CN111836274A - Service processing method and device - Google Patents
Service processing method and device Download PDFInfo
- Publication number
- CN111836274A CN111836274A CN201910309982.5A CN201910309982A CN111836274A CN 111836274 A CN111836274 A CN 111836274A CN 201910309982 A CN201910309982 A CN 201910309982A CN 111836274 A CN111836274 A CN 111836274A
- Authority
- CN
- China
- Prior art keywords
- attribute information
- sample
- determining
- neural network
- service request
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
- H04W72/044—Wireless resource allocation based on the type of the allocated resource
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/52—Allocation or scheduling criteria for wireless resources based on load
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/56—Allocation or scheduling criteria for wireless resources based on priority criteria
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The application provides a method for processing service, which comprises the following steps: training a neural network model; when a service request is received, determining resource attribute information corresponding to the service request; wherein the resource attribute information includes a resource configuration required for processing the service request; determining equipment attribute information corresponding to the resource attribute information according to the neural network model, and determining target control equipment matched with the equipment attribute information from an available equipment list; by adopting the target control equipment to process the service request, the efficient resource arrangement is realized, so that the repetitive labor of manual input is avoided and the error rate of manual input is reduced.
Description
Technical Field
The present application relates to the field of communications, and in particular, to a method and an apparatus for service processing.
Background
In the business processing process, resource arrangement is often required. In the existing 5G orchestration system, the orchestration is performed manually, and an administrator divides and deploys resources according to the resource usage, such as dividing subnets and deploying network service resources.
When arranging resources, an administrator needs to acquire mass parameter information, screen useful data, form an arrangement deployment file after evaluation, import the arrangement deployment file into a cloud system to distribute resources, arrange the resources according to different strategies through people, analyze a large amount of data, waste time and labor, and have high error rate.
Disclosure of Invention
The embodiment of the application provides a method and a device for service processing, which are used for solving the problems of low arrangement efficiency and high error rate caused by manual data analysis and resource arrangement, and comprise the following steps:
a method of traffic processing, the method comprising:
training a neural network model;
when a service request is received, determining resource attribute information corresponding to the service request; wherein the resource attribute information includes a resource configuration required for processing the service request;
determining equipment attribute information corresponding to the resource attribute information according to the neural network model, and determining target control equipment matched with the equipment attribute information from an available equipment list;
and processing the service request by adopting the target control equipment.
Optionally, the step of training the neural network model comprises:
acquiring sample resource attribute information;
determining sample equipment attribute information corresponding to the sample resource attribute information;
and training the sample resource attribute information by taking the sample equipment attribute information as a target to obtain a neural network model.
Optionally, the sample resource attribute information includes first sample information and second sample information, and the step of training the sample resource attribute information with the sample device attribute information as a target to obtain the neural network model includes:
determining a first link weight using the first sample information and the sample device attribute information;
determining a second link weight by using the second sample information and the sample device attribute information;
calculating a weight error between the second link weight and the first link weight;
and updating the first link weight by adopting the weight error to obtain a neural network model.
Optionally, the service request includes a communication request, the resource attribute information includes a traffic volume, and the target control device includes a centralized controller.
Optionally, the service request includes a request to create a virtual machine, and the target control device includes a server for creating a virtual machine.
Optionally, the method further comprises:
deleting the record of the target control device from the list of available devices.
Optionally, the method is applied to a base station and/or a core network, and the base station is a communication base station providing 5G network services.
An apparatus for traffic processing, the apparatus comprising:
the neural network model training module is used for training a neural network model;
the resource attribute information determining module is used for determining resource attribute information corresponding to a service request when the service request is received; wherein the resource attribute information includes a resource configuration required for processing the service request;
the target control equipment determining module is used for determining equipment attribute information corresponding to the resource attribute information according to the neural network model and determining target control equipment matched with the equipment attribute information from an available equipment list;
and the service request processing module is used for processing the service request by adopting the target control equipment.
Optionally, the neural network model training module includes:
the sample resource attribute information acquisition submodule is used for acquiring sample resource attribute information;
the sample equipment attribute information determining submodule is used for determining sample equipment attribute information corresponding to the sample resource attribute information;
and the neural network model training submodule is used for training the sample resource attribute information by taking the sample equipment attribute information as a target to obtain a neural network model.
Optionally, the sample resource attribute information includes first sample information and second sample information, and the neural network model training sub-module includes:
a first link weight determination unit for determining a first link weight using the first sample information and the sample device attribute information;
a second link weight determining unit, configured to determine a second link weight by using the second sample information and the sample device attribute information;
a weight error calculation unit for calculating a weight error between the second link weight and the first link weight;
and the first link weight updating unit is used for updating the first link weight by adopting the weight error to obtain a neural network model.
Optionally, the service request includes a communication request, the resource attribute information includes a traffic volume, and the target control device includes a centralized controller.
Optionally, when the service request includes a request to create a virtual machine, the target control device includes a server for creating a virtual machine.
Optionally, the method further comprises:
and the record deleting module is used for deleting the record of the target control device from the available device list.
Optionally, the apparatus is applied to a base station and/or a core network, and the base station is a communication base station providing 5G network services.
The application has the following advantages:
in the application, by training a neural network model, when a service request is received, resource attribute information corresponding to the service request is determined; wherein the resource attribute information includes resource configuration required for processing the service request; determining equipment attribute information corresponding to the resource attribute information according to the neural network model, and determining target control equipment matched with the equipment attribute information from the available equipment list; and the target control equipment is adopted to process the service request, so that the efficient resource arrangement is realized, the repeated labor of manual input is avoided, and the error rate of manual input is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings needed to be used in the description of the present application will be briefly introduced below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive labor.
FIG. 1 is a flow chart of steps of a method of business processing provided by an embodiment of the present application;
FIG. 2 is a flow chart of steps of a method of business processing provided by another embodiment of the present application;
FIG. 3 is a flow chart of steps of a method of business processing provided by another embodiment of the present application;
fig. 4 is a block diagram illustrating a service processing apparatus according to an embodiment of the present application.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a flowchart illustrating steps of a method for service processing according to an embodiment of the present application is shown, which may specifically include the following steps:
101, training a neural network model;
a neural network is an operational model, which is formed by connecting a large number of nodes (or neurons). Each node represents a particular output function, called the excitation function. Every connection between two nodes represents a weighted value, called weight, for the signal passing through the connection, which is equivalent to the memory of the artificial neural network. The output of the network is different according to the connection mode of the network, the weight value and the excitation function. The network itself is usually an approximation to some algorithm or function in nature, and may also be an expression of a logic strategy.
In an embodiment of the present application, step 101 may include the following steps:
substep 11, obtaining sample resource attribute information;
as an example, the sample resource attribute information may be a specification of a virtual machine to be created, for example, a memory of the virtual machine is 8G, a hard disk is 40G, and the number of CPUs is 8.
As another example, the sample resource attribute information may be traffic in the communication.
Substep 12, determining sample equipment attribute information corresponding to the sample resource attribute information;
as an example, the sample device attribute information corresponding to the sample resource attribute information may be a server specification that meets the specification of creating the virtual machine, for example, the memory of server No. 1 is 40G, the hard disk is 100T, the number of CPUs is 10, and the memory of server No. 2 is 7G, the hard disk is 100T, the number of CPUs is 10, and the memory of server No. 2 does not meet the specification requirement of the virtual machine, because the memory of server No. 2 cannot meet the memory requirement of the virtual machine.
As another example, the sample device attribute information corresponding to the sample resource attribute information may be the number of centralized controllers capable of handling traffic, for example, two centralized controllers capable of handling traffic of 0.5 are required for handling traffic of size 1.
And the sample device attribute information may be a correct result obtained by manual arrangement by an administrator according to the sample resource attribute information, that is, it is determined that the sample device attribute corresponding to the sample resource attribute information may be completed by the administrator.
And a substep 13, taking the sample equipment attribute information as a target, training the sample resource attribute information to obtain a neural network model.
In a specific implementation, a target sample device corresponding to the sample device attribute information needs to be determined according to the sample resource attribute information and the sample device attribute information corresponding to the sample resource attribute information, so as to construct nodes in the neural network and link weights among the nodes.
The neural network may be divided into two layers, an input layer and an output layer. The input layer needs to input data (memory size, hard disk size, and cpu number), and the output layer is a server number that the user wants to use.
Suppose there are three servers, numbered as Server No. 1, Server No. 2, Server No. 3, Winput_outputIs the weight of the link between the nodes,
then
In an embodiment of the present application, substep 13 may comprise the steps of:
the sample resource attribute information comprises first sample information and second sample information; determining a first link weight using the first sample information and the sample device attribute information; determining a second link weight by using the second sample information and the sample device attribute information; calculating a weight error between the second link weight and the first link weight; and updating the first link weight by adopting the weight error to obtain a neural network model.
In an example, the first sample information may be specifications of the virtual machine to be created, such as 8G of memory of the virtual machine, 40G of hard disk, and 8 CPU counts, and the second sample information may be specifications of the virtual machine to be created, such as 8G of memory of the virtual machine, 39G of hard disk, and 8 CPU counts.
The sample device attribute information may satisfy the server specification for creating the virtual machine corresponding to the first sample information and the second sample information, for example, the memory of the server No. 1 is 40G, the hard disk is 100T, and the number of CPUs is 10.
In another example, the first sample information may be a traffic volume, such as a size of 0.5, and the second sample information may be a traffic volume, such as a size of 0.55.
The sample device attribute information may be traffic handling the first sample information corresponding to the second sample information, such as 2 centralized controllers capable of handling traffic of 0.3 size.
Determining a first link weight W according to the link weight formula using the first sample information and the sample device attribute informationinput_output1Similarly, the second link weight Winput_output2。
With a first link weight Winput_output1As standard link weights, weight errors are calculated.
Suppose that
Obtaining the weight error, updating each link of the network by using a neural network back propagation algorithm, wherein the formula is as follows:
errorsoutput＝Weights*errorsinput
then, the weight error is adopted, and the first link weight is updated according to a formula of updating the lower link weight, so that the neural network model is obtained.
Δwjk＝∝*Ek*sigmoid(Ok)*(1-sigmoid(Ok))·Oj T
when a service request is received, resource attribute information corresponding to the request is determined, for example, it is determined that the received communication request corresponds to traffic.
according to the trained neural network model, determining device attribute information corresponding to the resource attribute information, if the traffic volume is 0.5, a centralized controller capable of processing the traffic volume greater than or equal to 0.5 is required, and determining target control devices matched with the device attribute information from an available device list, so as to complete a process of arranging the target control devices according to the resource attribute information.
And 104, processing the service request by adopting the target control equipment.
And after determining the target control equipment matched with the equipment attribute information, processing the service request by adopting the target control equipment.
In the embodiment of the application, by training a neural network model, when a service request is received, resource attribute information corresponding to the service request is determined; wherein the resource attribute information includes resource configuration required for processing the service request; determining equipment attribute information corresponding to the resource attribute information according to the neural network model, and determining target control equipment matched with the equipment attribute information from the available equipment list; and the target control equipment is adopted to process the service request, so that the efficient resource arrangement is realized, the repeated labor of manual input is avoided, and the error rate of manual input is reduced.
Referring to fig. 2, a flowchart illustrating steps of another service processing method provided in an embodiment of the present application is shown, which may specifically include the following steps:
step 202, when a service request is received, determining resource attribute information corresponding to the service request; the resource attribute information includes resource configuration required for processing the service request, and the service request includes a request for creating a virtual machine.
When a request for creating a virtual machine sent by a terminal or a server is received, resource attribute information corresponding to the request is determined, where the resource attribute information may include resource configuration required for processing the request, for example, a memory of the virtual machine is 8.5G, a hard disk is 39G, and the number of CPUs is 8.
Step 203, determining device attribute information corresponding to the resource attribute information according to the neural network model, and determining target control devices matched with the device attribute information from an available device list; the target control device includes a server for creating a virtual machine.
In an example, the target control device may include a server for creating the virtual machine, such as server number 1 that conforms to the resource configuration required by the virtual machine.
And according to the trained neural network model, determining equipment attribute information corresponding to the resource attribute information in the request for creating the virtual machine, and determining target control equipment matched with the equipment attribute information from the available equipment list.
For example, the resource attribute information is input into a neural network model, and the evaluation results corresponding to the server No. 1 and the server No. 2 in the available device list are respectively calculated according to the model, where the evaluation result corresponding to the server No. 1 is 0.53, the evaluation result corresponding to the server No. 2 is 0.51, and at this time, the evaluation result corresponding to the server No. 1 is greater than that of the server No. 2, which indicates that the server No. 1 better conforms to the resource configuration of the request than the server No. 2, so that the target control device matched with the device attribute information is determined to be the server No. 1.
And step 204, processing the service request by adopting the target control equipment.
After determining a target control device that matches the device attribute information, the computing resources are orchestrated using the target control device, creating a virtual machine.
In an embodiment of the present application, the method further includes:
deleting the record of the target control device from the list of available devices.
As can be seen from the above process, the server No. 1 is determined as the target control device to create the virtual machine, and the space occupied by the virtual machine at this time cannot be used by another user, so the occupied space is subtracted from the original hardware of the server No. 1 to update the available device list, and prepare to process the next request.
In an embodiment of the present application, the method is applied to a base station and/or a core network, where the base station is a communication base station providing a 5G network service.
In the embodiment of the application, by training a neural network model, when a service request is received, resource attribute information corresponding to the service request is determined; wherein the resource attribute information includes resource configuration required for processing the service request; determining equipment attribute information corresponding to the resource attribute information according to the neural network model, and determining target control equipment matched with the equipment attribute information from the available equipment list; and the target control equipment is adopted to process the service request, so that the efficient resource arrangement is realized, the repeated labor of manual input is avoided, and the error rate of manual input is reduced.
Referring to fig. 3, a flowchart illustrating steps of another service processing method provided in an embodiment of the present application is shown, which may specifically include the following steps:
When a service request is received, the traffic volume corresponding to the request is determined, and the base station may allocate different numbers of centralized controllers to process according to the size of the traffic volume, for example, when the traffic volume is large, a plurality of centralized controllers are required to share processing, and when the traffic volume is small, only one centralized controller may be required.
In an example, the device attribute information may be the number of centralized controllers in the base station and the capability of the centralized controllers to process traffic, such as the centralized controllers may process traffic of size 1.
The target control device may comprise a centralized controller.
According to the trained neural network model, determining device attribute information corresponding to the traffic volume, for example, determining the number of centralized controllers required for processing the traffic volume according to the size of the traffic volume, and determining target control devices matched with the device attribute information from an available centralized controller list, that is, determining which one or more centralized controllers are to be used for processing the traffic volume from the list, so as to complete the process of organizing the centralized controllers according to the traffic volume.
After determining the target control device matched with the device attribute information, arranging the computing resource by adopting the target control device, and processing the traffic corresponding to the communication request.
In an embodiment of the present application, the method further includes:
deleting the record of the target control device from the list of available devices.
When one or more centralized controllers are determined to be used to process traffic for a communication request, the one or more centralized controllers may no longer be called and may need to be deleted from the current list of available devices to record their current status as unavailable.
In an embodiment of the present application, the method is applied to a base station and/or a core network, where the base station is a communication base station providing a 5G network service.
In the embodiment of the application, by training a neural network model, when a service request is received, resource attribute information corresponding to the service request is determined; wherein the resource attribute information includes resource configuration required for processing the service request; determining equipment attribute information corresponding to the resource attribute information according to the neural network model, and determining target control equipment matched with the equipment attribute information from the available equipment list; and the target control equipment is adopted to process the service request, so that the efficient resource arrangement is realized, the repeated labor of manual input is avoided, and the error rate of manual input is reduced.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the embodiments. Further, those skilled in the art will also appreciate that the embodiments described in the specification are presently preferred and that no particular act is required of the embodiments of the application.
Referring to fig. 4, a block diagram of a service processing apparatus according to an embodiment of the present application is shown, which may specifically include the following modules:
a neural network model training module 401, configured to train a neural network model;
a resource attribute information determining module 402, configured to determine, when a service request is received, resource attribute information corresponding to the service request; wherein the resource attribute information includes a resource configuration required for processing the service request;
a target control device determining module 403, configured to determine device attribute information corresponding to the resource attribute information according to the neural network model, and determine a target control device matched with the device attribute information from an available device list;
a service request processing module 404, configured to process the service request by using the target control device.
In an embodiment of the present application, the neural network model training module 401 includes:
the sample resource attribute information acquisition submodule is used for acquiring sample resource attribute information;
the sample equipment attribute information determining submodule is used for determining sample equipment attribute information corresponding to the sample resource attribute information;
and the neural network model training submodule is used for training the sample resource attribute information by taking the sample equipment attribute information as a target to obtain a neural network model.
In an embodiment of the present application, the sample resource attribute information includes first sample information and second sample information, and the neural network model training sub-module includes:
a first link weight determination unit for determining a first link weight using the first sample information and the sample device attribute information;
a second link weight determining unit, configured to determine a second link weight by using the second sample information and the sample device attribute information;
a weight error calculation unit for calculating a weight error between the second link weight and the first link weight;
and the first link weight updating unit is used for updating the first link weight by adopting the weight error to obtain a neural network model.
In an embodiment of the present application, the service request includes a communication request, the resource attribute information includes a traffic volume, and the target control device includes a centralized controller.
In an embodiment of the application, when the service request includes a request to create a virtual machine, the target control device includes a server for creating a virtual machine.
In an embodiment of the present application, the method further includes:
and the record deleting module is used for deleting the record of the target control device from the available device list.
In an embodiment of the present application, the apparatus is applied to a base station and/or a core network, where the base station is a communication base station providing a 5G network service.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
An embodiment of the present application also provides an electronic device, which may include a processor, a memory, and a computer program stored on the memory and capable of running on the processor, and when the computer program is executed by the processor, the steps of the method for processing the business as above are implemented.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above method for business processing.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method and the apparatus for processing a service provided by the present application are introduced in detail, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (14)
1. A method for service processing, the method comprising:
training a neural network model;
when a service request is received, determining resource attribute information corresponding to the service request; wherein the resource attribute information includes a resource configuration required for processing the service request;
determining equipment attribute information corresponding to the resource attribute information according to the neural network model, and determining target control equipment matched with the equipment attribute information from an available equipment list;
and processing the service request by adopting the target control equipment.
2. The method of claim 1, wherein the step of training a neural network model comprises:
acquiring sample resource attribute information;
determining sample equipment attribute information corresponding to the sample resource attribute information;
and training the sample resource attribute information by taking the sample equipment attribute information as a target to obtain a neural network model.
3. The method of claim 2, wherein the sample resource attribute information comprises first sample information and second sample information, and the step of training the sample resource attribute information to obtain the neural network model with the sample device attribute information as a target comprises:
determining a first link weight using the first sample information and the sample device attribute information;
determining a second link weight by using the second sample information and the sample device attribute information;
calculating a weight error between the second link weight and the first link weight;
and updating the first link weight by adopting the weight error to obtain a neural network model.
4. A method according to claim 1, 2 or 3, wherein the service request comprises a communication request, the resource attribute information comprises traffic volume, and the target control device comprises a centralized controller.
5. A method according to claim 1, 2 or 3, wherein the service request comprises a create virtual machine request and the target control device comprises a server for creating a virtual machine.
6. The method of claim 1, further comprising:
deleting the record of the target control device from the list of available devices.
7. The method according to claim 1, wherein the method is applied to a base station and/or a core network, and the base station is a communication base station providing 5G network service.
8. An apparatus for traffic processing, the apparatus comprising:
the neural network model training module is used for training a neural network model;
the resource attribute information determining module is used for determining resource attribute information corresponding to a service request when the service request is received; wherein the resource attribute information includes a resource configuration required for processing the service request;
the target control equipment determining module is used for determining equipment attribute information corresponding to the resource attribute information according to the neural network model and determining target control equipment matched with the equipment attribute information from an available equipment list;
and the service request processing module is used for processing the service request by adopting the target control equipment.
9. The apparatus of claim 8, wherein the neural network model training module comprises:
the sample resource attribute information acquisition submodule is used for acquiring sample resource attribute information;
the sample equipment attribute information determining submodule is used for determining sample equipment attribute information corresponding to the sample resource attribute information;
and the neural network model training submodule is used for training the sample resource attribute information by taking the sample equipment attribute information as a target to obtain a neural network model.
10. The apparatus of claim 9, wherein the sample resource attribute information comprises first sample information and second sample information, and wherein the neural network model training sub-module comprises:
a first link weight determination unit for determining a first link weight using the first sample information and the sample device attribute information;
a second link weight determining unit, configured to determine a second link weight by using the second sample information and the sample device attribute information;
a weight error calculation unit for calculating a weight error between the second link weight and the first link weight;
and the first link weight updating unit is used for updating the first link weight by adopting the weight error to obtain a neural network model.
11. The apparatus of claim 8, 9 or 10, wherein the service request comprises a communication request, wherein the resource attribute information comprises traffic volume, and wherein the target control device comprises a centralized controller.
12. The apparatus of claim 8, 9 or 10, wherein when the service request comprises a create virtual machine request, the target control device comprises a server for creating a virtual machine.
13. The apparatus of claim 8, further comprising:
and the record deleting module is used for deleting the record of the target control device from the available device list.
14. The device according to claim 8, wherein the device is applied to a base station and/or a core network, and the base station is a communication base station providing 5G network service.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910309982.5A CN111836274B (en) | 2019-04-17 | 2019-04-17 | Service processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910309982.5A CN111836274B (en) | 2019-04-17 | 2019-04-17 | Service processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111836274A true CN111836274A (en) | 2020-10-27 |
| CN111836274B CN111836274B (en) | 2022-01-25 |
Family
ID=72914730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910309982.5A Active CN111836274B (en) | 2019-04-17 | 2019-04-17 | Service processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111836274B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114531448A (en) * | 2022-02-21 | 2022-05-24 | 联想(北京)有限公司 | Calculation force determination method and device and calculation force sharing system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040122785A1 (en) * | 2000-12-15 | 2004-06-24 | International Business Machines Corporation | Method, system, and program for converting application program code to executable code using neural networks based on characteristics of the inputs |
| CN102523166A (en) * | 2011-12-23 | 2012-06-27 | 中山大学 | Structured network system applicable to future internet |
| CN102681899A (en) * | 2011-03-14 | 2012-09-19 | 金剑 | Virtual computing resource dynamic management system of cloud computing service platform |
| CN103699440A (en) * | 2012-09-27 | 2014-04-02 | 北京搜狐新媒体信息技术有限公司 | Method and device for cloud computing platform system to distribute resources to task |
| CN107045452A (en) * | 2016-02-06 | 2017-08-15 | 北京京东尚科信息技术有限公司 | Dispatching method of virtual machine and device |
-
2019
- 2019-04-17 CN CN201910309982.5A patent/CN111836274B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040122785A1 (en) * | 2000-12-15 | 2004-06-24 | International Business Machines Corporation | Method, system, and program for converting application program code to executable code using neural networks based on characteristics of the inputs |
| CN102681899A (en) * | 2011-03-14 | 2012-09-19 | 金剑 | Virtual computing resource dynamic management system of cloud computing service platform |
| CN102523166A (en) * | 2011-12-23 | 2012-06-27 | 中山大学 | Structured network system applicable to future internet |
| CN103699440A (en) * | 2012-09-27 | 2014-04-02 | 北京搜狐新媒体信息技术有限公司 | Method and device for cloud computing platform system to distribute resources to task |
| CN107045452A (en) * | 2016-02-06 | 2017-08-15 | 北京京东尚科信息技术有限公司 | Dispatching method of virtual machine and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114531448A (en) * | 2022-02-21 | 2022-05-24 | 联想(北京)有限公司 | Calculation force determination method and device and calculation force sharing system |
| CN114531448B (en) * | 2022-02-21 | 2024-02-27 | 联想(北京)有限公司 | Calculation force determining method and device and calculation force sharing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111836274B (en) | 2022-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10924535B2 (en) | Resource load balancing control method and cluster scheduler | |
| US20200364608A1 (en) | Communicating in a federated learning environment | |
| CN109872535B (en) | Intelligent traffic passage prediction method, device and server | |
| CN111158613B (en) | Data block storage method and device based on access heat and storage equipment | |
| CN112036577B (en) | Method and device for applying machine learning based on data form and electronic equipment | |
| US11829496B2 (en) | Workflow for evaluating quality of artificial intelligence (AI) services using held-out data | |
| CN116134448A (en) | Joint machine learning using locality sensitive hashing | |
| CN112764920A (en) | Edge application deployment method, device, equipment and storage medium | |
| CN115134371A (en) | Scheduling method, system, equipment and medium containing edge network computing resources | |
| CN110896344B (en) | Redundant service deployment method and device | |
| JP2023022831A (en) | Computer system, computer implementation method, program and computer implementation system (learning causal relation) | |
| CN111836274B (en) | Service processing method and device | |
| US10313457B2 (en) | Collaborative filtering in directed graph | |
| CN110347973B (en) | Method and device for generating information | |
| CN110958178A (en) | Method and device for determining shortest path between systems | |
| US10728116B1 (en) | Intelligent resource matching for request artifacts | |
| CN116225690A (en) | Memory multidimensional database calculation load balancing method and system based on docker | |
| CN106330556B (en) | A kind of method and apparatus calling related information for generating service module | |
| CN107688582B (en) | Resource recommendation model obtaining method and device | |
| US11645049B2 (en) | Automated software application generation | |
| CN112416488B (en) | User portrait implementing method, device, computer equipment and computer readable storage medium | |
| CN106611100B (en) | User behavior analysis method and device | |
| CN116107732A (en) | Task decomposition method and system for collaborative task system | |
| CN108551484B (en) | User information synchronization method, device, computer device and storage medium | |
| US11080632B2 (en) | Optimization of steady state cost for multi-site high availability application deployment of management and managed intrastructure |
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 |