CN116074541B - Resource processing method, system, device and electronic equipment - Google Patents
Resource processing method, system, device and electronic equipment Download PDFInfo
- Publication number
- CN116074541B CN116074541B CN202310224227.3A CN202310224227A CN116074541B CN 116074541 B CN116074541 B CN 116074541B CN 202310224227 A CN202310224227 A CN 202310224227A CN 116074541 B CN116074541 B CN 116074541B
- Authority
- CN
- China
- Prior art keywords
- video analysis
- algorithm
- service
- analysis service
- target
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 381
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 236
- 238000000034 method Methods 0.000 claims description 51
- 230000008569 process Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008520 organization Effects 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2181—Source of audio or video content, e.g. local disk arrays comprising remotely distributed storage units, e.g. when movies are replicated over a plurality of video servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
- H04N21/2393—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2543—Billing, e.g. for subscription services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
In the embodiment of the invention, a plurality of private cloud users share the same AI computing resource pool, when the private cloud users need to perform video analysis service, the cloud service control center sends a video analysis service request to the video analysis end according to the video analysis service request, and releases AI computing power required by a video analysis service algorithm after completing video analysis, so that other users can occupy AI computing power resources in the AI computing power resource pool in busy hours even if one user is idle, and the utilization rate of the AI computing power resources is greatly improved. In the embodiment, when the charging bill is generated, the algorithm cost of the video analysis algorithm is considered, so that the charging accuracy of the video analysis service is improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method, a system, an apparatus, and an electronic device for processing resources.
Background
With the development of artificial intelligence and cloud computing technology, AI computing power has become one of the important resources on which business systems of various industries depend. The AI calculation force, such as GPU and other resources, is applied to an intelligent video monitoring system, each private cloud user such as an enterprise and government structure independently establishes the AI calculation force, and analyzes the video shot by the video monitoring system based on the established AI calculation force.
However, since the service of the video monitoring system has the characteristic of tidal flow, that is, when the video monitoring system is in a specified monitoring period, the video amount shot by the video monitoring system is large, and when the video monitoring system is in a non-specified monitoring period, the video amount shot by the video monitoring system is small, which results in the defect that the AI computing power of any private cloud user is underutilized, for example, when the video monitoring system is in the specified monitoring period, the AI computing power is largely occupied, and when the video monitoring system is in the non-specified monitoring period, the AI computing power is mostly in an idle state.
Disclosure of Invention
In view of this, the present application provides a resource processing method, system, device and electronic equipment, which are used for realizing full utilization of AI computing power.
Specifically, the application is realized by the following technical scheme:
the embodiment of the application provides a resource processing method, which is applied to a cloud service control center, wherein the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the method comprises the following steps:
receiving a video analysis service request sent by any private cloud user in the plurality of different private cloud users when video analysis service exists; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
Issuing a video analysis service to a video analysis end based on the video analysis service request, so that the video analysis end performs video analysis on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm;
receiving metering information counted by the video analysis end in the video analysis process; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; generating a charging bill according to the metering information and the obtained target selling price of the target video analysis service algorithm; the target selling price of the target video analysis service algorithm comprises the following steps: the cost of billing per unit time when the target video analytics service algorithm is run, the cost of billing per unit time when the algorithm result generated when the target video analytics service algorithm is run is stored, and the cost of billing per unit time for AI computing power resources required when the target video analytics service algorithm is run.
Optionally, the plurality of different private cloud users are different sub-organizations under the same organization.
Optionally, the method further comprises:
and issuing the charging bill to a private cloud user sending the video analysis service request, and determining a final bill based on a checking result of the private cloud user for the charging bill.
Optionally, the target selling price of the target video parsing service algorithm further includes an algorithm base unit price at which the target video parsing service algorithm is run.
The embodiment of the application also provides a resource processing method which is applied to the video analysis end, wherein the video analysis end is communicated with the deployed cloud service control center, and the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the method comprises the following steps:
receiving video analysis service issued by the cloud service control center; the video resolution service is generated based on a video resolution service request, the video resolution service request being sent by any one of the plurality of different private cloud users when there is a video resolution service; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
Performing video analysis on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm; reporting metering information counted in the video analysis process to the cloud service control center to generate a charging bill by the cloud service control center according to the metering information and the obtained target selling price of the target video analysis service algorithm; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; the target selling price of the target video analysis service algorithm comprises the following steps: the method comprises the steps of charging cost per unit time when a target video analysis service algorithm is operated, charging cost per unit time when an algorithm result generated when the target video analysis service algorithm is operated is stored, and charging cost per unit time of AI computing power resources required by the target video analysis service algorithm when the target video analysis service algorithm is operated;
and after the video analysis is completed by utilizing the target video analysis service algorithm, releasing the AI calculation force required by the target video analysis service algorithm.
Optionally, the performing video parsing on the video stream corresponding to the private cloud user sending the video parsing service request by using the target video parsing service algorithm based on the video parsing service includes:
the video stream ID carried in the video analysis service is obtained, the video stream corresponding to the private cloud user is obtained from a storage center storing the video according to the video stream ID, and video analysis is carried out on the video stream according to the target video analysis service algorithm.
The embodiment of the application also provides a resource processing system, which comprises: the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool;
the cloud service control center is used for executing any step of the cloud service control center;
the video parsing end is used for executing any step of the video parsing end in the application.
The embodiment of the application also provides a resource processing device which is applied to the cloud service control center, wherein the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the device comprises:
A receiving unit: the method comprises the steps of receiving a video analysis service request sent by any private cloud user in a plurality of different private cloud users when video analysis service exists; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
issuing unit: the video analysis method comprises the steps that video analysis service is issued to a video analysis end based on the video analysis service request, so that the video analysis end performs video analysis on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm;
a statistics unit: the metering information is used for receiving statistics of the video analysis end in the video analysis process; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; generating a charging bill according to the metering information and the obtained target selling price of the target video analysis service algorithm; the target selling price of the target video analysis service algorithm comprises the following steps: the cost of billing per unit time when the target video analytics service algorithm is run, the cost of billing per unit time when the algorithm result generated when the target video analytics service algorithm is run is stored, and the cost of billing per unit time for AI computing power resources required when the target video analytics service algorithm is run.
The embodiment of the application also provides a resource processing device which is applied to the video analysis end, wherein the video analysis end is communicated with the deployed cloud service control center, and the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the device comprises:
a receiving unit: the video analysis service is used for receiving video analysis service issued by the cloud service control center; the video resolution service is generated based on a video resolution service request, the video resolution service request being sent by any one of the plurality of different private cloud users when there is a video resolution service; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
an analysis unit: the video analysis service algorithm is used for carrying out video analysis on the video stream corresponding to the private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm; reporting metering information counted in the video analysis process to the cloud service control center to generate a charging bill by the cloud service control center according to the metering information and the obtained target selling price of the target video analysis service algorithm; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; the target selling price of the target video analysis service algorithm comprises the following steps: the method comprises the steps of charging cost per unit time when a target video analysis service algorithm is operated, charging cost per unit time when an algorithm result generated when the target video analysis service algorithm is operated is stored, and charging cost per unit time of AI computing power resources required by the target video analysis service algorithm when the target video analysis service algorithm is operated;
A release unit: and the AI algorithm is used for releasing the AI algorithm force required by the target video analysis service algorithm after the video analysis is completed by the target video analysis service algorithm.
The embodiment of the application also provides electronic equipment, which comprises:
one or more processors;
a machine-readable storage medium storing one or more computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to implement the method as in any of the above embodiments.
As can be seen from the above embodiments, compared with the existing method in which each private cloud user establishes an independent AI computing power pool, in this embodiment, multiple private cloud users share the same AI computing power resource pool, when the private cloud users need to perform video analysis service, by sending a video analysis service request to a cloud service control center, the cloud service control center issues video analysis service to a video analysis end according to the video analysis service request, and releases AI computing power required by a video analysis service algorithm after completing video analysis, so that even if a certain user is idle, other users can occupy AI computing power resources in the AI computing power resource pool in busy hours, thereby greatly improving the utilization rate of the AI computing power resources.
Further, in this embodiment, when the billing bill is generated, the algorithm cost of the video analysis algorithm itself is considered, so as to improve the accuracy of the video analysis service billing.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly introduce the drawings that are required to be used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may also be obtained according to these drawings for a person having ordinary skill in the art.
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a flow chart of a method according to an embodiment of the present application;
FIG. 2 is a flow chart of a method according to another embodiment of the present application;
FIG. 3 is a flow chart of the resource processing system interaction of the present application;
FIG. 4 is a block diagram of an apparatus according to an embodiment of the present application;
FIG. 5 is a block diagram of an apparatus according to another embodiment of the present application;
fig. 6 is a structural diagram of the electronic device of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
In order to better understand the technical solutions provided by the embodiments of the present application and make the above objects, features and advantages of the embodiments of the present application more obvious, the technical solutions in the embodiments of the present application are described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, an interactive flowchart of a resource processing method is shown in an embodiment of the present invention, where the method is applied to a cloud service control center, and the cloud service control center provides video resolution cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI-computing resource pool.
As shown in fig. 1, the process may include the steps of:
step S101, receiving a video analysis service request sent by any private cloud user in the plurality of different private cloud users when the video analysis service exists, wherein the video analysis service request carries a target video analysis service algorithm determined by the private cloud user.
In this embodiment, the target video parsing service algorithm may be selected by the private cloud user through each video parsing service algorithm displayed by the cloud service control center. For example, the cloud service control center may provide a video resolution service page for a user to access a unified portal of the private cloud video resolution service for providing a video resolution service selection function to the user. The video parsing service page provides each video parsing service algorithm for parsing the video stream for the user to select, and determines the video parsing service algorithm selected by the user as a target video parsing service algorithm.
When the private cloud user needs the video analysis service, the video analysis terminal can analyze the video according to the target video analysis service algorithm selected by the private cloud user by logging in to the cloud service control center and determining the video to be analyzed and the target video analysis service algorithm used for analyzing the video by utilizing the video analysis service page.
The cloud service control center can be in butt joint with an AI market, the AI market provides support for putting algorithms on shelf, and determining the types of the algorithms, pricing of the algorithms, AI calculation power consumed by the algorithms and the like. And the cloud service manager determines the final pricing of the video analysis service according to the algorithm pricing, the duration and the resource consumption, and puts the video analysis service on shelf. And the AI market can also upgrade and maintain the algorithm.
In another embodiment, the plurality of different private cloud users are different sub-organizations under the same organization.
In this embodiment, the same organization may be an organization similar to a municipal government that includes a plurality of subordinate units, and the sub-organization may be an organization of a water bureau, a power bureau, an educational bureau, and the like under the municipal government. The multiple sub-organizations share the same AI-computing resource pool. The same organization may also be an organization similar to a university that contains a plurality of buildings, each building being a sub-organization of the university, respectively.
Step S102, a video analysis service is issued to a video analysis end based on the video analysis service request, so that the video analysis end performs video analysis on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm.
In this embodiment, the video parsing end provides an actual environment for running the video parsing service, so as to implement running and metering work of the video parsing service. The video analysis service sent by the cloud service control center comprises a target video analysis service algorithm selected by a private cloud user. After the video analysis service is received by the video analysis service, a target video analysis service algorithm for analyzing the video stream can be obtained from the video analysis service.
It should be noted that, the video analysis end may also download all the video analysis service algorithms in advance, and at this time, the video analysis end may determine the corresponding target video analysis service algorithm according to the relevant parameters of the video analysis service algorithm only carried in the video analysis service sent by the cloud service control center. This application is not limited in this regard.
Step S103, receiving the metering information counted by the video analysis end in the video analysis process, and generating a charging bill according to the metering information and the obtained target selling price of the target video analysis service algorithm.
In this embodiment, the metering information includes: the AI computing power resources consumed by the target video analysis service algorithm when being operated, and the operation time of the target video analysis service algorithm. The target selling price of the target video analysis service algorithm comprises the following steps: the cost of billing per unit time when the target video analytics service algorithm is run, the cost of billing per unit time when the algorithm result generated when the target video analytics service algorithm is run is stored, and the cost of billing per unit time for AI computing power resources required when the target video analytics service algorithm is run.
For example, the unit time is set to 1 hour, the target video parsing service algorithm needs to consume 10 paths of AI computing power resources when being operated, the charging cost per hour of the target video parsing service algorithm is preset to be 0.1 yuan when being operated, the target video parsing service algorithm generates 10 pictures and data per hour on average, and then the charging cost per unit time of the algorithm result generated by the target video parsing service when being stored is 0.1/10=0.01 yuan. The AI computing power resources required by the target video analysis service algorithm during operation are, for example, video analysis is realized through a GPU, the price of the GPU is 1.2W yuan, 20 parts of video AI analysis is supported simultaneously, namely 20 parts of AI computing power resources are provided, the GPU is converted in one year, then the charging cost of the AI computing power resources required by the target video analysis service algorithm during operation is 0.06 yuan per hour, and then the target selling price of the target video analysis service algorithm is: 0.1+0.01+0.06=0.17 element. Assuming that the AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is executed in the metering information is 10 parts and the running time is 20 hours, the price on a charging bill generated by the metering information and the obtained target selling price of the target video analysis service algorithm is 0.17 element by 10 element by 20 element by 34 element.
In another embodiment, the method further comprises:
and issuing the charging bill to a private cloud user sending the video analysis service request, and determining a final bill based on a checking result of the private cloud user for the charging bill.
In this embodiment, the private cloud user who initiates the video resolution service request may check the charging bill, and if the private cloud user considers that the bill is correct, may click the submit button to determine the charging bill as a final bill. If the private cloud user considers that the charging bill has a problem, the charging bill can be sent to a cloud service management user for auditing.
In another embodiment, the target selling price of the target video parsing service algorithm further includes an algorithm base unit price at which the target video parsing service algorithm is operated.
In this embodiment, since the GPU performs multiple paths of video analysis, that is, consumes multiple AI computing power at the same time, when the number of paths analyzed by the user is smaller than the full specification of the GPU, the AI computing power of the GPU is wasted, for example, the full specification of the GPU is 10, and as long as the GPU performs video analysis, 10 AI computing power is consumed. When the AI computing power consumed by the video analysis service initiated by the private cloud user is less than 10 copies, the AI computing power resource is wasted.
Therefore, in this embodiment, an algorithm base unit price is set for the target selling price of the target video resolution service algorithm, so as to avoid the situation that the billing bill generated in step S103 does not match the AI computing power actually consumed due to the fact that the AI computing power resource is wasted when the AI computing power consumed by the video resolution service initiated by the private cloud user is less than the full rule of the GPU.
Thus, the flow shown in fig. 1 is completed.
According to the embodiment, when the private cloud users need to perform video analysis service, the cloud service control center sends the video analysis service request to the video analysis end according to the video analysis service request, and releases the AI calculation force required by the video analysis service algorithm after the video analysis is completed, so that each user requests AI calculation force resources in the same AI calculation force resource pool when having requirements in different time periods, and compared with the situation that each user independently occupies AI calculation force, the AI calculation force utilization rate is greatly improved.
The video analysis end counts AI computing power resources consumed by the algorithm during video analysis, and the problem that the price of video analysis service is inaccurate due to the fact that only resource consumption is considered and algorithm cost is not considered is avoided.
The resource processing method provided by the application can also be applied to a video analysis end, the video analysis end is communicated with a deployed cloud service control center, and the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI-computing resource pool.
As shown in fig. 2, the process may include the steps of:
step S201, receiving the video analysis service issued by the cloud service control center.
In this embodiment, the video parsing service is generated based on a video parsing service request, where the video parsing service request is sent by any private cloud user of the plurality of different private cloud users when there is a video parsing service, and the video parsing service request carries a target video parsing service algorithm determined by the private cloud user.
For example, after a private cloud user logs in a cloud service control center, an algorithm of a video analysis service is selected through a video analysis service page provided by the cloud service control center, and a required video analysis service is determined according to the video analysis service algorithm. After the private cloud user is determined, a video analysis service request is sent by a cloud service control center. And after receiving the video analysis service request, the cloud service control center transmits the corresponding video analysis service to the video analysis terminal.
Step S202, video analysis is carried out on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm; and reporting the metering information counted in the video analysis process to the cloud service control center so as to generate a charging bill by the cloud service control center according to the metering information and the obtained target selling price of the target video analysis service algorithm.
In this embodiment, the metering information includes: the AI computing power resources consumed by the target video analysis service algorithm when being operated, and the operation time of the target video analysis service algorithm. The target selling price of the target video analysis service algorithm comprises the following steps: the cost of billing per unit time when the target video analytics service algorithm is run, the cost of billing per unit time when the algorithm result generated when the target video analytics service algorithm is run is stored, and the cost of billing per unit time for AI computing power resources required when the target video analytics service algorithm is run. In this step, the method for determining the metering information and the target selling price is the same as that in step S103, and will not be described here again.
Step S203, after completing the video analysis by using the target video analysis service algorithm, releasing the AI calculation force required by the target video analysis service algorithm.
In this embodiment, the video parsing end may immediately release the AI computation power required by the target video parsing service algorithm after completing video parsing. For example, when the video parsing end parses the video of the educational administration under the urban government, it takes 10 hours, and then immediately releases the AI computing force required for parsing the video of the educational administration after the video parsing is completed, and the AI computing force can be immediately used for parsing the video of other sub-institutions. So as to achieve the full utilization of AI calculation force.
In this embodiment, the video analysis end may further notify the cloud service control center after completing video analysis, where the cloud service control center releases the AI computing power when the duration of the video analysis service selected by the private cloud user arrives. For example, if an educational bureau under the urban government pays 24 hours of video resolution service fee, even if the video resolution end only takes 10 hours to resolve the video of the educational bureau, the video resolution end does not release the AI computing power resource when the resolution is completed, but the cloud service control center releases the AI computing power when the video resolution service reaches 24 hours. So that the educational bureau can directly use the occupied AI computing power to analyze the video without acquiring the AI computing power from the AI computing power resource pool when other videos are needed to analyze within 10-24 hours.
In another embodiment, the video parsing of the video stream corresponding to the private cloud user sending the video parsing service request based on the video parsing service and using the target video parsing service algorithm includes:
the video stream ID carried in the video analysis service is obtained, the video stream corresponding to the private cloud user is obtained from a storage center storing the video according to the video stream ID, and video analysis is carried out on the video stream according to the target video analysis service algorithm.
In this embodiment, the storage center is used to store videos shot by the private cloud users. When the private cloud user logs in the cloud service control center to initiate a video analysis service request, a video to be analyzed can be selected in a video analysis service page so as to add a video stream ID of the video to the video analysis service request, and when the cloud service control center sends the video analysis service to a video analysis terminal according to the video analysis service request, the video stream ID is added to the video analysis service and sent to the video analysis terminal.
Thus, the flow shown in fig. 2 is completed.
As can be seen from the above embodiments, multiple private cloud users share the same AI computing power resource pool, and when a video analysis terminal receives a video analysis service from a private cloud user through a cloud service control center, the video analysis service is analyzed according to a target video analysis service algorithm in the video analysis service. And after the video analysis is completed, the AI computing power required by the target video analysis service algorithm is released, so that each user requests AI computing power resources in the same AI computing power resource pool when the user needs in different time periods, and compared with the situation that each user independently occupies AI computing power, the AI computing power utilization rate is greatly improved. And AI (automatic identification) computing power resources consumed by the algorithm are counted during video analysis, so that the problem that the price of video analysis service is inaccurate due to the fact that only resource consumption is considered and algorithm cost is not considered is avoided.
The application also provides a resource processing system, which comprises: the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool;
as shown in fig. 3, the interaction flow of each module in the resource processing system is specifically as follows:
s301, the cloud service control center receives an algorithm model on the AI market. The AI market is used to determine information such as the algorithm type, price, etc. of the algorithm.
S302, a cloud service manager determines the selling price of the video analysis service according to algorithm pricing and AI (advanced technology attachment) computing power resource consumption, and puts the video analysis service on the cloud service control center.
S303, when a private cloud user logs in a cloud service control center, after the private cloud user purchases a video analysis service on a video analysis service page, the cloud service control center issues information such as an algorithm, a video stream ID and the like to a video analysis end, and the video analysis end acquires a corresponding video stream to perform video analysis, and then counts AI (analog input) computing power resources consumed in the video analysis process and the running time of the algorithm.
S304, the cloud service control center generates a charging bill according to AI computing power resources which are counted and consumed in the video analysis process, the running time of the algorithm and the selling price of the video analysis service, and sends the charging bill to the private cloud user for verification.
The flow of fig. 3 is thus completed.
In the embodiment, each private cloud user shares the AI computing power resources in the same AI computing power resource pool, and compared with the situation that each user independently occupies AI computing power, the utilization rate of the AI computing power is greatly improved. In addition, the video analysis end counts AI (advanced technology) computing power resources consumed by the algorithm during video analysis, so that the problem of inaccurate price of video analysis service caused by unaccounted algorithm cost is avoided.
The method provided by the embodiment of the invention is described above, and the device provided by the embodiment of the invention is described below:
referring to fig. 4, the present application further provides a resource processing device, where the resource processing device is applied to a cloud service control center, and the cloud service control center provides video resolution cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the device comprises:
the receiving unit 401: the method comprises the steps of receiving a video analysis service request sent by any private cloud user in a plurality of different private cloud users when video analysis service exists; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
Issuing unit 402: the video analysis method comprises the steps that video analysis service is issued to a video analysis end based on the video analysis service request, so that the video analysis end performs video analysis on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm;
statistics unit 403: the metering information is used for receiving statistics of the video analysis end in the video analysis process; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; generating a charging bill according to the metering information and the obtained target selling price of the target video analysis service algorithm; the target selling price of the target video analysis service algorithm comprises the following steps: the cost of billing per unit time when the target video analytics service algorithm is run, the cost of billing per unit time when the algorithm result generated when the target video analytics service algorithm is run is stored, and the cost of billing per unit time for AI computing power resources required when the target video analytics service algorithm is run.
Referring to fig. 5, the application further provides a resource processing device, which is applied to a video analysis end, wherein the video analysis end communicates with a deployed cloud service control center, and the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the device comprises:
the receiving unit 501: the video analysis service is used for receiving video analysis service issued by the cloud service control center; the video resolution service is generated based on a video resolution service request, the video resolution service request being sent by any one of the plurality of different private cloud users when there is a video resolution service; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
parsing unit 502: the video analysis service algorithm is used for carrying out video analysis on the video stream corresponding to the private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm; reporting metering information counted in the video analysis process to the cloud service control center to generate a charging bill by the cloud service control center according to the metering information and the obtained target selling price of the target video analysis service algorithm; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; the target selling price of the target video analysis service algorithm comprises the following steps: the method comprises the steps of charging cost per unit time when a target video analysis service algorithm is operated, charging cost per unit time when an algorithm result generated when the target video analysis service algorithm is operated is stored, and charging cost per unit time of AI computing power resources required by the target video analysis service algorithm when the target video analysis service algorithm is operated;
Release unit 503: and the AI algorithm is used for releasing the AI algorithm force required by the target video analysis service algorithm after the video analysis is completed by the target video analysis service algorithm.
The embodiment of the application also provides the hardware structure of the device shown in fig. 4 and 5. Referring to fig. 6, a block diagram of an electronic device according to an embodiment of the present application is provided.
The electronic device includes:
one or more processors;
a machine-readable storage medium storing one or more computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to implement the methods disclosed in the above examples of the present application.
By way of example, the machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, and the like. For example, a machine-readable storage medium may be: RAM (Radom Access Memory, random access memory), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., hard drive), a solid state drive, any type of storage disk (e.g., optical disk, dvd, etc.), or a similar storage medium, or a combination thereof.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product 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 application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Moreover, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. The resource processing method is characterized by being applied to a cloud service control center, wherein the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the method comprises the following steps:
receiving a video analysis service request sent by any private cloud user in the plurality of different private cloud users when video analysis service exists; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
Issuing a video analysis service to a video analysis end based on the video analysis service request, so that the video analysis end performs video analysis on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm;
receiving metering information counted by the video analysis end in the video analysis process; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; generating a charging bill according to the metering information and the obtained target selling price of the target video analysis service algorithm; the target selling price of the target video analysis service algorithm comprises the following steps: the cost of billing per unit time when the target video analytics service algorithm is run, the cost of billing per unit time when the algorithm result generated when the target video analytics service algorithm is run is stored, and the cost of billing per unit time for AI computing power resources required when the target video analytics service algorithm is run.
2. The method of claim 1, wherein the plurality of different private cloud users are different sub-organizations under the same organization.
3. The method according to claim 1, characterized in that the method further comprises:
and issuing the charging bill to a private cloud user sending the video analysis service request, and determining a final bill based on a checking result of the private cloud user for the charging bill.
4. The method of claim 1, wherein the target selling price of the target video analytics service algorithm further comprises an algorithm base unit price at which the target video analytics service algorithm is run.
5. The resource processing method is characterized by being applied to a video analysis end, wherein the video analysis end is communicated with a deployed cloud service control center, and the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the method comprises the following steps:
receiving video analysis service issued by the cloud service control center; the video resolution service is generated based on a video resolution service request, the video resolution service request being sent by any one of the plurality of different private cloud users when there is a video resolution service; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
Performing video analysis on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm; reporting metering information counted in the video analysis process to the cloud service control center to generate a charging bill by the cloud service control center according to the metering information and the obtained target selling price of the target video analysis service algorithm; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; the target selling price of the target video analysis service algorithm comprises the following steps: the method comprises the steps of charging cost per unit time when a target video analysis service algorithm is operated, charging cost per unit time when an algorithm result generated when the target video analysis service algorithm is operated is stored, and charging cost per unit time of AI computing power resources required by the target video analysis service algorithm when the target video analysis service algorithm is operated;
and after the video analysis is completed by utilizing the target video analysis service algorithm, releasing the AI calculation force required by the target video analysis service algorithm.
6. The method of claim 5, wherein the video parsing of the video stream corresponding to the private cloud user sending the video parsing service request based on the video parsing service and using the target video parsing service algorithm comprises:
the video stream ID carried in the video analysis service is obtained, the video stream corresponding to the private cloud user is obtained from a storage center storing the video according to the video stream ID, and video analysis is carried out on the video stream according to the target video analysis service algorithm.
7. A resource processing system, the system comprising: the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool;
the cloud service control center for performing the steps in the method according to any one of claims 1 to 4;
the video parsing end is configured to perform the steps in the method according to any one of claims 5 to 6.
8. The resource processing device is characterized by being applied to a cloud service control center, wherein the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the device comprises:
A receiving unit: the method comprises the steps of receiving a video analysis service request sent by any private cloud user in a plurality of different private cloud users when video analysis service exists; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
issuing unit: the video analysis method comprises the steps that video analysis service is issued to a video analysis end based on the video analysis service request, so that the video analysis end performs video analysis on a video stream corresponding to a private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm;
a statistics unit: the metering information is used for receiving statistics of the video analysis end in the video analysis process; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; generating a charging bill according to the metering information and the obtained target selling price of the target video analysis service algorithm; the target selling price of the target video analysis service algorithm comprises the following steps: the cost of billing per unit time when the target video analytics service algorithm is run, the cost of billing per unit time when the algorithm result generated when the target video analytics service algorithm is run is stored, and the cost of billing per unit time for AI computing power resources required when the target video analytics service algorithm is run.
9. The resource processing device is characterized by being applied to a video analysis end, wherein the video analysis end is communicated with a deployed cloud service control center, and the cloud service control center provides video analysis cloud services for a plurality of different private cloud users; the plurality of different private cloud users share the same AI computing resource pool; the device comprises:
a receiving unit: the video analysis service is used for receiving video analysis service issued by the cloud service control center; the video resolution service is generated based on a video resolution service request, the video resolution service request being sent by any one of the plurality of different private cloud users when there is a video resolution service; the video analysis service request carries a target video analysis service algorithm determined by the private cloud user;
an analysis unit: the video analysis service algorithm is used for carrying out video analysis on the video stream corresponding to the private cloud user sending the video analysis service request based on the video analysis service and by utilizing the target video analysis service algorithm; reporting metering information counted in the video analysis process to the cloud service control center to generate a charging bill by the cloud service control center according to the metering information and the obtained target selling price of the target video analysis service algorithm; the metering information comprises AI computing power resources consumed by the target video analysis service algorithm when the target video analysis service algorithm is operated and operation time of the target video analysis service algorithm when the target video analysis service algorithm is operated; the target selling price of the target video analysis service algorithm comprises the following steps: the method comprises the steps of charging cost per unit time when a target video analysis service algorithm is operated, charging cost per unit time when an algorithm result generated when the target video analysis service algorithm is operated is stored, and charging cost per unit time of AI computing power resources required by the target video analysis service algorithm when the target video analysis service algorithm is operated;
A release unit: and the AI algorithm is used for releasing the AI algorithm force required by the target video analysis service algorithm after the video analysis is completed by the target video analysis service algorithm.
10. An electronic device, comprising: a processor and a machine-readable storage medium;
a machine-readable storage medium for storing computer-readable instructions which, when executed by the processor, implement the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310224227.3A CN116074541B (en) | 2023-03-09 | 2023-03-09 | Resource processing method, system, device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310224227.3A CN116074541B (en) | 2023-03-09 | 2023-03-09 | Resource processing method, system, device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116074541A CN116074541A (en) | 2023-05-05 |
| CN116074541B true CN116074541B (en) | 2023-06-02 |
Family
ID=86180378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310224227.3A Active CN116074541B (en) | 2023-03-09 | 2023-03-09 | Resource processing method, system, device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116074541B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109981301A (en) * | 2019-03-20 | 2019-07-05 | 新华三云计算技术有限公司 | Cloud service charging method and system |
| CN113542316A (en) * | 2020-04-13 | 2021-10-22 | 展讯半导体(南京)有限公司 | Computing power sharing method and related equipment |
| CN114296924A (en) * | 2021-12-29 | 2022-04-08 | 中国联合网络通信集团有限公司 | Edge calculation force sharing method, server and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10033729B2 (en) * | 2016-04-14 | 2018-07-24 | International Business Machines Corporation | Dynamic phrase base authentication system |
-
2023
- 2023-03-09 CN CN202310224227.3A patent/CN116074541B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109981301A (en) * | 2019-03-20 | 2019-07-05 | 新华三云计算技术有限公司 | Cloud service charging method and system |
| CN113542316A (en) * | 2020-04-13 | 2021-10-22 | 展讯半导体(南京)有限公司 | Computing power sharing method and related equipment |
| CN114296924A (en) * | 2021-12-29 | 2022-04-08 | 中国联合网络通信集团有限公司 | Edge calculation force sharing method, server and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116074541A (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104579768B (en) | Client side upgrading method and device | |
| US11556877B2 (en) | Generation of engagement and support recommendations for content creators | |
| CN110830735B (en) | Video generation method and device, computer equipment and storage medium | |
| US10783002B1 (en) | Cost determination of a service call | |
| WO2017166643A1 (en) | Method and device for quantifying task resources | |
| WO2020082611A1 (en) | Method for carrying out deep learning on basis of blockchain platform and electronic device | |
| CN110233741B (en) | Service charging method, device, equipment and storage medium | |
| US20100010799A1 (en) | Device simulation method and system | |
| US9619827B1 (en) | Flexible resource commitments for computing resources | |
| CN111415179B (en) | User rights and interests information processing method and device and electronic equipment | |
| CN111224791B (en) | Cloud resource charging method and device, electronic equipment and storage medium | |
| CN108241535B (en) | Resource management method and device and server equipment | |
| CN111402058A (en) | Data processing method, device, equipment and medium | |
| CN110826786A (en) | Method and device for predicting number of target place population and storage medium | |
| CN113852834A (en) | Content display method, device, equipment and storage medium | |
| CN116074541B (en) | Resource processing method, system, device and electronic equipment | |
| US11755379B2 (en) | Liaison system and method for cloud computing environment | |
| CN110096352A (en) | Process management method, device and computer readable storage medium | |
| US9922298B2 (en) | System and method for determining optimal asset configurations while minimizing disruption to existing business operations in a service delivery environment | |
| CN116185731A (en) | Terminal test system and method based on blockchain network and electronic equipment | |
| CN109146147A (en) | Event prediction method and device, electronic equipment | |
| CN108717735A (en) | The remote deployment method of parking fee fees policy, storage medium, apparatus and system | |
| CN114493756A (en) | Resource management method, device, equipment and storage medium | |
| CN111160991A (en) | PDB advertisement traffic optimization method, device, storage medium and electronic equipment | |
| CN111260418A (en) | Method, device, server and storage medium for probability selection of object |
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 |