A task processing system, method, apparatus, electronic device and storage medium

Abstract

Embodiments of the present application provide a task processing system, method, device, electronic equipment and storage medium. The system comprises a server and a non-dedicated terminal, and the non-dedicated terminal is deployed with an intelligent scheduling terminal agent. The server is configured to issue a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent. The intelligent scheduling terminal agent is configured to receive the target intelligent analysis task and the intelligent analysis algorithm, adopt the intelligent analysis algorithm, and process the target intelligent analysis task by using the computing power of the non-dedicated terminal. Instead of deploying a dedicated intelligent computing device, the computing power of the non-dedicated terminal is used to process the target intelligent analysis task by deploying the intelligent scheduling terminal agent on the non-dedicated terminal, thereby greatly reducing the deployment cost of the intelligent task processing system. At the same time, the computing resources of the non-dedicated terminal can be effectively utilized by using the computing power of the non-dedicated terminal, thereby greatly improving the utilization rate of the computing resources of the non-dedicated terminal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent analysis, in particular to a task processing system, method, device, electronic equipment and storage medium. BACKGROUND

[0002] With the rapid development of artificial intelligence technology, more and more enterprises, individuals, etc. have appeared the demand of deploying intelligent task processing system, for example, schools, companies, special units, etc.

[0003] At present, the deployment of intelligent task processing system needs to purchase special intelligent operation equipment and deploy in the computer room. For example, for the scene needing image processing, special GPU (Graphics Processing Unit, graphics processing unit) processing equipment needs to be purchased and deployed in the computer room. However, the cost of special intelligent operation equipment is high, which seriously restricts the realization of intelligence by users and is not conducive to the development of intelligent technology. SUMMARY

[0004] The purpose of the embodiment of the present application is to provide a task processing system, method, device, electronic equipment and storage medium, so as to reduce the deployment cost of intelligent task processing system, which is conducive to the realization of intelligence and the development of intelligent technology. The specific technical scheme is as follows:

[0005] In the first aspect, the embodiment of the present application provides a task processing system, which comprises a server and a non-special terminal, wherein the non-special terminal is deployed with an intelligent scheduling terminal agent;

[0006] The server is configured to issue a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent.

[0007] The intelligent scheduling terminal agent is configured to receive the target intelligent analysis task and the intelligent analysis algorithm, adopt the intelligent analysis algorithm, and process the target intelligent analysis task by using the computing power of the non-special terminal.

[0008] Optionally, the intelligent scheduling terminal agent is further configured to report terminal computing resources of the non-special terminal to the server, wherein the terminal computing resources include residual resources.

[0009] The server is specifically configured to determine a target intelligent analysis task from the tasks to be processed based on the computing resources required by each task to be processed and the residual resources, and issue the target intelligent analysis task and the intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent.

[0010] Optionally, the terminal computing resources further include total resources.

[0011] The intelligent scheduling terminal agent is further configured to detect a resource occupation rate of the non-dedicated terminal, and send a request for reducing the resource occupation rate to the server when the resource occupation rate reaches a first preset ratio;

[0012] The server is further configured to, when receiving the request for reducing the resource occupation rate, determine a task adjustment strategy based on total resources of the non-dedicated terminal, the first preset ratio and a second preset ratio, and adjust a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so as to reduce the resource occupation rate of the non-dedicated terminal to the second preset ratio.

[0013] Optionally, the server is further configured to send a state query message to the intelligent scheduling terminal agent.

[0014] The intelligent scheduling terminal agent is further configured to report a processing state of the target intelligent analysis task to the server when receiving the state query message.

[0015] The server is further configured to, when determining that processing of the target intelligent analysis task is abnormal based on the processing state, distribute the target intelligent analysis task to another non-dedicated terminal, so that the another non-dedicated terminal continues to process the target intelligent analysis task.

[0016] Optionally, the server is deployed with an intelligent scheduling center service.

[0017] The intelligent scheduling center service is configured to distribute a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent.

[0018] In a second aspect, an embodiment of the present application provides a task processing method applied to an intelligent scheduling terminal agent deployed by a non-dedicated terminal in a task processing system, the system further comprising a server, and the method comprising:

[0019] receiving a target intelligent analysis task and an intelligent analysis algorithm distributed by the server;

[0020] processing the target intelligent analysis task by using the intelligent analysis algorithm and the computing power of the non-dedicated terminal.

[0021] Optionally, the method further comprises:

[0022] reporting terminal computing resources of the non-dedicated terminal to the server, so that the server determines a target intelligent analysis task from each to-be-processed task based on computing resources required by each to-be-processed task and remaining resources, and distributes the target intelligent analysis task and an intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent; wherein the terminal computing resources include the remaining resources.

[0023] Optionally, the terminal computing resources further include total resources; and the method further includes:

[0024] detecting a resource occupancy rate of the non-dedicated terminal;

[0025] when the resource occupancy rate reaches a first preset ratio, sending a request for reducing the resource occupancy rate to the server, so that the server determines a task adjustment strategy based on total resources of the non-dedicated terminal, the first preset ratio and a second preset ratio when receiving the request for reducing the resource occupancy rate, and adjusts a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupancy rate of the non-dedicated terminal is reduced to the second preset ratio.

[0026] Optionally, the method further includes:

[0027] receiving a state query message sent by the server;

[0028] when receiving the state query message, reporting a processing state of the target intelligent analysis task to the server, so that the server distributes the target intelligent analysis task to another non-dedicated terminal to continue processing the target intelligent analysis task when determining that processing of the target intelligent analysis task is abnormal based on the processing state.

[0029] Optionally, the server is deployed with an intelligent scheduling center service; and the step of receiving the target intelligent analysis task and the intelligent analysis algorithm distributed by the server includes:

[0030] receiving the target intelligent analysis task and the intelligent analysis algorithm distributed by the intelligent scheduling center service.

[0031] In a third aspect, an embodiment of the present application provides a task processing method applied to a server in a task processing system, the system further including a non-dedicated terminal, wherein the non-dedicated terminal is deployed with an intelligent scheduling terminal agent, and the method includes:

[0032] determining an intelligent analysis algorithm corresponding to a target intelligent analysis task;

[0033] distribute the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, adopts the intelligent analysis algorithm, and processes the target intelligent analysis task by using the computing power of the non-dedicated terminal.

[0034] Optionally, the method further comprises:

[0035] receiving the terminal computing resource of the non-dedicated terminal reported by the intelligent scheduling terminal agent, wherein the terminal computing resource comprises a remaining resource;

[0036] The step of determining the intelligent analysis algorithm corresponding to the target intelligent analysis task comprises:

[0037] determining the target intelligent analysis task from the tasks to be processed and determining the intelligent analysis algorithm corresponding to the target intelligent analysis task based on the computing resource required by each task to be processed and the remaining resource.

[0038] Optionally, the terminal computing resource further comprises a total resource; and the method further comprises:

[0039] receiving a request for reducing resource occupancy rate sent by the intelligent scheduling terminal agent, wherein the request for reducing resource occupancy rate is sent by the intelligent scheduling terminal agent when the intelligent scheduling terminal agent detects that the resource occupancy rate of the non-dedicated terminal reaches a first preset ratio;

[0040] determining a task adjustment strategy based on the total resource of the non-dedicated terminal, the first preset ratio and a second preset ratio;

[0041] adjusting a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupancy rate of the non-dedicated terminal is reduced to the second preset ratio.

[0042] Optionally, the method further comprises:

[0043] sending a state query message to the intelligent scheduling terminal agent;

[0044] receiving a processing state of the target intelligent analysis task reported by the intelligent scheduling terminal agent;

[0045] when it is determined that the processing of the target intelligent analysis task is abnormal based on the processing state, distributing the target intelligent analysis task to another non-dedicated terminal, so that the other non-dedicated terminal continues to process the target intelligent analysis task.

[0046] Optionally, the server is deployed with an intelligent scheduling center service; the step of issuing the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent comprises:

[0047] The intelligent scheduling center service issues the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent.

[0048] In a fourth aspect, an embodiment of the present application provides a task processing apparatus applied to an intelligent scheduling terminal agent of a non-dedicated terminal deployed in a task processing system, the system further comprising a server, wherein the apparatus comprises:

[0049] a task receiving module configured to receive a target intelligent analysis task and an intelligent analysis algorithm issued by the server;

[0050] a task processing module configured to process the target intelligent analysis task by using the intelligent analysis algorithm and the computing power of the non-dedicated terminal.

[0051] Optionally, the apparatus further comprises:

[0052] a computing resource reporting module configured to report terminal computing resources of the non-dedicated terminal to the server, so that the server determines a target intelligent analysis task from each task to be processed based on computing resources required by the each task to be processed and remaining resources, and issues the target intelligent analysis task and an intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent; wherein the terminal computing resources comprise the remaining resources.

[0053] Optionally, the terminal computing resources further comprise total resources; and the apparatus further comprises:

[0054] an occupancy rate detecting module configured to detect a resource occupancy rate of the non-dedicated terminal;

[0055] an occupancy rate reduction request sending module configured to send a resource occupancy rate reduction request to the server when the resource occupancy rate reaches a first preset ratio, so that the server determines a task adjustment strategy based on total resources of the non-dedicated terminal, the first preset ratio and a second preset ratio when receiving the resource occupancy rate reduction request, and adjusts a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupancy rate of the non-dedicated terminal is reduced to the second preset ratio.

[0056] Optionally, the apparatus further comprises:

[0057] a query message receiving module configured to receive a state query message sent by the server;

[0058] The state reporting module is configured to report the processing state of the target intelligent analysis task to the server when the state query message is received, so that the server determines that the processing of the target intelligent analysis task is abnormal based on the processing state, and then distributes the target intelligent analysis task to other non-dedicated terminals to enable the other non-dedicated terminals to continue processing the target intelligent analysis task.

[0059] Optionally, the server is deployed with an intelligent scheduling center service; and the task receiving module comprises:

[0060] The task receiving unit is configured to receive a target intelligent analysis task and an intelligent analysis algorithm distributed by the intelligent scheduling center service.

[0061] In a fifth aspect, an embodiment of the present application provides a task processing apparatus applied to a server in a task processing system, wherein the system further comprises a non-dedicated terminal, and the non-dedicated terminal is deployed with an intelligent scheduling terminal agent, and the apparatus comprises:

[0062] The task determining module is configured to determine an intelligent analysis algorithm corresponding to a target intelligent analysis task.

[0063] The task distribution module is configured to distribute the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, adopts the intelligent analysis algorithm, and processes the target intelligent analysis task by using the computing power of the non-dedicated terminal.

[0064] Optionally, the apparatus further comprises:

[0065] The computing resource receiving module is configured to receive terminal computing resources of the non-dedicated terminal reported by the intelligent scheduling terminal agent, wherein the terminal computing resources comprise residual resources.

[0066] The task determining module comprises:

[0067] The task determining unit is configured to determine a target intelligent analysis task from the tasks to be processed based on the computing resources required by the tasks to be processed and the residual resources, and determine an intelligent analysis algorithm corresponding to the target intelligent analysis task.

[0068] Optionally, the terminal computing resources further comprise total resources; and the apparatus further comprises:

[0069] The resource reduction request receiving module is configured to receive a resource occupation rate reduction request sent by the intelligent scheduling terminal agent, wherein the resource occupation rate reduction request is sent by the intelligent scheduling terminal agent when the intelligent scheduling terminal agent detects that the resource occupation rate of the non-dedicated terminal reaches a first preset ratio.

[0070] an adjustment policy determining module, configured to determine a task adjustment policy based on the total resource of the non-dedicated terminal, the first preset ratio and a second preset ratio;

[0071] a task adjustment module, configured to adjust a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment policy, so as to reduce the resource occupation ratio of the non-dedicated terminal to the second preset ratio.

[0072] Optionally, the apparatus further comprises:

[0073] a query message sending module, configured to send a state query message to the intelligent scheduling terminal agent;

[0074] a processing state receiving module, configured to receive a processing state of the target intelligent analysis task reported by the intelligent scheduling terminal agent;

[0075] an exception handling module, configured to, when it is determined that the processing of the target intelligent analysis task is abnormal based on the processing state, distribute the target intelligent analysis task to other non-dedicated terminals, so as to enable the other non-dedicated terminals to continue processing the target intelligent analysis task.

[0076] Optionally, the server can be deployed with an intelligent scheduling center service; and the task distribution module comprises:

[0077] a task distribution unit, configured to distribute a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent through the intelligent scheduling center service.

[0078] In a sixth aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;

[0079] the memory is configured to store a computer program;

[0080] the processor is configured to execute the program stored on the memory, so as to implement the method steps of the second aspect or the third aspect.

[0081] In a seventh aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method steps of the second aspect or the third aspect.

[0082] The embodiments of the present application have the following beneficial effects:

[0083] In the solution provided by this invention, the task processing system includes a server and a non-dedicated terminal. The non-dedicated terminal is equipped with an intelligent scheduling terminal agent. The server can distribute target intelligent analysis tasks and intelligent analysis algorithms to the intelligent scheduling terminal agent. The intelligent scheduling terminal agent can then receive the target intelligent analysis tasks and intelligent analysis algorithms, employ the intelligent analysis algorithms, and utilize the computing power of the non-dedicated terminal to process the target intelligent analysis tasks. This eliminates the need for dedicated intelligent computing equipment; instead, the user's non-dedicated terminal is used. By deploying an intelligent scheduling terminal agent on the non-dedicated terminal, the computing power of the non-dedicated terminal is utilized to process the target intelligent analysis tasks, significantly reducing the deployment cost of the intelligent task processing system. Simultaneously, by utilizing the computing power of the non-dedicated terminal, its computing resources can be effectively utilized, greatly improving the utilization rate of the non-dedicated terminal's computing resources. Of course, implementing any product or method of this invention does not necessarily require achieving all of the above-described advantages simultaneously. Attached Figure Description

[0084] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0085] Figure 1 This is a schematic diagram of the structure of a task processing system provided in an embodiment of the present invention;

[0086] Figure 2 Based on Figure 1 Another schematic diagram of the task processing system in the illustrated embodiment;

[0087] Figure 3 Based on Figure 1 A flowchart of the task processing process of the task processing system in the illustrated embodiment;

[0088] Figure 4 Based on Figure 1 A flowchart illustrating a terminal computing power adaptive adjustment method for a task processing system in the illustrated embodiment;

[0089] Figure 5 A flowchart of the first task processing method provided in the embodiments of the present invention;

[0090] Figure 6 A flowchart of the second task processing method provided in the embodiments of the present invention;

[0091] Figure 7 This is a schematic diagram of the structure of the first task processing device provided in an embodiment of the present invention;

[0092] Figure 8 This is a schematic diagram of the structure of the second task processing device provided in an embodiment of the present invention;

[0093] Figure 9 This is a schematic diagram of the structure of a non-dedicated terminal provided in an embodiment of the present invention;

[0094] Figure 10 This is a schematic diagram of the structure of a server provided in an embodiment of the present invention. Detailed Implementation

[0095] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of the present invention.

[0096] To reduce the deployment cost of intelligent task processing systems and facilitate the development of intelligentization and intelligent technologies, embodiments of the present invention provide a task processing system, method, apparatus, server, non-dedicated terminal, computer-readable storage medium, and computer program product. The task processing system provided by the embodiments of the present invention will be introduced first below.

[0097] The task processing system provided in this embodiment of the invention can be used for any task requiring intelligent analysis and processing. It can be a video processing task, such as target behavior analysis, face recognition, traffic event detection, etc. It can also be an image processing task, such as image classification, image feature extraction, target detection, etc. Furthermore, it can be a speech processing task, such as semantic recognition, speaker recognition, speech denoising, etc., without specific limitations.

[0098] like Figure 1 As shown, a task processing system includes a server 110 and a non-dedicated terminal 120, wherein the non-dedicated terminal 120 is equipped with an intelligent scheduling terminal agent 121.

[0099] The server 110 is used to send the target intelligent analysis task and intelligent analysis algorithm to the intelligent scheduling terminal agent 121;

[0100] The intelligent scheduling terminal agent 121 is used to receive the target intelligent analysis task and the intelligent analysis algorithm, and to process the target intelligent analysis task using the computing power of the non-dedicated terminal 120 by employing the intelligent analysis algorithm.

[0101] It can be seen that in the scheme provided by the embodiment of the application, the task processing system includes a server and a non-dedicated terminal, the non-dedicated terminal is deployed with an intelligent scheduling terminal agent; the server can be used to issue a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent, and then the intelligent scheduling terminal agent can be used to receive the target intelligent analysis task and the intelligent analysis algorithm, adopt the intelligent analysis algorithm, and process the target intelligent analysis task by using the computing power of the non-dedicated terminal. In this way, a dedicated intelligent computing device does not need to be deployed, but the computing power of the non-dedicated terminal of the user is used to process the target intelligent analysis task by deploying the intelligent scheduling terminal agent on the non-dedicated terminal, so that the deployment cost of the intelligent task processing system is greatly reduced. At the same time, since the computing power of the non-dedicated terminal is used, the computing resources of the non-dedicated terminal can be effectively used, and the utilization rate of the computing resources of the non-dedicated terminal is greatly improved.

[0102] The task processing system provided by the embodiment of the application can include a server and a non-dedicated terminal, wherein the non-dedicated terminal is not a dedicated intelligent computing device, and can be a personal terminal, for example, can be a notebook computer, a desktop computer, a tablet computer, etc. of a user.

[0103] Since the non-dedicated terminal cannot directly participate in the scheduling of the server, in order for the non-dedicated terminal to be able to communicate with the server and participate in the scheduling of the server, an intelligent scheduling terminal agent can be deployed on the non-dedicated terminal. The intelligent scheduling terminal agent can be referred to as an "engine service", which is a service program deployed on a computing resource and used to realize communication with an intelligent scheduling system.

[0104] In this way, when an intelligent analysis task needs to be processed, the server can issue a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent, and then the intelligent scheduling terminal agent can adopt the intelligent analysis algorithm and process the target intelligent analysis task by using the computing power of the non-dedicated terminal after receiving the target intelligent analysis task and the intelligent analysis algorithm, wherein the computing power of the non-dedicated terminal can include CPU (Central Processing Unit, central processor) computing power, GPU computing power, etc. After the target intelligent analysis task is executed, the intelligent scheduling terminal agent can send a task execution result to the server.

[0105] The intelligent analysis algorithm is an algorithm corresponding to the target intelligent analysis task. For example, if the target intelligent analysis task is a face recognition task, the intelligent analysis algorithm can be a face recognition algorithm. In an embodiment, the server can send an algorithm issuing command to the intelligent scheduling terminal agent, and the algorithm issuing command can carry a download address of the intelligent analysis algorithm. Then, the intelligent scheduling terminal agent can download the intelligent analysis algorithm from the download address. In another embodiment, the server can send the intelligent analysis algorithm to the intelligent scheduling terminal agent without the intelligent scheduling terminal agent downloading it, which is reasonable.

[0106] The intelligent analysis algorithm can be specifically an algorithm package. The algorithm package is a program library collection that can be executed in an electronic device basic operating environment and provides corresponding application program interfaces to the outside. For example, the algorithm package can implement video image content analysis, description, retrieval and other functions.

[0107] The non-specialized terminal in the task processing system described above can be one or more, which is not specifically limited here. As an embodiment, the task processing system described above can further include one or more special intelligent computing devices. The intelligent computing devices and the non-specialized terminals can jointly participate in the scheduling of the server, thereby realizing cloud, edge and terminal collaborative scheduling, that is, supporting cloud center (server), edge domain computing power (special intelligent computing device) and terminal computing power (non-specialized terminal) collaborative scheduling, which can meet the intelligent analysis task processing scenarios of one or more combinations of cloud, edge and terminal, can greatly improve the flexibility of the task processing system, and can shield the differences of different computing powers at the bottom and uniformly provide intelligent analysis task services.

[0108] In an embodiment, during the processing of the target intelligent analysis task, the server can issue a task stop command, a task deletion command and the like to the intelligent scheduling terminal agent, and the intelligent scheduling terminal agent can execute the command to perform a target intelligent analysis task stop processing operation, a target intelligent analysis task deletion operation and the like. The server can also issue an algorithm stop command, an algorithm deletion command and the like to the intelligent scheduling terminal agent, and the intelligent scheduling terminal agent can execute the command to perform an intelligent analysis algorithm stop processing operation, an intelligent analysis algorithm deletion operation and the like.

[0109] By adopting the scheme provided by the embodiment of the present application, without deploying a special intelligent operation device, a non-special terminal of a user is adopted, a smart scheduling terminal agent is deployed on the non-special terminal, the computing power of the non-special terminal is used to process a target intelligent analysis task, and the deployment cost of an intelligent task processing system is greatly reduced. Meanwhile, the current personal terminal generally has a GPU and strong CPU processing capability, but the computing power utilization rate of the personal terminal is generally low, and there is a certain waste of resources, especially for some 'group users', such as schools, enterprises, units, etc., the waste of computing power of the personal terminal is more, and by adopting the scheme provided by the embodiment of the present application, the computing resources of the non-special terminal can be effectively utilized by using the computing power of the non-special terminal, and the utilization rate of the computing resources of the non-special terminal is greatly improved.

[0110] When the non-special terminals are multiple, the scheme provided by the embodiment of the present application uses the idle computing power of the non-special terminals to perform intelligent algorithm analysis by using the terminal computing power pool formed by the multiple non-special terminals, and greatly reduces the artificial intelligence construction cost by resource reuse of the terminal computing power pool, and greatly improves the resource utilization rate.

[0111] As an implementation manner of the embodiment of the present application, the above-mentioned intelligent scheduling terminal agent can also be used to report the terminal computing resources of the non-special terminal to the server; and the above-mentioned server can be specifically used to determine a target intelligent analysis task from the tasks to be processed based on the computing resources required by each task to be processed and the terminal computing resources of the non-special terminal, and distribute the target intelligent analysis task and the intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent.

[0112] The intelligent scheduling terminal agent can detect the terminal computing resources of the non-special terminal at a fixed time or in real time, wherein the terminal computing resources at least include residual resources, and then the terminal computing resources can be reported to the server. After receiving the terminal computing resources of the non-special terminal, in order to allocate more suitable tasks to be processed to the non-special terminal, the server can determine a target intelligent analysis task from the tasks to be processed based on the computing resources required by each task to be processed and the terminal computing resources of the non-special terminal, and distribute the target intelligent analysis task and the intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent.

[0113] Since the residual resources of the non-special terminal need to be greater than the computing resources required for processing the target intelligent analysis task, the target intelligent analysis task can be successfully processed, therefore, the server can determine a task to be processed whose required computing resources are not greater than the residual resources of the non-special terminal as the target intelligent analysis task. In the case that the residual resources of the non-special terminal are sufficient and can process multiple tasks to be processed, multiple target intelligent analysis tasks can also be allocated to the non-special terminal, which is reasonable.

[0114] In an embodiment, the server can record the computing resources of each non-dedicated terminal in a computing resource summary table, so as to allocate target intelligent analysis tasks to each non-dedicated terminal. For example, the computing resource summary table can be as shown in the following table:

[0115] Number Non-dedicated terminal Remaining resource amount 1 Non-dedicated terminal 1 100G 2 Non-dedicated terminal 2 120G … … … N Non-dedicated terminal N 85G

[0116] If the computing resources required for processing the to-be-processed task A is 115G, the server can query the above computing resource summary table, so as to determine that the remaining resources of the non-dedicated terminal 1 can meet the processing requirement of the to-be-processed task A, and then determine the to-be-processed task A as the target intelligent analysis task corresponding to the non-dedicated terminal 1, and distribute the to-be-processed task A and the intelligent analysis algorithm corresponding to the to-be-processed task A to the intelligent scheduling terminal agent of the non-dedicated terminal 1.

[0117] It can be seen that, in the embodiment, the intelligent scheduling terminal agent can report the remaining resources of the non-dedicated terminal to the server, the server can determine the target intelligent analysis task from each to-be-processed task based on the computing resources required by each to-be-processed task and the remaining resources, and distribute the target intelligent analysis task and the intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent. In this way, the server can allocate the target intelligent analysis task whose processing requirement can be met by the remaining resources to each non-dedicated terminal, so as to ensure that the target intelligent analysis task can be completed smoothly, and further improve the utilization rate of the computing resources of the non-dedicated terminal.

[0118] As an embodiment of the present application, the terminal computing resources described above can further include total resources.

[0119] Correspondingly, the intelligent scheduling terminal agent described above can also be used to detect the resource occupation rate of the non-dedicated terminal, and send a request for reducing the resource occupation rate to the server when the resource occupation rate reaches a first preset ratio; the server can also be used to determine a task adjustment strategy based on the total resources of the non-dedicated terminal, the first preset ratio and a second preset ratio when the request for reducing the resource occupation rate is received, and adjust the target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so as to reduce the resource occupation rate of the non-dedicated terminal to the second preset ratio.

[0120] In addition to reporting the remaining resources of the non-dedicated terminal to the server, the intelligent scheduling terminal agent can also report the total resources of the non-dedicated terminal to the server. In an embodiment, the server can record the total resources of each non-dedicated terminal in the above computing resource summary table, for example, as shown in the following table:

[0121] Number Non-dedicated terminal Total resource amount Remaining resource amount 1 Non-dedicated terminal 1 200G 100G 2 Non-dedicated terminal 2 150G 120G … … … … N Non-dedicated terminal N 128G 85G

[0122] In order to ensure that the non-dedicated terminal can provide normal services for the user, the resource occupancy rate thereof cannot be too high. For example, the non-dedicated terminal is a notebook computer of the user A, and when the notebook computer is used to process the target intelligent analysis task, the normal use of the notebook computer by the user A cannot be affected, such as that the user A uses the notebook computer to make an electronic document, and the user A uses the notebook computer to view a monitoring video. Therefore, the intelligent scheduling terminal agent can also detect the resource occupancy rate of the non-dedicated terminal, and the intelligent scheduling terminal agent can detect the resource occupancy rate of the non-dedicated terminal in real time or at a fixed time, which is not specifically limited herein.

[0123] When the resource occupancy rate of the non-dedicated terminal reaches a first preset ratio, it indicates that the resource occupancy rate of the non-dedicated terminal is too high at this time, which can affect the normal use of the user. Therefore, the intelligent scheduling terminal agent can send a request for reducing the resource occupancy rate to the server. The first preset ratio can be set according to actual needs, for example, can be 90%, 88%, 85%, and the like, which is not specifically limited herein.

[0124] When the server receives the request for reducing the resource occupancy rate, in order to reduce the resource occupancy rate of the non-dedicated terminal, the server can determine a task adjustment strategy based on the total resources of the non-dedicated terminal, the first preset ratio, and a second preset ratio, and adjust the target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so as to reduce the resource occupancy rate of the non-dedicated terminal to the second preset ratio. The second preset ratio is generally less than the first preset ratio, and can also be set according to actual needs, for example, can be 70%, 75%, 60%, and the like, which is not specifically limited herein.

[0125] The server can calculate the amount of computing resources that need to be reduced according to the total resources of the non-dedicated terminal, the first preset ratio, and the second preset ratio, that is, the total resources × (the first preset ratio - the second preset ratio). Then, the task adjustment strategy can be determined according to the amount of computing resources that need to be reduced.

[0126] The task adjustment strategy can include at least two strategies, the first strategy is to reduce the speed of the non-dedicated terminal processing the target intelligent analysis task, and the second strategy is to distribute part or all of the target intelligent analysis task processed by the non-dedicated terminal to other non-dedicated terminals for processing.

[0127] For the case that the task adjustment strategy is the first strategy, the server can issue a speed adjustment command to the intelligent scheduling terminal agent, and the intelligent scheduling terminal agent adjusts the speed of the non-dedicated terminal processing the target intelligent analysis task after receiving the speed adjustment command, so as to reduce the resource occupancy rate of the non-dedicated terminal to the second preset ratio.

[0128] For the case that the task adjustment strategy is the second strategy, the server can send a task deletion command to the intelligent scheduling terminal agent. After receiving the task deletion command, the intelligent scheduling terminal agent can delete the target intelligent analysis task, and the non-dedicated terminal no longer continues to process the target intelligent analysis task, thereby reducing the resource occupation rate of the non-dedicated terminal to the second preset ratio.

[0129] As an implementation manner, after receiving the resource occupation rate reduction request, the server can also directly send a speed adjustment command to the intelligent scheduling terminal agent. After receiving the speed adjustment command, the intelligent scheduling terminal agent reduces the speed of the non-dedicated terminal processing the target intelligent analysis task according to a preset speed adjustment degree. Alternatively, the server can directly assign a part of the target intelligent analysis task processed by the non-dedicated terminal to other non-dedicated terminals for processing.

[0130] Since the intelligent scheduling terminal agent detects the resource occupation rate of the non-dedicated terminal in real time or at a fixed time, if the resource occupation rate of the non-dedicated terminal still reaches the first preset ratio when the resource occupation rate of the non-dedicated terminal is detected next time, the server can continue to send a resource occupation rate reduction request to the server. The server can repeatedly execute the operation of sending a speed adjustment command to the intelligent scheduling terminal agent or directly assigning a part of the target intelligent analysis task processed by the non-dedicated terminal to other non-dedicated terminals for processing until the resource occupation rate of the non-dedicated terminal is reduced to the second preset ratio.

[0131] As can be seen, in the embodiment, the intelligent scheduling terminal agent can also send a resource occupation rate reduction request to the server when the resource occupation rate of the non-dedicated terminal reaches the first preset ratio. Then, the server can determine a task adjustment strategy based on the total resources of the non-dedicated terminal, the first preset ratio, and the second preset ratio, and adjust the target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy to reduce the resource occupation rate of the non-dedicated terminal to the second preset ratio. In this way, the computing power of the non-dedicated terminal can be fully utilized to process the target intelligent analysis task, while ensuring that the user can normally use the non-dedicated terminal.

[0132] As an implementation manner of the embodiment, the server can also be configured to send a state query message to the intelligent scheduling terminal agent. The intelligent scheduling terminal agent can also be configured to report a processing state of the target intelligent analysis task to the server when receiving the state query message. The server can also be configured to determine that the processing of the target intelligent analysis task is abnormal based on the processing state, and assign the target intelligent analysis task to other non-dedicated terminals to enable the other non-dedicated terminals to continue processing the target intelligent analysis task.

[0133] In order to determine whether the non-dedicated terminal is normally processing the target intelligent analysis task, the server can query the processing state of the target intelligent analysis task of the non-dedicated terminal at a time, specifically, the server can send a state query message to the intelligent scheduling terminal agent at a time, and then the intelligent scheduling terminal agent can report the processing state of the target intelligent analysis task to the server when receiving the state query message. The processing state can include processing progress, whether the task state is normal, whether the processing is completed, and the like, which are not limited herein. The intelligent scheduling terminal agent can also report the processing state of the target intelligent analysis task to the server at a time, which is also reasonable, and is not limited herein.

[0134] After receiving the processing state reported by the intelligent scheduling terminal agent, the server can determine whether the processing of the target intelligent analysis task is abnormal based on the processing state, if not, the processing state can be recorded for subsequent management, state analysis and the like.

[0135] If the processing state of the target intelligent analysis task indicates that the target intelligent analysis task is in a stop state or the like, it can be determined that the processing of the target intelligent analysis task is abnormal. In order to ensure that the target intelligent analysis task can be completed smoothly, the server can distribute the target intelligent analysis task to other non-dedicated terminals, and the other non-dedicated terminals can continue to process the target intelligent analysis task. As an implementation manner, the processing state can include the processing progress of the target intelligent analysis task, so that the server can schedule other non-dedicated terminals to continue processing the target intelligent analysis task from the processing progress, and complete the abnormal recovery migration process of the target intelligent analysis task.

[0136] In an implementation manner, the intelligent scheduling terminal agent fails to normally report the processing state of the target intelligent analysis task, which can also determine that the processing of the target intelligent analysis task is abnormal, for example, the non-dedicated terminal is offline, the intelligent scheduling terminal agent does not respond to the state query message for a plurality of times, and the like. At this time, the above-mentioned abnormal recovery migration process of the target intelligent analysis task can also be performed.

[0137] The server can also delete the terminal computing resource of the non-dedicated terminal from the above-mentioned computing resource summary table, so as to avoid distributing the intelligent analysis task to the abnormal non-dedicated terminal in the future. Of course, after the abnormal non-dedicated terminal recovers normally, the intelligent scheduling terminal agent deployed by the non-dedicated terminal can report the terminal computing resource of the non-dedicated terminal to the server, and the server can record the terminal computing resource of the non-dedicated terminal in the above-mentioned computing resource summary table again.

[0138] It can be seen that in the embodiment, when the server determines that the processing of the target intelligent analysis task is abnormal based on the processing state, the target intelligent analysis task can be assigned to other non-dedicated terminals, and then the other non-dedicated terminals can continue to process the target intelligent analysis task. Therefore, when the processing of the target intelligent analysis task on the non-dedicated terminal is abnormal, the abnormal recovery migration process of the target intelligent analysis task can be performed, and it is ensured that the target intelligent analysis task can be successfully executed and completed.

[0139] As an embodiment of the present application, as shown in Figure 2 The server 110 can be deployed with an intelligent scheduling center service 111. The intelligent scheduling center service can be a service program deployed on the server, which can communicate with the intelligent scheduling terminal agent, schedule various intelligent analysis tasks to specific non-dedicated terminals for intelligent analysis through scheduling strategies, and output the analysis results after obtaining the analysis results reported by the intelligent scheduling terminal agent.

[0140] Correspondingly, the intelligent scheduling center service can be used to assign the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent.

[0141] The server can communicate with the intelligent scheduling terminal agent through the intelligent scheduling center service, and after determining the target intelligent analysis task and the corresponding intelligent analysis algorithm, the intelligent scheduling center service can be assigned to the intelligent scheduling terminal agent. During the processing of the target intelligent analysis task, the intelligent scheduling center service communicates with the intelligent scheduling terminal agent to transmit various commands and data, thereby completing the processing of the target intelligent analysis task.

[0142] For the case that the task processing system includes a plurality of non-dedicated terminals, the server is deployed with an intelligent scheduling center service, each non-dedicated terminal is deployed with an intelligent scheduling terminal agent, and each intelligent scheduling terminal agent can communicate with the intelligent scheduling center service. The intelligent scheduling center service can complete the scheduling of each intelligent scheduling terminal agent according to a preset task scheduling strategy, thereby completing the processing of each intelligent analysis task.

[0143] It can be seen that in the embodiment, the server can be deployed with an intelligent scheduling center service, which can be used to assign the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent. In this way, during the processing of the target intelligent analysis task, the intelligent scheduling center service communicates with the intelligent scheduling terminal agent, thereby ensuring the smooth completion of the processing of the target intelligent analysis task.

[0144] As an implementation of an embodiment of the present application, the intelligent dispatch terminal agent is configured with a connection address of the intelligent dispatch center service. The intelligent dispatch terminal agent can also be configured to send registration information to the intelligent dispatch center service based on the connection address; the intelligent dispatch center service can also be configured to receive the registration information before issuing the target intelligent analysis task and the intelligent analysis algorithm to the intelligent dispatch terminal agent, and to establish a communication connection with the intelligent dispatch terminal agent after completing the registration of the intelligent dispatch terminal agent based on the registration information.

[0145] In order to be able to establish a communication connection with the intelligent dispatch center service, each intelligent dispatch terminal agent can be pre-configured with a connection address of the intelligent dispatch center service, that is, a connection address of the server, which can be a domain name or an Internet Protocol Address (IP address) of the server, without specific limitation here.

[0146] Further, the intelligent dispatch terminal agent can send registration information to the intelligent dispatch center service based on the connection address. The registration information can include terminal information, such as a terminal identifier of a non-dedicated terminal. Since a non-dedicated terminal is generally a personal computer of a user, it does not have a fixed IP address and cannot use the passive IP addition method to establish a communication connection with the intelligent dispatch center service, so the intelligent dispatch terminal agent can be used to register with the intelligent dispatch center service. Of course, other methods can also be used as long as the intelligent dispatch terminal agent and the intelligent dispatch center service can establish a secure and legal communication connection, without specific limitation here.

[0147] When the intelligent dispatch center service receives the registration information, it can complete the registration of the intelligent dispatch terminal agent based on the registration information, and further establish a communication connection with the intelligent dispatch terminal agent. Based on the communication connection, the intelligent dispatch center service can perform subsequent operations such as issuing the target intelligent analysis task and the intelligent analysis algorithm to the intelligent dispatch terminal agent.

[0148] As can be seen, in the present embodiment, the intelligent dispatch terminal agent can be configured with a connection address of the intelligent dispatch center service, the intelligent dispatch terminal agent can send registration information to the intelligent dispatch center service based on the connection address, and then the intelligent dispatch center service can complete the registration of the intelligent dispatch terminal agent based on the registration information and establish a communication connection with the intelligent dispatch terminal agent. In this way, the intelligent dispatch terminal agent and the intelligent dispatch center service can interact with each other through the communication connection to complete the processing of each target intelligent analysis task.

[0149] The following will be described in conjunction with Figure 3The processing procedure of the target intelligent analysis task based on the task processing system provided by the embodiment of the present application is exemplarily introduced. The processing procedure can include the following steps:

[0150] S301, the intelligent scheduling terminal agent registers with the intelligent scheduling center service.

[0151] The non-dedicated terminal is deployed with the intelligent scheduling terminal agent and is configured with the connection address of the intelligent scheduling center service.

[0152] S302, the intelligent scheduling center service receives the registration information sent by the intelligent scheduling terminal agent and records the terminal information.

[0153] S303, the intelligent scheduling center service queries the terminal computing power details of the intelligent scheduling terminal agent, including the total resources and the remaining resources, records the terminal computing power details, and combines the total resources and the remaining resources into the summary table of all available computing resources.

[0154] S304, the intelligent scheduling center service finds the terminal computing power with remaining resources in the summary table of computing resources based on the internal scheduling strategy.

[0155] S305, the intelligent scheduling center service calculates the number of tasks executable by the terminal computing power, and distributes the algorithm and the task to be executed to the terminal computing power.

[0156] S306, the intelligent scheduling center service queries the running condition and the task execution state of the terminal computing power at regular intervals, and records the task execution state.

[0157] S307, it is judged whether the intelligent scheduling terminal agent returns the task execution state. If yes, step S308 is executed; if there is no response for 3 times continuously, step S309 is executed.

[0158] S308, it is determined whether the task is completed based on the task execution state. If yes, step S311 is executed; if no, step S306 is returned.

[0159] S309, the intelligent scheduling center service marks the terminal computing power as abnormal offline, and deletes the information of the terminal computing power from the summary table of computing resources.

[0160] S310, the intelligent scheduling center service finds other terminal computing power with remaining resources in the summary table of computing resources, resumes the task execution from the recorded task execution state, and distributes the task to the found other terminal computing power for continuous execution.

[0161] S311, the completed task is deleted from the terminal computing power, and the resources occupied by the task are re-registered in the summary table of computing resources.

[0162] Since the specific implementation manners of the above steps have been described in detail in the above embodiments, the description of the corresponding parts in the above embodiments can be referred to, and thus the description is not repeated here.

[0163] It can be seen that in the embodiment, a special intelligent computing device does not need to be deployed, but a user's non-dedicated terminal is used, the intelligent scheduling terminal agent is deployed in the non-dedicated terminal, the computing power of the non-dedicated terminal is used to process the target intelligent analysis task, and the deployment cost of the intelligent task processing system is greatly reduced. At the same time, the computing resources of the non-dedicated terminal can be effectively utilized by using the computing power of the non-dedicated terminal, and the utilization rate of the computing resources of the non-dedicated terminal is greatly improved.

[0164] The following will be described in combination with Figure 4 The processing process of the target intelligent analysis task of the task processing system provided in the embodiment of the application will be described by way of example. The processing process can include the following steps:

[0165] S401, the intelligent scheduling terminal agent detects the usage of the terminal computing power resource in real time;

[0166] The user can submit an analysis task in advance in the terminal computing power, so that the intelligent scheduling terminal agent can detect the usage of the terminal computing power resource in real time.

[0167] S402, the intelligent scheduling terminal agent determines whether the total resource usage rate reaches a preset proportion, if the preset proportion is not exceeded, step S403 is performed; if the preset proportion is exceeded, step S404 is performed;

[0168] S403, the intelligent scheduling terminal agent normally reports the usage of the terminal computing power resource and the task execution state;

[0169] S404, the intelligent scheduling terminal agent reports a request for reducing resource occupation to the intelligent scheduling center service;

[0170] S405, after the intelligent scheduling center service receives the request for reducing resource occupation, based on the resource usage rate, the task information that needs to be reduced in operation is calculated, and the speed of task execution in the terminal computing power is reduced, or the task is assigned to other terminals.

[0171] Since the specific implementation manners of the above steps have been described in detail in the above embodiments, the description of the corresponding parts in the above embodiments can be referred to, and thus the description is not repeated here. Figure 3 and Figure 4 The terminal computing power in the embodiment shown is the computing power of the non-dedicated terminal described above, and the task is the target intelligent analysis task.

[0172] It can be seen that in the embodiment, the intelligent scheduling terminal agent can detect the use of terminal computing resources, so as to adaptively adjust the computing power, and ensure that the target intelligent analysis task is processed without affecting the normal use of the non-dedicated terminal by the user.

[0173] Corresponding to the above task processing system, the embodiment of the application also provides a task processing method. The first task processing method provided by the embodiment of the application will be introduced below. The first task processing method provided by the embodiment of the application can be applied to the intelligent scheduling terminal agent deployed on the non-dedicated terminal in the above task processing system.

[0174] As shown in Figure 5 A task processing method applied to an intelligent scheduling terminal agent deployed on a non-dedicated terminal in a task processing system, the system also comprising a server, the method comprising:

[0175] S501, receiving a target intelligent analysis task and an intelligent analysis algorithm issued by the server;

[0176] S502, using the intelligent analysis algorithm to process the target intelligent analysis task by using the computing power of the non-dedicated terminal.

[0177] It can be seen that in the scheme provided by the embodiment of the application, the intelligent scheduling terminal agent deployed on the non-dedicated terminal in the task processing system can receive the target intelligent analysis task and the intelligent analysis algorithm issued by the server, and then use the intelligent analysis algorithm to process the target intelligent analysis task by using the computing power of the non-dedicated terminal. In this way, without deploying dedicated intelligent computing equipment, the target intelligent analysis task can be processed by using the computing power of the non-dedicated terminal through deploying the intelligent scheduling terminal agent on the non-dedicated terminal, which greatly reduces the deployment cost of the intelligent task processing system. At the same time, since the computing power of the non-dedicated terminal is used, the computing resources of the non-dedicated terminal can be effectively utilized, and the utilization rate of the computing resources of the non-dedicated terminal is greatly improved.

[0178] As an embodiment of the embodiment of the application, the above method can further comprise:

[0179] Reporting the terminal computing resources of the non-dedicated terminal to the server, so that the server determines a target intelligent analysis task from the tasks to be processed based on the computing resources required by each task to be processed and the remaining resources, and issues the target intelligent analysis task and the intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent.

[0180] The terminal computing resources comprise the remaining resources.

[0181] As an implementation of an embodiment of the present application, the terminal computing resource can further include total resources, and the method can further include:

[0182] detecting a resource occupation rate of the non-dedicated terminal;

[0183] when the resource occupation rate reaches a first preset ratio, sending a request for reducing the resource occupation rate to the server, so that the server, upon receiving the request for reducing the resource occupation rate, determines a task adjustment strategy based on the total resources of the non-dedicated terminal, the first preset ratio, and a second preset ratio, and adjusts a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupation rate of the non-dedicated terminal is reduced to the second preset ratio.

[0184] As an implementation of an embodiment of the present application, the method can further include:

[0185] receiving a state query message sent by the server;

[0186] upon receiving the state query message, reporting a processing state of the target intelligent analysis task to the server, so that the server, upon determining that processing of the target intelligent analysis task is abnormal based on the processing state, assigns the target intelligent analysis task to another non-dedicated terminal, so that the another non-dedicated terminal continues processing the target intelligent analysis task.

[0187] As an implementation of an embodiment of the present application, the server is deployed with an intelligent scheduling center service, and the step of receiving the target intelligent analysis task and the intelligent analysis algorithm assigned by the server can include:

[0188] receiving the target intelligent analysis task and the intelligent analysis algorithm assigned by the intelligent scheduling center service.

[0189] As an implementation of an embodiment of the present application, the intelligent scheduling terminal agent can be configured with a connection address of the intelligent scheduling center service, and the method can further include:

[0190] sending registration information to the intelligent scheduling center service based on the connection address, so that the intelligent scheduling center service, before assigning the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, receives the registration information, and after completing registration of the intelligent scheduling terminal agent based on the registration information, establishes a communication connection with the intelligent scheduling terminal agent.

[0191] Corresponding to the above task processing system, the embodiment of the application also provides a task processing method. The second task processing method provided by the embodiment of the application is introduced below. The first task processing method provided by the embodiment of the application can be applied to the server in the above task processing system.

[0192] As shown in Figure 6 A task processing method applied to a server in a task processing system, the system also comprising a non-dedicated terminal, wherein the non-dedicated terminal is deployed with an intelligent scheduling terminal agent, the method comprising:

[0193] S601, determining an intelligent analysis algorithm corresponding to a target intelligent analysis task;

[0194] S602, issuing the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, adopts the intelligent analysis algorithm, and processes the target intelligent analysis task by using the computing power of the non-dedicated terminal.

[0195] It can be seen that in the scheme provided by the embodiment of the application, the server in the task processing system can determine an intelligent analysis algorithm corresponding to a target intelligent analysis task, and then issue the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, adopts the intelligent analysis algorithm, and processes the target intelligent analysis task by using the computing power of the non-dedicated terminal. In this way, it is not necessary to deploy a dedicated intelligent computing device, but to use the non-dedicated terminal of a user, to process the target intelligent analysis task by deploying an intelligent scheduling terminal agent on the non-dedicated terminal, thereby greatly reducing the deployment cost of the intelligent task processing system. At the same time, since the computing power of the non-dedicated terminal is utilized, the computing resources of the non-dedicated terminal can be effectively utilized, and the utilization rate of the computing resources of the non-dedicated terminal is greatly improved.

[0196] As an embodiment of the embodiment of the application, the above method can further comprise:

[0197] receiving the terminal computing resources of the non-dedicated terminal reported by the intelligent scheduling terminal agent;

[0198] The terminal computing resources comprise residual resources.

[0199] The step of determining the intelligent analysis algorithm corresponding to the target intelligent analysis task comprises:

[0200] determining a target intelligent analysis task from the tasks to be processed based on the required computing resources of each of the tasks to be processed and the remaining resources, and determining an intelligent analysis algorithm corresponding to the target intelligent analysis task.

[0201] As an implementation of an embodiment of the present application, the terminal computing resources can further include total resources, and the method can further include:

[0202] receiving a request for reducing resource occupancy rate sent by the intelligent scheduling terminal agent;

[0203] The request for reducing resource occupancy rate is sent by the intelligent scheduling terminal agent when it detects that the resource occupancy rate of the non-dedicated terminal reaches a first preset ratio.

[0204] determining a task adjustment strategy based on the total resources of the non-dedicated terminal, the first preset ratio, and a second preset ratio;

[0205] adjusting a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so as to reduce the resource occupancy rate of the non-dedicated terminal to the second preset ratio.

[0206] As an implementation of an embodiment of the present application, the method can further include:

[0207] sending a state query message to the intelligent scheduling terminal agent;

[0208] receiving a processing state of the target intelligent analysis task reported by the intelligent scheduling terminal agent;

[0209] when it is determined that the processing of the target intelligent analysis task is abnormal based on the processing state, assigning the target intelligent analysis task to another non-dedicated terminal, so as to enable the other non-dedicated terminal to continue processing the target intelligent analysis task.

[0210] As an implementation of an embodiment of the present application, the server can be deployed with an intelligent scheduling center service, and the steps of assigning the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent include:

[0211] the intelligent scheduling center service assigns the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent.

[0212] As an implementation of an embodiment of the present application, the intelligent scheduling terminal agent can be configured with a connection address of the intelligent scheduling center service, and before the step of assigning the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, the method further includes:

[0213] receive registration information sent by the intelligent scheduling terminal agent based on the connection address;

[0214] after completing registration of the intelligent scheduling terminal agent based on the registration information, establish a communication connection with the intelligent scheduling terminal agent.

[0215] Corresponding to the above-mentioned first task processing method, the embodiment of the application also provides a task processing device.

[0216] As shown in Figure 7 A task processing device applied to an intelligent scheduling terminal agent deployed by a non-dedicated terminal in a task processing system, the system also includes a server, and the device includes:

[0217] A task receiving module 710 for receiving a target intelligent analysis task and an intelligent analysis algorithm issued by the server;

[0218] A task processing module 720 for processing the target intelligent analysis task using the computing power of the non-dedicated terminal by using the intelligent analysis algorithm.

[0219] It can be seen that in the scheme provided by the embodiment of the application, the intelligent scheduling terminal agent deployed by a non-dedicated terminal in a task processing system can receive a target intelligent analysis task and an intelligent analysis algorithm issued by a server, and then process the target intelligent analysis task using the computing power of the non-dedicated terminal by using the intelligent analysis algorithm. In this way, it is not necessary to deploy a dedicated intelligent computing device, but to use a non-dedicated terminal of a user, to process a target intelligent analysis task using the computing power of the non-dedicated terminal by deploying an intelligent scheduling terminal agent on the non-dedicated terminal, thereby greatly reducing the deployment cost of an intelligent task processing system. At the same time, since the computing power of the non-dedicated terminal is utilized, the computing resources of the non-dedicated terminal can be effectively utilized, and the utilization rate of the computing resources of the non-dedicated terminal is greatly improved.

[0220] As an embodiment of the embodiment of the application, the above-mentioned device can also include:

[0221] A computing resource reporting module for reporting terminal computing resources of the non-dedicated terminal to the server, so that the server determines a target intelligent analysis task from each to-be-processed task based on the computing resources required by each to-be-processed task and the remaining resources, and issues the target intelligent analysis task and an intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent.

[0222] The terminal computing resources include the remaining resources.

[0223] As an embodiment of the embodiment of the application, the above-mentioned terminal computing resources can also include total resources; and the above-mentioned device can also include:

[0224] an occupancy detection module, configured to detect a resource occupancy of the non-dedicated terminal;

[0225] a request sending module, configured to send a request for reducing resource occupancy to the server when the resource occupancy reaches a first preset ratio, so that the server determines a task adjustment strategy based on the total resource of the non-dedicated terminal, the first preset ratio and a second preset ratio, and adjusts a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so as to reduce the resource occupancy of the non-dedicated terminal to the second preset ratio.

[0226] As an embodiment of the present application, the device can further include:

[0227] a query message receiving module, configured to receive a state query message sent by the server;

[0228] a state reporting module, configured to report a processing state of the target intelligent analysis task to the server when the state query message is received, so that the server determines to assign the target intelligent analysis task to another non-dedicated terminal to continue processing the target intelligent analysis task when the processing state indicates that the processing of the target intelligent analysis task is abnormal.

[0229] As an embodiment of the present application, the server is deployed with an intelligent scheduling center service; the task receiving module 710 can include:

[0230] a task receiving unit, configured to receive a target intelligent analysis task and an intelligent analysis algorithm assigned by the intelligent scheduling center service.

[0231] As an embodiment of the present application, the intelligent scheduling terminal agent can be configured with a connection address of the intelligent scheduling center service; the device can further include:

[0232] a registration module, configured to send registration information to the intelligent scheduling center service based on the connection address, so that the intelligent scheduling center service receives the registration information before assigning a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent, and establishes a communication connection with the intelligent scheduling terminal agent after completing the registration of the intelligent scheduling terminal agent based on the registration information.

[0233] Corresponding to the second task processing method, the present application further provides another task processing device.

[0234] As Figure 8As shown, a task processing apparatus is applied to a server in a task processing system, the system further comprising a non-dedicated terminal, wherein the non-dedicated terminal is deployed with an intelligent scheduling terminal agent, and the apparatus comprises:

[0235] a task determination module 810, configured to determine an intelligent analysis algorithm corresponding to a target intelligent analysis task;

[0236] a task issuing module 820, configured to issue the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, adopts the intelligent analysis algorithm, and processes the target intelligent analysis task by using the computing power of the non-dedicated terminal.

[0237] It can be seen that in the scheme provided by the embodiment of the present application, the server in the task processing system can determine the intelligent analysis algorithm corresponding to the target intelligent analysis task, and then issue the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, adopts the intelligent analysis algorithm, and processes the target intelligent analysis task by using the computing power of the non-dedicated terminal. In this way, it is not necessary to deploy a dedicated intelligent operation device, but to use the non-dedicated terminal of a user, to process the target intelligent analysis task by deploying the intelligent scheduling terminal agent on the non-dedicated terminal, so as to greatly reduce the deployment cost of the intelligent task processing system. At the same time, since the computing power of the non-dedicated terminal is utilized, the computing resources of the non-dedicated terminal can be effectively utilized, and the utilization rate of the computing resources of the non-dedicated terminal is greatly improved.

[0238] As an embodiment of the present application, the above apparatus can further comprise:

[0239] a computing resource receiving module, configured to receive the terminal computing resources of the non-dedicated terminal reported by the intelligent scheduling terminal agent;

[0240] The terminal computing resources comprise residual resources.

[0241] The above task determination module 810 can comprise:

[0242] a task determination unit, configured to determine a target intelligent analysis task from the to-be-processed tasks based on the computing resources required by each to-be-processed task and the residual resources, and determine an intelligent analysis algorithm corresponding to the target intelligent analysis task.

[0243] As an embodiment of the present application, the above terminal computing resources can further comprise total resources; and the above apparatus can further comprise:

[0244] The resource reduction request receiving module is configured to receive a resource occupation rate reduction request sent by the intelligent scheduling terminal agent.

[0245] The resource occupation rate reduction request is sent by the intelligent scheduling terminal agent when the intelligent scheduling terminal agent detects that the resource occupation rate of the non-dedicated terminal reaches a first preset ratio.

[0246] The adjustment strategy determining module is configured to determine a task adjustment strategy based on the total resource of the non-dedicated terminal, the first preset ratio and a second preset ratio.

[0247] The task adjustment module is configured to adjust a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupation rate of the non-dedicated terminal is reduced to the second preset ratio.

[0248] As an embodiment of the present application, the above device can further include:

[0249] The query message sending module is configured to send a state query message to the intelligent scheduling terminal agent.

[0250] The processing state receiving module is configured to receive a processing state of the target intelligent analysis task reported by the intelligent scheduling terminal agent.

[0251] The abnormality processing module is configured to, when it is determined that the processing of the target intelligent analysis task is abnormal based on the processing state, distribute the target intelligent analysis task to another non-dedicated terminal, so that the another non-dedicated terminal continues to process the target intelligent analysis task.

[0252] As an embodiment of the present application, the above server can be deployed with an intelligent scheduling center service; and the task distribution module 820 includes:

[0253] The task distribution unit is configured to distribute a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent through the intelligent scheduling center service.

[0254] As an embodiment of the present application, the above intelligent scheduling terminal agent can be configured with a connection address of the intelligent scheduling center service; and the device can further include:

[0255] The registration information receiving module is configured to, before the target intelligent analysis task and the intelligent analysis algorithm are distributed to the intelligent scheduling terminal agent, receive registration information sent by the intelligent scheduling terminal agent based on the connection address.

[0256] The communication establishing module is configured to, after the registration of the intelligent scheduling terminal agent is completed based on the registration information, establish a communication connection with the intelligent scheduling terminal agent.

[0257] The embodiment of the present application also provides an electronic device, which can be the non-dedicated terminal or the server. Figure 9 As shown in the figure, the non-dedicated terminal comprises a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902 and the memory 903 complete mutual communication through the communication bus 904,

[0258] The memory 903 is used for storing a computer program.

[0259] The processor 901 is used for executing the program stored in the memory 903, and realizes the first task processing method steps of any of the above embodiments.

[0260] It can be seen that, in the scheme provided by the embodiment of the present application, the intelligent scheduling terminal agent of the non-dedicated terminal in the task processing system can receive the target intelligent analysis task and the intelligent analysis algorithm issued by the server, and then the intelligent analysis algorithm is used to process the target intelligent analysis task by using the computing power of the non-dedicated terminal. In this way, without deploying a dedicated intelligent operation device, the computing power of the non-dedicated terminal of the user is used to process the target intelligent analysis task by deploying the intelligent scheduling terminal agent on the non-dedicated terminal, which greatly reduces the deployment cost of the intelligent task processing system. At the same time, since the computing power of the non-dedicated terminal is used, the computing resources of the non-dedicated terminal can be effectively used, and the utilization rate of the computing resources of the non-dedicated terminal is greatly improved.

[0261] The communication bus of the non-dedicated terminal can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0262] The communication interface is used for communication between the non-dedicated terminal and other devices.

[0263] The memory can include a random access memory (RAM) and can also include a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0264] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0265] In the case where the aforementioned electronic device is the aforementioned server, an embodiment of the present invention provides a server, such as... Figure 10 As shown, it includes a processor 1001, a communication interface 1002, a memory 1003, and a communication bus 1004, wherein the processor 1001, the communication interface 1002, and the memory 1003 communicate with each other through the communication bus 1004.

[0266] Memory 1003 is used to store computer programs;

[0267] When the processor 1001 executes the program stored in the memory 1003, it implements the steps of the second task processing method described in any of the above embodiments.

[0268] As can be seen, in the solution provided by this embodiment of the invention, the server in the task processing system can determine the intelligent analysis algorithm corresponding to the target intelligent analysis task, and then send the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent. The intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, and uses the intelligent analysis algorithm to process the target intelligent analysis task using the computing power of the non-dedicated terminal. In this way, it is not necessary to deploy dedicated intelligent computing equipment; instead, the user's non-dedicated terminal can be used. By deploying the intelligent scheduling terminal agent on the non-dedicated terminal, the computing power of the non-dedicated terminal can be used to process the target intelligent analysis task, greatly reducing the deployment cost of the intelligent task processing system. At the same time, since the computing power of the non-dedicated terminal is utilized, the computing resources of the non-dedicated terminal can be effectively utilized, greatly improving the utilization rate of the non-dedicated terminal's computing resources.

[0269] The communication bus mentioned by the server can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0270] The communication interface is used for communication between the server and other devices.

[0271] The memory can include a Random Access Memory (RAM) and can also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0272] The processor mentioned above can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0273] In another embodiment provided by the application, a computer readable storage medium is also provided, and the computer readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the task processing method in any of the above embodiments are implemented.

[0274] In another embodiment provided by the application, a computer program product containing instructions is also provided, and when the computer program product is run on a computer, the computer is caused to execute the task processing method in any of the above embodiments.

[0275] In the embodiments described above, all or some of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or some of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded into and executed by a computer, all or some of the processes or functions according to the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, solid state disk (SSD)) and the like.

[0276] It should be noted that, in this document, the terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0277] Each of the embodiments in the specification is described in a related manner, and the same or similar parts between each of the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the method, device, non-dedicated terminal, server, computer readable storage medium and computer program product embodiments, since they are basically similar to the system embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0278] The above merely describes the preferred embodiments of the present application, but is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A task processing system, characterized by, The system comprises a server and a non-dedicated terminal, wherein the non-dedicated terminal is deployed with an intelligent scheduling terminal agent; The server is configured to distribute a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent; The intelligent scheduling terminal agent is configured to receive the target intelligent analysis task and the intelligent analysis algorithm, and process the target intelligent analysis task by using the intelligent analysis algorithm and the computing power of the non-dedicated terminal, wherein the computing power of the non-dedicated terminal comprises CPU computing power and / or GPU computing power; The server is configured to send an algorithm distribution command carrying a download address of the intelligent analysis algorithm to the intelligent scheduling terminal agent, and the intelligent scheduling terminal agent is configured to download the intelligent analysis algorithm from the download address in the algorithm distribution command; or the server is configured to send the intelligent analysis algorithm to the intelligent scheduling terminal agent; The intelligent scheduling terminal agent is further configured to report terminal computing resources of the non-dedicated terminal to the server, wherein the terminal computing resources comprise residual resources; The server is configured to determine a target intelligent analysis task from the tasks to be processed based on the computing resources required by each task to be processed and the residual resources, and distribute the target intelligent analysis task and an intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent.

2. The system of claim 1, wherein, The terminal computing resources further comprise total resources; The intelligent scheduling terminal agent is further configured to detect a resource occupancy rate of the non-dedicated terminal, and send a request for reducing the resource occupancy rate to the server when the resource occupancy rate reaches a first preset ratio; The server is further configured to determine a task adjustment strategy based on the total resources of the non-dedicated terminal, the first preset ratio and a second preset ratio when the request for reducing the resource occupancy rate is received, and adjust a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so as to reduce the resource occupancy rate of the non-dedicated terminal to the second preset ratio.

3. The system of claim 1, wherein The server is further configured to send a state query message to the intelligent scheduling terminal agent; The intelligent scheduling terminal agent is further configured to report a processing state of the target intelligent analysis task to the server when the state query message is received; The server is further configured to distribute the target intelligent analysis task to another non-dedicated terminal to continue processing the target intelligent analysis task when it is determined that the processing of the target intelligent analysis task is abnormal based on the processing state.

4. A task processing method characterized by, An intelligent scheduling terminal agent deployed on a non-dedicated terminal in a task processing system, the system further comprising a server, the method comprising: Receiving a target intelligent analysis task and an intelligent analysis algorithm distributed by the server; Processing the target intelligent analysis task by using the intelligent analysis algorithm and the computing power of the non-dedicated terminal, wherein the computing power of the non-dedicated terminal comprises CPU computing power and / or GPU computing power; The method further comprises: The method further comprises: The method further comprises: The method further comprises:

5. The method of claim 4, wherein the terminal computing resources further comprise total resources, and the method further comprises: detecting a resource occupancy rate of the non-dedicated terminal; when the resource occupancy rate reaches a first preset ratio, sending a request for reducing the resource occupancy rate to the server, so that the server, upon receiving the request for reducing the resource occupancy rate, determines a task adjustment strategy based on the total resources of the non-dedicated terminal, the first preset ratio, and a second preset ratio, and adjusts a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupancy rate of the non-dedicated terminal is reduced to the second preset ratio; The method further comprises: receiving a state query message sent by the server; upon receiving the state query message, reporting a processing state of the target intelligent analysis task to the server, so that the server, upon determining that processing of the target intelligent analysis task is abnormal based on the processing state, distributes the target intelligent analysis task to another non-dedicated terminal, so that the another non-dedicated terminal continues to process the target intelligent analysis task; The server is deployed with an intelligent scheduling center service, and the step of receiving the target intelligent analysis task and the intelligent analysis algorithm distributed by the server comprises: receiving the target intelligent analysis task and the intelligent analysis algorithm distributed by the intelligent scheduling center service. A server applied to a task processing system, the system further comprising a non-dedicated terminal, wherein the non-dedicated terminal is deployed with an intelligent scheduling terminal agent, and the method comprises:

6. A task processing method characterized by, determining an intelligent analysis algorithm corresponding to a target intelligent analysis task; distributing the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, uses the intelligent analysis algorithm to process the target intelligent analysis task by using computing power of the non-dedicated terminal, wherein the computing power of the non-dedicated terminal comprises CPU computing power and / or GPU computing power; wherein distributing the intelligent analysis algorithm to the intelligent scheduling terminal agent comprises: ​ sending an algorithm issuing command carrying a download address of the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent downloads the intelligent analysis algorithm from the download address in the algorithm issuing command; or, sending the intelligent scheduling terminal agent the intelligent analysis algorithm; The method further includes: receiving the terminal computing resources of the non-dedicated terminal reported by the intelligent scheduling terminal agent, wherein the terminal computing resources include residual resources; The step of determining the intelligent analysis algorithm corresponding to the target intelligent analysis task includes: determining the target intelligent analysis task from the tasks to be processed and determining the intelligent analysis algorithm corresponding to the target intelligent analysis task based on the computing resources required by each task to be processed and the residual resources.

7. The method of claim 6, wherein: The terminal computing resources further include total resources; and the method further includes: receiving a request for reducing resource occupancy rate sent by the intelligent scheduling terminal agent, wherein the request for reducing resource occupancy rate is sent by the intelligent scheduling terminal agent when it detects that the resource occupancy rate of the non-dedicated terminal reaches a first preset ratio; determining a task adjustment strategy based on the total resources of the non-dedicated terminal, the first preset ratio, and a second preset ratio; adjusting the target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupancy rate of the non-dedicated terminal is reduced to the second preset ratio; The method further includes: sending a state query message to the intelligent scheduling terminal agent; receiving the processing state of the target intelligent analysis task reported by the intelligent scheduling terminal agent; when it is determined that the processing of the target intelligent analysis task is abnormal based on the processing state, issuing the target intelligent analysis task to another non-dedicated terminal, so that the other non-dedicated terminal continues to process the target intelligent analysis task; The server is deployed with an intelligent scheduling center service; and the steps of issuing the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent include: The intelligent scheduling center service issues the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent.

8. A task processing apparatus characterized by comprising: An intelligent scheduling terminal agent deployed on a non-dedicated terminal in a task processing system, the system further including a server, wherein the device includes: a task receiving module configured to receive a target intelligent analysis task and an intelligent analysis algorithm issued by the server; a task processing module configured to process the target intelligent analysis task using the computing power of the non-dedicated terminal by using the intelligent analysis algorithm, wherein the computing power of the non-dedicated terminal includes CPU computing power and / or GPU computing power; The task receiving module is specifically configured to: receive an algorithm issuing command carrying a download address of the intelligent analysis algorithm sent by the server, and download the intelligent analysis algorithm from the download address in the algorithm issuing command; or, receive the intelligent analysis algorithm sent by the server; The device further includes: The computing resource reporting module is configured to report terminal computing resources of the non-dedicated terminal to the server, so that the server determines a target intelligent analysis task from the to-be-processed tasks based on computing resources required by each to-be-processed task and remaining resources, and distributes the target intelligent analysis task and an intelligent analysis algorithm corresponding to the target intelligent analysis task to the intelligent scheduling terminal agent; wherein the terminal computing resources include the remaining resources.

9. The apparatus of claim 8, wherein, The terminal computing resources further include total resources; and the apparatus further includes: An occupancy rate detection module configured to detect a resource occupancy rate of the non-dedicated terminal; An occupancy rate reduction request sending module configured to send a request for reducing the resource occupancy rate to the server when the resource occupancy rate reaches a first preset ratio, so that the server determines a task adjustment strategy based on total resources of the non-dedicated terminal, the first preset ratio, and a second preset ratio when the request for reducing the resource occupancy rate is received, and adjusts a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupancy rate of the non-dedicated terminal is reduced to the second preset ratio; The apparatus further includes: A query message receiving module configured to receive a state query message sent by the server; A state reporting module configured to report a processing state of the target intelligent analysis task to the server when the state query message is received, so that the server distributes the target intelligent analysis task to another non-dedicated terminal to continue processing the target intelligent analysis task when it is determined based on the processing state that processing of the target intelligent analysis task is abnormal. The server is deployed with an intelligent scheduling center service; and the task receiving module includes: A task receiving unit configured to receive a target intelligent analysis task and an intelligent analysis algorithm distributed by the intelligent scheduling center service.

10. A task processing apparatus characterized by comprising: A server applied to a task processing system, the system further including a non-dedicated terminal, wherein the non-dedicated terminal is deployed with an intelligent scheduling terminal agent, and the apparatus includes: A task determination module configured to determine an intelligent analysis algorithm corresponding to a target intelligent analysis task; A task distribution module configured to distribute the target intelligent analysis task and the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent receives the target intelligent analysis task and the intelligent analysis algorithm, uses the intelligent analysis algorithm to process the target intelligent analysis task by using computing power of the non-dedicated terminal, wherein the computing power of the non-dedicated terminal includes CPU computing power and / or GPU computing power; The task distribution module is specifically configured to: Send an algorithm distribution command carrying a download address of the intelligent analysis algorithm to the intelligent scheduling terminal agent, so that the intelligent scheduling terminal agent downloads the intelligent analysis algorithm from the download address in the algorithm distribution command; or send the intelligent analysis algorithm to the intelligent scheduling terminal agent; The apparatus further includes: An occupancy rate detection module configured to detect a resource occupancy rate of the non-dedicated terminal; An occupancy rate reduction request sending module configured to send a request for reducing the resource occupancy rate to the server when the resource occupancy rate reaches a first preset ratio, so that the server determines a task adjustment strategy based on total resources of the non-dedicated terminal, the first preset ratio, and a second preset ratio when the request for reducing the resource occupancy rate is received, and adjusts a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so that the resource occupancy rate of the non-dedicated terminal is reduced to the second preset ratio; The apparatus further includes: A query message receiving module configured to receive a state query message sent by the server; A state reporting module configured to report a processing state of the target intelligent analysis task to the server when the state query message is received, so that the server distributes the target intelligent analysis task to another non-dedicated terminal to continue processing the target intelligent analysis task when it is determined based on the processing state that processing of the target intelligent analysis task is abnormal. The computing resource receiving module is configured to receive the terminal computing resource of the non-dedicated terminal reported by the intelligent scheduling terminal agent, wherein the terminal computing resource comprises a residual resource. The task determining module comprises: The task determining unit is configured to determine a target intelligent analysis task from the tasks to be processed based on the computing resource required by each of the tasks to be processed and the residual resource, and determine an intelligent analysis algorithm corresponding to the target intelligent analysis task.

11. The apparatus of claim 10, wherein The terminal computing resource further comprises a total resource, and the apparatus further comprises: The resource reduction request receiving module is configured to receive a resource occupation rate reduction request sent by the intelligent scheduling terminal agent, wherein the resource occupation rate reduction request is sent by the intelligent scheduling terminal agent when the intelligent scheduling terminal agent detects that the resource occupation rate of the non-dedicated terminal reaches a first preset ratio. The adjustment strategy determining module is configured to determine a task adjustment strategy based on the total resource of the non-dedicated terminal, the first preset ratio, and a second preset ratio. The task adjustment module is configured to adjust a target intelligent analysis task being processed by the non-dedicated terminal according to the task adjustment strategy, so as to reduce the resource occupation rate of the non-dedicated terminal to the second preset ratio. The apparatus further comprises: The query message sending module is configured to send a state query message to the intelligent scheduling terminal agent. The processing state receiving module is configured to receive a processing state of the target intelligent analysis task reported by the intelligent scheduling terminal agent. The exception handling module is configured to, when it is determined that the processing of the target intelligent analysis task is abnormal based on the processing state, distribute the target intelligent analysis task to another non-dedicated terminal, so that the another non-dedicated terminal continues to process the target intelligent analysis task. The server can be deployed with an intelligent scheduling center service; and the task distribution module comprises: The task distribution unit is configured to distribute a target intelligent analysis task and an intelligent analysis algorithm to the intelligent scheduling terminal agent through the intelligent scheduling center service.

12. An electronic device, comprising: The apparatus comprises a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete mutual communication through the communication bus. The memory is configured to store a computer program. The processor is configured to execute the program stored on the memory, and implement the method steps of any one of claims 4 to 7.

13. A computer-readable storage medium, characterized in that, The computer program stored in the computer readable storage medium is executed by the processor, and the method steps of any one of claims 4 to 7 are implemented. The computer program stored in the computer readable storage medium is executed by the processor, and the method steps of any one of claims 4 to 7 are implemented.

Images