WO2018053831A1

WO2018053831A1 - Method and device for providing targeting content

Info

Publication number: WO2018053831A1
Application number: PCT/CN2016/100091
Authority: WO
Inventors: Qiang He; Wenchao Ma; Gao Zhang
Original assignee: Thomson Licensing
Priority date: 2016-09-26
Filing date: 2016-09-26
Publication date: 2018-03-29

Abstract

It is provided a method for providing targeting content items from a gateway to user devices, the method comprising at a gateway: determining user behavior information including content types and corresponding number of occurrence times of content types based on data that comprises keywords and is sent by the user device but not destined to the gateway and information on a corresponding relationship between content types and corresponding keywords; determining at least one content type based on number of occurrence times based on user behavior information; receiving content items, each of which is associated with one or more content types; and sending content items, whose one or more content types overlaps with the at least one type to the user device.

Description

METHOD AND DEVICE FOR PROVIDING TARGETING CONTENT

TECHNICAL FIELD

The present disclosure relates to data processing, and particularly relates to a method and a device for providing targeting content.

BACKGROUND

Nowadays the advertising system over the Internet has several of broadcast or multicast methods, which can be found in the private or public places like end-user home or cafe shop. In the end-user home scenario, people can watch various advertisements via Internet Television, personal computer and other kinds of terminals, such as tablet, smart phone etc.

On the server side, the advertisements are offered by an Operator, from which the operator floods advertisements to the end users. That is, the advertisements are sent to the end users’screen indiscriminately, because the operator has no idea about differences between the end users (e.g. age, gender, job background, daily interest, or potential purchase needs) .

On the user or client side, there are privacy concerns that can restrict the operator’s collection and storage of end users’ private data, such as data on personal interest and surfing history.

In current situation, due to the lack of specific targeting information, the operator is only able to flood the advertisement content to various large groups of users. And the end users are not able to choose to watch the content he is interested in. The result can be wasted effort for the operator as it has no idea who is the targeting audience for a specific advertisement content.

SUMMARY

According to an aspect of the present disclosure, it is provided a method for providing targeting content items from a gateway to user devices, the method comprising at a gateway: determining user behavior information including content types and corresponding number of occurrence times of content types based on data that comprises keywords and is sent by the user device but not destined to the gateway and information on a corresponding relationship between content types and corresponding keywords (302) ； determining at least one content type based on number of occurrence times based on user behavior information (303) ； receiving content items, each of which is associated with one or more content types (305) ； and sending content items, whose one or more content types overlaps with the at least one type to the user device (306) .

According to another aspect of present disclosure, it is provided a gateway for providing targeting content items to user devices, comprising a first interface, a second interface and a processor, wherein for one of the user devices, the processor (201) is used for determining user behavior information including content types and corresponding number of occurrence times of content types based on data that comprises keywords and is sent by the user device but not destined to the gateway and information on a corresponding relationship between content types and corresponding keywords； and determining at least one content type based on number of occurrence times based on user behavior information； the first interface (202) is used for receiving content items, each of which is associated with one or more content types； and the second interface (203) is used for sending content items, whose one or more content types overlaps with the at least one type to the user device.

It is to be understood that more aspects and advantages of the invention will be found in the following detailed description of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, will be used to illustrate an embodiment of the invention, as explained by the description. The invention is not limited to the embodiment.

In the drawings:

Fig. 1 is a system diagram according to an embodiment of present disclosure；

Fig. 2 is a block diagram of an exemplary gateway according to an embodiment of the present disclosure；

Fig. 3 is a flow chart describing a method for providing targeting advertising item in accordance with the embodiment of present disclosure.

DETAILED DESCRIPTION

The embodiment of the present invention will now be described in detail in conjunction with the drawings. In the following description, some detailed descriptions of known functions and configurations may be omitted for clarity and conciseness.

A method for providing targeting content for every end user based on automatically collected end user’s behavior is desired without exposing privacy data of the end user to the operator.

In an embodiment of present disclosure, the method is implemented on a home gateway, which is an intermediate device between the operator and the end users, and uses ads as the targeting content. The embodiment contains three parts:

a) The ad operator needs to establish the advertising keywords classification category that depends on the content types of advertisement from advertising companies. For example, food type (steak, vegetables, drinks, etc. ) , travel type (hotel, ticket, booking sites, etc. ) ...., etc.

b) The home gateway at user’s home can use several methods (e.g. URL resolution) to learn the end-user’s behavior of using the internet, with the embedded self-learning mechanism, then the gateway can “know” and “remember” what is user looking for and what is his interested area. The learning processing can use the BP (Back Propagation) algorithm so that the data can be updated on time and grow with accuracy. Herein, BP algorithm is a common method of training artificial neural networks used in connection with an optimization method such as gradient descent.

c) When the operator starts to broadcast an advertisement, a server on operator’s side firstly sends out the notification signal to the gateway. When the gateway receives the notification, the gateway replies with an alive status and asks the server to send the classification category. Then the server sends the latest classification category to the gateway. The gateway generates and sends a predetermined number of topping types (e.g. top 10) for each user connecting to the gateway based on the classification category and collected user data. After the server receives the top 10 types from the gateway, it broadcasts the matched content to the end-user via the gateway. By using these matching methods, the operator can more precisely find the targeting audience for the specific advertiser, and the end-user also benefits from this because he can watch the advertisement that can arise his interests.

Since privacy network information analysis and information matching are conducted in the gateway, and no private data is sent to or stored in the server, it prevents leaking end-user's private information.

Fig. 1 is a system diagram according to an embodiment of present disclosure.

The user side includes a mobile device 101, a personal computer (PC) 102, a tablet 103, and a gateway 104. The mobile device 101 and the tablet 103 connect to the gateway 104 through wireless connection (wireless interface) , e.g. IEEE 802.11. The PC 102 connects to the gateway 104 through either wireless connection e.g. IEEE 802.11 or wired connection, e.g. Ethernet connection (RJ-45 interface/port) . The gateway 104 connects to the Internet through wired connection, e.g. DSL, PON (passive optical network) , RJ-45 port, EPON, GPON, Wi-Fi (IEEE 802.11) etc. Note that the diagram is for illustrative purpose, and at the user side the number of devices connecting to the gateway 104 is arbitrary and is not limited to three.

At the remote side, it includes a server 105 for providing advertisement. The server connects to the Internet, too. It shall note that the diagram is for illustrative purpose, and there can be more devices and servers at the remote side.

The following will describe the server, the gateway, and the end user device one by one.

THE SERVER

The ad operator sells advertising services to companies who want to advertise or some advertising companies. So the advertisement is in different content types or content categories, e.g. food, sport utility, women clothes, baby care, insurance, travel, etc. The ad operator needs to classify the advertisement into categories and stores the categories and content of the advertisement in the server. Below is an example of ads-classified-type-table. Each record includes an advertising item (which can be in the form of video, text, photo etc. ) , the company that is associated with the advertising item, the type to which the advertising item belongs and relevant keywords. Note that this table is only for illustrative purpose, and a person skilled in the art can change its organization, for example, cancelling the columns of company and type, and move them to another table. Herein, the purpose of the table is used as reference information for the user devices to detect the occurrence or existence of keywords in behavior information of user devices (e.g. URL etc. ) , and then use the occurrence of keywords to decide the occurrence times of the types. Or, in other words, the table is to detect occurrence times of the types based on keywords associated with the types.

Table 1: ads-classified-type-table

Further, when the ad operator receives new advertising item, it needs to update this table.

THE GATEWAY

Fig. 2 is a block diagram of an exemplary gateway according to an embodiment of the present disclosure.

It includes at least one microprocessor (MPC) or processor 201, at least one first link interface 202, at least one second link interface 203, a power supplier 204, a volatile storage 205 and a non-volatile storage 206.

The MPC 201 is used to process program instructions stored on the non-volatile storage 206.

The first link interface 202 is used to receive and send data from and to the Internet. Its type comprises Ethernet transceiver, DSL transceiver, Wi-Fi transceiver, ONU (optical network unit) or ONT (optical network terminal) etc.

The second link interface 203 is used to receive and send data from and to user devices, e.g. the mobile device 101, the PC 102, the tablet 103 in the Fig. 1. Its type comprises Ethernet transceiver, Wi-Fi transceiver etc.

The power supplier 204 is used to supply power to all modules of the gateway. It usually converts alternating current to a 5 V direct current.

The volatile storage 205 is used to store temporary data. In implementations, it can use volatile random access memory (RAM) , e.g. SDRAM.

The non-volatile storage 206 is used to store data and program instructions, which remain in the non-volatile storage 306 if it is not powered. In implementations, it can use read only memory (ROM) , flash etc. As to flash, it can use NOR flash and NAND flash.

According to the implementation requirements, the gateway optionally may further include at least one of a Bluetooth transceiver, a ZigBee transceiver, a USB port, a USB/SD/MMC port for storage expansion, a LED indicator for indicating the status of a certain function, a physical button on the gateway body to enable and disable a certain function, a display for displaying information, and a display port for connecting to a display in order for displaying information.

The gateway is used to perform following actions. Fig. 3 is a flow chart describing a method for providing targeting advertising item in accordance with the embodiment of present disclosure.

In the step 301, the gateway receives and stores the latest ads-classified-type-table from the server. It shall note that the information in the table can be organized in other format or form, e.g. xml file etc.

In the step 302, the gateway detects and stores behavior information of the user device for each user device based on data (e.g. URLs) sent by each user device. Herein, the data is not destined to the gateway and can be understood in terms of intelligibility on the data content. The detection of the behavior information can be implemented by using the basic URL resolution to obtain the searching content keyword to accumulate characteristic or profile for each user device. Concerning the URL resolution as example when a user device surfs on an online shopping web site, such as taobao. com, and inputs search key word “sport shoes” , the user device sends the following HTTP URL to taobao. com, and the gateway can detect such HTTP URL.https: //s. taobao. com/search？ q＝sports+shoes&imgfile＝&commend＝all&ssid＝s5- e&search_type＝item&sourceId＝tb. index&spm＝a21bo. 50862.201856-taobao- item. 1&ie＝utf8&initiative_id＝tbindexz_20160720. In this URL, the search pattern is used to filter out the user query content is “q＝sports+shoes” , search type is “search_type＝item” . With this information, the gateway knows this user is looking for a sports shoe. Taking another website as example, when the user is searching something in a search engine, such as searching a fast food restaurant nearby in baidu. com , the URL may take the form: https: //www. baidu. com/s？ wd＝fast％20food&rsv_spt＝1&rsv_iqid＝0xecc876a70001758d &issp＝1&f＝8&rsv_bp＝1&rsv_idx＝2&ie＝utf- 8&rqlang＝cn&tn＝baiduhome_pg&rsv_enter＝1&oq＝％E9％BD％BF％E7％A7％91&rsv _t＝1a3bo3％2FFuVQNI2li4uS0m8Kiax％2BbBtVkQ5bIvq4UC1ogW95Jtkh8Fb98HeV x72dCnYMZ&rsv_sug3＝25&rsv_sug1＝25&rsv_sug7＝100&rsv_pq＝dd7959fd000173d 7&bs＝％E9％BD％BF％E7％A7％91 And in this URL, the gateway can filter out the word : ‘s？ wd＝fast％20food’ , and then the gateway knows that the user is searching the fast food.

As to implementation on keywords filtering, the gateway can use the URL filter extension under Netfilter (Netfilter is a frame provided by the Linux kernel that allows various networking-related operations to be implemented in the form of customized handlers) to achieve this goal, because all HTTP packages are processed in the Netfilter in the gateway. With the URL filter extension, the gateway can filter out the required value, detailed using steps shown as below:

1) : the gateway enables the urlfilter module in the kernel；

2) : the gateway uses the defined key words to generate required filter iptable rules. Herein, the defined key words refer to key words in the received ads-classified-type-table；

3) : when the Internet packages passes through the gateway, the gateway will capture the package. Also, Netfilter does match-filter work with the pre-defined rule, such as detecting occurrence and occurrence times of key words.

Every time the gateway detects occurrence of some key words, the gateway updates the user interest table. An example of the user interest table is shown below. Herein, the access device Mac is used to uniquely identify the user device. And once a key word is detected, the value weight of the type corresponding to the key word is increased with 1.

Access Device Mac	Type	Value Weight
00 : 01 : 5e : 44 : 33 : ff	Food	8
00 : 01 : 53 : qq : cc : ee	Sports Utility	4
00 : 01 : 5e : 44 : 33 : ff	Travel	1

Table 2: user interest table

In the step 303, the gateway decides at least one type for each user device based on the stored behavior information, that is, the user interest table in the above example. In one example, the at least one type is determined based on the value weight, i.e. number of occurrence times.

When the gateway “knows” what is the user’s potential interests are by “learning” from the user’s searching content, the next step is information exchange with the operator. Thus, the operator can send the specific type of advertisement that really interests the user, instead of flooding all types of advertisements to the user. For example, on the operator side, it provides advertising services 10 companies, and the advertisement type includes food, sports, cloth, makeup, travel, cars, baby care, education etc. For a user device A, the gateway decides the top 3 interest types are food, travel and sports. For a user device B, the top 3 interest types are education, car and clothing.

In the step 304, the gateway sends the at least one type to the server for each user device. Herein, in one example, the transmission of the at least one type can be triggered upon a request from the server. In another example, the transmission is carried out periodically. Further in one example, the gateway does not send the at least one type for all user devices, but instead it only sends the at least one type for some chosen user devices. The at least one type is chosen based on number of occurrence times in a large to small order (i.e. descending order) .

Herein, in an example, when the operator needs to send the advertisement to the user, the gateway notifies the operator by sending an active notification that for user device A including the unique identifier and decided types (food, travel, sports) . After the gateway sends the notification to the operator, the operator sends advertising items of the relevant type to the gateway.

In another variant, the step 304 is redundant and can be cancelled. The gateway does not send the at least one type. It just passively receives all advertising items and forwards those items that meet the type requirements for each user device.

In the step 305, the gateway receives the advertising items, each of which is associated with at least one type, from the server.

In the step 306, the gateway forwards, for each user device, the advertising items based on the decided at least one type. Since the advertising item can be associated with one or more types, if the associated one or more types overlaps with (match or partially match) the at least one type, then the gateway should forward the items associated with the various types. Herein, the terms “overlap” means at least one type exists in the associated one or more type and the at least one type. In other words, the gateway does not forward an advertising item of a type to a user device if the type does not belong to the at least one type decided for the user device. It forwards each of the advertising items to its destined user device (s) based on decided types of user devices. During this phase, the gateway can use the existing FIT (Forward Information Table) to send the advertisement to the exact user device.

According to a variant of the embodiment, the method can be implemented to a chosen one user device or a chosen group of user devices instead of all user devices connecting to the gateway.

USER DEVICE

The user can view ads that match his current interests, like recommendation type in eBay and taobao. In this way, the advertising items are sent to relevant users.

As will be appreciated by one skilled in the art, aspects of the present principles can be embodied as a system, method or computer readable medium. Accordingly, aspects of the present principles can take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, and so forth) , or an embodiment combining software and hardware aspects that can all generally be referred to herein as a “circuit, ” “module” , or “system. ” Furthermore, aspects of the present principles can take the form of a computer readable storage medium. Any combination of one or more computer readable storage medium (s) may be utilized.

Further, above methods can be implemented in a program stored in a storage medium. The computer readable storage medium can take the form of a computer readable program product embodied in one or more computer readable medium (s) and having computer readable program code embodied thereon that is executable by a computer. A computer readable storage medium as used herein is considered a non-transitory storage medium given the inherent capability to store the information therein as well as the inherent capability to provide retrieval of the information therefrom. A computer readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. It is to be appreciated that the following, while providing more specific examples of computer readable storage mediums to which the present principles can be applied, is merely an illustrative and not an exhaustive listing as is readily appreciated by one of ordinary skill in the art: a portable computer diskette； a hard disk； a read-only memory (ROM) ； an erasable programmable read-only memory (EPROM or Flash memory) ； a portable compact disc read-only memory (CD-ROM) ； an optical storage device； a magnetic storage device； or any suitable combination of the foregoing. ”

Thus, for example, it will be appreciated by those skilled in the art that the block diagrams presented herein represent conceptual views of illustrative system components and/or circuitry embodying the principles of the invention. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable storage media and so executed by a computer or processor, whether or not such computer or processor is explicitly shown. ”

A number of implementations have been described. Nevertheless, it will be understood that various modifications may be made. For example, elements of different implementations may be combined, supplemented, modified, or removed to produce other implementations. Additionally, one of ordinary skill will understand that other structures and processes may be substituted for those disclosed and the resulting implementations will perform at least substantially the same function (s) , in at least substantially the same way (s) , to achieve at least substantially the same result (s) as the implementations disclosed. Accordingly, these and other implementations are contemplated by this application and are within the scope of the invention as defined by the appended claims.

Claims

A method for providing targeting content items from a gateway to user devices, the method comprising at a gateway:

determining user behavior information including content types and corresponding number of occurrence times of content types based on data that comprises keywords and is sent by the user device but not destined to the gateway and information on a corresponding relationship between content types and corresponding keywords (302) ；

determining at least one content type based on number of occurrence times based on user behavior information (303) ；

receiving content items, each of which is associated with one or more content types (305) ； and

sending content items, whose one or more content types overlaps with the at least one type to the user device (306) .
The method of claim 1, further comprising

receiving the information on a corresponding relationship from a server (301) .
The method of claim 1, further comprising

sending the at least one type to a server, wherein the content items are decided by the server based on the at least one type (304) .
The method of claim 1, wherein the data is URL request, further comprising

detecting the keywords in the URL request； and

increasing 1 to number of occurrence times of a content type corresponding to a detected keyword.
A gateway for providing targeting content items to user devices, comprising

a first interface, a second interface and a processor, wherein for one of the user devices,

the processor (201) is used for determining user behavior information including content types and corresponding number of occurrence times of content types based on data that comprises keywords and is sent by the user device but not destined to the gateway and information on a corresponding relationship between content types and corresponding keywords； and determining at least one content type based on number of occurrence times based on user behavior information；

the first interface (202) is used for receiving content items, each of which is associated with one or more content types； and

the second interface (203) is used for sending content items, whose one or more content types overlaps with the at least one type to the user device.
The gateway of claim 5, wherein

the first interface (202) is further used for receiving the information on a corresponding relationship from a server.
The gateway of claim 5, wherein

the second interface (203) is further used for sending the at least one type to a server, wherein the content items are decided by the server based on the at least one type.
The gateway of claim 5, wherein the data is URL request,

the processor (201) is further used for detecting the keywords in the URL request； and increasing 1 to number of occurrence times of a content type corresponding to a detected keyword.
Computer program comprising program code instructions executable by a processor for implementing a method according to at least one of claims 1 to 4.
Computer program product which is stored on a non-transitory computer readable medium and comprises program code instructions executable by a processor for implementing a method according to at least one of claims 1 to 4.