CN117056073A - Computing resource optimal configuration method and device under industrial visual analysis - Google Patents
Computing resource optimal configuration method and device under industrial visual analysis Download PDFInfo
- Publication number
- CN117056073A CN117056073A CN202311034410.3A CN202311034410A CN117056073A CN 117056073 A CN117056073 A CN 117056073A CN 202311034410 A CN202311034410 A CN 202311034410A CN 117056073 A CN117056073 A CN 117056073A
- Authority
- CN
- China
- Prior art keywords
- resource information
- computing
- video stream
- empty
- occupancy rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004458 analytical method Methods 0.000 title claims abstract description 42
- 230000000007 visual effect Effects 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 51
- 230000008569 process Effects 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44505—Configuring for program initiating, e.g. using registry, configuration files
Abstract
The invention provides a computing resource optimal allocation method and a computing resource optimal allocation device under industrial visual analysis, which relate to the technical field of video and image processing, and comprise the following steps: virtually dividing the computing resource information of the target area to determine computing nodes; determining unit computing resource information of a computing node when processing a real-time video stream received by a target area; the unit computing resource information comprises resource information occupancy rates of all computing nodes at different moments; determining the empty resource information of the computing node according to the unit computing resource information; and processing the acquired local video stream according to the empty resource information. Under the condition of ensuring the stability of the production environment, the optimal configuration of the computing resources under the industrial visual analysis is realized, and the resource utilization rate is improved.
Description
Technical Field
The invention relates to the technical field of video and image processing, in particular to a computing resource optimal configuration method and device under industrial visual analysis.
Background
In recent years, the intelligent detection technology of visual AI is gradually applied to the industrial field, and is used for self-adaptive control, energy consumption optimization, defect detection and the like in the production and manufacturing process, and on the other hand, detection analysis and early warning treatment are performed on real-time detection pictures of video monitoring equipment, so that the defect of traditional personnel monitoring is overcome. The vision AI algorithm model application brings a great deal of computing resource requirements, and because many industrial enterprises use private networks and cannot utilize cloud computing platforms on the Internet, a large-scale AI reasoning server cluster needs to be established, and each device is responsible for a certain number of video stream analyses. However, in practical industrial applications, real-time visual AI detection is no longer needed in a part of the areas during shutdown, which results in idle computing resources and low utilization of resources. Therefore, how to fully utilize idle computing resources while ensuring industrial production is a problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a computing resource optimal configuration method and device under industrial visual analysis.
In a first aspect, an embodiment of the present invention provides a method for optimizing configuration of computing resources under industrial visual analysis, including:
virtually dividing the computing resource information of the target area to determine computing nodes;
determining unit computing resource information of the computing node when processing the real-time video stream received by the target area; the unit computing resource information comprises resource information occupancy rates of all computing nodes at different moments;
determining the empty resource information of the computing node according to the unit computing resource information;
and processing the acquired local video stream according to the empty resource information.
Optionally, the determining unit computing resource information of the computing node when processing the real-time video stream received by the target area includes:
acquiring a historical real-time video stream processed by the target area in a historical time;
and carrying out statistical analysis on the historical real-time video stream to determine the resource information occupancy rate of the computing node at different moments.
Optionally, the resource information occupancy rate includes a CPU occupancy rate, a GPU occupancy rate, a memory occupancy rate, and a video memory occupancy rate;
the determining the empty resource information of the computing node according to the unit computing resource information comprises the following steps:
screening the resource information occupancy rate with the highest occupancy rate from the unit computing resource information, and determining the resource information occupancy rate as key resource information;
and determining the empty resource information of the computing node at different moments according to the key resource information and the preset full load occupancy rate.
Optionally, the empty resource information includes an empty resource occupancy rate; the empty resource occupancy rate is determined by the following formula:
IR t ＝R max -R t-m
wherein IR t For characterizing the unoccupied resource occupancy within a time period t; r is R max For characterizing the preset full load occupancy; r is R t-m And the maximum resource information occupancy rate reached by the key resource information in the t time period is represented.
Optionally, the processing the acquired local video stream according to the empty resource information includes:
according to the empty resource information, performing slicing processing on the local video stream to obtain a sliced video;
extracting features of the segmented video to obtain a segmented video to be processed carrying space-time information; wherein the spatio-temporal information includes temporal information and spatial information of the segmented video in the local video stream;
processing the to-be-processed segmented video according to the empty resource information to obtain an analysis result;
and fusing the analysis results according to the space-time information to obtain a target analysis result corresponding to the local video stream.
Optionally, the processing the to-be-processed segmented video according to the empty resource information includes:
the empty resource information comprises an empty resource occupancy rate;
acquiring the occupancy rate of the empty resource in each time period in the historical time so as to predict the occupancy rate of the target empty resource at the current moment;
determining the resource rate occupied by a single channel, and calculating the ratio of the target unoccupied resource occupancy rate to the resource rate occupied by the single channel to obtain the channel number of the virtual video channels;
and creating virtual video channels with the channel number, and sending the to-be-processed segmented video to the virtual video channels for processing.
Optionally, after the processing the acquired local video stream according to the empty resource information, the method further includes:
when the target area receives the real-time video stream to be processed again, optimizing configuration is carried out on the computing resource information according to the unit computing resource information and the empty resource information at the current moment so as to preferentially configure the computing nodes configured to the local video stream to the real-time video stream to be processed;
and reconfiguring the computing node to process the local video stream when the empty resource information is larger than a preset threshold resource information.
In a second aspect, an embodiment of the present invention further provides a computing resource optimization configuration device under industrial visual analysis, including:
the dividing module is used for virtually dividing the computing resource information of the target area and determining computing nodes;
the determining module is used for determining unit computing resource information of the computing node when the computing node processes the real-time video stream received by the target area; the unit computing resource information comprises resource information occupancy rates of all computing nodes at different moments;
the computing module is used for determining the empty resource information of the computing node according to the unit computing resource information;
and the configuration processing module is used for processing the acquired local video stream according to the empty resource information.
In a third aspect, an embodiment of the present invention further provides a computing device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the processor implements the method for optimizing configuration of computing resources under any one of the above industrial visual analysis.
In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium, on which a computer program is stored, which when executed in a computer, causes the computer to perform the method for optimizing configuration of computing resources under the industrial vision analysis described in any one of the above.
The embodiment of the invention provides a computing resource optimal configuration method and a computing resource optimal configuration device under industrial visual analysis, which virtually divide computing resource information into a plurality of computing nodes, acquire unit computing resource information of each computing node at different moments when processing real-time video streams, determine idle resource information of the computing nodes according to the information, further process local video streams by utilizing the idle resource information, realize the utilization of idle resources, ensure the original real-time video streams to keep stable processing, realize the optimal configuration of the computing resources, improve the resource utilization rate, solve the problem of setting the idle resources at night or in the stopping process in industrial manufacturing service scenes, and realize the cost reduction and efficiency improvement of enterprise intelligent reconstruction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for optimizing configuration of computing resources under industrial visual analysis according to an embodiment of the present invention;
FIG. 2 is a hardware architecture diagram of a computing device according to one embodiment of the present invention;
FIG. 3 is a block diagram of a computing resource optimizing configuration device under industrial visual analysis according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
The following is a concept of the present invention, as shown in fig. 1, and an embodiment of the present invention provides a method for optimizing and configuring computing resources under industrial visual analysis, where the method includes:
step 100, virtually dividing computing resource information of a target area to determine computing nodes;
step 102, determining unit computing resource information of a computing node when processing a real-time video stream received by a target area; the unit computing resource information comprises resource information occupancy rates of all computing nodes at different moments;
104, determining the empty resource information of the computing node according to the unit computing resource information;
and 106, processing the acquired local video stream according to the empty resource information.
In the embodiment of the invention, the computing resource information is virtually divided into a plurality of computing nodes, and then the unit computing resource information of each computing node at different moments when the real-time video stream is processed is acquired, so that the idle resource information of the computing nodes is determined according to the information, the processing of the local video stream is realized by utilizing the idle resource information, and the utilization of the idle resources is realized. For most industrial enterprise groups, the peak-trough phase difference of the video analysis calculation task is more than 20%. The invention can fully utilize the part of idle computing resources to perform non-real-time visual analysis task reasoning, such as local monitoring video inspection, operation flow compliance inspection, paper operation ticket work order identification and the like. The invention reduces the intelligent transformation cost of enterprise production management, saves the computing resource and improves the resource utilization rate.
The manner in which the individual steps shown in fig. 1 are performed is described below.
In step 100, in the industrial visual analysis application scenario, computing resource information (for example, an AI computing device cluster) of a target area is divided into a plurality of computing nodes by using a resource virtualization technology, multiple paths of real-time video streams are accessed, and each path of video stream loads N models to perform inference analysis on the real-time video streams.
In step 102, determining unit computing resource information of a computing node when processing a real-time video stream received by a target area includes:
acquiring a historical real-time video stream processed by a target area in a historical time;
and carrying out statistical analysis on the historical real-time video stream, and determining the resource information occupancy rate of the computing node at different moments.
In a preferred embodiment, the resource information occupancy rate includes a CPU occupancy rate, a GPU occupancy rate, a memory occupancy rate, and a video memory occupancy rate.
In the embodiment of the invention, the historical real-time video stream processed by each computing node in the historical time is counted, so that the CPU occupancy rate, GPU occupancy rate, memory occupancy rate, video memory occupancy rate and other resource information occupancy rates of each computing node at different moments can be determined, and a user can schedule settlement tasks of each computing node in time according to the occupancy rates, thereby improving the resource utilization rate of each computing node and ensuring the efficient operation of the computing nodes.
In step 104, determining empty resource information of the computing node according to the unit computing resource information, including:
screening the resource information occupancy rate with the highest occupancy rate from the unit calculation resource information, and determining the resource information occupancy rate as key resource information;
and determining the empty resource information of the computing node at different moments according to the key resource information and the preset full load occupancy rate.
In the embodiment of the invention, the resource information occupancy rate with the highest occupancy rate is determined as the key resource information, so that the original occupancy rate focusing on a plurality of resource information is converted into the occupancy rate focusing on only one key resource information, the empty resource occupancy rate of each computing node can be obtained by calculation only through the key resource information, and meanwhile, the computing node can still stably and efficiently operate by ensuring the occupancy rate of the key resource information.
In a preferred embodiment, the empty resource information includes empty resource occupancy; the empty resource occupancy is determined by the following formula:
IR t ＝R max -R t-m
wherein IR t The method comprises the steps of representing the unoccupied resource occupancy rate in a t time period; r is R max The method is used for representing the preset full load occupancy rate; r is R t-m And the method is used for representing the maximum resource information occupancy rate reached by the key resource information in the t time period.
Specifically, the t time period may be within 1 hour from the time t, i.e., corresponding to IR t Empty resource within 1 hour from time tSource occupancy, R t-m And the maximum resource information occupancy rate reached by the key resource information within 1h from the moment t is represented.
In the embodiment of the invention, the occupation rate of the empty resources is determined by presetting the occupation rate of full load and the maximum resource information occupation rate reached by the key resource information in the time period t, so that the stable operation of the corresponding computing nodes can be ensured by presetting the occupation rate of full load, and the occupation rate of the empty resources of each computing node in each time period can be further determined, thereby facilitating the users to schedule each computing node in different time periods.
In step 106, the processing of the acquired local video stream according to the empty resource information includes:
according to the empty resource information, performing slicing processing on the local video stream to obtain a sliced video;
feature extraction is carried out on the segmented video to obtain a segmented video to be processed, wherein the segmented video carries space-time information; the space-time information comprises time information and space information of the segmented video in a local video stream;
processing the segmented video to be processed according to the empty resource information to obtain an analysis result;
and fusing analysis results according to the space-time information to obtain target analysis results of the corresponding local video stream.
In the embodiment of the invention, after the information of the vacant resources of each computing node is known, the vacant resources can be utilized to process the local video stream so as to enable the vacant resources to be put into use and improve the utilization rate. In order to further and more efficiently utilize each computing node, the local video can be segmented into a plurality of segmented videos, after time information and space information are extracted through features, the time information and the space information are added to each segmented video, so that the segmented video subjected to segmentation and splitting processing can be fused according to the carried time information and space information after being processed independently by multiple threads, and a target analysis result corresponding to the complete local video stream is obtained.
In a preferred embodiment, processing the fragmented video to be processed according to the empty resource information includes:
the empty resource information comprises an empty resource occupancy rate;
acquiring the occupancy rate of the empty resource in each time period in the historical time so as to predict the occupancy rate of the target empty resource at the current moment;
determining the resource rate occupied by a single channel, and calculating the ratio of the occupied rate of the target empty resource to the resource rate occupied by the single channel to obtain the channel number of the virtual video channels;
creating virtual video channels with the number of channels, and sending the segmented video to be processed to the virtual video channels for processing.
According to the method and the device, the target empty resource occupancy rate at the current moment can be predicted according to the empty resource occupancy rate in the historical time, then the ratio of the target empty resource occupancy rate to the resource occupancy rate occupied by a single channel is calculated by confirming the resource occupancy rate occupied by the single channel, the channel number of the virtual video channels is obtained, the virtual video channels with the channel number are created, and the to-be-processed fragmented video is sent to the virtual video channels for processing, so that efficient operation of multiple threads is achieved, and the resource utilization rate is improved.
In a preferred embodiment, after step 106, further comprising:
when the target area receives the real-time video stream to be processed again, optimizing and configuring the computing resource information according to the unit computing resource information and the empty resource information at the current moment so as to preferentially configure the computing nodes configured to the local video stream to the real-time video stream to be processed;
and reconfiguring the computing node to process the local video stream when the empty resource information is greater than the preset threshold resource information.
In the invention, the priority of the processing task of the local video stream is arranged behind the processing task of the real-time video stream, and after the task of the real-time video stream to be processed is received again, the configuration is optimized again, the computing nodes configured to the local video stream are configured to the real-time video stream to be processed preferentially, and the processing task of the local video stream is stopped in sequence according to the channel, so that the smooth and stable operation of the original task in the industrial manufacturing can be ensured. But restarting the processing of the local video stream when the empty resource information is larger than the preset threshold resource information, namely when the occupied rate of the empty resource reaches the threshold.
As shown in fig. 2 and 3, the embodiment of the invention provides a computing resource optimizing configuration device under industrial vision analysis. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. In terms of hardware, as shown in fig. 2, a hardware architecture diagram of a computing device where a computing resource optimizing configuration device under industrial visual analysis provided by an embodiment of the present invention is located, in addition to a processor, a memory, a network interface, and a nonvolatile memory shown in fig. 2, the computing device where the device is located in the embodiment may generally include other hardware, such as a forwarding chip responsible for processing a packet, and so on. Taking a software implementation as an example, as shown in fig. 3, as a device in a logic sense, the device is formed by reading a corresponding computer program in a nonvolatile memory into a memory by a CPU of a computing device where the device is located. The device for optimizing and configuring the computing resources under the industrial visual analysis provided by the embodiment comprises:
the dividing module 300 is configured to virtually divide computing resource information of the target area, and determine computing nodes;
a determining module 302, configured to determine unit computing resource information of the computing node when processing the real-time video stream received by the target area; the unit computing resource information comprises resource information occupancy rates of all computing nodes at different moments;
a calculation module 304, configured to determine, according to the unit calculation resource information, empty resource information of the calculation node;
and the configuration processing module 306 is configured to process the acquired local video stream according to the empty resource information.
In some embodiments, the partitioning module 300 may be configured to perform the above-described step 100, the determining module 302 may be configured to perform the above-described step 102, the calculating module 304 may be configured to perform the above-described step 104, and the configuration processing module 306 may be configured to perform the above-described step 106.
In some specific embodiments, the determining module 302 is further configured to perform the following operations:
acquiring a historical real-time video stream processed by a target area in a historical time;
carrying out statistical analysis on the historical real-time video stream, and determining the resource information occupancy rate of the computing node at different moments; the resource information occupancy rate comprises CPU occupancy rate, GPU occupancy rate, memory occupancy rate and video memory occupancy rate.
In some specific embodiments, the computing module 304 is further configured to perform the following operations:
screening the resource information occupancy rate with the highest occupancy rate from the unit calculation resource information, and determining the resource information occupancy rate as key resource information;
according to the key resource information and the preset full load occupancy rate, determining the empty resource information of the computing node at different moments; the empty resource information comprises an empty resource occupancy rate;
the empty resource occupancy is determined by the following formula:
IR t ＝R max -R t-m
wherein IR t The method comprises the steps of representing the unoccupied resource occupancy rate in a t time period; r is R max The method is used for representing the preset full load occupancy rate; r is R t-m And the method is used for representing the maximum resource information occupancy rate reached by the key resource information in the t time period.
In some specific embodiments, the configuration processing module 306 is further configured to perform the following operations:
according to the empty resource information, performing slicing processing on the local video stream to obtain a sliced video; the empty resource information comprises an empty resource occupancy rate;
feature extraction is carried out on the segmented video to obtain a segmented video to be processed, wherein the segmented video carries space-time information; the space-time information comprises time information and space information of the segmented video in a local video stream;
acquiring the occupancy rate of the empty resource in each time period in the historical time so as to predict the occupancy rate of the target empty resource at the current moment;
determining the resource rate occupied by a single channel, and calculating the ratio of the occupied rate of the target empty resource to the resource rate occupied by the single channel to obtain the channel number of the virtual video channels;
creating virtual video channels with the number of channels, and sending the segmented video to be processed to the virtual video channels for processing to obtain an analysis result;
and fusing analysis results according to the space-time information to obtain target analysis results of the corresponding local video stream.
In some specific embodiments, the configuration processing module 306 is further configured to perform the following operations:
when the target area receives the real-time video stream to be processed again, optimizing and configuring the computing resource information according to the unit computing resource information and the empty resource information at the current moment so as to preferentially configure the computing nodes configured to the local video stream to the real-time video stream to be processed;
and reconfiguring the computing node to process the local video stream when the empty resource information is greater than the preset threshold resource information.
It will be appreciated that the architecture illustrated in the embodiments of the present invention does not constitute a specific limitation on a computing resource optimal configuration apparatus under industrial visual analysis. In other embodiments of the invention, a computing resource optimal configuration device under industrial visual analysis may include more or fewer components than shown, or may combine certain components, or may split certain components, or may have a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The content of information interaction and execution process between the modules in the device is based on the same conception as the embodiment of the method of the present invention, and specific content can be referred to the description in the embodiment of the method of the present invention, which is not repeated here.
The embodiment of the invention also provides a computing device which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the optimal configuration method of the computing resources under the industrial visual analysis in any embodiment of the invention when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, which when being executed by a processor, causes the processor to execute the method for optimizing and configuring the computing resources under the industrial vision analysis in any embodiment of the invention.
Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present invention.
Examples of the storage medium for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer by a communication network.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion module connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion module is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
It is noted that relational terms such as first and second, and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one …" does not exclude the presence of additional identical elements in a process, method, article or apparatus that comprises the element.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: various media in which program code may be stored, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The method for optimizing and configuring the computing resources under the industrial visual analysis is characterized by comprising the following steps of:
virtually dividing the computing resource information of the target area to determine computing nodes;
determining unit computing resource information of the computing node when processing the real-time video stream received by the target area; the unit computing resource information comprises resource information occupancy rates of all computing nodes at different moments;
determining the empty resource information of the computing node according to the unit computing resource information;
and processing the acquired local video stream according to the empty resource information.
2. The method of claim 1, wherein said determining unit computing resource information of the computing node in processing the real-time video stream received by the target area comprises:
acquiring a historical real-time video stream processed by the target area in a historical time;
and carrying out statistical analysis on the historical real-time video stream to determine the resource information occupancy rate of the computing node at different moments.
3. The method of claim 1, wherein the resource information occupancy rate comprises a CPU occupancy rate, a GPU occupancy rate, a memory occupancy rate, and a video memory occupancy rate;
the determining the empty resource information of the computing node according to the unit computing resource information comprises the following steps:
screening the resource information occupancy rate with the highest occupancy rate from the unit computing resource information, and determining the resource information occupancy rate as key resource information;
and determining the empty resource information of the computing node at different moments according to the key resource information and the preset full load occupancy rate.
4. A method according to claim 3, wherein the empty resource information comprises empty resource occupancy; the empty resource occupancy rate is determined by the following formula:
IR t ＝R max -R t-m
wherein IR t For characterizing the unoccupied resource occupancy within a time period t; r is R max For characterizing the preset full load occupancy; r is R t-m And the maximum resource information occupancy rate reached by the key resource information in the t time period is represented.
5. The method of claim 1, wherein the processing the acquired local video stream according to the empty resource information comprises:
according to the empty resource information, performing slicing processing on the local video stream to obtain a sliced video;
extracting features of the segmented video to obtain a segmented video to be processed carrying space-time information; wherein the spatio-temporal information includes temporal information and spatial information of the segmented video in the local video stream;
processing the to-be-processed segmented video according to the empty resource information to obtain an analysis result;
and fusing the analysis results according to the space-time information to obtain a target analysis result corresponding to the local video stream.
6. The method of claim 5, wherein processing the fragmented video to be processed according to the empty resource information comprises:
the empty resource information comprises an empty resource occupancy rate;
acquiring the occupancy rate of the empty resource in each time period in the historical time so as to predict the occupancy rate of the target empty resource at the current moment;
determining the resource rate occupied by a single channel, and calculating the ratio of the target unoccupied resource occupancy rate to the resource rate occupied by the single channel to obtain the channel number of the virtual video channels;
and creating virtual video channels with the channel number, and sending the to-be-processed segmented video to the virtual video channels for processing.
7. The method according to any one of claims 1 to 6, further comprising, after said processing the acquired local video stream according to the empty resource information:
when the target area receives the real-time video stream to be processed again, optimizing configuration is carried out on the computing resource information according to the unit computing resource information and the empty resource information at the current moment so as to preferentially configure the computing nodes configured to the local video stream to the real-time video stream to be processed;
and reconfiguring the computing node to process the local video stream when the empty resource information is larger than a preset threshold resource information.
8. An apparatus for optimizing and configuring computing resources under industrial visual analysis, comprising:
the dividing module is used for virtually dividing the computing resource information of the target area and determining computing nodes;
the determining module is used for determining unit computing resource information of the computing node when the computing node processes the real-time video stream received by the target area; the unit computing resource information comprises resource information occupancy rates of all computing nodes at different moments;
the computing module is used for determining the empty resource information of the computing node according to the unit computing resource information;
and the configuration processing module is used for processing the acquired local video stream according to the empty resource information.
9. A computing device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the method of any of claims 1-7 when the computer program is executed.
10. A computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311034410.3A CN117056073B (en) | 2023-08-16 | 2023-08-16 | Computing resource optimal configuration method and device under industrial visual analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311034410.3A CN117056073B (en) | 2023-08-16 | 2023-08-16 | Computing resource optimal configuration method and device under industrial visual analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117056073A true CN117056073A (en) | 2023-11-14 |
| CN117056073B CN117056073B (en) | 2024-03-08 |
Family
ID=88660383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311034410.3A Active CN117056073B (en) | 2023-08-16 | 2023-08-16 | Computing resource optimal configuration method and device under industrial visual analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117056073B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203799368U (en) * | 2013-12-13 | 2014-08-27 | 广州必视谷信息技术有限公司 | Distributed video analyzing system |
| US20200301741A1 (en) * | 2019-03-22 | 2020-09-24 | Amazon Technologies, Inc. | Coordinated predictive autoscaling of virtualized resource groups |
| CN111813502A (en) * | 2020-07-10 | 2020-10-23 | 重庆邮电大学 | Computing resource management scheduling method for industrial edge nodes |
| CN113157418A (en) * | 2021-04-25 | 2021-07-23 | 腾讯科技（深圳）有限公司 | Server resource allocation method and device, storage medium and electronic equipment |
| CN113867927A (en) * | 2020-06-30 | 2021-12-31 | 北京达佳互联信息技术有限公司 | Resource allocation method, device, electronic equipment and storage medium |
-
2023
- 2023-08-16 CN CN202311034410.3A patent/CN117056073B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203799368U (en) * | 2013-12-13 | 2014-08-27 | 广州必视谷信息技术有限公司 | Distributed video analyzing system |
| US20200301741A1 (en) * | 2019-03-22 | 2020-09-24 | Amazon Technologies, Inc. | Coordinated predictive autoscaling of virtualized resource groups |
| CN113867927A (en) * | 2020-06-30 | 2021-12-31 | 北京达佳互联信息技术有限公司 | Resource allocation method, device, electronic equipment and storage medium |
| CN111813502A (en) * | 2020-07-10 | 2020-10-23 | 重庆邮电大学 | Computing resource management scheduling method for industrial edge nodes |
| CN113157418A (en) * | 2021-04-25 | 2021-07-23 | 腾讯科技（深圳）有限公司 | Server resource allocation method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117056073B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ali et al. | RES: Real-time video stream analytics using edge enhanced clouds | |
| US9361161B2 (en) | Workload routing for managing energy in a data center | |
| US20210042578A1 (en) | Feature engineering orchestration method and apparatus | |
| US11036539B2 (en) | Workflow engine framework | |
| CN108920153A (en) | A kind of Docker container dynamic dispatching method based on load estimation | |
| US20100161368A1 (en) | Managing energy in a data center | |
| CN106897133B (en) | Implementation method for managing cluster load based on PBS job scheduling | |
| US20230037783A1 (en) | Resource scheduling method and related apparatus | |
| CN109301936B (en) | Intelligent substation operation and maintenance information monitoring system based on container scheduling framework | |
| CN117056073B (en) | Computing resource optimal configuration method and device under industrial visual analysis | |
| CN108833304A (en) | The management method and device of message in cloud data system | |
| CN113535379A (en) | Power transformation edge calculation method, system and equipment based on Internet of things | |
| CN115391051A (en) | Video computing task scheduling method, device and computer readable medium | |
| WO2022110974A1 (en) | Method and apparatus for training data analysis model, and storage medium | |
| CN110971532A (en) | Network resource management method, device and equipment | |
| US10986036B1 (en) | Method and apparatus for orchestrating resources in multi-access edge computing (MEC) network | |
| CN111144495B (en) | Service distribution method, device and medium | |
| CN115082911A (en) | Video analysis method and device and video processing equipment | |
| CN112035316A (en) | Method for monitoring and analyzing data by cloud monitoring system | |
| CN115080197A (en) | Computing task scheduling method and device, electronic equipment and storage medium | |
| CN112693502A (en) | Urban rail transit monitoring system and method based on big data architecture | |
| CN112654077A (en) | Energy-saving method and device and computer storage medium | |
| US20220201066A1 (en) | Proactive placement of virtualized computing resources and tuning of network resources based on seasonal variations | |
| CN111741097B (en) | Method for tenant to monopolize node, computer equipment and storage medium | |
| CN113992687B (en) | Intelligent service cluster scheduling method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |