CN115242865A - Switching standard of remote video manual service - Google Patents
Switching standard of remote video manual service Download PDFInfo
- Publication number
- CN115242865A CN115242865A CN202210814978.6A CN202210814978A CN115242865A CN 115242865 A CN115242865 A CN 115242865A CN 202210814978 A CN202210814978 A CN 202210814978A CN 115242865 A CN115242865 A CN 115242865A
- Authority
- CN
- China
- Prior art keywords
- area
- video
- standard
- service
- video service
- 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.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims abstract description 4
- 230000005540 biological transmission Effects 0.000 claims abstract description 3
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 239000012466 permeate Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/22—Parsing or analysis of headers
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a switching standard of remote manual service. Wherein the criteria include: and predicting the type and the calculated amount of the video artificial intelligence service demand in the area A, sending the prediction to the area B, feeding back the prediction by the area B and returning the prediction to the area A, and performing comprehensive evaluation by the area A according to the feedback and the transmission performance indexes to finally determine whether to send the video service demand to the area B for completion. By the method and the device, the bandwidth pressure for processing more video service requirements in the area with less computing power is reduced. The method is suitable for engineering projects with the property of east, west and west calculations, and is also suitable for areas with rich video resources or stronger calculation power.
Description
Technical Field
The invention relates to the technical field of network communication.
Background
In recent years, the scale of users and the scale of markets in the online video industry are rapidly expanded. Mass data and video service requirements are generated, in order to improve the video watching experience of users and meet the service requirements of the users, the artificial intelligence technology gradually permeates into the video industry, and efficiency is improved, value is created, and then the users are precipitated.
However, for different areas with different data distribution and resources, the following problems may exist in the video service requirement and data processing: 1) In areas with large user scale and strong application requirements, the computing power of the system is difficult to bear to process the generated mass data to a great extent, so that the problem of large delay in responding to the user requirements is caused; 2) In areas with abundant computing resources and relatively small data generation amount, the problem of resource idling is caused.
Disclosure of Invention
The embodiment of the invention mainly solves the technical problem of providing a remote service standard which can be applied to two areas with rich video resources and strong calculation resources.
In order to achieve the above object, the remote service standard of the present invention has the following constitution:
s101: firstly, computing power estimation is carried out on the existing video artificial intelligence service requirements of the area A, and the computing power estimation is transmitted to a computing power hub of the area B.
S102: after receiving the request of the area A, the area B firstly determines whether the server has the video artificial intelligence service requirement meeting the requirement of the area A;
s103: if yes, comparing the received computing power estimation with the computing power resource of the user, and transmitting the computing power result capable of being born back to the area A;
s104: if not, the result is directly returned to the area A.
S105: and the area A carries out comprehensive evaluation according to the feedback result of the area B and the technical indexes of bandwidth, time delay, throughput, effectiveness, reliability and recognition rate in the process, and further determines whether to transmit the video service requirement to the area B to finish the process.
Drawings
FIG. 1 is a flow chart of switching criteria for remote video manual service according to the present disclosure
FIG. 2 is a table of budget resource consumption estimation for area A video services according to an embodiment of the present disclosure
FIG. 3 is a table of budget resource consumption estimation for video service in area B according to an embodiment of the present disclosure
FIGS. 4-6 are block diagrams of an overall framework for packet transmission in the eastern and western regions according to an embodiment of the present disclosure
Detailed Description
The first step is as follows: the base station hub in the area A is provided with pre-configured calculation capacity resource consumption prediction tables of different types of video services, wherein the calculation capacity prediction tables not only contain the calculation capacity prediction of each video service at the peak value, but also contain the calculation capacity threshold capable of bearing the video service.
The second step is that: the computational resource data of each video service is collected in real time, and when the used computational resource exceeds the threshold value, a data packet containing the video service requirement and the computational prediction value thereof is sent to the B area.
The following factors are mainly considered for site selection in the area B:
1) Electric power energy level: data centers are very power hungry and the amount of power must be guaranteed to be sufficient and stable. On the one hand, the cost of electricity needs to be compared, and the cost of the power source per kilowatt-hour should be sufficiently low; on the other hand, alternative renewable energy sources are available, such as solar energy, wind energy, air, and the like.
2) Hydrothermal conditions: another important key to data centers is the water cooling facility. Data center facilities require a large amount of water, can meet the cooling requirements during peak periods, and can extinguish fires.
3) Geographic location: the probability and frequency of natural disasters (flood, hurricane, tornado and the like) at the alternative site, and the degree of influence of the data center on the environment of the site; and climate factors, whether the climate of the data center alternate site has free external air cooling-would be an additional, very advantageous resource.
4) Maintenance cost: the data center needs to be maintained regularly, and if the maintenance cost is too high, the construction is still not facilitated.
The third step: after a base station hub in the area B successfully receives a data packet transmitted by the area A, analyzing the data packet, firstly detecting whether a calculation resource consumption estimation table of the video service of the base station hub in the area B contains the video service requirement, and if not, immediately replying to the area A that no corresponding video service exists; if yes, analyzing according to the calculation power resource use condition and the calculation power resource total amount condition of the video service corresponding to the local area to obtain a calculation power bearable result, and returning the calculation power bearable result to the area A.
The fourth step: and after the base station hub in the area A successfully receives the data packet returned by the area B, analyzing the data packet, and if the data packet is analyzed to obtain a calculation result capable of being born by the area B, comprehensively evaluating the data packet by combining the technical indexes of bandwidth, delay, throughput, effectiveness, reliability and identification rate in the process to further determine whether to send the video service requirement to the area B to finish the video service.
The following takes the Long triangular region as an example to illustrate the implementation steps of the standard:
the Long triangular region has a thick development technology, mass data can be generated every day, and the demand for computing power is very large. According to the first step, different types of video service computational power resource consumption prediction tables are pre-configured for a base station hub in the Long triangular region, and the video artificial intelligence services comprise three video artificial intelligence services of face bullet screen shielding, face recognition and video labels, and a computational power value prediction value and a computational power threshold value capable of bearing when the three video artificial intelligence services are at a peak value, wherein the computational power threshold value is smaller than the peak value computational power value.
Comprehensively considering the site selection factors of the area B in the second step, the western area of China is wide in area, rare in people, wide in space, proper in climate, quite rich in natural resources such as wind, light, water, coal and the like, and quite considerable in both power cost and land and manpower cost. The optimal site selection area is the Yunguagawa area, the inner Mongolia, gansu and Ningxia areas are inferior to the Yunguagawa area in terms of water resource conditions, and although the renewable energy level is at the forefront in China in the areas of Tibet, xinjiang and the like, the areas have many adverse conditions such as high altitude, low temperature, strong wind and raised dust and the like from the construction point of view, and the maintenance cost is high. In conclusion, the site of the area B is finally determined to be the area of Yunhuan.
And according to the second step, starting to monitor the computing power resource use condition of each video artificial intelligence service in real time, and once the computing power value consumed in real time exceeds the computing power threshold value, encapsulating a data packet by the base station hub in the Yangtze river region, wherein the data packet comprises the video artificial intelligence service requirement exceeding the computing power threshold value and the computing power estimated value required by the video artificial intelligence service requirement, and then transmitting the data packet to the base station hub in the Yuntai river region, and simultaneously setting a countdown.
If the base station hub in the Long triangular region does not receive any response after the countdown is finished, the data packet is retransmitted until the response is received.
As can be seen from fig. 2, the real-time computation power consumption value C1 of the video AI service of the face bullet screen is greater than the computation power threshold value B1, and therefore, the computation power predicted value of the face bullet screen is packaged into a data packet.
According to the third step, after successfully receiving the data packet from the Yangtze river district, the base station hub in the Yuangui area analyzes the data packet, and inquires and compares the video artificial intelligence service requirement obtained after analysis with the video AI service in the video service computational power resource consumption estimation table configured by the base station hub in the Yuangui area, so that a matched video artificial intelligence service (human face bullet screen shielding) can be obtained from fig. 3. And then, analyzing according to the calculation resources of the Yunchuan region, packaging the calculation resources available for the Yangtze river delta region into a data packet, transmitting the data packet back to the Yangtze river delta region, and setting a countdown.
Similarly, if the cloud nobile area does not receive any response after the countdown is finished, the data packet is retransmitted until the response is received.
According to the fourth step, after the data packet from the Yunobucang region is successfully received in the Yangtze river region, analyzing the data packet, providing resources for the calculation power obtained after analysis, and performing comprehensive evaluation by combining with the technical indexes of bandwidth, delay, throughput, effectiveness, reliability and recognition rate in the process, if the following conditions are met:
computing power resources provided by the Yunhuan region are more than or equal to computing power predicted values of face barrage shielding in data packets sent by the Yangtze river region;
because the human face barrage shields the artificial intelligent service of the video, namely the mask barrage, the requirement on the real-time performance is higher, the real-time processing needs to be carried out on the video image of each frame to achieve the real-time mask barrage, and the requirements on the bandwidth and the time delay are stricter.
The requirement of the face barrage shielding video service is sent to the cloud and noble region to be completed.
The amount of data generated daily in kyojin Ji area is also very large. The Jingjin Ji area is assumed to be located in the Yunhuan region because the site selection of the B area is the same as that of the Yangtze triangle area. As shown in fig. 4, if the long delta area sends the data packet (1) to the yunnan and precious land, after the third step, the yunnan and precious land transmits the analysis result back to the long delta area, and after the fourth step, the long delta area determines that the video service requirement is sent to the yunnan and precious land to be completed.
Meanwhile, the Jingjin Ji area sends a data packet (2) to the Yunhuan area. At this time, the result of whether the cloud precious city and town area will send the video service requirement to the local area to complete is unknown, so in the process of performing the third step, the analysis result does not consider the situation that resources are provided for the long and triangular areas before.
As shown in fig. 5, the yunhuai region transmits the results of the calculation to the kynjin region, and the long triangle region transmits a data packet (3) to the yunhuai region, wherein the data packet includes a determination result that the video service request is transmitted to the yunhuai region to be completed.
As shown in fig. 6, when the data packet (3) is successfully received in the yunchuan and country, the data packet is analyzed, and after an analysis result is obtained, the data packet is broadcasted. After the kyojin Ji area receives the broadcast from the yunpichuan area, the second step and the subsequent steps are repeated no matter whether the result is comprehensively evaluated according to the fourth step or not.
Claims (10)
1. A switching standard of remote manual service is characterized by being applied to two areas with rich video resources and strong calculation resources. The standard is specifically as follows:
the type of service requirements of video artificial intelligence and the estimation and refinement of the calculated amount of the service requirements are available in the area A;
and sends this to area B;
and B, after receiving, feeding back: whether such service needs exist and the amount of computing power that can be tolerated;
and sends this back to area a;
and the area A carries out comprehensive evaluation according to the feedback of the area B and the related technical indexes in the process, and further determines whether the video service requirement is sent to the area B to be finished.
2. The standard of claim 1, wherein the area a corresponds to an area with abundant video resources, the area B corresponds to an area with stronger computational power resources, and a video service computational power resource consumption prediction table is pre-configured for both areas.
3. The standard of claim 2, wherein the video service computational resource consumption prediction tables comprise different kinds of video artificial intelligence services and corresponding peak computational power prediction values, computational power threshold values and real-time computational power consumption values.
4. The standard of claim 1, wherein addressing for area B takes into account several factors, including:
an electrical energy level;
hydrothermal conditions;
a geographic location;
maintenance costs.
5. The standard of claim 1 wherein region a sends a packet to region B, which includes the video service requirements and its budget estimate.
6. A standard according to claims 1 and 5 wherein a countdown is set whilst zone A sends packets to zone B, and when the countdown is over, if zone A has not received any replies, the packets are re-sent to zone B until successful acceptance.
7. The standard of claim 1, wherein after the area B successfully receives the data packet, the result obtained by parsing the data packet is compared with the budget resource consumption prediction table of the video service configured in the local area, and if there is a corresponding video artificial intelligence service, the analysis is performed according to the usage of the budget resource and the total amount of the budget resource of the video service corresponding to the local area, and the available budget resource is encapsulated in the data packet; if no corresponding video artificial intelligence service exists, the result is directly returned to the area A.
8. The standard of claims 1 and 7 wherein the area A is comprehensively evaluated according to the feedback of the area B and the technical indicators of bandwidth, delay, throughput and effectiveness, reliability and recognition rate in the process, and then determines whether to send the video service requirement to the area B for completion.
9. The standard of claim 8 wherein the a site encapsulates the decision whether to send the video service request to the B site for completion into a packet for transmission to the B site.
10. The standard of claim 9 wherein if the parsed decision results in the sending of the video service request to region B for completion, region B broadcasts; otherwise, no other operations are performed in region B.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210814978.6A CN115242865A (en) | 2022-07-11 | 2022-07-11 | Switching standard of remote video manual service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210814978.6A CN115242865A (en) | 2022-07-11 | 2022-07-11 | Switching standard of remote video manual service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115242865A true CN115242865A (en) | 2022-10-25 |
Family
ID=83673876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210814978.6A Pending CN115242865A (en) | 2022-07-11 | 2022-07-11 | Switching standard of remote video manual service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115242865A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112383878A (en) * | 2020-09-27 | 2021-02-19 | 中国信息通信研究院 | Collaborative computing method and electronic device |
| CN113095781A (en) * | 2021-04-12 | 2021-07-09 | 山东大卫国际建筑设计有限公司 | Temperature control equipment control method, equipment and medium based on edge calculation |
| CN113535343A (en) * | 2020-04-15 | 2021-10-22 | 展讯半导体(南京)有限公司 | Computing power sharing method based on network scheduling and related product |
| WO2022027224A1 (en) * | 2020-08-04 | 2022-02-10 | 北京大学深圳研究生院 | In-network computing power or resource service-oriented communication method |
| CN114035945A (en) * | 2021-10-29 | 2022-02-11 | 深圳市晨北科技有限公司 | Computing power resource allocation method, device, equipment and storage medium |
| 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 |
| CN114356587A (en) * | 2022-03-17 | 2022-04-15 | 梯度云科技(北京)有限公司 | Calculation power task cross-region scheduling method, system and equipment |
-
2022
- 2022-07-11 CN CN202210814978.6A patent/CN115242865A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113535343A (en) * | 2020-04-15 | 2021-10-22 | 展讯半导体(南京)有限公司 | Computing power sharing method based on network scheduling and related product |
| WO2022027224A1 (en) * | 2020-08-04 | 2022-02-10 | 北京大学深圳研究生院 | In-network computing power or resource service-oriented communication method |
| CN112383878A (en) * | 2020-09-27 | 2021-02-19 | 中国信息通信研究院 | Collaborative computing method and electronic device |
| CN113095781A (en) * | 2021-04-12 | 2021-07-09 | 山东大卫国际建筑设计有限公司 | Temperature control equipment control method, equipment and medium based on edge calculation |
| CN114035945A (en) * | 2021-10-29 | 2022-02-11 | 深圳市晨北科技有限公司 | Computing power resource allocation method, device, equipment and storage medium |
| 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 |
| CN114356587A (en) * | 2022-03-17 | 2022-04-15 | 梯度云科技(北京)有限公司 | Calculation power task cross-region scheduling method, system and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106059067B (en) | A kind of remote monitoring system of electric power system | |
| CN115864661B (en) | Remote monitoring method for operation data of power equipment | |
| CN107508550A (en) | A kind of photovoltaic apparatus monitoring method and system based on Internet of Things | |
| CN113009212B (en) | System and method for intelligently monitoring state of lightning arrester of power distribution network based on Internet of things | |
| CN210490557U (en) | Transmission line intelligence prison claps device based on wireless private network of electric power | |
| CN114062872A (en) | Method, device and system for monitoring state of electrical equipment and storage medium | |
| CN208386595U (en) | A kind of emergent broadcast platform data interactive system | |
| CN114154733A (en) | Photovoltaic power generation power prediction system | |
| CN115242865A (en) | Switching standard of remote video manual service | |
| CN110838760B (en) | Power grid fault data collection method and device | |
| CN104537571A (en) | GIS-based power dispatching data graphical display method | |
| Audu et al. | Reliability and quality of service of an off-grid wind powered roadside unit in a motorway vehicular environment | |
| Bhattarai et al. | Optimizing the location deployment of dynamic mobile base stations | |
| CN113381508B (en) | Power carrier communication regulation and control system and method combined with switch conversion device | |
| CN115314919A (en) | Continuous and reliable transmission method for online data of power internet of things | |
| CN214154556U (en) | Electric power private network system based on 5G network | |
| CN108632290B (en) | Real-time data forwarding system and method for power dispatching automation system | |
| CN209419634U (en) | A kind of emergency broadcase system based on terrestrial DTV and mobile communication | |
| CN203950345U (en) | A kind of intelligent grid unified information shoring of foundation system | |
| CN102843700B (en) | The discharge model of a kind of LTE230M electric power radio communication and implementation method | |
| CN202178783U (en) | Pollution data detection system based on cloud computing | |
| CN203894624U (en) | Low-voltage intelligent controller | |
| CN219536115U (en) | Production big data centralized control system for hydroelectric power station and new energy power station | |
| CN113891293B (en) | Robust data processing method for Internet of things | |
| CN215895460U (en) | New generation central station system with hierarchical management |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20221025 |