type; According to the camera type marked by each camera and the camera type required by each temporary subtask, the temporary subtask is associated with the corresponding camera, and a second relationship correspondence table is generated.

7. A device for collaboratively processing tasks between a recording and broadcasting host and a camera, characterized in that: include: A first receiving module, configured to receive an AI analysis task of a docked platform, wherein the AI ​​analysis task includes at least one platform subtask; A first matching module, used for matching with a first relationship correspondence table to obtain the camera corresponding to each platform subtask in the AI ​​analysis task, wherein the first relationship correspondence table is an association list of all platform subtasks and corresponding cameras; The first allocation module is used to package the platform subtasks that each camera is responsible for and allocate them to the corresponding camera; The second receiving module is used to receive AI analysis data returned by each camera; The summary and sending module is used to summarize all AI analysis data to the docking platform.

8. The device for collaboratively processing tasks between a recording and broadcasting host and a camera according to claim 7, characterized in that: Also includes: The analysis module is used to determine the triggered temporary tasks based on the received AI analysis data; A second matching module is used to match with the second relationship correspondence table when a temporary task is triggered, and obtain the camera corresponding to each temporary subtask in the triggered temporary task, wherein the second relationship correspondence table is an association list of all temporary subtasks and corresponding cameras; The second allocation module is used to package the temporary subtasks that each camera is responsible for and allocate them to the corresponding camera, and instruct the camera to execute the temporary subtasks first.

9. A computer device 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 program, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images