CN114286127B - Distributed artificial intelligence analysis method and device - Google Patents
Distributed artificial intelligence analysis method and device Download PDFInfo
- Publication number
- CN114286127B CN114286127B CN202210218287.XA CN202210218287A CN114286127B CN 114286127 B CN114286127 B CN 114286127B CN 202210218287 A CN202210218287 A CN 202210218287A CN 114286127 B CN114286127 B CN 114286127B
- Authority
- CN
- China
- Prior art keywords
- artificial intelligence
- intelligence analysis
- multicast
- router
- address
- 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
Images
Abstract
The invention discloses a distributed artificial intelligence analysis method and a device, wherein a client initiates an artificial intelligence analysis request, a DR router sends an artificial intelligence analysis task arrangement message after receiving the artificial intelligence analysis request, the destination IP address of the artificial intelligence analysis task arrangement message is a multicast group IP address, a source IP address is a video source IP address, the artificial intelligence analysis task arrangement message carries a gateway router IP address or a client IP address corresponding to the client, and the gateway router corresponding to the client undertakes a corresponding artificial intelligence analysis task after receiving the artificial intelligence analysis task arrangement message. The invention performs artificial intelligence analysis work by routers as close to the client as possible. When multiple clients initiate requests, the routers performing the analysis merge. The invention avoids repeated analysis as much as possible, avoids repeated analysis work as much as possible and gives full play to the processing potential of the routing node.
Description
Technical Field
The application belongs to the technical field of artificial intelligence analysis, and particularly relates to a distributed artificial intelligence analysis 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 replace human eyes for measurement and judgment. The machine vision system converts the shot target into image signal by machine vision product (image shooting device, which is divided into CMOS and CCD), and transmits it to special image processing system, to obtain the form information of shot target, and converts it into digital signal according to the information of pixel distribution, brightness and color, the image system carries out various operations to these signals to extract the characteristic of target, and then according to the result of discrimination, it can accurately identify, effectively push and accurately guide. 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 duration is large, and the real-time performance is poor.
Disclosure of Invention
The application aims to provide a distributed artificial intelligence analysis 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:
a distributed artificial intelligence analysis 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 distributed artificial intelligence analysis method comprises 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 destination IP addresses of the artificial intelligence analysis requests are IP addresses of the video sources, the source IP addresses are multicast group IP addresses, and the artificial intelligence analysis requests carry gateway router IP addresses or client IP addresses corresponding to the clients;
after receiving the artificial intelligence analysis request, the DR router sends an artificial intelligence analysis task arrangement message, wherein the target IP address of the artificial intelligence analysis task arrangement message is a multicast group IP address, the source IP address is a video source IP address, and the artificial intelligence analysis task arrangement message carries a gateway router IP address or a client IP address corresponding to the client;
and after receiving the artificial intelligence analysis task arrangement message, the gateway router corresponding to the client bears the corresponding artificial intelligence analysis task.
Further, the distributed artificial intelligence analysis method further includes:
when the gateway router corresponding to the client bears the corresponding artificial intelligence analysis task, the gateway router also returns 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 multicast router in the multicast distribution tree records the gateway router bearing the artificial intelligence analysis task after receiving the registration message.
Further, the distributed artificial intelligence analysis method further includes:
after receiving the artificial intelligence analysis request, the multicast router in the multicast distribution tree undertakes the artificial intelligence analysis task if finding that the corresponding artificial intelligence analysis task is registered to be undertaken by the gateway router at the downstream of the multicast router, and informs the gateway router which originally undertakes the artificial intelligence analysis task to stop undertaking the artificial intelligence analysis task.
Further, the distributed artificial intelligence analysis method further includes:
after receiving the artificial intelligence analysis request, the multicast router in the multicast distribution tree continues to transmit the artificial intelligence analysis request upstream if finding that the corresponding artificial intelligence analysis task is registered as being borne by the multicast router upstream of the multicast router.
Further, the distributed artificial intelligence analysis method further includes:
and after receiving the registration message, the multicast router in the multicast distribution tree records the multicast router bearing the artificial intelligence analysis task.
The application also provides a distributed artificial intelligence analysis device, which comprises a processor and a memory, wherein the memory is used for storing a plurality of computer instructions, and the computer instructions are executed by the processor to realize the steps of the distributed artificial intelligence analysis method.
According to the distributed artificial intelligence analysis method and device, the client side initiates an artificial intelligence analysis request, and the router which is as close to the client side as possible executes artificial intelligence analysis work. When multiple clients initiate requests, the routers performing the analysis merge. According to the method and the system, the router executes the artificial intelligence analysis task and combines the executed schemes, so that real distributed analysis is realized, repeated analysis is avoided as much as possible, repeated analysis work is avoided as much as possible, and the processing potential of the routing node is fully exerted.
Drawings
Fig. 1 is a schematic diagram of a network structure according to an embodiment of the present application.
FIG. 2 is a flow chart of a distributed artificial intelligence analysis method of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The distributed artificial intelligence analysis method provided by the application can be applied to the application environment shown in fig. 1. The network of the application environment comprises a video source, a network connection device and a client device receiving a video stream. The video source is a device for collecting or distributing video, such as the webcam 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, the description is given by taking the router as an example, and the designated router DR and the gateway router GW connected with the client PC or IPC and other routers connected with the DR and GW are included in the router, and all the routers form the whole network. The routers in the network all support multicast, have artificial intelligence analysis capability and are multicast routers. 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 has been established. The need for analysis of artificial intelligence is initiated by the client. All messages in the network contain router IDs, and the IDs of all routers are unique in the whole network and do not conflict.
In one embodiment, as shown in fig. 2, a distributed artificial intelligence analysis 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 distributed artificial intelligence analysis method comprises the following steps:
and step S1, distributing the multicast video stream sent by the video source to the client through a multicast distribution tree, and initiating an artificial intelligence analysis request by the client, wherein the destination IP address of the artificial intelligence analysis request is the IP address of the video source, the source IP address is the IP address of a multicast group, and the artificial intelligence analysis request carries the IP address of a gateway router corresponding to the client or the IP address of the client.
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 reversely transmitted to the video source along the multicast distribution tree, each multicast router sends the message to an upstream router from an inlet interface of the (S, G) table entry, and each multicast router on the multicast distribution tree can receive the 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 of the request is the IP address of the video source through artificial intelligence analysis, and the source IP address is the IP address of the multicast group, so that the request can be transmitted to the video source along the reverse direction of the multicast distribution tree and reaches 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, it initiates an artificial intelligence analysis request and passes the request to the video source IPC1 along the reverse path of the video stream (S, G).
The artificial intelligence analysis request carries the gateway router IP address or the client IP address corresponding to the client, so that the DR router can obtain the IP address of the gateway router DW1 or the IP address of the client PC1 corresponding to the client conveniently.
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, the source IP address is a video source IP address, and the artificial intelligence analysis task arrangement message carries a gateway router IP address or a client IP address corresponding to the client.
The artificial intelligence analysis request is transmitted in the network, if the artificial intelligence analysis request reaches a DR router connected with a video source all the time, and no router is executing the artificial intelligence analysis task midway, the DR sends an artificial intelligence analysis task arrangement message, the target IP is a multicast group G, the source IP is video source IPC1, and the artificial intelligence analysis task arrangement message carries the IP address of a gateway router DW1 or the IP address of a client PC1 corresponding to the client.
In a specific embodiment, if there is a router executing a corresponding artificial intelligence analysis task in the middle of sending an artificial intelligence analysis request, the router does not forward the request message to the upstream any more, and directly forwards the artificial intelligence analysis result to the downstream through an (S, G) multicast stream, and the client initiating the request can receive the analysis result through the multicast stream.
And step S3, the gateway router corresponding to the client undertakes the corresponding artificial intelligence analysis task after receiving the artificial intelligence analysis task arrangement message.
The artificial intelligence analysis task scheduling message is transmitted to the gateway router GW connected to the client PC, and the router GW takes on the task of artificial intelligence analysis.
For example, the gateway router GW1 connected to the client PC1 receives the artificial intelligence analysis task scheduling message, and then assumes the artificial intelligence analysis task initiated by the client PC 1.
Because the artificial intelligence analysis task arrangement message carries the IP address of the gateway router DW1 or the IP address of the client PC1 corresponding to the client, the gateway router DW1 undertakes the corresponding artificial intelligence analysis task when judging that the carried gateway router IP address is the own IP address according to the gateway router IP address or the IP address of the client carried in the arrangement message, otherwise, does not undertake, thus avoiding other gateway routers from undertaking. Or according to the IP address of the client, searching the corresponding client IP from the ARP list item, and then undertaking the analysis task, or else not undertaking.
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 after executing the artificial intelligence analysis, the gateway router issues an artificial intelligence analysis result to the client side sending the request.
In another embodiment of the present application, the distributed artificial intelligence analysis method further includes:
when the gateway router corresponding to the client bears the corresponding artificial intelligence analysis task, the gateway router also returns 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 multicast router in the multicast distribution tree records the gateway router bearing the artificial intelligence analysis task after receiving the registration message.
As shown in fig. 2, the gateway router GW1 undertakes the artificial intelligence analysis task requested by the client PC1, and replies a registration message, where the destination IP address of the registration message is the video source IPC1, the source IP is the multicast group IP address G, the registration message carries the ID or IP address of the gateway router GW1, and also carries the identifier of the undertaken artificial intelligence analysis task, and is reversely transmitted to the video source along the path of the video stream (S, G).
All multicast routers in the multicast distribution tree, such as the upstream router of gateway router GW1 up to the DR router, record information that "gateway router GW1 undertakes artificial intelligence analysis tasks".
The steps of this embodiment allow other routers in the network to be aware that the artificial intelligence analysis task was undertaken by gateway router GW1, thereby facilitating the same artificial intelligence analysis task to be undertaken by one gateway router at a later time.
In another embodiment of the present application, the distributed artificial intelligence analysis method further includes:
after receiving the artificial intelligence analysis request, the multicast router in the multicast distribution tree undertakes the artificial intelligence analysis task if finding that the corresponding artificial intelligence analysis task is registered to be undertaken by the gateway router at the downstream of the multicast router, and informs the gateway router which originally undertakes the artificial intelligence analysis task to stop undertaking the artificial intelligence analysis task.
After receiving the artificial intelligence analysis request, the multicast router in the multicast distribution tree continues to transmit the artificial intelligence analysis request upstream if finding that the corresponding artificial intelligence analysis task is registered as being borne by the multicast router upstream of the multicast router.
Specifically, as shown in fig. 2, if the client PC2 of the other (S, G) also initiates the same artificial intelligence analysis request, and gradually transmits the request to the video source IPC1 through the other gateway router GW2, and after receiving the request by the multicast router R in the middle, the multicast router R finds that the analysis task is registered and is assumed by the GW1, the multicast router R assumes the corresponding artificial intelligence analysis task, and sends the analysis result to the downstream through multicast (S, G), and notifies the gateway router GW1 to stop the analysis.
It will be readily appreciated that if the artificial intelligence analysis task to which the artificial intelligence analysis request corresponds has been undertaken by a multicast router S upstream of multicast router R, multicast router R continues to pass artificial intelligence analysis request messages upstream. Until delivered to the multicast router S, the multicast router S performs an artificial intelligence analysis task and issues artificial intelligence analysis results to the client PC2 and the client PC 1.
In a specific embodiment, the multicast router R may first determine, according to the unicast routing table, whether the router executing the artificial intelligence analysis task belongs to its upstream or downstream, if so, continue to forward the message upstream, and if so, the router R undertakes the analysis task, and sends the analysis result to all downstream clients including the PC2 and the PC1 by multicast (S, G).
The multicast router R simultaneously issues an execution notification message "execute the artificial intelligence analysis task by itself and request the GW1 to stop executing" to the downstream through the multicast message (S, G), notifying the gateway, particularly, the GW1, that the corresponding artificial intelligence analysis task is stopped executing.
In a specific embodiment, the multicast router in the multicast distribution tree undertakes the artificial intelligence analysis task, and further issues a registration message upstream, where a destination IP address of the registration message is a video source, a source IP address of the registration message is a multicast group IP address, and the multicast router in the multicast distribution tree records the multicast router undertaking the artificial intelligence analysis task after receiving the registration message.
For example, after undertaking the corresponding artificial intelligence analysis task, the multicast router R issues a registration message upstream, where the destination IP is the video source S and the source IP is the multicast group G, and transmits information "the artificial intelligence analysis task is instead undertaken by me" to the video source along the path of the video stream (S, G) — where "self", "GW 1" and "me" are all represented by the router ID.
After receiving the execution notification message or the registration message, GW1 stops executing the task, and all other routers record "router R takes on artificial intelligence analysis task".
It should be noted that, if the multicast router R finds that another multicast router (not the gateway router GW 1) in the downstream is registered to undertake the corresponding artificial intelligence analysis task when receiving the artificial intelligence analysis request, the multicast router R undertakes the artificial intelligence analysis task and notifies the multicast router that originally undertakes the artificial intelligence analysis task to stop undertaking the artificial intelligence analysis task, which is not described herein again.
In another embodiment, the present application further provides a distributed artificial intelligence analysis apparatus, comprising a processor and a memory storing computer instructions, which when executed by the processor, implement the steps of the distributed artificial intelligence analysis method.
For specific limitations of the distributed artificial intelligence analysis apparatus, reference may be made to the above limitations of the distributed artificial intelligence analysis method, which will not be described herein again. The distributed artificial intelligence analysis 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 (4)
1. A distributed artificial intelligence analysis method is applied to a video stream multicast network, wherein the video stream multicast network comprises a video source, a DR router, a client and a gateway router corresponding to the client, and the distributed artificial intelligence analysis 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 destination IP addresses of the artificial intelligence analysis requests are IP addresses of the video sources, the source IP addresses are multicast group IP addresses, and the artificial intelligence analysis requests carry gateway router IP addresses or client IP addresses corresponding to the clients;
after receiving the artificial intelligence analysis request, the DR router sends an artificial intelligence analysis task arrangement message, wherein the target IP address of the artificial intelligence analysis task arrangement message is a multicast group IP address, the source IP address is a video source IP address, and the artificial intelligence analysis task arrangement message carries a gateway router IP address or a client IP address corresponding to the client;
after receiving the artificial intelligence analysis task arrangement message, the gateway router corresponding to the client undertakes the corresponding artificial intelligence analysis task;
after receiving the artificial intelligence analysis request, if finding that the corresponding artificial intelligence analysis task is registered as being borne by the gateway router at the downstream of the multicast router, the multicast router in the multicast distribution tree bears the artificial intelligence analysis task and informs the gateway router which originally bears the artificial intelligence analysis task to stop bearing the artificial intelligence analysis task;
after receiving the artificial intelligence analysis request, the multicast router in the multicast distribution tree continues to transmit the artificial intelligence analysis request upstream if finding that the corresponding artificial intelligence analysis task is registered as being borne by the multicast router upstream of the multicast router.
2. The distributed artificial intelligence analysis method of claim 1, further comprising:
when the gateway router corresponding to the client bears the corresponding artificial intelligence analysis task, the gateway router also returns 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 multicast router in the multicast distribution tree records the gateway router bearing the artificial intelligence analysis task after receiving the registration message.
3. The distributed artificial intelligence analysis method of claim 1, further comprising:
and after receiving the registration message, the multicast router in the multicast distribution tree records the multicast router bearing the artificial intelligence analysis task.
4. A distributed artificial intelligence analysis 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 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210218287.XA CN114286127B (en) | 2022-03-08 | 2022-03-08 | Distributed artificial intelligence analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210218287.XA CN114286127B (en) | 2022-03-08 | 2022-03-08 | Distributed artificial intelligence analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114286127A CN114286127A (en) | 2022-04-05 |
| CN114286127B true CN114286127B (en) | 2022-05-27 |
Family
ID=80882275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210218287.XA Active CN114286127B (en) | 2022-03-08 | 2022-03-08 | Distributed artificial intelligence analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114286127B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101222414A (en) * | 2007-01-11 | 2008-07-16 | 华为技术有限公司 | Device, system and method for implementing multicast communication |
| CN101621747A (en) * | 2009-08-12 | 2010-01-06 | 广州海格通信集团股份有限公司 | Reliable multicast transmission method of wireless mesh network |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7698456B2 (en) * | 2003-09-29 | 2010-04-13 | Cisco Technology, Inc. | Methods and apparatus to support routing of information |
| US20070127508A1 (en) * | 2003-10-24 | 2007-06-07 | Terry Bahr | System and method for managing the transmission of video data |
| JP2006180434A (en) * | 2004-12-24 | 2006-07-06 | Matsushita Electric Ind Co Ltd | Distribution route determination method, multicast distribution method, multicast distribution system, distribution terminal, node, and distribution route determination program |
| US20090106807A1 (en) * | 2007-10-19 | 2009-04-23 | Hitachi, Ltd. | Video Distribution System for Switching Video Streams |
| JP2010124232A (en) * | 2008-11-19 | 2010-06-03 | Hitachi Ltd | Conference system and conference method |
| CN101576994B (en) * | 2009-06-22 | 2012-01-25 | 中国农业大学 | Method and device for processing remote sensing image |
| US20140280701A1 (en) * | 2013-03-14 | 2014-09-18 | Comcast Cable Communications, Llc | Distributed computing |
| US9401003B2 (en) * | 2013-11-18 | 2016-07-26 | Zebrafish Labs, Inc. | Just-in-time processing of images |
| US10701321B2 (en) * | 2015-02-27 | 2020-06-30 | Sensormatic Electronics, LLC | System and method for distributed video analysis |
| US10051022B2 (en) * | 2016-03-30 | 2018-08-14 | Juniper Networks, Inc. | Hot root standby support for multicast |
| WO2017201750A1 (en) * | 2016-05-27 | 2017-11-30 | 华为技术有限公司 | Method, device and system for processing multicast data |
| US9729581B1 (en) * | 2016-07-01 | 2017-08-08 | Tempered Networks, Inc. | Horizontal switch scalability via load balancing |
| CN106209688B (en) * | 2016-07-13 | 2019-01-08 | 腾讯科技（深圳）有限公司 | Cloud data multicast methods, devices and systems |
| GB2557949B (en) * | 2016-12-19 | 2021-01-13 | Cisco Tech Inc | Data handling method and apparatus |
| CN109039922A (en) * | 2018-09-18 | 2018-12-18 | 深圳市风云实业有限公司 | Multicast processing method |
| AU2019375082A1 (en) * | 2018-11-08 | 2021-06-03 | Juganu Ltd. | Systems and methods for multicast group routing, firmware updating, and next-hop routing in tree-based wireless networks |
| CN110474841B (en) * | 2019-08-30 | 2021-09-10 | 中国人民财产保险股份有限公司 | Service request routing processing method and terminal equipment |
| CN211429438U (en) * | 2019-09-23 | 2020-09-04 | 中国移动通信集团终端有限公司 | Gateway, application equipment and intelligent system |
| CN111225280B (en) * | 2020-01-22 | 2021-10-01 | 复旦大学 | Lightweight video analysis system based on embedded platform |
| US20210409792A1 (en) * | 2020-06-29 | 2021-12-30 | Seagate Technology Llc | Distributed surveillance system with distributed video analysis |
-
2022
- 2022-03-08 CN CN202210218287.XA patent/CN114286127B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101222414A (en) * | 2007-01-11 | 2008-07-16 | 华为技术有限公司 | Device, system and method for implementing multicast communication |
| CN101621747A (en) * | 2009-08-12 | 2010-01-06 | 广州海格通信集团股份有限公司 | Reliable multicast transmission method of wireless mesh network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114286127A (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102970227B (en) | The method and apparatus of VXLAN message repeating is realized in ASIC | |
| CN100433730C (en) | Method and system of multicast and video-on-demand | |
| CN105897444B (en) | Multicast group management method and device | |
| CN102377640B (en) | Message processing apparatus, message processing method and preprocessor | |
| CN108810444B (en) | Video conference processing method, conference scheduling terminal and protocol conversion server | |
| CN110190973B (en) | Online state detection method and device | |
| CN109617956B (en) | Data processing method and device | |
| JP7375203B2 (en) | Account access methods and devices, storage media, and electronic devices | |
| CN107181681B (en) | SDN two-layer forwarding method and system | |
| CN110022307A (en) | A kind of control method of monitoring device and monitoring access server | |
| CN111698346B (en) | Private network address conversion method and device, private network gateway and storage medium | |
| WO2017185780A1 (en) | Forwarding table entry establishment method and apparatus | |
| CN110932972B (en) | Data transmission method and device and electronic equipment | |
| CN111447393A (en) | Conference maintenance method and device and readable storage medium | |
| CN109451001B (en) | Communication method and system | |
| WO2021254442A1 (en) | Session initiation method, apparatus and system, electronic device, and computer readable storage medium | |
| CN114827677B (en) | Artificial intelligence analysis load balancing method and device | |
| CN108667735B (en) | Method and device for forwarding multicast data | |
| CN114286127B (en) | Distributed artificial intelligence analysis method and device | |
| CN110417792B (en) | Communication method, system, gateway device and storage medium | |
| CN111478882A (en) | Terminal detection method and device | |
| CN102868642A (en) | Method and device for achieving NVGRE message transmission in application specific integrated circuit (ASIC) | |
| CN101309154B (en) | Datagram sending method, sending apparatus and transmission system | |
| CN110719433B (en) | Method and device for displaying online state of terminal, electronic equipment and storage medium | |
| KR101279790B1 (en) | An ip multicast route monitoring system and the method thereof |
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 |