CN114979411B - Distributed image processing method, device, equipment and system - Google Patents

Abstract

The embodiment of the application provides a distributed image processing method, device, equipment and system, wherein the method comprises the following steps: receiving an image processing request sent by a client, and if the task type corresponding to the image processing request is determined to be a real-time task according to the image processing information of the image to be processed included in the image processing request, determining a target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule; the image processing request is sent to the target task distribution equipment, so that the target task distribution equipment determines target image processing equipment from the distributed multiple image processing equipment according to a first preset mode, performs image processing on the image to be processed through the target image processing equipment, and sends image processing result information to the client. Therefore, the method not only can meet the image processing requirement of large concurrency, but also can reduce the waste of equipment resources and maintain the stability of the system.

Description

A distributed image processing method, device, equipment and system

technical field

The present application relates to the technical field of image processing, and in particular to a distributed image processing method, device, device and system.

Background technique

With the advent of the era of big data, various data processing services have emerged as the times require, and image data processing services are one of the typical ones. The current image processing services such as image comparison and image recognition are usually provided based on the API (Application Programming Interface, Application Programming Interface) interface, that is, the client can directly obtain the corresponding image processing from the server by calling the API interface. Serve. However, some image processing services have higher requirements on the computing power of the server. Therefore, when an image processing service with higher computing power is provided through the API interface, a GPU (Graphics Processing Unit, Graphics Processing Unit) is required to carry an image processing request. Deploying a large number of GPU servers will lead to a great waste of server resources in idle time. Therefore, if the image processing service is only provided through the API interface, it is difficult to meet the current large concurrent image processing requirements.

Contents of the invention

The purpose of the embodiments of the present invention is to provide a distributed image processing method, device, device and system to solve the problem that the existing image processing service provision methods are difficult to meet the large concurrent image processing requirements.

In order to solve the above technical problems, the embodiment of the present application is implemented as follows:

In the first aspect, the embodiment of the present application provides a distributed image processing method, including:

receiving an image processing request sent by the client, where the image processing request includes image processing information of the image to be processed;

determining a task type corresponding to the image processing request according to the image processing information;

If the task type is a real-time task, then determine the target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule;

sending the image processing request to the target task distribution device, so that the target task distribution device determines a target image processing device from a plurality of distributed image processing devices according to a first preset method, and uses the target The image processing device performs image processing on the image to be processed, and sends image processing result information to the client.

In the second aspect, the embodiment of the present application provides a distributed image processing device, including:

A receiving module, configured to receive an image processing request sent by a client; the image processing request includes image processing information of an image to be processed;

A determining module, configured to determine a task type corresponding to the image processing request according to the image processing information;

A first scheduling module, configured to determine a target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule if the task type is a real-time task;

A sending module, configured to send the image processing request to the target task distribution device, so that the target task distribution device determines a target image processing device from a plurality of distributed image processing devices according to a preset method, and passes The target image processing device performs image processing on the image to be processed, and sends image processing result information to the client.

In a third aspect, an embodiment of the present application provides a distributed image processing system, including a client, multiple distributed task scheduling devices, multiple distributed task distribution devices, and multiple distributed image processing devices;

The client is configured to determine the image processing information of the image to be processed in response to the user's image processing operation; determine the target task scheduling device from the distributed plurality of task scheduling devices according to the second preset method, and determine the target task scheduling device according to the second preset method The image processing information sends an image processing request to the target task scheduling device;

The task scheduling device is configured to, when receiving the image processing request sent by the client, determine a task type corresponding to the image processing request according to the image processing information; if the task type is a real-time task, Then determine a target task distribution device from among the distributed plurality of task distribution devices according to a preset first scheduling rule; send the image processing request to the target task distribution device;

The task distribution device is configured to, when receiving the image processing request sent by the task scheduling device, determine a target image processing device from the plurality of distributed image processing devices according to a first preset manner, and sending the image processing request to the target image processing device;

The image processing device is configured to, when receiving the image processing request sent by the task distribution device, perform image processing on the image to be processed according to the image processing request, and send an image processing request to the client. result information.

In a fourth aspect, an embodiment of the present application provides a distributed image processing device, including a processor, a memory, and a computer program stored on the memory and operable on the processor, the computer program being executed by the The processor realizes the steps of the distributed image processing method as described in the first aspect when executed.

In the fifth aspect, the embodiment of the present application provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the distribution as described in the first aspect is realized. The steps of the formula image processing method.

In the distributed image processing method, device, device, and system in the embodiments of the present application, when receiving the image processing request sent by the client, if the corresponding task type is determined according to the image processing information of the image to be processed included in the image processing request is For real-time tasks, the target task distribution device is determined from multiple distributed task distribution devices according to the preset first scheduling rule; and, the image processing request is sent to the target task distribution device, so that the target task distribution device according to the first The preset method determines a target image processing device from among multiple distributed image processing devices, performs image processing on the image to be processed through the target image processing device, and sends image processing result information to the client. Therefore, by reasonably scheduling distributed devices to realize image processing, it can not only meet the large amount of concurrent image processing requirements, but also reduce the waste of device resources and maintain the stability of the system. In addition, corresponding processing is performed according to the task type corresponding to the image processing request, which realizes the hierarchical processing of the request, and can improve user experience in the case of a large amount of concurrent image processing requests, thereby maintaining or even increasing the business volume.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments described in the present invention. Those skilled in the art can also obtain other drawings based on these drawings without any creative effort.

FIG. 1 is a first schematic flow diagram of a distributed image processing method provided in an embodiment of the present application;

Fig. 2 is a second schematic flow diagram of the distributed image processing method provided by the embodiment of the present application;

FIG. 3 is a schematic flow chart of a third distributed image processing method provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of the module composition of the distributed image processing device provided by the embodiment of the present application;

Figure 5 is a schematic diagram of the composition of the distributed image processing system provided by the embodiment of the present application

FIG. 6 is a schematic structural diagram of a distributed image processing device provided by an embodiment of the present application.

Detailed ways

In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described The embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Accompanying drawing 1 is a schematic flow chart of the first distributed image processing method provided by the embodiment of the present invention. The method in FIG. 1 can be executed by distributed task scheduling devices arranged in different areas; wherein, the task scheduling device can be a mobile phone , Tablet PC, desktop computer, portable notebook and other terminal equipment, it can also be a server. As shown in Figure 1, the method at least includes the following steps:

Step S102, receiving an image processing request sent by the client; wherein, the image processing request includes image processing information of the image to be processed;

Specifically, an image processing-related client may be installed in the user's terminal device, and the client may be an independent application program (Application, APP for short), or a small program embedded in other application programs, or an web applications, etc. When the user needs to perform image processing, the client can be operated; correspondingly, the client determines the image processing information of the image to be processed in response to the user's image processing operation; A target task scheduling device is determined in the device, and an image processing request is sent to the target task scheduling device according to the image processing information. When the distributed task scheduling device is determined by the client as the target task scheduling device, it receives the image processing request sent by the client and performs subsequent processing.

Wherein, the image processing information includes image processing type information, image attribute information of the image to be processed, IP address of the client, and the like. Image processing type information represents operations that need to be performed on the image to be processed, such as download, upload, feature extraction, image recognition, etc.; image attribute information may include image identification information, image size, etc. of the image to be processed. The second preset method can be set according to the needs in practical applications. For example, it can be an automatic route distribution method. It can also be that the client obtains the IP address of each task scheduling device, and determines the relationship with each task scheduling device according to the obtained IP address. The minimum distance is obtained by comparing the determined distances, and the task scheduling device corresponding to the minimum distance is determined as the target task scheduling device.

Step S104, determining the task type corresponding to the image processing request according to the image processing information;

In order to improve user experience while satisfying a large amount of concurrent image processing requirements, in the embodiment of the present application, task classification is performed on each image processing request, and corresponding processing is performed according to the task type. The task types may include real-time tasks and delayed tasks. Real-time tasks indicate that image processing requests need to be processed immediately, and delayed tasks indicate that image processing requests can be processed after a period of time.

Step S106, if the task type is a real-time task, then determine the target task distribution device from a plurality of distributed task distribution devices according to the preset first scheduling rule;

The distributed image processing system corresponding to the distributed image processing method provided in the embodiment of the present application includes not only distributed multiple task scheduling devices with task scheduling functions, but also distributed multiple task distribution devices and distributed Multiple image processing devices. Wherein, the task distribution device has a task distribution function, capable of distributing image processing requests whose task type is a real-time task, so as to distribute the image processing requests to a determined target image processing device. The image processing device is used to provide image processing services, and can perform corresponding processing on the image to be processed according to the obtained image processing request, such as download processing, feature comparison processing, etc. It should be pointed out that each device can integrate at least one function. For example, a certain device not only has a task scheduling function, but also has a task distribution function, that is, the device is not only a task scheduling device, but also a task distribution device, which can reduce image processing. The waste of bandwidth resources caused by the transfer of image resources in the process can ensure real-time processing speed. In practical applications, containerization technologies such as virtual machines and docker images can be used to realize the integration of the above-mentioned multiple functions.

Step S108, sending the image processing request to the target task distribution device, so that the target task distribution device determines the target image processing device from a plurality of distributed image processing devices according to the first preset method, and uses the target image processing device to be processed The image is processed, and the image processing result information is sent to the client.

Specifically, when the target task distribution device receives the image processing request, it determines the target image processing device from multiple distributed image processing devices according to the first preset method, and sends the image processing request to the target image processing device. The target image processing device performs image processing on the image to be processed according to the received image processing request, and sends image processing result information to the corresponding client according to information such as the client's IP address or client ID in the image processing request. Among them, the first preset method can be set according to the needs in practical applications. For example, it can be an automatic distribution method of routing, or it can also be that the target task distribution device obtains the IP address of each image processing device connected to it. Determine the distance between the address and each connected image processing device, compare the determined distances to obtain the minimum distance, and determine the image processing device corresponding to the minimum distance as the target image processing device, etc.

It should be noted that the image processing request may or may not include the image to be processed. For example, when the image processing request is used to request operations such as uploading and image recognition of the image to be processed, the image processing request may include the image to be processed provided by the user; when the image processing request is used to request operations such as downloading and viewing, the image processing request The image to be processed may not be included, and the image to be processed is stored in a specified storage area, such as the cloud. Correspondingly, when the image processing request does not include the image to be processed, the target image processing device obtains the corresponding image to be processed from the specified storage area according to the image identification information of the image to be processed included in the image processing request, and The operation type information of the obtained image to be processed is processed accordingly.

In one or more embodiments of the present application, when receiving the image processing request sent by the client, if it is determined according to the image processing information of the image to be processed included in the image processing request that the corresponding task type is a real-time task, then according to the preset The first scheduling rule determines the target task distribution device from among the distributed multiple task distribution devices; Determine the target image processing device among the image processing devices, and perform image processing on the image to be processed by the target image processing device, and send the image processing result information to the client. Therefore, by reasonably scheduling distributed devices to realize image processing, it can not only meet the large amount of concurrent image processing requirements, but also reduce the waste of device resources and maintain the stability of the system. In addition, corresponding processing is performed according to the task type corresponding to the image processing request, which realizes the hierarchical processing of the request, and can improve user experience in the case of a large amount of concurrent image processing requests, thereby maintaining or even increasing the business volume.

Since multiple distributed task distribution devices are deployed in different areas, such as different cities, different places in the same city, etc., in order to improve the processing efficiency of image processing requests whose task type is real-time tasks, one or more embodiments of the present application In the method, the target task distribution device is determined based on the transmission bandwidth of the task distribution device and the transmission delay between the task scheduling device and the task distribution device. Specifically, as shown in FIG. 2, step S106 may include the following steps S106-2 to S106-6:

Step S106-2, if the task type is a real-time task, obtain the transmission bandwidth and transmission delay corresponding to each task distribution device among the multiple distributed task distribution devices;

Specifically, the task scheduling device sends information acquisition requests to each connected task distribution device, and records the sending time of the information acquisition requests. After receiving the information acquisition request, the task distribution device sends response data to the task scheduling device according to its current transmission bandwidth. The task scheduling device receives the response data sent by the task distribution device and records the receiving time, determines the transmission delay between the task scheduling device and the corresponding task distribution device according to the recorded sending time and receiving time, and calculates the time delay from the received response data Obtain the transmission bandwidth of the corresponding task distribution device.

Step S106-4, according to the obtained transmission bandwidth and transmission delay, determine the second weight corresponding to each task distribution device;

Optionally, in one or more embodiments of the present application, the second weight is determined based on a preset correspondence relationship. Specifically, step S106-4 may include: based on the preset correspondence between the transmission bandwidth and the third sub-weight, determining the third sub-weight corresponding to each acquired transmission bandwidth; based on the preset transmission delay and the fourth sub-weight The corresponding relationship of the sub-weights is to determine the obtained fourth sub-weight corresponding to each transmission delay; and to determine the second weight corresponding to each task distribution device according to the determined third sub-weight and fourth sub-weight.

Wherein, the corresponding relationship between the transmission bandwidth and the third sub-weight, and the corresponding relationship between the transmission delay and the fourth sub-weight can be set according to actual needs in practical applications. As an example, the third sub-weight is recorded as Wb, and the fourth sub-weight is recorded as Wt; when the transmission bandwidth is less than 100M, the corresponding third sub-weight Wb=0.8; when the transmission bandwidth is between 100M and 500M (including 100M and 500M), the corresponding third sub-weight Wb=1; when the transmission bandwidth is greater than 500M, the corresponding third sub-weight Wb=1.2. When the transmission delay is less than 10ms, the corresponding fourth sub-weight Wt=1; when the transmission delay is between 10ms and 100ms (including 10ms and 100ms), the corresponding fourth sub-weight Wt=0.9; when the transmission delay When greater than 100ms, the corresponding fourth sub-weight Wt=0.7. Record the second weight as W2, then it can be W2=Wb+Wt, that is, add the third sub-weight and the second sub-weight, and determine the result of the addition as the second weight; it can also be W2 =a*Wb+c*Ws, wherein, a and c are coefficients, and their specific values can be set by themselves in practical applications.

In one or more embodiments of the present application, the second weight may also be determined according to a preset calculation manner. Specifically, step S106-4 may include: calculating the second weight corresponding to each task distribution device based on the transmission bandwidth and transmission delay corresponding to each task distribution device according to a preset calculation method. Among them, the calculation method can be set according to the needs in practical applications. For example, the second weight is recorded as W2, W2=d*transmission bandwidth+f*transmission delay, where 0<d<1, 0<f<1 wait.

Step S106-6, according to the second weight, determine a target task distribution device for distributing the image processing request from multiple task distribution devices.

Specifically, the obtained second weights are compared to obtain the largest second weight; and the task distribution device corresponding to the largest second weight is determined as the target task distribution device for distributing the image processing request.

Therefore, based on the transmission bandwidth and transmission delay corresponding to each task distribution device, determining the target task distribution device from multiple distributed task distribution devices can effectively reduce the transmission time of image processing requests between devices, and It can ensure that the target task distribution device has enough physical resources to distribute and process the image processing request, which not only realizes the effective scheduling of the task distribution device, avoids the waste of device resources, but also improves the processing efficiency of the image processing request to meet the real-time requirements image processing needs.

Considering that for different image processing types and images of different sizes, the real-time requirements of image processing are often different. Take the image processing type as an example. For example, when the user wants to upload the image in his mobile phone to the network disk for storage, that is, the image processing type is upload. At this time, the user may not pay attention to when the upload is completed, that is, real-time The demand is relatively low; another example is that the user performs image comparison to achieve identity authentication when handling business, that is, the image processing type is image comparison. At this time, the user hopes to get the image comparison result as soon as possible, so as to complete the business as soon as possible, that is, real-time Sexual needs are high. Based on this, as shown in FIG. 3, step S104 may include the following steps S104-2 to S104-4, and correspondingly, step S106 may include the following steps S106-8, and the method may also include the following steps S110 to S112:

Step S104-2, according to the image processing type information and image attribute information included in the image processing information, determine the first weight corresponding to the image processing request;

Specifically, based on the preset correspondence between the image processing type information and the first sub-weight, determine the first sub-weight corresponding to the image processing type information included in the image processing information; according to the preset second sub-weight determination method, Determining a second sub-weight corresponding to the image attribute information included in the image processing information; determining a first weight corresponding to the image processing request according to the determined first sub-weight and the second sub-weight.

Wherein, the first sub-weight corresponding to the image processing type, the second sub-weight corresponding to the image attribute information, and the determination method of the first weight can all be set according to needs in practical applications. As an example, the first sub-weight corresponding to image processing types such as image search and image comparison is 1, which can be recorded as Wr=1, and the first sub-weight corresponding to image processing types such as uploading, downloading, and viewing is 0.5, which can be recorded as Wr = 0.5. The method for determining the second sub-weight may be Ws=1.2-0.1x, where x is the size of the image to be processed, and the unit is Mb. Record the first weight as W1, then it can be W1=Wr+Ws, that is, sum the first sub-weight and the second sub-weight, and determine the result of the sum as the first weight; it can also be W1 =m*Wr+n*Ws, where m and n are coefficients, and their specific values can be set by themselves.

Step S104-4, determine whether the first weight is less than the first preset weight, if so, determine that the task type corresponding to the image processing request is a delayed task, and perform step S110; if not, determine that the task type corresponding to the image processing request is For real-time tasks, execute step S106-2.

Wherein, the first preset weight can be set according to needs in practical applications, for example, it is 1.6.

Step S106-8, determining a target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule;

For the process of determining the target task distribution device according to the first scheduling rule, reference may be made to the above-mentioned related descriptions, and repeated descriptions will not be repeated here.

Step S110, determining a target message queue from a plurality of distributed message queues according to a preset second scheduling rule;

Wherein, the second dispatching rule can be set according to needs in practical applications, for example, it can be an automatic route distribution method; it can also determine the distance to each message queue according to the preset address information of each message queue. The minimum distance is obtained for each determined distance, and the message queue corresponding to the minimum distance is determined as the target message queue, etc.

Step S112, saving the image processing request to the target message queue, so that the image processing device corresponding to the target message queue performs image processing on the image to be processed according to the image processing request in the target message queue, and sends image processing result information to the client.

In this embodiment of the application, each message queue can correspond to multiple image processing devices, and each image processing device can access the corresponding message queue every preset first time interval, or access the corresponding message when the preset time point is reached queue, and process the image processing requests in the accessed message queue. Wherein, the preset first time interval or the preset time point of each image processing device may be the same or different.

Further, in order to avoid repeated processing of the same image processing request, in one or more embodiments of the present application, when the image processing device obtains the image processing request to be processed from the corresponding message queue, the message queue management module sends The state flag of the corresponding image processing request is set to the first flag representing locked, and when the processing completion information is obtained from the image processing device, the state flag is set to the second flag representing the completion of processing, or the corresponding image The processing request is removed from the message queue.

Further, in order to improve user experience, in one or more embodiments of the present application, processing priorities may also be set for image processing requests whose task type is a delayed task, and processed in order of priority from high to low. Specifically, the image processing information may also include the user information of the user. Step S112 may include: determining the priority information of the image processing request according to the user information included in the image processing request, and saving the determined priority information to the image processing request corresponding to the In the target message queue, based on the priority information in the target message queue, the image processing device corresponding to the target message queue performs image processing on the corresponding image to be processed according to the corresponding image processing request, and sends the image processing device to the client. result information.

Among them, the specific content of the user information can be set according to the needs in practical applications. For example, the user information can be information indicating that the user is an ordinary user, an ordinary member user, a super member user, etc., and image processing requests sent by ordinary member users are given priority. The priority is higher than that of image processing requests sent by ordinary users, and the priority of image processing requests sent by ordinary member users is lower than that of super member users. The user information may also be grade information and the like determined by evaluating the user's image processing situation.

Further, considering that in practical applications, for image processing requests whose task type is delayed tasks, users may repeatedly send image processing requests. For example, the user submitted an image processing request whose image operation type is upload in Beijing this Monday Request, the user went to Shenzhen on a business trip on Wednesday and found that the image to be processed had not been uploaded, so the user submitted the image processing request again in Shenzhen. When the user submits the same image processing request repeatedly, to a certain extent, it means that the user wants the image processing request to be processed as soon as possible. Based on this, in one or more embodiments of the present application, the method may also include:

If it is determined by the message queue management module that the image processing request satisfies the preset priority adjustment condition, then the priority information of the corresponding image processing request will be adjusted, so that the image processing device will adjust the corresponding priority information according to the adjusted priority information. Process images for image processing.

Specifically, as in the aforementioned example, the user may repeatedly send image processing requests through the client at different locations, and each time the task scheduling module receives the repeated image processing requests, it will The message queues may be different, therefore, the repeated image processing requests may be stored in different target message queues. Based on this, the image processing requests in each message queue are compared at every preset second time interval by the message queue management module, and if it is determined that there are repeated image processing requests, the number of the repeated image processing requests is counted; If it is determined that the counted number is not less than the preset number, it is determined that the repeated image processing request satisfies the priority adjustment condition, and the priority information corresponding to the first saved image processing request is adjusted according to the order of storage time, increasing the priority so that the image processing request is processed first; and deleting other image processing requests in the repeated image processing request. Therefore, by applying the message queue and classifying the image processing requests whose task type is a delayed task, it can not only relieve the system pressure in the case of bursting requests, but also improve the utilization rate of computing power resources of the image processing equipment, and can Improve user experience and reduce business loss.

In the distributed image processing method provided by the embodiment of the present application, when receiving the image processing request sent by the client, if it is determined according to the image processing information of the image to be processed included in the image processing request that the corresponding task type is a real-time task, then according to the preset The set first scheduling rule determines the target task distribution device from among the distributed task distribution devices; and, sends the image processing request to the target task distribution device, so that the target task distribution device starts from the distributed Determine the target image processing device among the plurality of image processing devices, perform image processing on the image to be processed by the target image processing device, and send image processing result information to the client. Therefore, by reasonably scheduling distributed devices to realize image processing, it can not only meet the large amount of concurrent image processing requirements, but also reduce the waste of device resources and maintain the stability of the system. In addition, corresponding processing is performed according to the task type corresponding to the image processing request, which realizes the hierarchical processing of the request, and can improve user experience in the case of a large amount of concurrent image processing requests, thereby maintaining or even increasing the business volume.

Corresponding to the distributed image processing method provided in the foregoing embodiments, based on the same technical concept, an embodiment of the present invention further provides a distributed image processing device, which can be applied to a task scheduling device. Fig. 4 is a schematic diagram of the module composition of the distributed image processing device provided by the embodiment of the present application. As shown in Fig. 4, the data query device includes:

The receiving module 201 is configured to receive an image processing request sent by the client; the image processing request includes image processing information of the image to be processed;

A determining module 202, configured to determine a task type corresponding to the image processing request according to the image processing information;

The first scheduling module 203 is configured to determine a target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule if the task type is a real-time task;

A sending module 204, configured to send the image processing request to the target task distribution device, so that the target task distribution device determines a target image processing device from a plurality of distributed image processing devices according to a preset method, and Perform image processing on the image to be processed by the target image processing device, and send image processing result information to the client.

Optionally, the image processing information includes image processing type information and image attribute information of the image to be processed; correspondingly, the determining module 202 is specifically configured to:

determining a first weight corresponding to the image processing request according to the image processing type information and the image attribute information;

determining whether the first weight is less than a first preset weight;

If so, then determine that the task type corresponding to the image processing request is a delayed processing task;

If not, it is determined that the task type corresponding to the image processing request is a real-time task.

Optionally, the determining module 202 is further specifically configured to:

Based on the preset correspondence between the image processing type information and the first sub-weight, determine the first sub-weight corresponding to the image processing type information included in the image processing information;

Determine the second sub-weight corresponding to the image attribute information included in the image processing information according to the preset second sub-weight determination method;

Determine the first weight corresponding to the image processing request according to the determined first sub-weight and the second sub-weight.

Optionally, the first scheduling module 203 is specifically configured to:

Obtain the transmission bandwidth and transmission delay corresponding to each task distribution device among the multiple distributed task distribution devices;

determining a second weight corresponding to each task distribution device according to the transmission bandwidth and the transmission delay;

A target task distribution device for performing distribution processing on the image processing request is determined from the plurality of task distribution devices according to the second weight.

Optionally, the first scheduling module 203 is further specifically configured to:

Based on the preset correspondence between the transmission bandwidth and the third sub-weight, determine the acquired third sub-weight corresponding to each of the transmission bandwidths; based on the preset correspondence between the transmission delay and the fourth sub-weight, determine the acquired The fourth sub-weight corresponding to each of the transmission delays; according to the third sub-weight and the fourth sub-weight, determine the second weight corresponding to each of the task distribution devices;

or,

According to a preset calculation manner, the second weight corresponding to each task distribution device is calculated based on the transmission bandwidth and transmission delay corresponding to each task distribution device.

Optionally, the device further includes: a second scheduling module;

The second scheduling module, if the determining module 202 determines that the task type is a delayed processing task, then determine a target message queue from among multiple distributed message queues according to a preset second scheduling rule; and,

storing the image processing request in the target message queue, so that the image processing device corresponding to the target message queue performs image processing on the image to be processed according to the image processing request in the target message queue process, and send image processing result information to the client.

In the distributed image processing device provided in the embodiment of the present application, when receiving the image processing request sent by the client, if it is determined according to the image processing information of the image to be processed included in the image processing request that the corresponding task type is a real-time task, then according to the preset The set first scheduling rule determines the target task distribution device from among the distributed task distribution devices; and, sends the image processing request to the target task distribution device, so that the target task distribution device starts from the distributed Determine the target image processing device among the plurality of image processing devices, perform image processing on the image to be processed by the target image processing device, and send image processing result information to the client. Therefore, by reasonably scheduling distributed devices to realize image processing, it can not only meet the large amount of concurrent image processing requirements, but also reduce the waste of device resources and maintain the stability of the system. In addition, corresponding processing is performed according to the task type corresponding to the image processing request, which realizes the hierarchical processing of the request, and can improve user experience in the case of a large amount of concurrent image processing requests, thereby maintaining or even increasing the business volume.

The distributed image processing apparatus provided in the embodiment of the present application can implement each process in the embodiment corresponding to the above-mentioned distributed image processing method, and details are not repeated here to avoid repetition.

It should be noted that the distributed image processing device provided in the embodiment of the present application and the distributed image processing method provided in the embodiment of the present application are based on the same inventive concept, so the specific implementation of this embodiment can refer to the implementation of the aforementioned distributed image processing method , the repetitions will not be repeated.

Corresponding to the distributed image processing method provided in the foregoing embodiments, based on the same technical concept, an embodiment of the present invention also provides a distributed image processing system. Figure 5 is a schematic diagram of the composition of the distributed image processing system provided by the embodiment of the present application. As shown in Figure 5, the distributed image processing system includes: a client 301, a distributed multiple task scheduling device 302, a A task distribution device 303 and a plurality of distributed image processing devices 304;

The client 301 is configured to determine the image processing information of the image to be processed in response to the user's image processing operation; determine the target task scheduling device 302 from the distributed plurality of task scheduling devices 302 according to a second preset method , and send an image processing request to the target task scheduling device 302 according to the image processing information;

The task scheduling device 302 is configured to, when receiving the image processing request sent by the client 301, determine a task type corresponding to the image processing request according to the image processing information; if the task type is real-time task, then determine the target task distribution device 303 from the distributed plurality of task distribution devices 303 according to the preset first scheduling rule; send the image processing request to the target task distribution device 303;

The task distribution device 303 is configured to, when receiving the image processing request sent by the task scheduling device 302, determine the target image processing device from the distributed plurality of image processing devices 304 according to a first preset method. device 304, and send the image processing request to the target image processing device 304;

The image processing device 304 is configured to, when receiving the image processing request sent by the task distribution device 303, perform image processing on the image to be processed according to the image processing request, and send the request to the client 301 Send image processing result information.

In the distributed image processing system provided in the embodiment of the present application, when the task scheduling device receives the image processing request sent by the client, if it determines that the corresponding task type is a real-time task according to the image processing information of the image to be processed included in the image processing request, Then determine the target task distribution device from the distributed multiple task distribution devices according to the preset first scheduling rule; and send the image processing request to the target task distribution device, so that the target task distribution device A target image processing device is determined from a plurality of distributed image processing devices, image processing is performed on the image to be processed by the target image processing device, and image processing result information is sent to the client. Therefore, by reasonably scheduling distributed devices to realize image processing, it can not only meet the large amount of concurrent image processing requirements, but also reduce the waste of device resources and maintain the stability of the system. In addition, corresponding processing is performed according to the task type corresponding to the image processing request, which realizes the hierarchical processing of the request, and can improve user experience in the case of a large amount of concurrent image processing requests, thereby maintaining or even increasing the business volume.

The distributed image processing system provided in the embodiment of the present application can implement each process in the embodiment corresponding to the above-mentioned distributed image processing method, and details are not repeated here to avoid repetition.

It should be noted that the distributed image processing system provided by the embodiment of the present application and the distributed image processing method provided by the embodiment of the present application are based on the same inventive concept, so the specific implementation of this embodiment can refer to the implementation of the aforementioned distributed image processing method , the repetitions will not be repeated.

Corresponding to the distributed image processing method provided in the above embodiment, based on the same technical concept, the embodiment of the present invention further provides a distributed image processing device, which is used to execute the above distributed image processing method. Fig. 6 is a schematic structural diagram of a distributed image processing device implementing various embodiments of the present invention. As shown in Fig. 6, distributed image processing devices may have relatively large differences due to different configurations or performances, and may include one or one The above-mentioned processor 401 and memory 402 may store one or more stored application programs or data in the memory 402 . Wherein, the storage 402 may be a short-term storage or a persistent storage. The application program stored in the memory 402 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions for distributed image processing devices. Furthermore, the processor 401 may be configured to communicate with the memory 402, and execute a series of computer-executable instructions in the memory 402 on the distributed image processing device. The distributed image processing device may also include one or more power sources 403 , one or more wired or wireless network interfaces 404 , one or more input and output interfaces 405 , and one or more keyboards 406 .

In a specific embodiment, the distributed image processing device includes 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 bus; the memory is used to store computer Program; the processor is used to execute the program stored on the memory, and realize the following method steps:

receiving an image processing request sent by the client, where the image processing request includes image processing information of the image to be processed;

determining a task type corresponding to the image processing request according to the image processing information;

If the task type is a real-time task, then determine the target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule;

sending the image processing request to the target task distribution device, so that the target task distribution device determines a target image processing device from a plurality of distributed image processing devices according to a first preset method, and uses the target The image processing device performs image processing on the image to be processed, and sends image processing result information to the client.

In the distributed image processing device in the embodiment of the present application, when receiving the image processing request sent by the client, if it is determined according to the image processing information of the image to be processed included in the image processing request that the corresponding task type is a real-time task, then according to the preset The set first scheduling rule determines the target task distribution device from among the distributed task distribution devices; and, sends the image processing request to the target task distribution device, so that the target task distribution device starts from the distributed Determine the target image processing device among the plurality of image processing devices, perform image processing on the image to be processed by the target image processing device, and send image processing result information to the client. Therefore, by reasonably scheduling distributed devices to realize image processing, it can not only meet the large amount of concurrent image processing requirements, but also reduce the waste of device resources and maintain the stability of the system. In addition, corresponding processing is performed according to the task type corresponding to the image processing request, which realizes the hierarchical processing of the request, and can improve user experience in the case of a large amount of concurrent image processing requests, thereby maintaining or even increasing the business volume.

The distributed image processing device provided in the embodiment of the present application can implement each process in the embodiment corresponding to the above-mentioned distributed image processing method, and details are not repeated here to avoid repetition.

It should be noted that the distributed image processing device provided by the embodiment of the present invention and the distributed image processing method provided by the embodiment of the present invention are based on the same inventive concept, so the specific implementation of this embodiment can refer to the implementation of the aforementioned distributed image processing method , the repetitions will not be repeated.

The embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the following method steps are implemented:

receiving an image processing request sent by the client, where the image processing request includes image processing information of the image to be processed;

determining a task type corresponding to the image processing request according to the image processing information;

If the task type is a real-time task, then determine the target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule;

sending the image processing request to the target task distribution device, so that the target task distribution device determines a target image processing device from a plurality of distributed image processing devices according to a first preset method, and uses the target The image processing device performs image processing on the image to be processed, and sends image processing result information to the client.

When the computer-readable storage medium in the embodiment of the present invention is executed by the processor, it receives the image processing request sent by the client, and if it is determined according to the image processing information of the image to be processed included in the image processing request that the corresponding task type is a real-time task, Then determine the target task distribution device from the distributed multiple task distribution devices according to the preset first scheduling rule; and send the image processing request to the target task distribution device, so that the target task distribution device A target image processing device is determined from a plurality of distributed image processing devices, image processing is performed on the image to be processed by the target image processing device, and image processing result information is sent to the client. Therefore, by reasonably scheduling distributed devices to realize image processing, it can not only meet the large amount of concurrent image processing requirements, but also reduce the waste of device resources and maintain the stability of the system. In addition, corresponding processing is performed according to the task type corresponding to the image processing request, which realizes the hierarchical processing of the request, and can improve user experience in the case of a large amount of concurrent image processing requests, thereby maintaining or even increasing the business volume.

The computer-readable storage medium provided in the embodiment of the present application can realize each process in the embodiment corresponding to the above-mentioned distributed image processing method, and to avoid repetition, details are not repeated here.

It should be noted that the computer-readable storage medium provided by the embodiment of the present invention and the distributed image processing method provided by the embodiment of the present invention are based on the same inventive concept, so the specific implementation of this embodiment can refer to the implementation of the aforementioned distributed image processing method , the repetitions will not be repeated.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-permanent storage in computer readable media, in the form of random access memory (RAM) and/or nonvolatile memory such as read only memory (ROM) or flash RAM. Memory is an example of computer readable media.

Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridge, tape magnetic disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media excludes transitory computer-readable media, such as modulated data signals and carrier waves.

It should also be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes Other elements not expressly listed, or elements inherent in the process, method, commodity, or apparatus are also included. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The above are only examples of the present application, and are not intended to limit the present application. For those skilled in the art, various modifications and changes may occur in this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims (10)

1. A distributed image processing method, characterized in that, comprising: receiving an image processing request sent by the client, where the image processing request includes image processing information of the image to be processed; determining a task type corresponding to the image processing request according to the image processing information; If the task type is a real-time task, then determine the target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule; sending the image processing request to the target task distribution device, so that the target task distribution device determines a target image processing device from a plurality of distributed image processing devices according to a first preset method, and uses the target The image processing device performs image processing on the image to be processed, and sends image processing result information to the client. 2. The method according to claim 1, wherein the image processing information includes image processing type information and image attribute information of the image to be processed; The determining the task type corresponding to the image processing request according to the image processing information includes: determining a first weight corresponding to the image processing request according to the image processing type information and the image attribute information; determining whether the first weight is less than a first preset weight; If so, then determine that the task type corresponding to the image processing request is a delayed processing task; If not, it is determined that the task type corresponding to the image processing request is a real-time task. 3. The method according to claim 2, wherein the determining the first weight corresponding to the image processing request according to the image processing type information and the image attribute information comprises: Based on the preset correspondence between the image processing type information and the first sub-weight, determine the first sub-weight corresponding to the image processing type information included in the image processing information; Determine the second sub-weight corresponding to the image attribute information included in the image processing information according to the preset second sub-weight determination method; Determine the first weight corresponding to the image processing request according to the determined first sub-weight and the second sub-weight. 4. The method according to claim 1, wherein the determining the target task distribution device from a plurality of distributed task distribution devices according to the preset first task scheduling rule comprises: Obtain the transmission bandwidth and transmission delay corresponding to each task distribution device among the multiple distributed task distribution devices; determining a second weight corresponding to each task distribution device according to the transmission bandwidth and the transmission delay; A target task distribution device for performing distribution processing on the image processing request is determined from the plurality of task distribution devices according to the second weight. 5. The method according to claim 4, wherein the determining the second weight corresponding to each of the task distribution devices according to the transmission bandwidth and the transmission delay comprises: Based on the preset correspondence between the transmission bandwidth and the third sub-weight, determine the acquired third sub-weight corresponding to each of the transmission bandwidths; based on the preset correspondence between the transmission delay and the fourth sub-weight, determine the acquired The fourth sub-weight corresponding to each of the transmission delays; according to the third sub-weight and the fourth sub-weight, determine the second weight corresponding to each of the task distribution devices; or, According to a preset calculation manner, the second weight corresponding to each task distribution device is calculated based on the transmission bandwidth and transmission delay corresponding to each task distribution device. 6. The method according to claim 1, further comprising: If it is determined that the task type is a delayed processing task, then determine the target message queue from a plurality of distributed message queues according to the preset second scheduling rule; storing the image processing request in the target message queue, so that the image processing device corresponding to the target message queue performs image processing on the image to be processed according to the image processing request in the target message queue process, and send image processing result information to the client. 7. A distributed image processing device, comprising: A receiving module, configured to receive an image processing request sent by a client; the image processing request includes image processing information of an image to be processed; A determining module, configured to determine a task type corresponding to the image processing request according to the image processing information; A first scheduling module, configured to determine a target task distribution device from a plurality of distributed task distribution devices according to a preset first scheduling rule if the task type is a real-time task; A sending module, configured to send the image processing request to the target task distribution device, so that the target task distribution device determines a target image processing device from a plurality of distributed image processing devices according to a preset method, and passes The target image processing device performs image processing on the image to be processed, and sends image processing result information to the client. 8. A distributed image processing system, comprising: a client, a plurality of distributed task scheduling devices, a plurality of distributed task distribution devices and a plurality of distributed image processing devices; The client is configured to determine the image processing information of the image to be processed in response to the user's image processing operation; determine the target task scheduling device from the distributed plurality of task scheduling devices according to the second preset method, and determine the target task scheduling device according to the second preset method The image processing information sends an image processing request to the target task scheduling device; The task scheduling device is configured to, when receiving the image processing request sent by the client, determine a task type corresponding to the image processing request according to the image processing information; if the task type is a real-time task, Then determine a target task distribution device from among the distributed plurality of task distribution devices according to a preset first scheduling rule; send the image processing request to the target task distribution device; The task distribution device is configured to, when receiving the image processing request sent by the task scheduling device, determine a target image processing device from the plurality of distributed image processing devices according to a first preset manner, and sending the image processing request to the target image processing device; The image processing device is configured to, when receiving the image processing request sent by the task distribution device, perform image processing on the image to be processed according to the image processing request, and send an image processing request to the client. result information. 9. A distributed image processing device, characterized in that it comprises a processor, a memory, and a computer program stored on the memory and operable on the processor, when the computer program is executed by the processor Realize the steps of the distributed image processing method as described in any one of claims 1 to 6. 10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the distribution according to any one of claims 1 to 6 is realized. The steps of the formula image processing method.

Images