CN109246231B - Intelligent routing method and intelligent routing equipment - Google Patents
Intelligent routing method and intelligent routing equipment Download PDFInfo
- Publication number
- CN109246231B CN109246231B CN201811145875.5A CN201811145875A CN109246231B CN 109246231 B CN109246231 B CN 109246231B CN 201811145875 A CN201811145875 A CN 201811145875A CN 109246231 B CN109246231 B CN 109246231B
- Authority
- CN
- China
- Prior art keywords
- service
- service provider
- evaluation
- evaluation item
- evaluation items
- 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
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
- H04L67/60—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
- H04L67/63—Routing a service request depending on the request content or context
-
- 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
- H04L67/61—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 taking into account QoS or priority requirements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application relates to an intelligent routing method, which comprises the steps of determining evaluation items corresponding to received service requests, obtaining numerical values of the evaluation items corresponding to all service providers of available services, calculating the numerical values of the evaluation items corresponding to all the service providers, obtaining the service quality of all the service providers, selecting the service provider with the best service quality as a target service provider, and routing the service requests to the target service provider.
Description
Technical Field
The present application relates to the field of communications, and in particular, to an intelligent routing method and an intelligent routing device.
Background
At present, most software function services are completely transparent and invisible to clients calling services on the internet or a local area network, a server really performing processing operation is determined according to the running condition of each real server, and the processed server returns to the client.
How to send a task request of a client to a service provider faster in a service calling process of the client and how to find a service provider with better service quality to provide service for the client is a technical problem to be solved by technical personnel in the field.
Disclosure of Invention
In order to overcome the problems in the related art at least to a certain extent, the present application provides an intelligent routing method and an intelligent routing device.
The scheme of the application is as follows:
according to a first aspect of embodiments of the present application, there is provided an intelligent routing method, including:
receiving a service request;
determining the evaluation items corresponding to the service requests, and acquiring the numerical values of the evaluation items corresponding to the service providers of all available services;
calculating the numerical value of the evaluation item corresponding to each service provider by adopting a preset evaluation model to obtain the service quality of each service provider;
determining a target service provider in each service provider according to the service quality;
routing the service request to the target service provider.
Preferably, with reference to the above, in a possible implementation manner of the present application, the determining an evaluation item corresponding to the service request includes:
and determining an evaluation item corresponding to the service request according to the corresponding relation between preset service classification information and the evaluation item.
Preferably, in combination with the above, in one possible implementation manner of the present application, the service classification information includes an object identification class, and the evaluation item includes: calculating time, identification accuracy and classification confidence.
Preferably, with reference to the above, in a possible implementation manner of the present application, the acquiring the numerical values of the evaluation items corresponding to the service providers of all available services includes:
and acquiring the numerical values of the evaluation items corresponding to the service providers of all the available services in a local routing table, wherein the numerical values of the evaluation items corresponding to each service provider are recorded in the local routing table.
Preferably, in combination with the above, in one possible implementation manner of the present application, the method further includes:
and updating the numerical value of each evaluation item periodically, and updating the updated information into the local routing table.
Preferably, in combination with the above, in one possible implementation of the present application,
the evaluation item comprises calculation time and transmission time;
the evaluation model is a summation operation;
correspondingly, the service quality is the sum of the calculation time and the transmission time;
the determining a target service provider in the service providers according to the service quality includes:
and determining the service provider with the minimum sum of the calculation time and the transmission time as a target service provider.
Preferably, in combination with the above, in one possible implementation manner of the present application, the evaluation model is a reinforcement learning model.
Preferably, with reference to the above, in a possible implementation manner of the present application, the reinforcement learning model includes a weight value of each evaluation item, and the calculating, by using a preset evaluation model, a numerical value of the evaluation item corresponding to each service provider to obtain the service quality of each service provider includes:
and performing weighted operation on the numerical value of each evaluation item according to the weight value to obtain the service quality of each service provider.
Preferably, in combination with the above, in one possible implementation of the present application, the service provider is located in one or more of the following:
the system comprises a terminal local, a local area network server and a cloud server.
According to a second aspect of the embodiments of the present application, there is provided an intelligent routing device, including:
a memory 31 for storing a computer program;
a processor 32 connected to the memory for executing the computer program stored in the memory to perform the method as described in any one of the above.
The technical scheme provided by the application can comprise the following beneficial effects: in the intelligent routing method provided by the application, the evaluation items corresponding to the received service request are determined, the numerical values of the evaluation items corresponding to all the service providers with available services are obtained, the numerical values of the evaluation items corresponding to all the service providers are calculated, the service quality of all the service providers is obtained, the service provider with the best service quality is selected as the target service provider, and the service request is routed to the target service provider.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a flowchart of an intelligent routing method according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for intelligent routing according to another embodiment of the present application;
fig. 3 is a block diagram of an intelligent routing device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of an intelligent routing method and intelligent routing device consistent with certain aspects of the present application, as detailed in the appended claims.
Fig. 1 is a flowchart of an intelligent routing method according to an embodiment of the present application, and referring to fig. 1, the intelligent routing method includes:
s101: receiving a service request;
the service request is a service request sent by a client.
S102: determining evaluation items corresponding to the service requests, and acquiring numerical values of the evaluation items corresponding to service providers of all available services;
the service provider is used for solving the service requests, the service requests are multiple in number, the service provider corresponding to each service request is multiple in number, each service request is provided with a corresponding evaluation item, the service provider solving the service requests is evaluated according to the evaluation items, and the evaluation values are scalar quantities, namely numerical values of the evaluation items corresponding to the service providers.
S103: calculating the numerical values of the evaluation items corresponding to the service providers by adopting a preset evaluation model to obtain the service quality of each service provider;
s104: determining a target service provider in each service provider according to the service quality;
s105: the service request is routed to the target service provider.
In the intelligent routing method provided by the application, the evaluation items corresponding to the received service request are determined, the numerical values of the evaluation items corresponding to all the service providers with available services are obtained, the numerical values of the evaluation items corresponding to all the service providers are calculated, the service quality of all the service providers is obtained, the service provider with the best service quality is selected as the target service provider, and the service request is routed to the target service provider.
In the intelligent routing method in some embodiments, the service request includes service classification information;
s102: determining an evaluation item corresponding to the service request, including:
and determining the evaluation item corresponding to the service request according to the corresponding relation between the preset service classification information and the evaluation item.
In one possible implementation manner of the present application, the service classification information includes an object identification class, and the evaluation item includes: calculating time, identification accuracy and classification confidence.
The service classification information may also include other classifications, such as: face recognition, etc.
In this embodiment, the service classification information includes: object recognition class is an example. When the service classification information contained in the service request is an object identification class, the corresponding evaluation items comprise: calculating time, recognition accuracy and classification confidence, distributing a weight to each evaluation score after a plurality of evaluation items exist, and calculating the evaluation value of the service provider according to the weight corresponding to each evaluation item.
S102: acquiring the numerical values of the evaluation items corresponding to the service providers of all available services, wherein the numerical values comprise:
and acquiring the numerical values of the evaluation items corresponding to the service providers of all the available services in a local routing table, wherein the numerical values of the evaluation items corresponding to the service providers are recorded in the local routing table.
A routing table refers to a table of routing information stored on a router or other internet network device that stores paths to a particular network terminal and, in some cases, metrics associated with those paths. The local routing table is a collection table of all network segments connected with the local routing table by using a protocol, and indicates the transmission direction of local data and data passing through a computer. And after determining the evaluation items corresponding to the service requests and acquiring the numerical values of the evaluation items corresponding to the service providers of all the available services, recording the numerical values of the evaluation items corresponding to the service providers of all the available services in the local routing table, so that the service providers of all the available services can acquire the numerical values conveniently at any time.
Further, the numerical values of the evaluation items are updated periodically, and the updated information is updated to the local routing table.
If more task requests are processed by the service provider with the optimal service quality, the processing speed of the service provider is reduced, the numerical value of the evaluation item is also reduced, and when the service provider with the optimal service quality is refreshed to the combination with the highest score, the task request is received and sent to the service provider with the optimal service quality.
S102: determining evaluation items corresponding to the service requests, and acquiring numerical values of the evaluation items corresponding to service providers of all available services;
the evaluation item comprises calculation time and transmission time;
the evaluation model is summation operation;
correspondingly, the service quality is the sum of the calculation time and the transmission time;
determining a target service provider in each service provider according to the service quality, wherein the method comprises the following steps:
and determining the service provider with the minimum sum of the calculation time and the transmission time as a target service provider.
Calculating time as the time for the service provider to process the task request; further, the time mean and the variance of the service provider for processing the task request are calculated so as to ensure the accuracy of the calculation time;
the transmission time is the time consumed by transmission in a routing path from the service request to the service provider, different service providers may be crossed in the transmission process, the time consumption of each service provider node needs to be integrated, and the final transmission time is calculated.
According to the method in the above embodiment, the evaluation item further includes an evaluation item corresponding to the service request, for example, if the service classification information included in the service request is an object identification class, the evaluation item includes: calculating time, identification accuracy, classification confidence and transmission time;
the evaluation model is summation operation;
correspondingly, when the service request comprises service classification information of an object identification class, the service quality is the sum of the calculation time, the identification accuracy, the classification confidence and the transmission time.
If the service classification information contained in the service request is not considered, the evaluation item only considers the calculation time of the service provider and the transmission time of the service request from the route to the service provider; the quality of service is the sum of the calculation time and the transmission time.
Preferably, the evaluation model is a reinforcement learning model.
The algorithm for selecting the service provider selects an algorithm for the service provider.
Further, the reinforcement learning model includes a weight value of each evaluation item, and a preset evaluation model is adopted to calculate a numerical value of the evaluation item corresponding to each service provider to obtain the service quality of each service provider, including:
and performing weighted operation on the numerical values of the evaluation items according to the weight values to obtain the service quality of each service provider.
In this embodiment, the algorithm for reinforcement learning is applied to the field of selection algorithm of the service provider, specifically,
first, a plurality of evaluation items are listed for the service request according to the characteristics of the service request. Taking object recognition as an example, the evaluation items include: calculating time, object recognition accuracy, classification confidence and the like.
The training method is deployed at a terminal, and software of the training algorithm exists as a background service or as a module integrated in client codes.
The content of the training is to learn how to balance the advantages and disadvantages in factors such as calculation time, object recognition accuracy rate and classification confidence "
The implementation method is that all the characteristics (calculation time, object recognition accuracy and classification confidence) are scored, and the person with the highest score is selected.
Setting the values of the parameters P1, P2 and P3 between 0 and 1, so that P1+ P2+ P3=1,
total Score = Score1 × P1+ Score2 × P2+ Score3 × P3.
The specific action of training is to continuously adjust the values of P1, P2 and P3 according to the practical result. The value of the evaluation item of the service request is made higher. Therefore, the value of the evaluation item corresponding to the service request of each service provider is improved.
In some embodiments, the intelligent routing method, the service provider is located in one or more of:
the system comprises a terminal local, a local area network server and a cloud server.
Deployment of service providers is based on real-time.
Real-time is a factor that first needs attention in a particular application considering where the service provider is deployed to run. Each specific application scenario has its determined real-time requirements. Various deployment scenarios have the highest real-time performance that it can achieve. Unreasonable deployment schemes will make the product unable to work effectively.
The intelligent service and the traditional service are distinguished by the following points: the intelligent service also has the requirement of being deployed in the local, and many clients can smoothly transfer to the local resource to obtain the service when the clients cannot be supported by the server. Therefore, the inventor deploys the service provider locally on the terminal through a large amount of work, so that each smart technology platform can locally invoke the service of the service provider by the terminal.
The terminal executes locally, corresponding to the highest response speed, possibly up to the order of 1 millisecond, requiring the task request to be executed in the core of the device digital system (in the embedded system), for example a task request generated by a mechanical device controlled by the embedded system, to be completed by a service provider running in the embedded system.
The task request is transmitted to a service provider deployed in the local area network through Ethernet and local area network routing, and the service provider uniformly solves the task requests of all the clients in the local area network and returns the task requests to all the clients.
The task request is transmitted to a service provider deployed in the internet, and the service provider uniformly solves the task requests of all clients in the internet and returns the task requests to all the clients.
In addition to real-time, there are many other factors that need to be taken into account. Such as:
energy consumption, many mobile devices are powered by batteries and hope to reach reasonable endurance, and such devices often need to be executed by placing service providers at far ends, namely, a local area network server and a cloud server;
cost, calculation of task requests, hardware acceleration equipment such as a GPU (graphics processing unit) and the like are often required, certain cost is achieved, when products need price competition, if the task requests are solved locally at a terminal, more expensive hardware cost is required, the problem can be solved when the task requests are placed at far ends, namely a local area network server and a cloud server, and real-time performance can be reduced;
similarly, there is a volume issue, with GPU devices having a certain volume; the heat dissipation problem, high frequency calculation, can produce a large amount of heats, is far higher than the calculation heat dissipation of CPU, for airtight, the equipment of silence, need do special design for this reason.
Fig. 2 is an exemplary diagram of an intelligent routing method provided in an embodiment of the present application, and referring to fig. 2, 21,45,51 are all service providers, each having its own service content, and the middle 51 service provider is closer to the rightmost client.
51 can be considered as a service provider within a local area network, 21,45 is a service provider on the internet, 51 has a local service D, but on the routing table it maintains service a and service B of 21 service providers on the internet, 45 service a and service C provided by service provider, and with respect to service a,51 has selected the best service a from 45,
when the client issues a task request a, service a on 45 is found directly 51 here, and service a on 45 is superior to service a local to the client, i.e. the terminal, so the client will choose 45 to provide the service.
In this embodiment, only the calculation time of the service provider for processing the task request and the transmission time of the service request routed to the routing path of the service provider are considered.
Fig. 3 is a structural diagram of an intelligent routing device according to an embodiment of the present application, and referring to fig. 3, an intelligent routing device is characterized by including:
a memory 31 for storing a computer program;
a processor 32, connected to the memory 31, is used to run the computer program stored in the memory 31 to perform the method as described above.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present application, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried out in the method of implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (3)
1. An intelligent routing method, comprising:
receiving a service request; the service request comprises service classification information;
determining an evaluation item corresponding to the service request according to a corresponding relation between preset service classification information and the evaluation item, and acquiring numerical values of the evaluation items corresponding to all service providers of available services in a local routing table, wherein the numerical values of the evaluation items corresponding to all the service providers are recorded in the local routing table; the service classification information includes: an object identification class, the evaluation items including: calculating time, recognition accuracy and classification confidence;
calculating the numerical value of the evaluation item corresponding to each service provider by adopting a preset evaluation model to obtain the service quality of each service provider;
determining a target service provider in each service provider according to the service quality;
routing the service request to the target service provider;
wherein the service provider is located in one or more of:
the system comprises a terminal local, a local area network server and a cloud server;
deployment of the service provider is based at least on real-time, energy consumption, cost and volume;
the evaluation model is a reinforcement learning model, a reinforcement learning algorithm is adopted for selection of a service provider, and weight values P are respectively set according to calculation time, object identification accuracy and classification confidence 1 ，P 2 ，P 3 And making the associated weight value between 0-1, making P 1 +P 2 +P 3 And =1, and the evaluation items are scored, and the numerical value of each evaluation item is weighted according to the weight value, wherein the weighting operation formula is as follows: total score = calculated time score P 1 + object recognition accuracy score P 2 + classification confidence score P 3 Obtaining the total service quality score of each service provider, and selecting the high-ranking person; training the evaluation model, i.e. continuously adjusting P 1 、P 2 、P 3 The value of (b) is made higher for the evaluation item of the service request.
2. The method of claim 1, further comprising:
and updating the numerical value of each evaluation item periodically, and updating the updated information into the local routing table.
3. An intelligent routing device, comprising:
a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored in the memory to perform the method of any of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811145875.5A CN109246231B (en) | 2018-09-29 | 2018-09-29 | Intelligent routing method and intelligent routing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811145875.5A CN109246231B (en) | 2018-09-29 | 2018-09-29 | Intelligent routing method and intelligent routing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109246231A CN109246231A (en) | 2019-01-18 |
| CN109246231B true CN109246231B (en) | 2022-11-18 |
Family
ID=65054566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811145875.5A Active CN109246231B (en) | 2018-09-29 | 2018-09-29 | Intelligent routing method and intelligent routing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109246231B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104767776A (en) * | 2014-01-07 | 2015-07-08 | 腾讯科技（深圳）有限公司 | Real-time network routing adjustment method, device and system |
| CN105812255A (en) * | 2016-05-06 | 2016-07-27 | 网宿科技股份有限公司 | Source return line selection method and device |
| US9510279B2 (en) * | 2013-06-03 | 2016-11-29 | Electronics And Telecommunications Research Institute | Intelligent multiple access communication control apparatus and method |
| CN106936709A (en) * | 2017-01-19 | 2017-07-07 | 广州华多网络科技有限公司 | Remote service access path control method and relevant device |
| CN108123878A (en) * | 2016-11-30 | 2018-06-05 | 华为技术有限公司 | A kind of method for routing, device and data transfer equipment |
| CN108540384A (en) * | 2018-04-13 | 2018-09-14 | 西安交通大学 | Intelligent heavy route method and device based on congestion aware in software defined network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106657367B (en) * | 2016-12-30 | 2019-09-17 | 北京三快在线科技有限公司 | A kind of business datum acquisition methods, apparatus and system |
-
2018
- 2018-09-29 CN CN201811145875.5A patent/CN109246231B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9510279B2 (en) * | 2013-06-03 | 2016-11-29 | Electronics And Telecommunications Research Institute | Intelligent multiple access communication control apparatus and method |
| CN104767776A (en) * | 2014-01-07 | 2015-07-08 | 腾讯科技（深圳）有限公司 | Real-time network routing adjustment method, device and system |
| CN105812255A (en) * | 2016-05-06 | 2016-07-27 | 网宿科技股份有限公司 | Source return line selection method and device |
| CN108123878A (en) * | 2016-11-30 | 2018-06-05 | 华为技术有限公司 | A kind of method for routing, device and data transfer equipment |
| CN106936709A (en) * | 2017-01-19 | 2017-07-07 | 广州华多网络科技有限公司 | Remote service access path control method and relevant device |
| CN108540384A (en) * | 2018-04-13 | 2018-09-14 | 西安交通大学 | Intelligent heavy route method and device based on congestion aware in software defined network |
Non-Patent Citations (2)
| Title |
|---|
| "A Ranking-oriented Hybrid Approach to QoS-aware Web Service Recommendation";Mingming Chen，Yutao Ma，Bo Hu，LiangJie Zhang;《2015 IEEE International Conference on Services Computing》;20150820;全文 * |
| "用户QoS需求导向的服务演化选择策略";杨真谛，秦江龙、李彤;《计算机应用于软件》;20171231;第83-43页、表1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109246231A (en) | 2019-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiao et al. | Toward an automated auction framework for wireless federated learning services market | |
| CN111835827B (en) | Internet of things edge computing task unloading method and system | |
| CN110352584A (en) | Across the automatic priority ranking of the equipment flow of local network | |
| CN108777625A (en) | Verification method, device and system, storage medium, the electronic device of signature | |
| US20140180978A1 (en) | Instance weighted learning machine learning model | |
| CN104115165A (en) | Method for mapping media components employing machine learning | |
| CN110493734B (en) | Channel selection method and device for sending short messages | |
| Kim et al. | Multi-agent reinforcement learning-based resource management for end-to-end network slicing | |
| CN103942049A (en) | Augmented reality realizing method, client-side device and server | |
| US10325332B2 (en) | Incentivizing human travel patterns to reduce traffic congestion | |
| CN109886699A (en) | Activity recognition method and device, electronic equipment, storage medium | |
| US7904561B2 (en) | Brokering mobile web services | |
| WO2019116417A1 (en) | Communication quality deterioration prediction system, method, and program | |
| WO2023065869A1 (en) | Data processing method and related apparatus | |
| CN112764920A (en) | Edge application deployment method, device, equipment and storage medium | |
| US11847671B2 (en) | Smart campaign with autopilot features | |
| Cao et al. | Softwarized resource management and allocation with autonomous awareness for 6G-enabled cooperative intelligent transportation systems | |
| CN115580882A (en) | Dynamic network slice resource allocation method and device, storage medium and electronic equipment | |
| CN108966316A (en) | Show the method, device and equipment of multimedia resource, prediction connection waiting time | |
| Ramkumar et al. | Constrained cuckoo search optimization based protocol for routing in cloud network | |
| KR102590112B1 (en) | Coded and Incentive-based Mechanism for Distributed Training of Machine Learning in IoT | |
| CN112995303B (en) | Cross-cluster scheduling method and device | |
| Besharati et al. | An Auction‐Based Bid Prediction Mechanism for Fog‐Cloud Offloading Using Q‐Learning | |
| CN109246231B (en) | Intelligent routing method and intelligent routing equipment | |
| WO2017024020A1 (en) | Real-time routing system and associated methodology for adapting order flow for enhanced execution performance |
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 |