CN115766489A - Data processing apparatus, method and storage medium - Google Patents
Data processing apparatus, method and storage medium Download PDFInfo
- Publication number
- CN115766489A CN115766489A CN202211666005.9A CN202211666005A CN115766489A CN 115766489 A CN115766489 A CN 115766489A CN 202211666005 A CN202211666005 A CN 202211666005A CN 115766489 A CN115766489 A CN 115766489A
- Authority
- CN
- China
- Prior art keywords
- data
- service
- cloud platform
- optical splitter
- mec
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000003287 optical effect Effects 0.000 claims abstract description 97
- 238000012549 training Methods 0.000 claims abstract description 97
- 238000013507 mapping Methods 0.000 claims description 30
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 12
- 239000000284 extract Substances 0.000 description 7
- 238000003672 processing method Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a data processing apparatus, a method and a storage medium. The apparatus comprises: the system comprises a DPI device, an MEC device, a first optical splitter and a second optical splitter, wherein the first optical splitter is used for receiving service data sent by a terminal and respectively sending the service data to the DPI device and the second optical splitter; the DPI device is used for extracting the service data, acquiring service characteristic data and sending the service characteristic data to the second optical splitter; the second optical splitter is used for sending the service data to the MEC device and sending the service characteristic data to the MEC device; and the MEC device is used for determining a corresponding cloud platform according to the service characteristic data, obtaining training data according to the service data, and sending the training data to the corresponding cloud platform, wherein the cloud platform adopts the training data to train a service model corresponding to the service data. The data processing equipment can effectively provide training data for different cloud platforms, and does not need to manually acquire the training data.
Description
Technical Field
The present application relates to communications technologies, and in particular, to a data processing apparatus, a method, and a storage medium.
Background
For artificial intelligence, data, algorithms and computing power are the three major elements. The combination of the three major elements helps the artificial intelligence technology to play a great role. Among them, the algorithm is an important link and factor. The artificial intelligence technique needs to rely on an algorithm to perform data training and model realization.
Taking image recognition as an example, the general training method is as follows: and acquiring a plurality of images in the data set, inputting the images, training the neural network model by adopting the input images, and finishing the training when the error of the model is converged in a smaller interval finally. The data set is used as a training basis and used for estimating parameters in the model, so that the model can reflect reality, and the more comprehensive the acquired data volume is, the more accurate the training result is.
However, the existing data acquisition method needs to consume a lot of manpower, and training data suitable for different fields cannot be efficiently acquired.
Disclosure of Invention
The application provides data processing equipment, a data processing method and a storage medium, which are used for solving the problems that a large amount of manpower is consumed in the conventional data acquisition method, and training data suitable for different fields cannot be efficiently acquired.
In a first aspect, the present application provides a data processing apparatus comprising: the system comprises a depth message Detection (DPI) device, a Mobile Edge Computing (MEC) device, a first optical splitter and a second optical splitter, wherein the DPI device is respectively connected with the first optical splitter and the second optical splitter, the second optical splitter is respectively connected with the first optical splitter and the MEC device, and the MEC device is connected with a plurality of cloud platforms;
the first optical splitter is configured to receive service data sent by a terminal, and send the service data to the DPI device and the second optical splitter respectively;
the DPI device is used for extracting the service data to obtain service characteristic data and sending the service characteristic data to the second optical splitter;
the second optical splitter is configured to send the service data to the MEC apparatus, and send the service feature data to the MEC apparatus;
the MEC device is used for determining a corresponding cloud platform according to the service characteristic data, obtaining training data according to the service data, and sending the training data to the corresponding cloud platform, wherein the corresponding cloud platform adopts the training data to train a service model corresponding to the service data.
Optionally, the MEC apparatus, when determining the corresponding cloud platform according to the service feature data, is specifically configured to:
acquiring a mapping relation between preset service characteristic data and a cloud platform;
and determining a matched cloud platform according to the mapping relation and the service characteristic data, and taking the matched cloud platform as a corresponding cloud platform.
Optionally, the MEC apparatus, when determining the matched cloud platform according to the mapping relationship and the service feature data, is specifically configured to:
matching preset service characteristic data in the mapping relation with service characteristic data;
and determining the cloud platform corresponding to the preset service characteristic data matched with the service characteristic data as a matched cloud platform.
Optionally, the MEC apparatus, after obtaining training data according to the service data, is specifically configured to:
carrying out format conversion on the service data to obtain converted service data;
and removing redundant data in the converted service data to obtain training data.
In a second aspect, the present application provides a data processing method, including:
receiving service data sent by a terminal;
extracting the service data to obtain service characteristic data;
determining a corresponding cloud platform according to the service characteristic data, and obtaining training data according to the service data;
and sending the training data to the corresponding cloud platform so that the corresponding cloud platform can train the business model corresponding to the business data by adopting the training data.
Optionally, the determining a corresponding cloud platform according to the service feature data includes:
acquiring a mapping relation between preset service characteristic data and a cloud platform;
and determining a matched cloud platform according to the mapping relation and the service characteristic data, and taking the matched cloud platform as a corresponding cloud platform.
Optionally, the determining a matched cloud platform according to the mapping relationship and the service feature data includes:
matching preset service characteristic data in the mapping relation with service characteristic data;
and determining the cloud platform corresponding to the preset service characteristic data matched with the service characteristic data as a matched cloud platform.
Optionally, the obtaining training data according to the service data includes:
carrying out format conversion on the service data to obtain converted service data;
and removing redundant data in the converted service data to obtain training data.
Optionally, the sending the training data to the cloud platform includes:
and receiving the trained service model sent by the cloud platform.
In a third aspect, the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored, and when executed by a processor, the computer-executable instructions are used to implement the method according to the second aspect.
The data processing device, the data processing method and the storage medium provided by the application comprise a Deep Packet Inspection (DPI) device, a Mobile Edge Computing (MEC) device, a first optical splitter and a second optical splitter, wherein the DPI device is respectively connected with the first optical splitter and the second optical splitter, the second optical splitter is respectively connected with the first optical splitter and the MEC device, and the MEC device is connected with a plurality of cloud platforms; the first optical splitter is configured to receive service data sent by a terminal, and send the service data to the DPI device and the second optical splitter respectively; the first optical splitter is configured to receive service data sent by a terminal, and send the service data to the DPI device and the second optical splitter respectively; the DPI device is used for extracting the service data to obtain service characteristic data and sending the service characteristic data to the second optical splitter; the second optical splitter is configured to send the service data to the MEC apparatus, and send the service feature data to the MEC apparatus; the MEC device is used for determining a corresponding cloud platform according to the service characteristic data, obtaining training data according to the service data, and sending the training data to the corresponding cloud platform, the corresponding cloud platform adopts the training data to train a service model corresponding to the service data, and the data processing equipment can effectively provide training data for different cloud platforms without manually collecting the training data.
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 schematic structural diagram of a data processing apparatus provided in the present application;
FIG. 2 is a schematic block diagram of another data processing apparatus provided in the present application;
FIG. 3 is a schematic flow chart of a data processing method provided in the present application;
fig. 4 is a schematic flow chart of another data processing method provided in the present application.
Description of the symbols:
101-DPI device 102-MEC device 103-first beam splitter
104-second splitter 105-communication unit
Specific embodiments of the present application have been shown by way of example in the drawings and will be described in more detail below. The drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the concepts of the application by those skilled in the art with reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application, as detailed in the appended claims.
Taking image recognition as an example, the general training method is as follows: and acquiring a plurality of images in the data set, inputting the images, training the neural network model by adopting the input images, and finishing the training when the error of the model is converged in a smaller interval finally. The data set is used as a training basis for estimating parameters in the model, so that the model can reflect reality, and the more comprehensive the acquired data volume is, the more accurate the training result is.
However, the existing data acquisition method needs a lot of manpower, and training data suitable for different fields cannot be efficiently acquired.
Therefore, aiming at the problems that a large amount of manpower is consumed in a data acquisition method in the prior art, and training data suitable for different fields cannot be efficiently acquired, the inventor finds in research that data processing equipment is provided with a DPI device, an MEC device, a first optical splitter and a second optical splitter, the DPI device is respectively connected with the first optical splitter and the second optical splitter, the second optical splitter is respectively connected with the first optical splitter and the MEC device, and the MEC device is connected with a plurality of cloud platforms; the first optical splitter is used for receiving the service data sent by the terminal and respectively sending the service data to the DPI device and the second optical splitter; the first optical splitter is used for receiving the service data sent by the terminal and respectively sending the service data to the DPI device and the second optical splitter; the DPI device is used for extracting the service data, acquiring service characteristic data and sending the service characteristic data to the second optical splitter; the second optical splitter is used for transmitting the service data to the MEC device and transmitting the service characteristic data to the MEC device; the MEC device is used for determining the corresponding cloud platform according to the service characteristic data, obtaining training data according to the service data and sending the training data to the corresponding cloud platform, the corresponding cloud platform adopts the training data to train a service model corresponding to the service data, and the data processing equipment can effectively provide the training data for different cloud platforms without manually collecting the training data. And the DPI is arranged in the data processing equipment in a parallel mode, the transmission of data cannot be influenced, the service data can be extracted, and the cloud platform needing the service data is determined based on the extracted service characteristic data.
Therefore, the inventor proposes a technical scheme of the embodiment of the invention based on the above creative discovery.
Fig. 1 is a schematic structural diagram of a data processing apparatus provided in the present application.
The data processing device provided by the application comprises: the method comprises the following steps that a DPI device 101, a mobile edge computing MEC device 102, a first optical splitter 103, a second optical splitter 104 and a DPI device 101 are respectively connected with the first optical splitter 103 and the second optical splitter 104, the second optical splitter 104 is respectively connected with the first optical splitter 103 and the MEC device 102, and the MEC device 102 is connected with a plurality of cloud platforms; a first optical splitter 103, configured to receive service data sent by a terminal, and send the service data to the DPI device 101 and the second optical splitter 104 respectively; the DPI device 101 is configured to extract the service data, obtain service characteristic data, and send the service characteristic data to the second optical splitter 104; a second optical splitter 104, configured to send the service data to the MEC apparatus 102, and send the service feature data to the MEC apparatus 102; the MEC device 102 is configured to determine a corresponding cloud platform according to the service feature data, obtain training data according to the service data, and send the training data to the corresponding cloud platform, where the corresponding cloud platform trains a service model corresponding to the service data by using the training data.
Referring to fig. 1, the data processing apparatus includes: DPI device 101, MEC device 102, first beam splitter 103, second beam splitter 104.DPI (Deep Packet Inspection) is a Packet-based Deep Inspection technology, which performs Deep Inspection for different network application layer loads (e.g. HTTP, DNS, etc.). The DPI device 101 is respectively connected to a first optical splitter 103 and a second optical splitter 104, wherein the first optical splitter 103 receives service data sent by a terminal, the first optical splitter 103 sends the service data to the DPI device 101, the DPI device 101 receives the service data sent by the first optical splitter 103, the DPI device 101 extracts the service data to obtain service characteristic data, the DPI device 101 sends the service characteristic data to the second optical splitter 104, and the second optical splitter 104 sends the service characteristic data to the MEC device 102.
The MEC device 102 is further connected to a plurality of cloud platforms, each cloud platform is provided with a different service model, the MEC device 102 receives service characteristic data sent by the second optical splitter 104, the service characteristic data is sent to the second optical splitter 104 by the DPI device 101, and the MEC device 102 determines a corresponding cloud platform according to the service characteristic data. The MEC apparatus 102 is further configured to receive the service data sent by the second optical splitter 104, where the service data is sent by the first optical splitter 103 to the second optical splitter 104.
The DPI device 101 is connected to not only the first optical splitter 103 but also the second optical splitter 104, and the second optical splitter 104 is connected to the first optical splitter 103, so that the DPI device 101 is accessed to the data processing device in a parallel manner, and normal transmission of service data is not affected. The optical splitter is a passive device, also called an optical splitter, which does not require external energy but only needs input light. The beam splitter consists of entrance and exit slits, a mirror and a dispersive element, and has the function of separating out the required resonance absorption lines.
The MEC device 102 is further configured to obtain training data according to the service data, the MEC device 102 is further configured to send the training data to a corresponding cloud platform, and the cloud platform MEC device 102 is determined according to the service feature data.
The cloud platform receives training data sent by the MEC device 102, trains a service model by using the training data to obtain a trained service model, wherein the service model corresponds to the service data one to one, and the service model and the service data belong to the same field.
Optionally, the MEC apparatus 102 determines, according to the service characteristic data, a corresponding cloud platform, and is specifically configured to: acquiring a mapping relation between preset service characteristic data and a cloud platform; and determining a matched cloud platform according to the mapping relation and the service characteristic data, and taking the matched cloud platform as a corresponding cloud platform.
The MEC device 102 is configured to obtain a mapping relationship between preset service characteristic data and a cloud platform, the MEC device 102 is configured to determine a matched cloud platform according to the mapping relationship and the service characteristic data, different cloud platforms store different service models, and a cloud platform corresponding to the service data needs to be found for the service data, so that the cloud platform performs model training by using the service data, and the MEC device 102 is configured to use the matched cloud platform as the corresponding cloud platform.
Optionally, the MEC apparatus 102, when determining the matched cloud platform according to the mapping relationship and the service feature data, is specifically configured to: matching preset service characteristic data in the mapping relation with the service characteristic data; and determining the cloud platform corresponding to the preset service characteristic data matched with the service characteristic data as the matched cloud platform.
The MEC device 102 is configured to match preset service feature data in the mapping relationship with the service feature data, the MEC device 102 is configured to determine a matched cloud platform according to a matching result, specifically, the MEC device 102 is configured to determine a cloud platform corresponding to the preset service feature data matched with the service feature data as the matched cloud platform, and use the matched cloud platform as a target sending object of the service data.
Optionally, the MEC apparatus 102, after obtaining the training data according to the service data, is specifically configured to: carrying out format conversion on the service data to obtain converted service data; and removing redundant data in the converted service data to obtain training data.
The MEC device 102 is configured to process the service data, and mainly includes format conversion and redundancy processing, the MEC device 102 is configured to perform format conversion on the service data to obtain converted service data, the MEC device 102 is further configured to remove redundant data in the converted service data to obtain training data, and the training data is used as training data for model training of a relevant cloud platform.
The data processing equipment can extract the received service data to obtain service characteristic data, the corresponding cloud platform is determined according to the service characteristic data, the training data obtained based on the service data are sent to the cloud platform, the data processing equipment can effectively provide training data for different cloud platforms, and training data do not need to be collected manually. And the DPI is arranged in the data processing equipment in a parallel mode, the transmission of data cannot be influenced, the service data can be extracted, and the cloud platform needing the service data is determined based on the extracted service characteristic data.
Fig. 2 is a schematic structural diagram of a data processing apparatus provided in the present application.
The data processing device provided by the application further comprises: the communication unit 105, the communication unit 105 is connected to the first optical splitter 103, and the first optical splitter 103 is configured to receive the service data sent by the terminal, specifically: the first optical splitter 103 receives traffic data transmitted by the terminal through the communication unit 105.
The MEC apparatus 102 further includes a communication unit 105, the communication unit 105 is connected to the first optical splitter 103, the first optical splitter 103 receives service data sent by the terminal through the communication unit 105, the communication unit 105 may be in a wired or wireless form, and for the wired form of the communication unit 105, the communication unit includes a Broadband Access Server and a service router, where the Broadband Access Server is a BRAS (Broadband Remote Access Server), and is a new Access gateway for Broadband network applications. The Service Router is SR (Service Router), and is a full Service Router. The communication unit 105 in a wireless form includes a base station and a UPF (User Plane Function) device, wherein the UPF is a User Plane Function entity.
The first optical splitter 103 sends the service data to the DPI device 101, the DPI device 101 receives the service data sent by the first optical splitter 103, the DPI device 101 extracts the service data to obtain service characteristic data, and the DPI device 101 sends the service characteristic data to the second optical splitter 104. The DPI device 101 is connected to not only the first optical splitter 103 but also the second optical splitter 104, and the second optical splitter 104 is connected to the first optical splitter 103, so that the DPI device 101 is connected to the data processing equipment in a parallel manner, and normal transmission of the service data is not affected. The MEC device 102 is further configured to obtain training data according to the service data, the MEC device 102 is further configured to send the training data to a corresponding cloud platform, and the cloud platform MEC device 102 is determined according to the service feature data. The cloud platform receives training data sent by the MEC device 102, trains a business model by the training data to obtain a trained business model, wherein the business model corresponds to the business data one to one, and the business model and the business data belong to the same field.
The data processing equipment can extract the received service data sent by the terminal to obtain service characteristic data, determine a corresponding cloud platform according to the service characteristic data, and send training data obtained based on the service data to the cloud platform, and the data processing equipment can provide the training data for the cloud platform, wherein the DPI is arranged in the data processing equipment in a parallel mode, so that the transmission of the data cannot be influenced, the service data can be extracted, and the cloud platform needing the service data is determined based on the extracted service characteristic data.
Fig. 3 is a schematic flowchart of a data processing method provided in the present application, and the method is applied to a data processing device.
In this embodiment, a data processing device receives service data sent by a terminal, and specifically, the data processing device is provided with a DPI device, an MEC device, a first optical splitter and a second optical splitter, where the DPI device is connected to the first optical splitter and the second optical splitter respectively, the second optical splitter is connected to the first optical splitter and the MEC device respectively, the MEC device is connected to a plurality of cloud platforms, and the data processing device receives the service data sent by the terminal by using the first optical splitter.
In this embodiment, the data processing device extracts the service data to obtain service feature data, and the data processing device extracts the service data by using a DPI device.
In this embodiment, the data processing device determines a corresponding cloud platform according to the service feature data, the data processing device is connected to the plurality of cloud platforms, and each cloud platform sets a different service model. Specifically, the data processing equipment adopts a DPI device to determine a corresponding cloud platform according to the service characteristic data.
And 304, sending the training data to the corresponding cloud platform so that the corresponding cloud platform can train the business model corresponding to the business data by adopting the training data.
In this embodiment, the data processing device sends the training data to the cloud platform, and specifically, the data processing device sends the training data to the cloud platform by using a DPI device. The cloud platform receives training data sent by the data processing equipment, the cloud platform trains the service model by adopting the training data to obtain a trained service model, wherein the service model corresponds to the service data one by one, and the service model and the service data belong to the same field.
Fig. 4 is a schematic flowchart of another data processing method provided in the present application, where the method is applied to a data processing device, and as shown in fig. 4, the method includes:
In this embodiment, step 401 and step 301 have the same technical features, and the detailed description may refer to step 301, which is not described herein again.
In this embodiment, step 402 and step 302 have the same technical features, and the detailed description may refer to step 302, which is not described herein again.
And 403, determining a corresponding cloud platform according to the service characteristic data, and obtaining training data according to the service data.
In a possible implementation manner, determining a matched cloud platform according to the mapping relationship and the service feature data includes:
step 4031, a mapping relation between the preset service characteristic data and the cloud platform is obtained.
In this embodiment, the data processing device obtains a preset mapping relationship between service characteristic data and cloud platforms, where the service characteristic data corresponds to the cloud platforms one to one, where different cloud platforms store different service models, and a cloud platform corresponding to the service data needs to be found for the service data, so that the cloud platform performs model training by using the service data.
Step 4032, the matched cloud platform is determined according to the mapping relation and the service characteristic data, and the matched cloud platform is used as a corresponding cloud platform.
In this embodiment, the data processing device matches preset service characteristic data in the mapping relationship with the service characteristic data, and the data processing device determines a matched cloud platform according to a matching result.
Optionally, determining a matched cloud platform according to the mapping relationship and the service feature data includes:
matching preset service characteristic data in the mapping relation with the service characteristic data; and determining the cloud platform corresponding to the preset service characteristic data matched with the service characteristic data as the matched cloud platform.
In this embodiment, the data processing device determines a cloud platform corresponding to preset service characteristic data matched with the service characteristic data as a matched cloud platform, and the data processing device uses the matched cloud platform as a target sending object of the service data.
In one possible implementation, obtaining training data according to the traffic data includes:
step 403a, performing format conversion on the service data to obtain converted service data.
In this embodiment, the processing of the service data mainly includes format conversion and redundancy processing, and the data processing device performs format conversion on the service data to obtain converted service data.
And step 403b, removing redundant data in the converted service data to obtain training data.
In this embodiment, the data processing device removes redundant data in the converted service data to obtain training data, and the training data is used as training data for model training of a relevant cloud platform.
In this embodiment, step 404 and step 304 have the same technical features, and the detailed description may refer to step 304, which is not described herein again.
In this embodiment, the cloud platform receives training data sent by the data processing device, the cloud platform trains the service model by using the training data to obtain the trained service model, the cloud platform feeds back the trained service model, and the data processing device receives the trained service model sent by the cloud platform, so as to process related services. And the cloud platform sends the trained service model to the corresponding cloud platform.
The data processing equipment can extract the received service data to obtain service characteristic data, the corresponding cloud platform is determined according to the service characteristic data, the training data obtained based on the service data are sent to the cloud platform, the data processing equipment can effectively provide training data for different cloud platforms, and training data do not need to be collected manually.
In an exemplary embodiment, a computer-readable storage medium is also provided, in which computer-executable instructions are stored, and the computer-executable instructions are executed by a processor to perform the method in any one of the above embodiments.
In an exemplary embodiment, a computer program product is also provided, comprising a computer program for execution by a processor of the method in any of the above embodiments.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A data processing apparatus, characterized in that the apparatus comprises: the system comprises a depth message Detection (DPI) device, a Mobile Edge Computing (MEC) device, a first optical splitter and a second optical splitter, wherein the DPI device is respectively connected with the first optical splitter and the second optical splitter, the second optical splitter is respectively connected with the first optical splitter and the MEC device, and the MEC device is connected with a plurality of cloud platforms;
the first optical splitter is configured to receive service data sent by a terminal, and send the service data to the DPI device and the second optical splitter respectively;
the DPI device is used for extracting the service data to obtain service characteristic data and sending the service characteristic data to the second optical splitter;
the second optical splitter is configured to send the service data to the MEC apparatus, and send the service feature data to the MEC apparatus;
the MEC device is used for determining a corresponding cloud platform according to the service characteristic data, obtaining training data according to the service data, and sending the training data to the corresponding cloud platform, wherein the corresponding cloud platform adopts the training data to train a service model corresponding to the service data.
2. The device according to claim 1, wherein the MEC apparatus, when determining the corresponding cloud platform according to the service feature data, is specifically configured to:
acquiring a mapping relation between preset service characteristic data and a cloud platform;
and determining a matched cloud platform according to the mapping relation and the service characteristic data, and taking the matched cloud platform as a corresponding cloud platform.
3. The device according to claim 2, wherein the MEC apparatus, in determining the matched cloud platform according to the mapping relationship and the service feature data, is specifically configured to:
matching preset service characteristic data in the mapping relation with service characteristic data;
and determining the cloud platform corresponding to the preset service characteristic data matched with the service characteristic data as a matched cloud platform.
4. The apparatus according to claim 1, wherein the MEC device, when obtaining training data according to the service data, is specifically configured to:
carrying out format conversion on the service data to obtain converted service data;
and removing redundant data in the converted service data to obtain training data.
5. A method of data processing, the method comprising:
receiving service data sent by a terminal;
extracting the service data to obtain service characteristic data;
determining a corresponding cloud platform according to the service characteristic data, and obtaining training data according to the service data;
and sending the training data to the corresponding cloud platform so that the corresponding cloud platform can train the business model corresponding to the business data by adopting the training data.
6. The method of claim 5, wherein determining the corresponding cloud platform from the business feature data comprises:
acquiring a mapping relation between preset service characteristic data and a cloud platform;
and determining a matched cloud platform according to the mapping relation and the service characteristic data, and taking the matched cloud platform as a corresponding cloud platform.
7. The method of claim 6, wherein determining the matching cloud platform according to the mapping relationship and the business feature data comprises:
matching preset service characteristic data in the mapping relation with service characteristic data;
and determining the cloud platform corresponding to the preset service characteristic data matched with the service characteristic data as a matched cloud platform.
8. The method of claim 5, wherein the obtaining training data according to the traffic data comprises:
carrying out format conversion on the service data to obtain converted service data;
and removing redundant data in the converted service data to obtain training data.
9. The method according to any one of claims 5 to 8, wherein after sending the training data to the corresponding cloud platform, further comprising:
and receiving the trained service model sent by the corresponding cloud platform.
10. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, are configured to implement the method of any one of claims 5 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211666005.9A CN115766489A (en) | 2022-12-23 | 2022-12-23 | Data processing apparatus, method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211666005.9A CN115766489A (en) | 2022-12-23 | 2022-12-23 | Data processing apparatus, method and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115766489A true CN115766489A (en) | 2023-03-07 |
Family
ID=85347358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211666005.9A Pending CN115766489A (en) | 2022-12-23 | 2022-12-23 | Data processing apparatus, method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115766489A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108683901A (en) * | 2018-05-10 | 2018-10-19 | Oppo广东移动通信有限公司 | A kind of data processing method, MEC servers and computer readable storage medium |
| CN111242710A (en) * | 2018-11-29 | 2020-06-05 | 北京京东尚科信息技术有限公司 | Business classification processing method and device, service platform and storage medium |
| CN113032440A (en) * | 2021-03-18 | 2021-06-25 | 上海数禾信息科技有限公司 | Data processing method and device for training risk model |
| CN114019921A (en) * | 2021-11-01 | 2022-02-08 | 碳纪科技(北京)有限公司 | Production line equipment control method, device, equipment and medium based on combined model |
| CN114185657A (en) * | 2021-12-08 | 2022-03-15 | 推想医疗科技股份有限公司 | Task scheduling method and device of cloud platform, storage medium and electronic equipment |
| CN114970761A (en) * | 2022-06-22 | 2022-08-30 | 中国电信股份有限公司 | Model training method, device and system |
| CN115344690A (en) * | 2021-11-30 | 2022-11-15 | 中国银联股份有限公司 | Data processing method and device for business problems |
-
2022
- 2022-12-23 CN CN202211666005.9A patent/CN115766489A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108683901A (en) * | 2018-05-10 | 2018-10-19 | Oppo广东移动通信有限公司 | A kind of data processing method, MEC servers and computer readable storage medium |
| CN111242710A (en) * | 2018-11-29 | 2020-06-05 | 北京京东尚科信息技术有限公司 | Business classification processing method and device, service platform and storage medium |
| CN113032440A (en) * | 2021-03-18 | 2021-06-25 | 上海数禾信息科技有限公司 | Data processing method and device for training risk model |
| CN114019921A (en) * | 2021-11-01 | 2022-02-08 | 碳纪科技(北京)有限公司 | Production line equipment control method, device, equipment and medium based on combined model |
| CN115344690A (en) * | 2021-11-30 | 2022-11-15 | 中国银联股份有限公司 | Data processing method and device for business problems |
| CN114185657A (en) * | 2021-12-08 | 2022-03-15 | 推想医疗科技股份有限公司 | Task scheduling method and device of cloud platform, storage medium and electronic equipment |
| CN114970761A (en) * | 2022-06-22 | 2022-08-30 | 中国电信股份有限公司 | Model training method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111082997B (en) | Network function arrangement method based on service identification in mobile edge computing platform | |
| CN112784718A (en) | Insulator state identification method based on edge calculation and deep learning | |
| CN107516063A (en) | Method based on cloud branch server recognition of face | |
| CN111476376B (en) | Alliance learning method, alliance learning device and alliance learning system | |
| CN112989894B (en) | Target detection method, task processing method, device, equipment and storage medium | |
| CN109286506B (en) | Method, system and device for charging flow | |
| CN108683901B (en) | Data processing method, MEC server and computer readable storage medium | |
| CN106649829A (en) | Method and device for processing business based on palmprint data | |
| CN114492739A (en) | Federal learning method based on Internet of vehicles, roadside unit, vehicle node and base station | |
| CN114494916A (en) | Black-neck crane monitoring and tracking method based on YOLO and DeepsORT | |
| CN114268967A (en) | Unmanned aerial vehicle-assisted mobile edge network user matching method and device | |
| CN113839838A (en) | Business type identification method for federal learning based on cloud edge cooperation | |
| CN113660687A (en) | Network difference cell processing method, device, equipment and storage medium | |
| CN111600929B (en) | Transmission line detection method, routing strategy generation method and proxy server | |
| CN115766489A (en) | Data processing apparatus, method and storage medium | |
| CN102595467A (en) | Data acquisition method and data acquisition device | |
| CN108768584A (en) | The method, apparatus and system of a kind of data compression, decompression | |
| CN112596894B (en) | Tracking method and device based on edge calculation | |
| CN110059146B (en) | Data acquisition method, server, computing equipment and storage medium | |
| Lee et al. | Timely update probability analysis of blockchain ledger in UAV-assisted data collection networks | |
| CN106652137A (en) | WIFI-based scenic spot entrance guard examination system and use method thereof | |
| CN109558839A (en) | Adaptive face identification method and the equipment and system for realizing this method | |
| CN114531193B (en) | Bridge state monitoring method based on unmanned aerial vehicle cellular topology networking and mobile edge calculation | |
| CN109673038A (en) | A kind of recognition methods of the mobile terminal brand and model based on IFAT fingerprint | |
| CN111127313B (en) | Face sketch conversion method and related products |
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 |