CN106210073A - There is the network service platform of self-learning function - Google Patents

Abstract

The invention discloses a kind of network service platform with self-learning function, including: partition security domain unit: buffer zone is divided into network domains, command field and user domain, network flow velocity allocation unit: set up classification and process inquiry list and store；Storage element: be used for storing data；Indexing units: be used for preserving the keyword of storage element storage data, and provide the user search service；Control unit: according to the user instruction received, user is grouped；Download unit, data file piecemeal to storage element request particular range, customer flow timing unit, time threshold is set, between when reached during threshold value, transmission order to control unit, data redundancy administrative unit: to the data redundancy management preserved in storage element, the data of user domain and command field are sampled by control unit, draw the download preference of user.Reach to provide the purpose of quick and cheap network service.

Description

There is the network service platform of self-learning function

Technical field

The present invention relates to network data field, in particular it relates to a kind of network service platform with self-learning function.

Background technology

At present, along with the development of the Internet, network has become as the pith of people's life, but in some public fields Close, as on waiting hall, workman apartment and train not wifi cover, it is the most to add user, and Internet service provider provides 3G or 4G network service can be slow, and 3G or the 4G network service price comparison that Internet service provider provides is expensive.

Summary of the invention

It is an object of the invention to, for the problems referred to above, propose a kind of network service platform with self-learning function, with Realize the advantage providing the user quick and cheap network service.

For achieving the above object, the technical solution used in the present invention is:

A kind of network service platform with self-learning function, including:

Partition security domain unit: buffer zone is divided into network domains, command field and user domain, described network domains is used for network Data update in storage element, and described user domain provides the user data download service, and described command field is used for receiving user Request command；

Network flow velocity allocation unit: set up classification and process inquiry list and store, this classification processes inquiry list according to network eventually The ID of end and the instruction of controller are by user grouping, and different packets arranges different flow threshold values；

Storage element: be used for storing data；

Indexing units: be used for preserving the keyword of storage element storage data, and provide the user search service；

Control unit: according to the user instruction received, user is grouped, and packet instruction is issued to the distribution of network flow velocity Unit, and according to data traffic, the network domains in buffer zone and user domain size are dynamically adjusted；

Download unit: specific to storage element request for transmitting the Search Results come and respective stored address according to indexing units The data file piecemeal of scope；

Customer flow timing unit: time threshold is set, when reached between threshold value time, transmission order to control unit, controls single By the zeros data in user domain after the order of unit's reception customer flow timing unit；

Data redundancy administrative unit: to the data redundancy management preserved in storage element, and redundant data is deleted；

The data of user domain and command field are sampled by control unit, thus set up training sample, then utilize BP nerve net Training sample is trained by network method, thus sets up BP neural network model, and control unit obtains according to BP neural network model Go out the download preference of user, thus go search for the data relevant to the download preference of user on network and relevant data downloaded To network domains, finally preserve to storage element for user's download.

Technical scheme has the advantages that

Technical scheme, by providing a kind of LAN, in advance by the hot spot data on network, such as TV play, little The locally downloading storage such as say, then provide the user LAN services, because of time locally downloading, it is only necessary to use primary network The service of operator, thus cheap, and build LAN, the transmission speed of network can be improved, thus reach to provide fast The purpose of fast and cheap network service.

Detailed description of the invention

A kind of network service platform with self-learning function, including: partition security domain unit: buffer zone is divided into Network domains, command field and user domain, described network domains is used for updating in storage element by network data, and described user domain is for using Family provides data download service, and described command field is used for receiving the request command of user；

Network flow velocity allocation unit: set up classification and process inquiry list and store, this classification processes inquiry list according to network eventually The ID of end and the instruction of controller are by user grouping, and different packets arranges different flow threshold values；

Storage element: be used for storing data；

Indexing units: be used for preserving the keyword of storage element storage data, and provide the user search service；

Control unit: according to the user instruction received, user is grouped, and packet instruction is issued to the distribution of network flow velocity Unit, and according to data traffic, the network domains in buffer zone and user domain size are dynamically adjusted；

Download unit: specific to storage element request for transmitting the Search Results come and respective stored address according to indexing units The data file piecemeal of scope；

Customer flow timing unit: time threshold is set, when reached between threshold value time, transmission order to control unit, controls single By the zeros data in user domain after the order of unit's reception customer flow timing unit；

Data redundancy administrative unit: to the data redundancy management preserved in storage element, and redundant data is deleted；

The data of user domain and command field are sampled by control unit, thus set up training sample, then utilize BP nerve net Training sample is trained by network method, thus sets up BP neural network model, and control unit obtains according to BP neural network model Go out the download preference of user, thus go search for the data relevant to the download preference of user on network and relevant data downloaded To network domains, finally preserve to storage element for user's download.

Buffer zone is divided into network domains, command field and user domain by partition security domain unit, guarantee data security Meanwhile, further speed up the transmission speed of data, data upload and download is required for through buffer zone, network domains be used for connect Receiving the data downloaded from network, the data that network domains is downloaded need the filtration through antivirus software and fire wall, to ensure number According to safety, the safest data are just transferred to storage element from network domains, and command field is used for receiving the order of user, order The data that territory receives also will be through antivirus software and the filtration of fire wall, and user domain provides only download service, does not receive any Data, therefore need not move through the filtration of antivirus software and fire wall, thus improve the transfer rate of data.

Finally it is noted that the foregoing is only the preferred embodiments of the present invention, it is not limited to the present invention, Although being described in detail the present invention with reference to previous embodiment, for a person skilled in the art, it still may be used So that the technical scheme described in foregoing embodiments to be modified, or wherein portion of techniques feature is carried out equivalent. All within the spirit and principles in the present invention, any modification, equivalent substitution and improvement etc. made, should be included in the present invention's Within protection domain.

Claims (1)

1. a network service platform with self-learning function, it is characterised in that including:

Partition security domain unit: buffer zone is divided into network domains, command field and user domain, described network domains is used for network Data update in storage element, and described user domain provides the user data download service, and described command field is used for receiving user Request command；

Network flow velocity allocation unit: set up classification and process inquiry list and store, this classification processes inquiry list according to network eventually The ID of end and the instruction of controller are by user grouping, and different packets arranges different flow threshold values；

Storage element: be used for storing data；

Indexing units: be used for preserving the keyword of storage element storage data, and provide the user search service；

Control unit: according to the user instruction received, user is grouped, and packet instruction is issued to the distribution of network flow velocity Unit, and according to data traffic, the network domains in buffer zone and user domain size are dynamically adjusted；

Download unit: specific to storage element request for transmitting the Search Results come and respective stored address according to indexing units The data file piecemeal of scope；

Customer flow timing unit: time threshold is set, when reached between threshold value time, transmission order to control unit, controls single By the zeros data in user domain after the order of unit's reception customer flow timing unit；

Data redundancy administrative unit: to the data redundancy management preserved in storage element, and redundant data is deleted；

The data of user domain and command field are sampled by control unit, thus set up training sample, then utilize BP nerve net Training sample is trained by network method, thus sets up BP neural network model, and control unit obtains according to BP neural network model Go out the download preference of user, thus go search for the data relevant to the download preference of user on network and relevant data downloaded To network domains, finally preserve to storage element for user's download.