KR101048408B1 - Personalized advertising content recommending device, method and computer readable storage medium storing program for executing the method - Google Patents

Abstract

The present invention relates to a personalized advertisement content recommendation apparatus and method based on user preference information. The personalized advertisement content recommendation apparatus according to an aspect of the present invention collects metadata of a broadcast program including advertisement content from each channel. A metadata collection unit configured to generate a user behavior record, a user behavior record generator that generates a user history, a user behavior record analyzer that analyzes the user behavior record, and extracts user preference information and the user preference And an advertisement content recommendation unit for recommending advertisement content preferred by the user based on information and metadata of the broadcast program.

Personalized ad recommendation device, user preference, TV-Anytime

Description

Apparatus and method for recommending individual containment advertisement contents and computer readable storage medium storing program for executing method

The present invention relates to a personalized advertisement service providing service, and more particularly, to an apparatus and method for recommending personalized advertisement content based on user preference information in TV-Anytime.

Recently, as digital broadcasting services are in full swing, researches on technologies for providing customized broadcasting services in a multi-channel multimedia environment have been actively conducted. As an example, TV-Anytime, a private international standard, allows users to freely save content by matching their preference information with the aforementioned metadata based on metadata representing the description information of the content. This is a standard for providing Anytime services that can be viewed on the web. As described above, the metadata is description information about content. In TV-Anytime, metadata includes contents-based description and EPG (electronic program guide) information defined in MPEG-7. Make it easy to navigate and select. The metadata standard consists of two parts, and part A defines a format for describing metadata, that is, a schema, and is an MPEG-7 description definition language (DDL) based on eXtensible Markuo Language (XML) (ISO). / IEC 15938-2). Part B relates to metadata transmission, which is binary format [MPEG-7 BiM (Binary Format For MPEG-7) (ISO / IEC 15938-1), fragmentation model, encapsulation and indexing. It includes techniques.

TV-Anytime metadata will be described with reference to the drawings.

1 is a diagram illustrating a schema configuration of a TV-Anytime according to the prior art.

The TV-Anytime metadata is an XML document having a root element of "TVAMain" and has sub-components including CopyrightNotice, ClassificationSchemaTable, ProgramDescription, and UserDescription.

In the TV-Anytime forum, metadata associated with content is defined as content description metadata or instance description metadata for metadata, and metadata related to a user is defined as user metadata. ).

First, the content description metadata represents content-specific information such as a program title, a story line, a genre, and the like. The content description metadata is mainly created by a content creator, and the instance description metadata includes a content location (broadcast time and channel) and a video format. Information needed when a user finds a specific instance of the desired content, such as delivery parameters, is generated by the content provider. Therefore, content description metadata and instance description metadata may be used in the process of searching for and selecting content desired by a user.

The user description metadata is used to describe user information, defines user preferences, user history, and adopts the MPEG-7 Metadata Description Schema (MDS) standard. The user preferences are preference information of the user's genre, time, channel, etc., and may help the user to easily select the content by filtering the content according to the preference. The user behavior record is for expressing the user's content consumption form (fast forward, rewind, pause, play, etc.) and may be used to derive user profile information. As such, the user description metadata is metadata that directly enables a personalized broadcasting service.

On the other hand, based on the technology of analyzing the metadata in the form of XML in real time, a task of recommending a program using a user's viewing history in digital TV broadcasting is provided through an electronic programming guide (EPG).

For example, there is a broadcast program recommendation service based on user information using metadata for user information processing. However, in the case of user information-based broadcast program recommendation service, technologies for providing a customized service for a broadcast program have been disclosed. It is a required situation.

Meanwhile, in relation to the advertisement recommendation service, a correlation between advertisements is calculated using advertisement click information on the web, and referring to the correlation between the calculated advertisements, an advertisement highly correlated with the advertisement previously clicked by the user is recommended. Although a method and a system related technology exist in the related art, recommendation services of web advertisements and multimedia multimedia advertisements for broadcasting are not compatible with each other because their data have different characteristics. Therefore, there is a need for a unique model capable of recommending broadcast multimedia video advertisements.

An object of the present invention is to provide an apparatus for recommending advertising content based on user preferences for personalized broadcasting.

Another object of the present invention is to provide a method for recommending advertisement content based on user preference for personalized broadcasting.

The object of the present invention is not limited to the above-mentioned object, and other objects that are not mentioned will be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a personalized advertisement content recommendation apparatus, comprising: a metadata collector configured to collect metadata of a broadcast program including advertisement content from each channel; and a user history record. A user behavior record generation unit for generating a user behavior record analysis unit for analyzing user behavior records and extracting user preference information, and the user based on the user preference information and metadata of the broadcast program; It includes an advertising content recommendation unit for recommending preferred advertising content.

According to another aspect of the present invention, there is provided a method of recommending personalized advertisement content, collecting metadata of a broadcast program including advertisement content, generating a user history, and analyzing the user behavior record. And extracting user preference information, and recommending advertisement content preferred by the user based on the extracted user preference information and metadata of the broadcast program.

Specific details of other embodiments are included in the detailed description and the drawings.

According to the present invention, only advertisements that match the user's preference in the customized broadcasting service can be broadcast.

In addition, according to the present invention, it is possible to apply the advertisement content provision according to the user's preference provided on the conventional web also for a multimedia video advertisement for broadcasting.

In addition, by providing differentiated advertisements for each individual, the user can be less dissatisfied with watching the advertisement, and broadcast program service providers can reduce the user's dissatisfaction with the broadcast and broadcast by providing advertisements that match the user's preference during the advertisement airtime. Users can be satisfied with the program.

In addition, the advertisement content providers can increase the advertisement effect by increasing the advertisement viewing rate and users' satisfaction with the advertisement.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the embodiments make the disclosure of the present invention complete, and the general knowledge in the technical field to which the present invention belongs. It is provided to fully convey the scope of the invention to those skilled in the art, and the invention is defined only by the scope of the claims. Like reference numerals refer to like elements throughout. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification. As used herein, “comprise” and / or “comprising” refers to a component, step, operation and / or element that is present in one or more other components, steps, operations and / or elements. Or does not exclude additions.

Hereinafter, with reference to the accompanying drawings will be described in detail the customized advertising content recommendation apparatus and method according to an embodiment of the present invention.

2 is a view showing a personalized advertising service recommendation system including a personalized advertising content recommendation apparatus according to an embodiment of the present invention.

Referring to FIG. 2, the customized advertisement content recommendation system includes a customized broadcast server 100, a customized broadcast terminal 200, and a customized advertisement content recommendation device 300.

The customized advertisement content recommendation system according to the present invention supports an interactive customized broadcasting environment. That is, in two-way broadcasting, the customized broadcasting server 100 transmits the broadcasting content and metadata for the broadcasting content to the customized broadcasting terminal 200, and the customized broadcasting terminal is a user history based on the user related metadata TV-Anytime standard. And user preference information (User Preference) is transmitted to the customized broadcast server (100).

The user related metadata received from the customized broadcasting terminal 200 is used to recommend personalized contents by a user profiling engine (not shown) of the customized broadcasting server 100.

The customized advertisement content recommendation apparatus 300 analyzes the metadata of the broadcastable advertisement contents and ranks and extracts the advertisement contents that match the user's user preference information based on the match. That is, only advertisements matching the information included in the user preference information are extracted and transmitted to the customized broadcasting terminal 200 of each user. The recommended advertisements for each user from the customized advertisement content recommendation device are broadcast in the customized broadcasting terminal 200 which receives only selected advertisements preferred by the user in the advertisement time zone during the broadcast program.

The device that recommends advertisements based on user history is compatible based on the MPEG-2 and TV-Anytime standards, which are related to digital broadcasting, and the feature extraction for multimedia search by applying the theory and methodology of web information retrieval. And search method to improve the search speed and to expand the system to web contents.

Hereinafter, a personalized advertising content recommendation apparatus based on user preferences according to the present invention will be described with reference to FIGS. 3 and 4. 3 is a view showing the configuration of a personalized advertising content recommendation apparatus according to an embodiment of the present invention, Figure 4 is a view showing the configuration of the user behavior record analysis unit for extracting user preference information.

Referring to FIG. 3, the customized advertisement content recommendation apparatus 300 includes a metadata collector 310, a user behavior record generator 320, a user behavior record analyzer 330, and an advertisement content recommender 340. do.

The metadata collection unit 310 provides information directly or indirectly related to broadcasting content transmitted from the customized broadcasting server 100 (for example, a general broadcasting program including an actual data such as video, audio, and text, and an advertising program). Collect and store metadata.

The user behavior record generation unit 320 generates a user behavior record.

The user behavior record generation unit 320 generates the user behavior record based on, for example, a user input while viewing. In other words, the user may select the advertisement contents through a remote controller or the like, and generate a user behavior record based on various operations during the viewing of predetermined advertisement contents, for example, recording or repetitive viewing or zooming, and user input such as volume control. do.

The user behavior record generation unit 320 generates a user behavior record by monitoring and accumulating the user's behavior on the broadcast program. When a user watches a broadcast program, an advertisement, etc., user behavior signal information is input and the information is generated as an XML document.

The above-described user behavior signal information means information about a command, a target program, a target advertisement content, a watched time zone, and the like performed by the user in the viewing process. For example, when a program or a commercial that a user is interested in while adjusting a broadcasting channel is output, information that the user watched for a predetermined time may be recorded as a user action.

On the other hand, a series of actions that the user takes with respect to a broadcast program or advertisement content, such as changing a channel while a predetermined advertisement is being broadcast or changing a channel each time a predetermined advertisement is broadcast, is monitored. It can be recorded as an action record.

The user behavior record analyzer 330 extracts the user's preference information from the user behavior record generated by the user behavior record generator 320. For example, the list of advertisements watched by a user interested in a specific advertisement time period is collected from the user behavior record, and the characteristics of the advertisement contents included in the collected advertisement lists are analyzed. Correlation between the advertisements can be analyzed, and information of the person cast in the advertisement, the background of the advertisement, music, and other props can be analyzed to extract what the user prefers. Specifically, the user preference may be extracted by analyzing metadata of advertisement contents viewed by the user.

A process of extracting user preference information will be described with reference to FIG. 4.

Referring to FIG. 4, the user behavior record analyzer 330 includes a pattern collector 331, a pattern determiner 332, and a user preference information extractor 333.

The pattern collector 331 collecting the user's behavior pattern analyzes and collects the behavior pattern of the user's broadcast program from the user's behavior record. For example, a user behavior pattern in which a plurality of actions, such as predetermined actions A, B, C A-B, A-B-C, and A-C, are performed separately or in association with each other is extracted from the user behavior record.

The pattern determination unit 332 that determines the behavior pattern of the user determines the behavior pattern for the preferred program and the behavior pattern for the non-preferred program among the broadcasting programs watched by the user. That is, the preferred behavior pattern and the non-preferred behavior pattern are generated for the plurality of user behavior patterns collected by the pattern collector 331. Such preference behavior pattern and non-preferred behavior pattern generation work can be extracted based on the frequency in the user behavior record.

The determination of the preference pattern and the non-preferred pattern based on the user behavior pattern is performed periodically even when the user does not watch the broadcast. Through this method, the user's latest preference information can be managed by automatically collecting user's behavior patterns and updating preference patterns and non-preferred patterns based on the user's behavior patterns.

The user preference information extractor 333 extracts user preference information based on the pattern collector 331 and the pattern determiner 332. The extracted user preference information is a user preference information proposed in the TV-Anytime standard.

The user preference information extractor 333 may extract user preference information by extracting positive and negative preference information based on the preference pattern and the non-preferred pattern determined by the pattern determination unit 332. Positive preference and negative preference information may be used later when extracting advertisement content according to user preference.

3, the advertisement content recommendation unit 340 extracts and presents the user preferred content to the user.

Based on the preference information of each user extracted by the user preference information extraction unit 333 based on the preference information and the program-specific metadata scores and ranking the programs of the EPG (Electronic Program Guide) to list the content of the advertising content It can be presented to the user. Meanwhile, the advertisement content may be automatically aired in the advertisement time zone without presenting the content list to the user.

Based on the user preference information of the user preference information extraction unit 333 and metadata of each advertisement content and program, a list of advertisement content contents preferred by the user is extracted from the plurality of advertisement contents.

For example, when the user preference information extraction unit 333 extracts the positive preference information and the negative preference information, weights may be assigned to each of the positive preference information and the negative preference information.

Afterwards, the preferences for the advertisement contents are extracted by scoring and ranking the positive preference information and the negative preference information based on the aforementioned weights for the programs and metadata for each advertisement content received through the EPG (Electronic Program Guide).

When the preference is extracted based on the metadata of each program and the advertisement content, the user preference advertisement content list may be extracted in the order of high preference.

User preference information appears in various ways depending on the user's life pattern and taste. Some users mainly watch these genres through dramas, movies, and advertising content with specific topics, specific people, and specific music, while users who do not prefer the content related to the specific subject, specific person, or specific music There can be. In addition, the user's preference information may appear in a variety of complex, such as the preferred advertising content, the genre may appear differently depending on the viewing time.

Therefore, the user preference information should be extracted based on the behavior pattern of the user, and the user preference information should be extracted by automatically identifying and managing the user behavior pattern, and the advertisement content preferred by the user should be provided.

Hereinafter, a method of providing personalized advertisement content according to an embodiment of the present invention will be described with reference to FIGS. 5 and 6. 5 is a flowchart illustrating a method of providing personalized advertisement content according to an embodiment of the present invention, and FIG. 6 is a flowchart illustrating a process of extracting user preference information through analyzing user behavior records according to an embodiment of the present invention. .

5 and 6, in order to provide personalized advertisement content based on user preference information, first, metadata is collected (S410).

The metadata includes metadata of a broadcast program including advertisement content transmitted from the customized broadcast server 100 and user related metadata transmitted from the customized broadcast terminal 200.

The metadata is metadata of advertisement content viewed by a user, but does not exclude metadata of a general broadcast program. This is because user preference is required in order to provide the user's preferred advertisement contents, and user preference information is not only provided through advertisement contents but also through general broadcasting programs. For example, when the user is interested in a drama or a movie, the user's preference information may be extracted by analyzing metadata related to the drama or the movie. In addition, if the user is interested in the spot broadcasting provided through the sports channel, when the regular program ends and the commercial starts, a customized sports content or a preferred sports player is provided through the customized advertisement content providing device according to the present invention. Appearing advertising content can be provided.

A user history record is generated along with metadata collection (S420). When the user watches the advertisement content during the advertisement time period, the user selects another advertisement content through the remote control or the like, or during the advertisement content viewing, various operations such as recording or repeated watching or zooming, user input such as volume control, etc. Create user behavior records as a basis.

After that, the user behavior record is analyzed to extract user preference information based on the user behavior record generated in the user behavior record generation unit 320 (S430). User behavior record analysis will be described with reference to FIG.

Referring to FIG. 6, the user behavior pattern is collected based on the user behavior record (S431). The collection of user behavior patterns is periodically performed even when the user does not watch the advertisement. In this manner, the user behavior patterns can be automatically collected to manage the user's latest preference information. The user's behavior pattern is collected from the user's behavior record by extracting the user's behavior pattern that is continuously performed by a plurality of behaviors, such as behaviors A, B, C, A-B, A-B-C, A-C, respectively, which are correlated with EH.

Based on the collected user behavior patterns, a behavior pattern for a user's preferred program and a behavior pattern for a non-preferred program are determined (S432).

When the behavior pattern of the user is determined, the user preference information is extracted based on the behavior pattern of the user (S433).

Referring back to FIG. 5, when the user preference information is extracted, the user recommends the user preferred advertisement content according to the preference in the advertisement time zone based on the extracted user preference information (S440).

The user preference advertisement content recommendation includes extracting advertisement content preferred by the user. The user preference advertisement content extraction is based on the user's preference pattern and non-preferred pattern extracted by analyzing the user's behavior record for each user and analyzing the user's preferred time zone and what behavior pattern is shown when watching a broadcasting program or advertisement. Here, the behavior pattern of the user is analyzed automatically and based on this, the user's preference information can be automatically extracted and updated without inputting directly.

On the other hand, the step of recommending the user-preferred advertising content may provide the user-preferred advertising content in the advertisement time zone as an advertisement, or a list of user preferred advertising content may be displayed according to the user's selection.

Meanwhile, the above-described embodiments of the present invention can be written in a program that can be executed in a computer, and can be implemented in a general-purpose digital computer for operating a program using a computer-readable storage medium. In addition, the structure of data used in the embodiments of the present invention described above may be recorded and / or stored in a computer-readable storage medium through various means. Computer-readable storage media include magnetic storage media (e.g., ROMs, floppy disks, hard disks, etc.), optical read media (e.g., CD-ROMs, DVDs, etc.) and carrier waves (e.g., transmission over the Internet). Storage media such as

Those skilled in the art will appreciate that the present invention can be embodied in other specific forms without changing the technical spirit or essential features of the present invention. For example, the program for providing the advertisement content providing method of the present invention may be implemented in various forms such as a storage medium in which a program is stored. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. The scope of the invention is indicated by the following claims rather than the above description, and all changes or modifications derived from the claims and their equivalents should be construed as being included in the scope of the invention.

1 is a diagram illustrating a schema configuration of a TV-Anytime according to the prior art.

2 is a view showing a personalized advertising service recommendation system including a personalized advertising content recommendation apparatus according to an embodiment of the present invention.

3 is a view showing the configuration of a customized advertising content recommendation apparatus according to an embodiment of the present invention.

4 is a diagram illustrating a configuration of a user behavior record analyzer extracting user preference information.

5 is a flowchart illustrating a method of providing customized advertisement content according to an embodiment of the present invention.

6 is a flowchart illustrating a process of extracting user preference information through analyzing user behavior records according to an embodiment of the present invention.

Explanation of symbols on the main parts of the drawings

100: customized broadcasting server 200: customized broadcasting terminal

300: customized advertisement content recommendation device 310: metadata collection unit

320: user behavior record generation unit 330: user behavior record analysis unit

340: advertising content recommendation unit

Claims (14)

delete delete delete delete delete A metadata collector which collects metadata about advertisement content from each channel; A user behavior record generation unit that monitors and accumulates a user's behavior including recording, repetitive viewing, and volume control of advertisement content to generate a user history; Based on the pattern collecting unit for collecting a behavior pattern consisting of the user behavior record for the advertising content, a pattern determination unit for determining whether the behavior pattern for the collected advertising content is a preference pattern or a non-preferred pattern, and based on the determined preference pattern A user behavior record analyzer including a user preference information extractor which extracts user preference information; And An advertisement content recommending unit for recommending advertisement contents preferred by the user based on the extracted user preference information and the collected metadata; Personalized advertising content recommendation device comprising a. The method of claim 6, A metadata storage unit which stores metadata of the collected broadcast program; A program storage unit for storing the collected broadcast program information; Personalized advertising content recommendation device characterized in that it further comprises. delete delete delete delete delete Collecting metadata about advertising content from each channel; Generating a user history by monitoring and accumulating a user's behavior including recording, repetitive viewing, and volume control of the advertisement content; Collecting a behavior pattern comprising a user behavior record for the advertisement content; Determining whether a behavior pattern for the collected advertisement content is a preference pattern or a non-preferred pattern; Extracting user preference information based on the determined preference pattern; And Recommending advertisement content preferred by the user based on the extracted user preference information and the collected metadata; Personalized advertising content recommendation method comprising a. A computer readable storage medium storing a program for carrying out the method of claim 13.

Images