CN114827677A - Artificial intelligence analysis load balancing method and device - Google Patents
Artificial intelligence analysis load balancing method and device Download PDFInfo
- Publication number
- CN114827677A CN114827677A CN202210219861.3A CN202210219861A CN114827677A CN 114827677 A CN114827677 A CN 114827677A CN 202210219861 A CN202210219861 A CN 202210219861A CN 114827677 A CN114827677 A CN 114827677A
- Authority
- CN
- China
- Prior art keywords
- artificial intelligence
- intelligence analysis
- router
- gateway
- message
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 175
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 165
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000008707 rearrangement Effects 0.000 claims description 16
- 238000013508 migration Methods 0.000 abstract description 4
- 230000005012 migration Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 5
- 238000011144 upstream manufacturing Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012916 structural analysis Methods 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
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream 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]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
- H04N21/64—Addressing
- H04N21/6405—Multicasting
-
- 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]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
- H04N21/647—Control signaling between network components and server or clients; Network processes for video distribution between server and clients, e.g. controlling the quality of the video stream, by dropping packets, protecting content from unauthorised alteration within the network, monitoring of network load, bridging between two different networks, e.g. between IP and wireless
- H04N21/64723—Monitoring of network processes or resources, e.g. monitoring of network load
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an artificial intelligence analysis load balancing method and a device, wherein a client initiates an artificial intelligence analysis request, a DR router sends an arrangement message after receiving the artificial intelligence analysis request to know which gateway routers can bear, then the load sharing is carried out, and the gateway routers are arranged to respectively bear the split artificial intelligence analysis tasks. And when the gateway router is invalid, carrying out load migration. The technical scheme of the invention distributes the artificial intelligence analysis task to each edge gateway router, thereby improving the service efficiency of each gateway router.
Description
Technical Field
The application belongs to the technical field of artificial intelligence analysis, and particularly relates to an artificial intelligence analysis load balancing method and device.
Background
Machine vision is a branch of the rapid development of artificial intelligence. In brief, machine vision is to use a machine to take measurements and judgments instead of human eyes. The machine vision system converts the shot target into image signals through a machine vision product (namely an image shooting device which is divided into a CMOS (complementary metal oxide semiconductor) product and a CCD (charge coupled device), transmits the image signals to a special image processing system to obtain the form information of the shot target, and converts the form information into digital signals according to the information of pixel distribution, brightness, color and the like; the image system performs various operations on the signals to extract the characteristics of the target, and then the accurate identification, effective pushing and accurate guiding are performed according to the judgment result. The machine vision system has the basic characteristics of improving the accuracy and the automation degree of information identification. Through the identification and analysis of external characteristic information such as portrait, article, trade mark, combine LBS (Location Based Services, LBS), XR (Extended Reality, XR) technique at application scenes such as wisdom community, wisdom business district, virtual shopping effectively to use, provide the digital living space service of novel social system.
The artificial intelligence analysis of current machine vision either through the centralized processing of cloud center, or through cloud limit side coprocessing, all relatively more centralization, the equipment of undertaking artificial intelligence analysis task often needs the task of handling more, and is higher to the performance requirement of equipment itself, and the cost is more expensive. Meanwhile, when an artificial intelligence analysis task is processed, the occupied time is long, and the real-time performance is poor.
Disclosure of Invention
The application aims to provide an artificial intelligence analysis load balancing method and device so as to overcome the defects caused by centralized processing in the prior art.
In order to achieve the purpose, the technical scheme of the application is as follows:
an artificial intelligence analysis load balancing method is applied to a video stream multicast network, the video stream multicast network comprises a video source, a DR router, a client and a gateway router corresponding to the client, and the artificial intelligence analysis load balancing method is characterized by comprising the following steps:
the method comprises the steps that multicast video streams sent by video sources are distributed to clients through a multicast distribution tree, the clients initiate artificial intelligence analysis requests, the target IP addresses of the artificial intelligence analysis requests are IP addresses of the video sources, and the source IP addresses are multicast group IP addresses;
after receiving the artificial intelligence analysis request, the DR router sends an artificial intelligence analysis task arrangement message, wherein the destination IP address of the artificial intelligence analysis task arrangement message is a multicast group IP address, and the source IP address is a video source IP address;
after receiving an artificial intelligence analysis task arrangement message, if the artificial intelligence analysis task can be borne by any gateway router in the multicast group, replying a registration message, wherein the destination IP address of the registration message is a video source, the source IP address is a multicast group IP address, and the registration message carries a gateway router ID;
after the DR router receives the registration message, if a plurality of gateway routers undertake the same artificial intelligence analysis task, splitting the artificial intelligence analysis task, sending an artificial intelligence analysis task rearrangement message, and rearranging the split artificial intelligence analysis task to the plurality of gateway routers;
and the gateway routers receiving the artificial intelligence analysis task rearrangement message respectively undertake the arranged split artificial intelligence analysis tasks.
Further, the artificial intelligence analysis load balancing method further includes:
and after the gateway routers which receive the artificial intelligence analysis task rearrangement message respectively undertake the arranged split artificial intelligence analysis tasks, the gateway routers also send registration messages.
Further, the artificial intelligence analysis load balancing method further includes:
and each gateway router sends the artificial intelligence analysis result to the DR router, and the DR router sends the artificial intelligence analysis result in a multicast mode.
Further, the artificial intelligence analysis load balancing method further includes:
and the client does not send the corresponding artificial intelligence analysis request when finding that the artificial intelligence analysis result corresponding to the artificial intelligence analysis task needing to be carried out can be obtained from the multicast group.
Further, the artificial intelligence analysis load balancing method further includes:
the DR router periodically detects whether the gateway router bearing the artificial intelligence analysis task is effective, if the DR router detects that the gateway router is ineffective, the DR router sends an artificial intelligence analysis task arrangement message, selects one gateway router from the gateway routers replying the registration message, issues an artificial intelligence analysis task rearrangement message, and designates the selected gateway router to bear the artificial intelligence analysis task of the ineffective gateway router.
The application also provides an artificial intelligence analysis load balancing device, which comprises a processor and a memory, wherein the memory is stored with a plurality of computer instructions, and the computer instructions are executed by the processor to realize the steps of the artificial intelligence analysis load balancing method.
According to the artificial intelligence analysis load balancing method and device, the client side initiates an artificial intelligence analysis request, and the gateway router shares the load to execute artificial intelligence analysis work. After receiving the artificial intelligence analysis task, the DR router sends a scheduling message to know which gateway routers can bear the artificial intelligence analysis task, and then carries out load sharing. And when the gateway router is invalid, carrying out load migration. According to the technical scheme, the artificial intelligence analysis tasks are distributed to each edge gateway router, and the service efficiency of each gateway router is improved.
Drawings
Fig. 1 is a schematic diagram of a network structure according to an embodiment of the present application;
fig. 2 is a flowchart of an artificial intelligence analysis load balancing method according to the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The artificial intelligence analysis load balancing method provided by the application can be applied to the application environment shown in fig. 1. The network of the application environment includes a video source, a network connection device, and a client device that receives a video stream. The video source is a device for collecting or distributing video, such as the network cameras IPC1 and IPC2 in fig. 1, and may also be a media server. The network connection device is various routers, switches and the like for networking, and the application takes the router as an example for description, wherein the router comprises a designated router DR, a gateway router GW connected with a client PC or IPC, and other routers connected with the DR and GW, and all the routers form the whole network. The routers in the network support multicast, and can also be called multicast routers, and have the analysis capability of artificial intelligence. The video stream transmitted by the IPC is transmitted in a multicast manner, for example (S, G). The client PC receives (S, G) the video stream in multicast. The multicast network runs the common PIM SM multicast routing protocol. A multicast distribution tree from the video source to the client is already established. The need for analysis of artificial intelligence is initiated by the client. All messages in the network contain router IDs (router identifications), and each router ID is unique in the whole network and does not conflict.
In one embodiment, as shown in fig. 2, an artificial intelligence analysis load balancing method is provided and applied to a video stream multicast network, where the video stream multicast network includes a video source, a DR router, a client, and a gateway router corresponding to the client. The artificial intelligence analysis load balancing method comprises the following steps:
and step S1, distributing the multicast video stream sent by the video source to the client through the multicast distribution tree, and the client initiates an artificial intelligence analysis request, wherein the destination IP address of the artificial intelligence analysis request is the IP address of the video source, and the source IP address is the IP address of the multicast group.
The router in the network of the embodiment supports multicast and has the analysis capability of artificial intelligence. A multicast video stream from a video source, such as IPC1, is distributed to the various client PCs via a multicast distribution tree. The client PC initiates an artificial intelligence analysis request, the destination IP of the request message is a video source, the source IP is a multicast group G, the request message is reversely transmitted to the video source along the path of the video stream (S, G), namely, the request message is reversely transmitted to the video source along a multicast distribution tree, each multicast router sends the request message to an upstream router from an inlet interface of an (S, G) table entry, and each multicast router on the multicast distribution tree can receive the request message. The forwarding lines between the multicast sender and the multicast receiver form a multicast distribution tree, which is a path of the video stream (S, G) in this embodiment, and the multicast distribution tree includes a DR router and other multicast routers, and the multicast distribution tree is a relatively mature technology in the art and is not described herein again.
According to the method and the system, the destination IP address is the IP address of the video source, and the source IP address is the multicast group IP address, so that the destination IP address can be reversely transmitted to the video source along the multicast distribution tree and can reach the DR router. The traditional IP message only can be routed to a destination IP address, and a DR router in multicast cannot be found.
For example, if the client PC1 has an artificial intelligence analysis task a, it initiates an artificial intelligence analysis request and passes the request to the video source IPC1 in the reverse direction along the path of the video stream (S, G).
Step S2, after receiving the artificial intelligence analysis request, the DR router sends an artificial intelligence analysis task arrangement message, wherein the destination IP address of the artificial intelligence analysis task arrangement message is a multicast group IP address, and the source IP address is a video source IP address.
The artificial intelligence analysis request is transmitted in the network and can reach the DR router inevitably, the DR router sends an artificial intelligence analysis task arrangement message, the destination IP address of the artificial intelligence analysis task arrangement message is a multicast group IP address, and the source IP address is a video source IP address. The artificial intelligence analysis task scheduling message carries artificial intelligence analysis task information, such as the content and identification of the artificial intelligence analysis task, and is mainly convenient for a router receiving the message to know what artificial intelligence analysis task is.
Step S3, after receiving the artificial intelligence analysis task scheduling message, if the gateway router in the multicast group can bear the artificial intelligence analysis task, replying a registration message, where the destination IP address of the registration message is a video source, the source IP address is a multicast group IP address, and the registration message carries a gateway router ID.
And sending the artificial intelligence analysis task arrangement message along the multicast distribution tree, wherein each gateway router in the same multicast group can receive the artificial intelligence analysis task arrangement message.
For example, gateway router GW1 connected to client PC1 receives artificial intelligence analysis task scheduling message; the gateway router GW2 connected to the client PC2 also receives the artificial intelligence analysis task scheduling message. If the multicast group further includes other gateway routers, such as GW3, the artificial intelligence analysis task may also be received, which is not described herein.
The gateway router is connected with the client and can automatically identify the gateway router. In addition, when the gateway router itself is both the PIM router and the IGMP querier, it is the gateway router. How to determine that the router itself is the gateway router is a relatively mature technology in the field and is not described herein again.
The gateway router receiving the artificial intelligence analysis task scheduling message may determine whether it is suitable for executing the artificial intelligence analysis task in the scheduling message, for example, may determine according to its own capability and load condition, and if it is suitable for execution, reply the registration message.
For example, GW1 and GW2 reply registration messages, and indicate to multicast routers upstream of the multicast distribution tree that they can undertake the artificial intelligence analysis task specified by the scheduling message, and the registration messages carry the undertaken artificial intelligence analysis task identifier and the identifier of the gateway router itself.
For artificial intelligence analysis task a, both gateway router GW1 and gateway router GW2 reply to the registration message after receiving the scheduling message. The registration message replied by gateway router GW1 carries: an artificial intelligence analysis task A, GW 1. The registration message replied by gateway router GW2 carries: artificial intelligence analysis tasks A, GW 2. The destination IP address of the registration message is video source IPC1, the source IP is multicast group IP address G, and the registration message is transmitted to the video source in reverse direction along the path of the video stream (S, G).
It should be noted that, the client PC initiates an artificial intelligence analysis request, such as performing a structural analysis on the video image, or performing intelligent identification on a target in the video image, and the specific content of the artificial intelligence analysis is not limited in the present application. And if the gateway router does not support the corresponding artificial intelligence analysis task, not replying the registration message. Or the gateway router can not increase tasks any more due to the self load problem, and does not reply the registration message.
The registration message is passed to the DR router, and the steps of this embodiment make the DR routers in the network aware that the artificial intelligence analysis task can be undertaken by gateway routers GW1, GW 2.
Step S4, after the DR router receives the registration message, if there are multiple gateway routers bearing the same artificial intelligence analysis task, the artificial intelligence analysis task is split, an artificial intelligence analysis task rearrangement message is sent, and the split artificial intelligence analysis task is rearranged to the multiple gateway routers.
And when the DR router in the network receives the registration message and finds that a plurality of gateway routers can bear the artificial intelligence analysis task, the DR router needs to disassemble the artificial intelligence analysis task and sends an artificial intelligence analysis task rearrangement message.
For example, the DR router receives registration messages from gateway routers GW1 and GW2 indicating that they can assume artificial intelligence analysis task a, and splits artificial intelligence analysis task a into subtasks a1 and a2, where a1 is assigned to GW1 and a2 is assigned to GW 2.
The artificial intelligence analysis task rearrangement message can carry the distributed artificial intelligence task information and the identification of the gateway router bearing the artificial intelligence task, so that the gateway router receiving the message can conveniently judge whether to bear the distributed task by itself.
Or only one gateway router replies the registration message, the DR router does not split the task, directly issues the rearrangement message, and appoints the network router to undertake the artificial intelligence analysis task. When splitting the task, the proportion of the split sub-tasks can be the same or different. For example, subtask A1 and subtask A2 each account for 50% of total task A, or A1 accounts for all of total task A, while A2 is 0. The proportion of the subtasks may also be determined by referring to the performance and load of the respective gateway router, which is not described herein again.
And step S5, the gateway routers which receive the artificial intelligence analysis task rearrangement message respectively undertake the arranged split artificial intelligence analysis tasks.
In this embodiment, the artificial intelligence analysis task rearrangement message carries the assigned subtasks and the identifier of the gateway router that undertakes the subtasks, so that the gateway routers undertake the corresponding subtasks after receiving the artificial intelligence analysis task rearrangement message. GW1 assumes subtask a1 and GW2 assumes subtask a 2.
And then, the gateway router can reply a registration message, and indicates the multicast router at the upstream of the multicast distribution tree that the gateway router undertakes the appointed artificial intelligence analysis task, wherein the registration message carries the undertaken artificial intelligence analysis task identifier and the identifier of the gateway router.
All multicast routers along the multicast distribution tree, e.g. upstream routers of gateway router GW1 up to the DR router, may receive information that "gateway router GW1 is charged with artificial intelligence analysis task a 1". Therefore, each multicast router at the upstream knows the artificial intelligence analysis task undertaken by each gateway router.
According to the technical scheme, each gateway router can share the artificial intelligence analysis task on average. For example, client PC1 sends 10 artificial intelligence analysis tasks, while client PC2 does not have artificial intelligence analysis tasks, and originally gateway router GW2 is idle, according to the technical solution of the present application, GW1 shares artificial intelligence analysis tasks with GW 2.
For the same artificial intelligence analysis task a, if after the client PC1 initiates a request, GW1 and GW2 have already assumed a1 and a2, respectively, after the client PC2 initiates the same artificial intelligence analysis task request, it is found that the task a has been split into a1 and a2, the DR router does not need to send an artificial intelligence analysis task scheduling message any more, and the client PC2 directly receives the analysis result.
In a specific embodiment, the artificial intelligence analysis load balancing method further includes:
and each gateway router sends the artificial intelligence analysis result to the DR router, and the DR router sends the artificial intelligence analysis result in a multicast mode.
Considering that the characteristics of the (S, G) multicast table entry do not allow receiving the (S, G) multicast packet from the egress interface, GW1 and GW2 unicast the analysis result to the DR, and the DR forwards the analysis result in multicast (S, G), so that the client PC1 receives the analysis results of task a1 and task a 2. Of course, the client PC2 will also receive the analysis results and it may choose to discard them, but if it needs to analyze the results of task a, it will find that the corresponding analysis results have been received, and no analysis request will be sent again.
In another specific embodiment, the artificial intelligence analysis load balancing method further includes:
the DR router periodically detects whether the gateway router bearing the artificial intelligence analysis task is effective, if the DR router detects that the gateway router is ineffective, the DR router sends an artificial intelligence analysis task arrangement message, selects one gateway router from the gateway routers replying the registration message, issues an artificial intelligence analysis task rearrangement message, and designates the selected gateway router to bear the artificial intelligence analysis task of the ineffective gateway router.
In particular, since the DR router has split task A into A1 and A2, it is the responsibility of the DR router to monitor the operational status of GW1 and GW2 so that migration of tasks can be scheduled in the event that the analytical execution of one of the routers fails.
In this embodiment, the DR router periodically multicast-sends the task scheduling message to the gateway routers GW1 and GW2, adds the router IDs of GW1 and GW2 in the message, and after receiving the message, GW1 and GW2 find that their own IDs exist in the message, and then replies a registration message to the DR router. If GW2 does not reply to the registration message for 3 consecutive cycles and GW2 does not send any analysis result to the DR router during this time, the DR router considers GW2 to have failed and needs to perform task migration.
Since the DR router does not know which routers are available to undertake the analysis task, a scheduling message is sent by multicast, containing information for "analysis task a 2". The message will reach each gateway router, and if GW1 and GW3 can undertake analysis task a2, a registration message is replied to the DR router, and the DR router selects one of the routers, for example GW3, according to a policy, which may be selected according to the task amount, execution time, performance index, etc. of each router stored in the DR router. The DR router sends a reschedule message to the gateway router 3, asking GW3 to assume task a 2.
The DR router of this embodiment also continues to send several schedule cancellation messages to GW2, informing GW2 to cancel its responsibility for task a 2. This is to prevent GW2 from continuing the analysis task, possibly because the task became relaxed, resulting in a scheduled repeat and multiple copies of the data being received by the client.
In another embodiment, the present application further provides an artificial intelligence analysis load balancing apparatus, which includes a processor and a memory storing computer instructions, wherein the computer instructions, when executed by the processor, implement the steps of the artificial intelligence analysis load balancing method.
For specific limitations of the artificial intelligence analysis load balancing apparatus, reference may be made to the above limitations of the artificial intelligence analysis load balancing method, which is not described herein again. The artificial intelligence analysis load balancing device can be wholly or partially realized by software, hardware and a combination thereof. The method can be embedded in hardware or independent from a processor in the computer device, and can also be stored in a memory in the computer device in software, so that the processor can call and execute the corresponding operation.
The memory and the processor are electrically connected, directly or indirectly, to enable transmission or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory stores a computer program that can be executed on the processor, and the processor executes the computer program stored in the memory, thereby implementing the network topology layout method in the embodiment of the present invention.
The Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory is used for storing programs, and the processor executes the programs after receiving the execution instructions.
The processor may be an integrated circuit chip having data processing capabilities. The Processor may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like. The various methods, steps and logic blocks disclosed in embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (6)
1. An artificial intelligence analysis load balancing method is applied to a video stream multicast network, the video stream multicast network comprises a video source, a DR router, a client and a gateway router corresponding to the client, and the artificial intelligence analysis load balancing method is characterized by comprising the following steps:
the method comprises the steps that multicast video streams sent by video sources are distributed to clients through a multicast distribution tree, the clients initiate artificial intelligence analysis requests, the target IP addresses of the artificial intelligence analysis requests are IP addresses of the video sources, and the source IP addresses are multicast group IP addresses;
after receiving the artificial intelligence analysis request, the DR router sends an artificial intelligence analysis task arrangement message, wherein the destination IP address of the artificial intelligence analysis task arrangement message is a multicast group IP address, and the source IP address is a video source IP address;
after receiving an artificial intelligence analysis task arrangement message, if the artificial intelligence analysis task can be borne by any gateway router in the multicast group, replying a registration message, wherein the destination IP address of the registration message is a video source, the source IP address is a multicast group IP address, and the registration message carries a gateway router ID;
after the DR router receives the registration message, if a plurality of gateway routers undertake the same artificial intelligence analysis task, splitting the artificial intelligence analysis task, sending an artificial intelligence analysis task rearrangement message, and rearranging the split artificial intelligence analysis task to the plurality of gateway routers;
and the gateway routers receiving the artificial intelligence analysis task rearrangement message respectively undertake the arranged split artificial intelligence analysis tasks.
2. The artificial intelligence analysis load balancing method of claim 1, further comprising:
and after the gateway routers which receive the artificial intelligence analysis task rearrangement message respectively undertake the arranged split artificial intelligence analysis tasks, the gateway routers also send registration messages.
3. The artificial intelligence analysis load balancing method of claim 1, further comprising:
and each gateway router sends the artificial intelligence analysis result to the DR router, and the DR router sends the artificial intelligence analysis result in a multicast mode.
4. The artificial intelligence analysis load balancing method of claim 1, wherein the artificial intelligence analysis load balancing method further comprises:
and the client does not send the corresponding artificial intelligence analysis request when finding that the artificial intelligence analysis result corresponding to the artificial intelligence analysis task needing to be carried out can be obtained from the multicast group.
5. The artificial intelligence analysis load balancing method of claim 1, further comprising:
the DR router periodically detects whether the gateway router bearing the artificial intelligence analysis task is effective, if the DR router detects that the gateway router is ineffective, the DR router sends an artificial intelligence analysis task arrangement message, selects one gateway router from the gateway routers replying the registration message, issues an artificial intelligence analysis task rearrangement message, and designates the selected gateway router to bear the artificial intelligence analysis task of the ineffective gateway router.
6. An artificial intelligence analysis load balancing apparatus comprising a processor and a memory having stored thereon computer instructions, wherein the computer instructions, when executed by the processor, implement the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210219861.3A CN114827677B (en) | 2022-03-08 | 2022-03-08 | Artificial intelligence analysis load balancing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210219861.3A CN114827677B (en) | 2022-03-08 | 2022-03-08 | Artificial intelligence analysis load balancing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114827677A true CN114827677A (en) | 2022-07-29 |
| CN114827677B CN114827677B (en) | 2024-02-09 |
Family
ID=82528756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210219861.3A Active CN114827677B (en) | 2022-03-08 | 2022-03-08 | Artificial intelligence analysis load balancing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114827677B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115426221A (en) * | 2022-10-14 | 2022-12-02 | 湖南省邮电规划设计院有限公司 | Gateway device of Internet of things |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101651609A (en) * | 2008-08-14 | 2010-02-17 | 华为技术有限公司 | Method and device for realizing multicast load sharing |
| CN102238092A (en) * | 2011-08-02 | 2011-11-09 | 杭州华三通信技术有限公司 | Method for performing load sharing on encoder and encoder |
| US20180152361A1 (en) * | 2016-11-29 | 2018-05-31 | Hong-Min Chu | Distributed assignment of video analytics tasks in cloud computing environments to reduce bandwidth utilization |
| CN113239792A (en) * | 2021-05-11 | 2021-08-10 | 深圳市安软科技股份有限公司 | Big data analysis processing system and method |
| CN113485842A (en) * | 2021-07-30 | 2021-10-08 | 浙江大华技术股份有限公司 | Method and device for analyzing data based on device cluster |
-
2022
- 2022-03-08 CN CN202210219861.3A patent/CN114827677B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101651609A (en) * | 2008-08-14 | 2010-02-17 | 华为技术有限公司 | Method and device for realizing multicast load sharing |
| CN102238092A (en) * | 2011-08-02 | 2011-11-09 | 杭州华三通信技术有限公司 | Method for performing load sharing on encoder and encoder |
| US20180152361A1 (en) * | 2016-11-29 | 2018-05-31 | Hong-Min Chu | Distributed assignment of video analytics tasks in cloud computing environments to reduce bandwidth utilization |
| CN113239792A (en) * | 2021-05-11 | 2021-08-10 | 深圳市安软科技股份有限公司 | Big data analysis processing system and method |
| CN113485842A (en) * | 2021-07-30 | 2021-10-08 | 浙江大华技术股份有限公司 | Method and device for analyzing data based on device cluster |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115426221A (en) * | 2022-10-14 | 2022-12-02 | 湖南省邮电规划设计院有限公司 | Gateway device of Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114827677B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240022650A1 (en) | Computing power application traffic forwarding method and apparatus | |
| US7729350B2 (en) | Virtual multicast routing for a cluster having state synchronization | |
| US8300646B2 (en) | Message handling in a local area network having redundant paths | |
| EP1677464B1 (en) | Packet distribution control method | |
| CN100433730C (en) | Method and system of multicast and video-on-demand | |
| EP3210348B1 (en) | Multicast traffic management in an overlay network | |
| CN102377640B (en) | Message processing apparatus, message processing method and preprocessor | |
| CN105897444B (en) | Multicast group management method and device | |
| WO2015101260A1 (en) | Method and system for processing instant communication service | |
| CN105099898B (en) | A kind of PPPOE message forwarding methods and BRAS servers | |
| EP1041775A1 (en) | Router monitoring in a data transmission system utilizing a network dispatcher for a cluster of hosts | |
| CN103117935B (en) | Be applied to multicast data forwarding method and the device of multi-home networking | |
| CN114024880B (en) | Network target range probe acquisition method and system based on proxy IP and flow table | |
| US9052951B2 (en) | Software bus | |
| CN112398755B (en) | Traffic forwarding method, service card and system | |
| CN111803925B (en) | Scheduling method and device of forwarding server of cloud game and readable storage medium | |
| CN114827677B (en) | Artificial intelligence analysis load balancing method and device | |
| CN110932972B (en) | Data transmission method and device and electronic equipment | |
| US8577984B2 (en) | State management in a distributed computing system | |
| CN111541765A (en) | Method and system for multi-level routing scheduling | |
| JP6402077B2 (en) | Relay system, relay method, and program | |
| CN107948273B (en) | SDN-based load sharing and secure access method and system | |
| CN114286127B (en) | Distributed artificial intelligence analysis method and device | |
| US20120191873A1 (en) | Relay apparatus, communication network system, and load distribution method | |
| CN111866046A (en) | Method for realizing cluster and related equipment |
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 |