CN109067840A - Method, system and the storage medium of artificial intelligence online service - Google Patents
Method, system and the storage medium of artificial intelligence online service Download PDFInfo
- Publication number
- CN109067840A CN109067840A CN201810717051.4A CN201810717051A CN109067840A CN 109067840 A CN109067840 A CN 109067840A CN 201810717051 A CN201810717051 A CN 201810717051A CN 109067840 A CN109067840 A CN 109067840A
- Authority
- CN
- China
- Prior art keywords
- mirror image
- user
- artificial intelligence
- unit
- cloud platform
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
Abstract
The present invention provides method, system and the storage medium of a kind of artificial intelligence online service, this method comprises: obtaining step, base containers mirror image is obtained from user or cloud platform, and personal code work is obtained from user, the code server that the network request of supplier's offer of personal code work and cloud platform receives server matches；Base containers mirror image, personal code work or base containers mirror image, personal code work and code server are combined into user's mirror image by combination step；User's mirror image and the online solicited message of artificial intelligence are sent to cloud platform by sending step；Allocation step limits multiple computing units in the resource pool in cloud platform to be used, and user's mirror image is respectively allocated to multiple computing units according to the online solicited message of artificial intelligence；Management process is managed the multiple computing units for being assigned user's mirror image, to realize artificial intelligence online service.
Description
Technical field
The present invention relates to the method for artificial intelligence online service, system and storage mediums.
Background technique
Artificial intelligence (AI) technology has progressed into the people's lives visual field.In order to construct artificial intelligence service, usually
Including three steps: big data is collected and processing, the training of AI algorithm model, AI algorithm online service.Wherein data collection with
Processing is processed for design and training in AI algorithm by data to structuring and non-structured data.AI is calculated
Method model training is then the AI algorithm of design feature, and is trained by mass data to algorithm model, obtains having certain
The algorithm model (such as recognition of face, speech recognition) of function.AI algorithm online service is then to carry out AI algorithm model online
Change service arrangement, can be run as a kind of service (such as recognition of face service, speech-recognition services).
Usual AI algorithm model includes two parts: the code that 1. online services execute；2. trained AI algorithm model.
It include: TensorFlow, Caffe, MXNet currently used for training and using the common frame of AI algorithm model,
Torch etc..
Manufacturer Google provides collection data processing, algorithms selection, an online service based on Tensorflow frame
In the one-stop machine learning algorithm and deep learning algorithm service platform of one.
(https://cloud.google.com/ml-engine/)
The machine learning PAI platform that manufacturer's Ali's cloud proposes provides a kind of collection data processing, algorithms selection, takes online
It is engaged in the one-stop machine learning algorithm service platform of one.
(https: //data.aliyun.com/product/learn? spm=a2c0j.103967.416540.116.0
hQEYB))
Tencent of manufacturer cloud proposes DI-X deep learning platform, provides a kind of collection data processing, algorithms selection, online clothes
It is engaged in the one-stop deep learning algorithm service platform of one
(https://www.qcloud.com/product/dix#scenarios)
Manufacturer's ability cloud propose it is a kind of based on Kubernetes+Tensorflow framework, collect AI training, online service in
The one-stop deep learning algorithm service platform of one.(https://caicloud.io/products/taas)
However, the deep learning platform that Google, Cai Yundeng company propose is only for a kind of deep learning of TensorFlow
Frame does not have versatility (can not be compatible with all kinds of AI deep learning frames).
The deep learning or machine learning platform that above-mentioned all companies are proposed are directed to a whole set of from data processing, calculate
Method selection, to algorithm training to the one-stop service of final online service, in whole process all data all in Internal Transfer,
The training of algorithm and onlineization are completed together, therefore AI algorithm not is implemented separately and changes online.
And AI algorithm is implemented separately and changes the diversity for being faced with AI algorithmic code, the multiplicity of code and model pattern online
The problems such as property, the diversity of AI frame and related versions used in AI algorithm, above-mentioned existing system can not solve such
Problem.After above system does not support user that AI algorithm is trained and is optimized in local yet simultaneously, carried out in cloud platform online
The scene of service arrangement, therefore there is very strong limitation.
Summary of the invention
In view of the above problems, the present invention provides a kind of method of artificial intelligence online service, this method comprises:
Obtaining step obtains base containers mirror image from user or cloud platform, and obtains personal code work from the user, described
The code server that the network request that the supplier of personal code work and the cloud platform provides receives server matches；
Combination step, by the base containers mirror image, the personal code work or the base containers mirror image, user's generation
Code and the code server are combined into user's mirror image；
User's mirror image and the online solicited message of artificial intelligence are sent to the cloud platform by sending step；
Allocation step limits the resource in the cloud platform to be used according to the online solicited message of the artificial intelligence
Multiple computing units in pond, and user's mirror image is respectively allocated to the multiple computing unit；
Management process is managed the multiple computing unit for being assigned user's mirror image, to realize artificial intelligence
It can online service.
The personal code work meets the network request input and output specification that the supplier of the cloud platform provides, thus
Match with the code server.
In the combination step,
When from the user obtain the base containers mirror image when, by the base containers mirror image, the personal code work with
And the code server is combined into user's mirror image；
When obtaining the base containers mirror image from the cloud platform, the base containers mirror image includes the server generation
Code, and the personal code work and the base containers mirror image comprising the code server are combined into user's mirror
Picture.
The allocation step further comprises: when the portfolio to the cloud platform increases, further increasing and limits institute
Extra computation unit to be used in resource pool is stated, and user's mirror image is distributed into the extra computation unit；
The management process further comprises: carrying out pipe to the extra computation unit for being assigned user's mirror image
Reason.
The allocation step further comprises: single from the multiple calculating when the portfolio to the cloud platform is reduced
Member reduces a part of computing unit used；
The management process further comprises: being managed to the remaining computing unit of the multiple computing unit.
The allocation step further comprises: when any one computing unit in the multiple computing unit breaks down
When, increase and limit supplement calculation unit to be used in the resource pool, and user's mirror image is distributed into the supplement and is counted
Calculate unit；
The management process further comprises: to computing unit without failure in the multiple computing unit and institute
Supplement calculation unit is stated to be managed.
The present invention also provides a kind of system of artificial intelligence online service, which includes artificial intelligence online service building
Device and cloud platform, wherein
The artificial intelligence online service construction device includes:
Acquiring unit obtains base containers mirror image from the mirror image memory cell in user or the cloud platform, and from described
User obtains personal code work, and the network request of supplier's offer of the personal code work and the cloud platform receives the clothes of server
Business device code matches；
Assembled unit, by the base containers mirror image, the personal code work or the base containers mirror image, user's generation
Code and the code server are combined into user's mirror image；
Transmission unit sends user's mirror image and the online solicited message of artificial intelligence in the cloud platform；
The cloud platform includes the mirror image memory cell, resource pool, allocation unit and the pipe for storing user's mirror image
Unit is managed, wherein
The allocation unit limits more in the resource pool to be used according to the online solicited message of the artificial intelligence
A computing unit, and user's mirror image is respectively allocated to the multiple computing unit；
The administrative unit is managed the multiple computing unit for being assigned user's mirror image, artificial to realize
Intelligent online service.
The present invention further provides a kind of non-volatile memory mediums, store someone on the non-volatile memory medium
The program of work intelligent online service, described program are computer-executed to implement the method for artificial intelligence online service, the program
Include:
Acquisition instruction obtains base containers mirror image from user or cloud platform, and obtains personal code work from the user, described
The code server that the network request that the supplier of personal code work and the cloud platform provides receives server matches；
Combined command, by the base containers mirror image, the personal code work or the base containers mirror image, user's generation
Code and the code server are combined into user's mirror image；
Instruction is sent, user's mirror image and the online solicited message of artificial intelligence are sent to the cloud platform；
Distribution instruction limits the resource in the cloud platform to be used according to the online solicited message of the artificial intelligence
Multiple computing units in pond, and user's mirror image is respectively allocated to the multiple computing unit；
Management instruction, is managed the multiple computing unit for being assigned user's mirror image, to realize artificial intelligence
It can online service.
In the present invention, since the code server that the supplier of personal code work and cloud platform 2 provides matches, and the service
Device code constructs on above-mentioned base containers mirror image, no matter so base containers mirror image (AI algorithmic code, AI model)
It is what type, what version, personal code work can be combined by unified code server with base containers mirror image, at
For the user's mirror image that can provide onlineization service.Moreover, system of the invention can support user locally passing through artificial intelligence
After online service construction device 1 is trained and optimizes to base containers mirror image (AI algorithmic code, AI model), cloud platform into
Row online service deployment, therefore there is very strong flexibility.
In addition, in the present invention, due in cloud platform allocation unit and administrative unit can be according to the specific need of cloud platform
It asks to increase, reduce or replace the computing resource used (computing unit in resource pool), so system of the invention can be with
Easily artificial intelligence online service is managed.
Detailed description of the invention
Fig. 1 is the structure chart of the system of artificial intelligence online service according to an embodiment of the present invention；
Fig. 2 is the flow chart of the method for artificial intelligence online service according to an embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawing, the embodiment of the present invention is described in detail.
Fig. 1 is the structure chart of the system 3 of artificial intelligence online service according to an embodiment of the present invention, and Fig. 2 is according to this hair
The flow chart of the method for the artificial intelligence online service of bright embodiment.
As shown in Figure 1, the system 3 includes online service construction device 1 and cloud platform 2, wherein artificial intelligence online service
Construction device 1 includes acquiring unit 11, assembled unit 12, transmission unit 13, and cloud platform 2 includes mirror image memory cell 21, resource
Pond 23, allocation unit 22 and administrative unit 25.
The embodiment of the present invention is described in detail below with reference to Fig. 1 and Fig. 2.In obtaining step S21, acquiring unit 11
Base containers mirror image is obtained from the mirror image memory cell 21 in user or cloud platform 2, and obtains personal code work, the user from user
The code server that the network request that the supplier of code and cloud platform 2 provides receives server matches.
Base containers mirror image is AI algorithmic code and AI model, such as to can be tensorflow, caffe, mxnet etc. each
Any version of class AI frame.
Wherein, personal code work is that the network request input and output specification provided according to the supplier of cloud platform 2 is encoded,
Therefore the personal code work meets the network request input and output specification, thus the above-mentioned code server phase provided with supplier
Match.
Next, in combination step S22, assembled unit 12 is by base containers mirror image, personal code work or base containers mirror
Picture, personal code work and code server are combined into user's mirror image.
Here, when acquiring unit 11 from user obtain base containers mirror image when, assembled unit 12 by base containers mirror image, use
Family code and code server are combined into user's mirror image.When acquiring unit 11 is obtained from the mirror image memory cell 21 of cloud platform 2
When base containers mirror image, which has contained above-mentioned code server, and therefore, assembled unit 12 is by user's generation
Code and the base containers mirror image comprising the code server are combined into user's mirror image.As described above, no matter acquiring unit 11 is
Base containers mirror image still is obtained from the mirror image memory cell 21 of cloud platform 2 from user, the final combination of assembled unit 12 obtains
User's mirror image all includes personal code work, code server and base containers mirror image.
In sending step S23, user's mirror image and the online solicited message of artificial intelligence are sent cloud by 13 as transmission
In platform 2.Wherein, which is saved in the mirror image memory cell 21 in cloud platform 2, and artificial intelligence is requested online
Information is sent to allocation unit 22.
In allocation step S24, allocation unit 22 limits to be used according to the online solicited message of the artificial intelligence received
Multiple computing units in resource pool 23, and the user's mirror image stored in mirror image memory cell 21 is respectively allocated to multiple calculating
Unit.
For example, allocation unit 22 defines 2 computing units 24a, 24b in resource pool 23, and user's mirror image is distinguished
Distribute to computing unit 24a, 24b.Here, allocation unit 22 limits in resource pool 23 according to the online solicited message of artificial intelligence
Computing unit 24a, 24b are determined as computing resource, and by user's mirror image distribution (deployment) into these computing resources.
Then, in management process S25, administrative unit 25 carries out pipe to the multiple computing units for being assigned user's mirror image
Reason, to realize artificial intelligence online service.For example, administrative unit 25 to be assigned computing unit 24a, 24b of user's mirror image into
Row management, to realize artificial intelligence online service.
In addition, need to further increase computing unit (computing resource) when the portfolio to cloud platform 2 increases, then
Allocation unit 22, which will further increase, limits extra computation unit to be used in resource pool 23, such as computing unit 24c, and
User's mirror image is distributed into computing unit 24c.At this point, administrative unit 25 will be to the computing unit 24c for being assigned user's mirror image
Also it is managed.That is, administrative unit 25 is simultaneously managed computing unit 24a, 24b, 24c for being assigned user's mirror image.
And when the portfolio to cloud platform 2 is reduced, then computing resource that should not be so much, then allocation unit 22 is from meter
It calculates in unit 24a, 24b and reduces a part of computing unit used, such as reduce computing unit 24b, and only retain and calculate 24a
Still used.At this point, administrative unit 25 is to being just managed remaining computing unit in multiple computing units, that is, management is single
25 management computing unit 24a of member.
On the other hand, when any one computing unit in multiple computing unit 24a, 24b breaks down, for example, calculating
When unit 24a breaks down, allocation unit 22, which just will increase, limits supplement calculation unit to be used in resource pool 23, such as counts
Unit 24c is calculated, and user's mirror image is distributed into computing unit 24c.At this point, administrative unit 25 in multiple computing units to not occurring
The computing unit (for example, computing unit 24b) and supplement calculation unit 24c of failure are managed.
Wherein, resource pool 23 provides the computing unit of magnanimity, and computing unit 24a, 24b, 24c in Fig. 1 are only intended to show
Example, and not limit.
In the present invention, artificial intelligence online service construction device 1 for example can be by being mounted on the user's computer
It realizes, cloud platform 2 can for example realize by Cloud Server.
In the present invention, since the code server that the supplier of personal code work and cloud platform 2 provides matches, and the service
Device code constructs on above-mentioned base containers mirror image, no matter so base containers mirror image (AI algorithmic code, AI model)
It is what type, what version, personal code work can be combined by unified code server with base containers mirror image, at
For the user's mirror image that can provide onlineization service.Moreover, system of the invention can support user locally passing through artificial intelligence
After online service construction device 1 is trained and optimizes to base containers mirror image (AI algorithmic code, AI model), cloud platform into
Row online service deployment, therefore there is very strong flexibility.
In addition, in the present invention, due in cloud platform allocation unit and administrative unit can be according to the specific need of cloud platform
It asks to increase, reduce or replace the computing resource used (computing unit in resource pool), so system of the invention can be with
Easily artificial intelligence online service is managed.
The present invention also provides a kind of non-volatile memory mediums, and artificial intelligence is stored on the non-volatile memory medium
The program of energy online service, described program are computer-executed to implement the method for artificial intelligence online service, which includes:
Acquisition instruction obtains base containers mirror image from user or cloud platform, and obtains personal code work from the user, described
The code server that the network request that the supplier of personal code work and the cloud platform provides receives server matches；
Combined command, by the base containers mirror image, the personal code work or the base containers mirror image, user's generation
Code and the code server are combined into user's mirror image；
Instruction is sent, user's mirror image and the online solicited message of artificial intelligence are sent to the cloud platform；
Distribution instruction limits the resource in the cloud platform to be used according to the online solicited message of the artificial intelligence
Multiple computing units in pond, and user's mirror image is respectively allocated to the multiple computing unit；
Management instruction, is managed the multiple computing unit for being assigned user's mirror image, to realize artificial intelligence
It can online service.
Although by being described in conjunction with specific embodiments to the present invention, for the ordinary artisan of this field,
It will be apparent according to many substitutions, modification and the variation made after mentioned above.Therefore, when such substitution, modification
When being fallen into variation within the spirit and scope of appended claims, it should be included in the present invention.
Claims (13)
1. a kind of method of artificial intelligence online service, which is characterized in that the described method includes:
Obtaining step obtains base containers mirror image from user or cloud platform, and obtains personal code work, the user from the user
The code server that the network request that the supplier of code and the cloud platform provides receives server matches；
Combination step, by the base containers mirror image, the personal code work or the base containers mirror image, the personal code work with
And the code server is combined into user's mirror image；
User's mirror image and the online solicited message of artificial intelligence are sent to the cloud platform by sending step；
Allocation step limits in the resource pool in the cloud platform to be used according to the online solicited message of the artificial intelligence
Multiple computing units, and user's mirror image is respectively allocated to the multiple computing unit；
Management process is managed the multiple computing unit for being assigned user's mirror image, to realize that artificial intelligence exists
Line service.
2. the method for artificial intelligence online service as described in claim 1, which is characterized in that the personal code work meets described
The network request input and output specification that the supplier of cloud platform provides, to match with the code server.
3. the method for artificial intelligence online service as described in claim 1, which is characterized in that in the combination step,
When obtaining the base containers mirror image from the user, by the base containers mirror image, the personal code work and institute
It states code server and is combined into user's mirror image；
When obtaining the base containers mirror image from the cloud platform, the base containers mirror image includes the code server,
And the personal code work and the base containers mirror image comprising the code server are combined into user's mirror image.
4. the method for artificial intelligence online service as claimed in any one of claims 1-3, which is characterized in that the distribution step
Suddenly further comprise: when the portfolio increase to the cloud platform, further increasing to be used in the restriction resource pool
Extra computation unit, and user's mirror image is distributed into the extra computation unit；
The management process further comprises: being managed to the extra computation unit for being assigned user's mirror image.
5. the method for artificial intelligence online service as claimed in any one of claims 1-3, which is characterized in that the distribution step
Suddenly further comprise: when the portfolio to the cloud platform is reduced, a part used is reduced from the multiple computing unit
Computing unit；
The management process further comprises: being managed to the remaining computing unit of the multiple computing unit.
6. the method for artificial intelligence online service as claimed in any one of claims 1-3, which is characterized in that the distribution step
Suddenly further comprise: when any one computing unit in the multiple computing unit breaks down, increasing and limit the resource
Supplement calculation unit to be used in pond, and user's mirror image is distributed into the supplement calculation unit；
The management process further comprises: to without failure computing unit and the benefit in the multiple computing unit
Computing unit is filled to be managed.
7. a kind of system of artificial intelligence online service, which is characterized in that the system comprises artificial intelligence online service buildings
Device and cloud platform, wherein
The artificial intelligence online service construction device includes:
Acquiring unit obtains base containers mirror image from the mirror image memory cell in user or the cloud platform, and from the user
Personal code work is obtained, the network request of supplier's offer of the personal code work and the cloud platform receives the server of server
Code matches；
Assembled unit, by the base containers mirror image, the personal code work or the base containers mirror image, the personal code work with
And the code server is combined into user's mirror image；
Transmission unit sends user's mirror image and the online solicited message of artificial intelligence in the cloud platform；
The cloud platform includes that the mirror image memory cell for storing user's mirror image, resource pool, allocation unit and management are single
Member, wherein
The allocation unit limits multiple meters in the resource pool to be used according to the online solicited message of the artificial intelligence
Unit is calculated, and user's mirror image is respectively allocated to the multiple computing unit；
The administrative unit is managed the multiple computing unit for being assigned user's mirror image, to realize artificial intelligence
Online service.
8. the system of artificial intelligence online service as claimed in claim 7, which is characterized in that the personal code work meets described
The network request input and output specification that the supplier of cloud platform provides, to match with the code server.
9. the system of artificial intelligence online service as claimed in claim 7, which is characterized in that in the assembled unit,
When obtaining the base containers mirror image from the user, by the base containers mirror image, the personal code work and institute
It states code server and is combined into user's mirror image；
When obtaining the base containers mirror image from the cloud platform, the base containers mirror image includes the code server,
And the personal code work and the base containers mirror image comprising the code server are combined into user's mirror image.
10. the system of artificial intelligence online service as claimed in any one of claims 7-9, which is characterized in that when to described
When the portfolio of cloud platform increases, the allocation unit, which further increases, limits extra computation list to be used in the resource pool
Member, and user's mirror image is distributed into the extra computation unit；
The administrative unit is managed the extra computation unit for being assigned user's mirror image.
11. the system of artificial intelligence online service as claimed in any one of claims 7-9, which is characterized in that when to described
When the portfolio of cloud platform is reduced, the allocation unit reduces a part of computing unit used from the multiple computing unit；
The administrative unit is managed the remaining computing unit of the multiple computing unit.
12. the system of artificial intelligence online service as claimed in any one of claims 7-9, which is characterized in that when described more
When any one computing unit in a computing unit breaks down, the allocation unit increases to limit will use in the resource pool
Supplement calculation unit, and the user is distributed into the supplement calculation unit；
The administrative unit is to computing unit and the supplement calculation unit without failure in the multiple computing unit
It is managed.
13. a kind of non-volatile memory medium is stored with artificial intelligence online service on the non-volatile memory medium
Program, described program are computer-executed to implement the method for artificial intelligence online service, which is characterized in that described program packet
It includes:
Acquisition instruction obtains base containers mirror image from user or cloud platform, and obtains personal code work, the user from the user
The code server that the network request that the supplier of code and the cloud platform provides receives server matches；
Combined command, by the base containers mirror image, the personal code work or the base containers mirror image, the personal code work with
And the code server is combined into user's mirror image；
Instruction is sent, user's mirror image and the online solicited message of artificial intelligence are sent to the cloud platform；
Distribution instruction limits in the resource pool in the cloud platform to be used according to the online solicited message of the artificial intelligence
Multiple computing units, and user's mirror image is respectively allocated to the multiple computing unit；
Management instruction, is managed the multiple computing unit for being assigned user's mirror image, to realize that artificial intelligence exists
Line service.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810717051.4A CN109067840A (en) | 2018-06-29 | 2018-06-29 | Method, system and the storage medium of artificial intelligence online service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810717051.4A CN109067840A (en) | 2018-06-29 | 2018-06-29 | Method, system and the storage medium of artificial intelligence online service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109067840A true CN109067840A (en) | 2018-12-21 |
Family
ID=64819054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810717051.4A Pending CN109067840A (en) | 2018-06-29 | 2018-06-29 | Method, system and the storage medium of artificial intelligence online service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109067840A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148494A (en) * | 2020-09-30 | 2020-12-29 | 北京百度网讯科技有限公司 | Processing method and device for operator service, intelligent workstation and electronic equipment |
| CN113472830A (en) * | 2020-03-31 | 2021-10-01 | 华为技术有限公司 | Communication method and device |
| US11768801B2 (en) | 2021-11-03 | 2023-09-26 | International Business Machines Corporation | Dynamic identification of cloud storage destination for multi-user files |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160274928A1 (en) * | 2015-03-20 | 2016-09-22 | International Business Machines Corporation | Virtual machine migration between hypervisor virtual machines and containers |
| CN106886455A (en) * | 2017-02-23 | 2017-06-23 | 北京图森未来科技有限公司 | A kind of method and system for realizing user isolation |
| CN107111519A (en) * | 2014-11-11 | 2017-08-29 | 亚马逊技术股份有限公司 | For managing the system with scheduling container |
| CN107220100A (en) * | 2016-03-22 | 2017-09-29 | 中国移动（深圳）有限公司 | One kind exploitation O＆M method, device and cloud computing PaaS platform |
| CN108076082A (en) * | 2016-11-09 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of expansion method of application cluster, device and system |
-
2018
- 2018-06-29 CN CN201810717051.4A patent/CN109067840A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107111519A (en) * | 2014-11-11 | 2017-08-29 | 亚马逊技术股份有限公司 | For managing the system with scheduling container |
| US20160274928A1 (en) * | 2015-03-20 | 2016-09-22 | International Business Machines Corporation | Virtual machine migration between hypervisor virtual machines and containers |
| CN107220100A (en) * | 2016-03-22 | 2017-09-29 | 中国移动（深圳）有限公司 | One kind exploitation O＆M method, device and cloud computing PaaS platform |
| CN108076082A (en) * | 2016-11-09 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of expansion method of application cluster, device and system |
| CN106886455A (en) * | 2017-02-23 | 2017-06-23 | 北京图森未来科技有限公司 | A kind of method and system for realizing user isolation |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113472830A (en) * | 2020-03-31 | 2021-10-01 | 华为技术有限公司 | Communication method and device |
| WO2021197144A1 (en) * | 2020-03-31 | 2021-10-07 | 华为技术有限公司 | Communication method and apparatus |
| CN113472830B (en) * | 2020-03-31 | 2023-03-10 | 华为技术有限公司 | Communication method and device |
| CN112148494A (en) * | 2020-09-30 | 2020-12-29 | 北京百度网讯科技有限公司 | Processing method and device for operator service, intelligent workstation and electronic equipment |
| CN112148494B (en) * | 2020-09-30 | 2023-07-25 | 北京百度网讯科技有限公司 | Processing method and device for operator service, intelligent workstation and electronic equipment |
| US11768801B2 (en) | 2021-11-03 | 2023-09-26 | International Business Machines Corporation | Dynamic identification of cloud storage destination for multi-user files |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10679169B2 (en) | Cross-domain multi-attribute hashed and weighted dynamic process prioritization | |
| CN104115165A (en) | Method for mapping media components employing machine learning | |
| US20150235282A1 (en) | Method and system to share, interconnect and execute components and compute rewards to contributors for the collaborative solution of computational problems. | |
| CN108763389B (en) | Data integration method and device, storage medium and terminal | |
| CN113037877B (en) | Optimization method for time-space data and resource scheduling under cloud edge architecture | |
| CN109067840A (en) | Method, system and the storage medium of artificial intelligence online service | |
| CN105446817B (en) | A kind of federated resource configuration of reservations algorithm based on robust optimization in mobile cloud computing | |
| CN113615137B (en) | CDN optimization platform | |
| CN103473320A (en) | Method for service combination facing cloud-spanning platform | |
| CN111126621A (en) | Online model training method and device | |
| CN104199820A (en) | Cloud platform MapReduce workflow scheduling optimizing method | |
| Qian et al. | A workflow-aided Internet of things paradigm with intelligent edge computing | |
| CN109034254B (en) | Method, system and storage medium for customizing artificial intelligence online service | |
| CN106845746A (en) | A kind of cloud Workflow Management System for supporting extensive example intensive applications | |
| US20170060985A1 (en) | System and method for matching resource capacity with resource needs | |
| Kumar et al. | Ai-Assisted Resource Allocation for improved business efficiency and profitability | |
| CN114036159A (en) | Bank business information updating method and system | |
| CN104735134B (en) | A kind of method and apparatus serviced for providing calculating | |
| Ikken et al. | Cost-efficient big intermediate data placement in a collaborative cloud storage environment | |
| Giacobbe et al. | The internet of things in oil and gas industry: a multi criteria decision making brokerage strategy | |
| CN106027344A (en) | Home service system based on big data | |
| CN111915102A (en) | Load prediction-based work platform workload prediction method and system | |
| CN110598931A (en) | Node electricity price prediction method and device based on graph convolution | |
| Ruby et al. | RenderSelect: a cloud broker framework for cloud renderfarm services | |
| Jiang et al. | Cost risk analysis for instance recommendation in a sustainable Cloud‐cyber‐physical system framework |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |