KR20100028748A - System and method for providing advertisement - Google Patents

Abstract

PURPOSE: A system and a method for providing an advertisement are provided to supply a target advertisement to a user by obtaining advertising supplying information and using the obtained information. CONSTITUTION: A storage unit(221) stores speech characteristic information corresponding to user's speech, and a user characteristic information extracting unit(213) extracts the user characteristic information by using the speech characteristic information. A content selector(219) recognizes user's speech and selects the contents requested from the user. An advertisement selecting unit(223) selects an advertisement which is supposed to be transmitted to a user by corresponding to the user characteristic information. A production unit(215) reproduces the selected contents with the selected advertisement, and a communication unit(217) transmits the user characteristic information to a service server and receives the selected advertisement.

Description

Ad serving system and method {SYSTEM AND METHOD FOR PROVIDING ADVERTISEMENT}

The present invention relates to an advertisement providing system and method, and more particularly, to an advertisement providing system and method for providing a target advertisement using user characteristic information. In more detail, when a user's voice requesting content provision is input, a voice recognition and content reproducing apparatus extracts user characteristic information using the user's voice and plays an advertisement corresponding to the user characteristic information along with the requested content; The present invention relates to an advertisement providing system including a service providing server connected to the voice recognition and content reproducing apparatus through a communication network to provide contents and advertisements.

Currently, advertisements using various media are provided in all industries, and types of advertisements and methods of providing the advertisements are evolving in various ways. In general, advertisements provided to users are provided randomly, and these advertisements do not give great attention to the advertisement consumers who accept the advertisements, so that the advertisements are not as effective as the advertisers expect.

In particular, advertisements provided through a communication network are targeted to an unspecified number, and advertisements that are not desired by an advertisement consumer are classified as spam. For this reason, information such as gender, age, occupation, hobbies, purchasing tendency, assets, and income, which are unique to advertising consumers, are subdivided, and classified advertisements are provided for each user. As described above, targeting advertisements that are selected for each advertisement consumer by using advertisement consumer information are provided as target advertisements.

However, in order to provide such a target advertisement in a communication network, information of the advertisement consumer must be obtained. In order to obtain the information on the advertisement consumer, a user authentication procedure such as pre-registration of user information and login is required.

However, not all electronic devices used in the communication network pre-register user information or perform login. For example, an Internet Protocol Television or a Digital Multimedia Broadcasting terminal provides a user with a service provided by the electronic device without a user login procedure.

Therefore, it is difficult to provide the appropriate target advertisement for each user because the information about each user cannot be obtained for the electronic devices that do not perform the user authentication procedure when the target network is intended to provide the target advertisement to each user using a communication network. there was.

An object of the present invention is to provide an advertisement providing system and method for providing a target advertisement without a user authentication procedure.

Another object of the present invention is to provide an advertisement providing system and method for providing a target advertisement suitable for each user.

According to an embodiment of the present invention, when a user voice requesting content provision is input, the system extracts user characteristic information using the user voice, and plays an advertisement corresponding to the user characteristic information together with the requested content. And a service providing server connected to the voice recognition and content reproducing apparatus and the voice recognition and content reproducing apparatus through a communication network to provide contents and advertisements.

To achieve the above objects, the apparatus for recognizing speech and contents of the present invention includes a communication unit for transmitting / receiving data, a storage unit for storing voice characteristic information corresponding to a user voice, and a user voice requesting to provide content. A user characteristic information extraction unit for extracting user characteristic information using voice characteristic information, a content selection unit for recognizing the user's voice and selecting requested content from the user, and an advertisement selected according to the user characteristic information; It includes a playback unit to play along with the selected content.

The service providing server of the present invention for achieving the above objects is characterized in that the communication unit for transmitting and receiving data, the database storing the content and advertisement, and the user characteristic information extracted from the user voice from the voice recognition and content playback device, And an advertisement selection unit for selecting an advertisement corresponding to the information and transmitting the selected advertisement to the speech recognition and content reproduction apparatus.

According to an aspect of the present invention, there is provided a method of providing a voice recognition and advertisement of an apparatus for reproducing a content. When a user voice requesting content is input, extracting user characteristic information using the input user voice. And playing the advertisement corresponding to the user characteristic information together with the requested content.

According to another aspect of the present invention, there is provided a method of providing an advertisement of a service providing server, the method comprising: receiving user characteristic information extracted from a user's voice from a voice recognition and content playback device, and corresponding to the user characteristic information; An advertisement is selected from the advertisements stored in the database and transmitted to the speech recognition and content reproduction apparatus.

According to the present invention, it is possible to provide a target advertisement to a user without a user authentication procedure such as user information pre-registration, login, or the like. In addition, in acquiring the advertisement consumer information, it is possible to obtain the advertisement consumer information without providing a user authentication procedure and to provide the target advertisement to the user by using the obtained information.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that in the following description, only parts necessary for understanding the operation according to the present invention will be described, and descriptions of other parts will be omitted so as not to distract from the gist of the present invention.

The present invention provides an advertisement providing system and method for providing a target advertisement using user characteristic information in a communication system. In particular, the present invention provides an advertisement providing system and method for providing a target advertisement using user characteristic information extracted from a user's voice.

In addition, the user characteristic information may provide a target advertisement using user characteristic information extracted from the image data when image data of the user can be obtained.

On the other hand, voice recognition technology is taking place as an essential field for communication with various electronic devices in the next-generation technology using the user voice. It is possible to control a variety of electronic devices using such a voice recognition technology, in order to control the electronic devices are gradually changing to the form of applying the voice recognition technology to various electronic devices.

In the present invention, a speech recognition and content playback apparatus capable of speech recognition will be described as an example, and in particular, an advertisement is provided using a speech recognition and content playback apparatus capable of providing contents to a user. In addition, when providing a target advertisement using the image data may be an electronic device having an image recognition device, for example a camera.

Next, a system structure for providing an advertisement according to the present invention will be described with reference to FIG. 1 below.

1 is a diagram showing the structure of an advertisement providing system according to an embodiment of the present invention.

Referring to FIG. 1, the advertisement providing system includes a voice recognition and content reproducing apparatus 110 and a service providing server 120.

The voice recognition and content playback device 110 is a user device controlled by a user's voice. The voice recognition and content reproducing apparatus 110 has a voice recognition function and recognizes a user voice when a user voice is input. The voice recognition and content reproducing apparatus 110 performs a control operation according to the recognized user voice.

In addition, the voice recognition and content playback apparatus 110 extracts user characteristic information, for example, information related to user age, gender, emotion, etc. using a user voice, and selectively uses an advertisement for the user using the user characteristic information. To provide.

For example, if the user control information is user control information for requesting content provision, the voice recognition and content reproducing apparatus 110 selectively provides an advertisement using user control information when providing content.

The service providing server 120 is connected to the voice recognition and content reproducing apparatus 110 through a wired / wireless communication network, and is a server in which contents and advertisements are stored or provided. The service providing server 120 may include an advertisement server and / or a content server or may be a separate server connected to the advertisement server or the content server. In addition, the service providing server 120 may be a database storing only content and advertisements.

The service providing server 120 provides content or an advertisement to the voice recognition and content playback device 110.

In addition, when the service providing server 120 receives the user characteristic information from the speech recognition and content reproduction apparatus 110, an advertisement to be provided to the speech recognition and content reproduction apparatus 110 using user characteristic information. It may select and provide the selected advertisement.

Next, a structure of a speech recognition and content reproduction device for providing an advertisement will be described with reference to FIG. 2.

2 is a diagram showing the structure of a voice recognition and content playback device according to an embodiment of the present invention.

Referring to FIG. 2, the apparatus for recognizing speech and contents may include a speech recognizer 211, a user characteristic information extractor 213, a reproducer 215, a communicator 217, a content selector 219, and a storage unit ( 221). In addition, the voice recognition and content playback device may optionally include an advertisement selection unit 223.

The voice recognition unit 211 receives a user voice, and recognizes the received user voice. That is, the voice recognition unit 211 extracts user control information requested from the user through voice recognition. In this case, the user control information is information received from the user for voice recognition and operation control of the content reproducing apparatus.

For example, it is assumed that the speech recognition unit 211 uses a Hidden Markov Model (HMM) speech recognition method that probabilistically handles fluctuations in a speech signal as a kind of speech recognition algorithm. In addition, the voice recognition unit 211 may use another voice recognition method for the voice recognition. The voice recognition unit 211 extracts user control information through the input user voice by comparing the input user voice with the modeled control information of the storage unit 221. The control information is information for controlling overall operations of the voice recognition and content reproducing apparatus. For example, the control information includes control information for selecting and / or reproducing specific content.

It is assumed that the user control information recognized by the voice recognition unit 211 is content request information (content selection information) for requesting provision of content.

The user characteristic information extractor 213 extracts user characteristic information using a user voice input from a user. The user characteristic information extractor 213 extracts user characteristic information from the input user voice by comparing the input voice with the modeled voice characteristic information of the storage unit 221. The user's voice may be divided into a fundamental frequency f0 and formant frequencies f1, f2, and f3, and the user feature extractor 213 may be divided into age and gender based on the fundamental frequency and the formant frequency. The user characteristic information is extracted from the storage unit 221 in which the voice characteristic information related to the emotion, etc. is modeled. The voice characteristic information is information obtained by analyzing frequency characteristics of voice for a plurality of people according to age, gender, emotion, and the like. For example, the voice characteristic information is information modeled as basic frequencies and formant frequencies according to age, gender, and emotion. The fundamental frequency is a frequency generated by vibration of the vocal cords of the user, and may recognize features such as intonation, timbre, and sound quality using the fundamental frequency. The formant frequencies are generally frequencies generated by the user's saints, and a plurality of resonance frequencies may be generated. By using the fundamental frequency and the formant frequencies, the user's age, gender, and emotion may be detected.

Accordingly, the user characteristic information extractor 213 detects the fundamental frequency and the formant frequency from the user's voice and extracts user characteristic information using the detected frequencies. The user characteristic information extractor 213 extracts user characteristic information corresponding to the input user voice by comparing the detected frequencies with the voice characteristic information stored in the storage unit 221.

The voice recognition unit 211 and the user characteristic information extraction unit 213 may include a microphone for user voice input, and the microphone may be at least one of the voice recognition unit 211 or the user characteristic information extraction unit 213. It is provided to receive the user's voice.

The user characteristic information extractor 213 may be provided with a camera module instead of a microphone or may further include a camera module to detect image data from a user. The user characteristic information extractor 213 may extract user characteristic information from the image data.

The user characteristic information extractor 213 may detect information related to a user's location, personnel, physique, motion, used article, gender, age, emotion, and the like from the image data. Here, the user characteristic information includes at least one of user location information, personnel information, physique information, motion information, used article information, gender information, age information, and emotion information.

The playback unit 215 includes an output device, for example, a display device for reproducing image data, a speaker for reproducing voice data, and the like, and reproduces the content requested from the user and provides the same to the user. In addition, the playback unit 215 plays the advertisement selected according to the user characteristic information.

The communication unit 217 performs data communication with a service providing server connected through a communication network. The communication unit 217 receives content and advertisement to be played in the voice recognition and content reproduction device through the service providing server. In addition, the communication unit 217 transmits at least one of the user characteristic information, the content information to be reproduced in the voice recognition and content reproducing apparatus, and the content request information according to the operation of the voice recognition and content reproducing apparatus, and the transmission information. Correspondingly, the selected advertisement is received according to the requested content and the user characteristic information in the voice recognition and content reproduction device.

The content selection unit 219 transmits content request information for selecting a content using the user request information recognized by the voice recognition unit 211 or requesting the selected content to the service providing server through the communication unit 217. do.

The advertisement selector 223 selects an advertisement from among advertisements stored in the storage unit 221 according to the user characteristic information extracted through the user characteristic information extractor 213. As an example of characteristic information unique to the user, an advertisement suitable for the user is selected according to gender, age, emotion, and the like. The advertisement selecting unit 223 may be included in the service providing server. When the advertisement selecting unit 223 is included in the service providing server to select an advertisement, the advertisement selecting unit 223 may recognize the voice and It may not be included in the content playback device.

In addition, when the advertisement is selected, the advertisement selecting unit 223 may additionally receive additional information such as weather information and time information through the voice recognition and content reproducing apparatus or an external server. Additional information may be available further.

The storage unit 221 stores a program for operating the voice recognition and content reproducing apparatus and temporary data generated when the voice recognition and content reproducing apparatus is operated. In addition, the storage unit 221 stores or temporarily stores the content and the advertisement for playing the content and the advertisement. The storage unit 221 models and stores control information for recognizing user control information from a user voice input to the voice recognition and content reproducing apparatus and voice property information for extracting user property information.

Next, a structure of a service providing server for providing an advertisement will be described with reference to FIG. 3 below.

3 is a diagram illustrating a structure of a service providing server according to an exemplary embodiment of the present invention.

Referring to FIG. 3, the service providing server includes a communication unit 311 and a database 313. In addition, the service providing server may optionally include the advertisement selection unit 315.

The communication unit 311 performs data communication with a voice recognition and content reproduction device connected through a communication network. The communication unit 311 transmits content and advertisements to be reproduced in the voice recognition and content reproducing apparatus. In addition, the communication unit 311 may receive at least one of the user characteristic information, the content information to be reproduced in the voice recognition and content reproducing apparatus, and the content request information according to the operation of the voice recognition and content reproducing apparatus. In response to the received information, the voice recognition and content reproduction device transmits the selected advertisement according to the requested content and the user characteristic information.

The advertisement selecting unit 315 selects an advertisement according to the user characteristic information when the user characteristic information is received from the voice recognition and content reproducing apparatus. Advertisements suitable for the user are selected from advertisements stored in the database 313 according to gender, age, emotion, and the like. The advertisement selector 315 may be included in the speech recognition and content reproduction apparatus. When the advertisement is selected in the speech recognition and content reproduction apparatus, the advertisement selection unit 315 may not be included in the service providing server. It may be.

In addition, when the advertisement is selected, the advertisement selecting unit 315 may further receive additional information such as weather information and time information through the service providing server or an external server. Additionally available.

The database 313 stores content and advertisements.

Next, the operation of the apparatus for recognizing speech and contents according to the embodiment of the present invention will be described with reference to FIG. 4.

4 is a flowchart illustrating the operation of a voice recognition and content playback device according to an embodiment of the present invention.

Referring to FIG. 4, in step 411, the voice recognition and content reproducing apparatus receives the voice from the user, and proceeds to step 413.

In step 413, the voice recognition and content reproducing apparatus extracts user control information using the input user voice, and proceeds to step 415. In this case, it is assumed that the user control information is content request information.

In step 415, the voice recognition and content reproducing apparatus extracts user characteristic information using the input user voice, and proceeds to step 417. The user characteristic information includes at least one of gender information, age information, and emotion information. When the voice recognition and content reproducing apparatus includes a camera module to input user image data, the gender information, age information, In addition to the emotion information, a variety of user characteristic information may be utilized.

In step 417, the voice recognition and content reproducing apparatus checks whether content is stored in the voice recognition and content reproducing apparatus.

If the content of the check result is stored, the process proceeds to step 421.

In step 421, the voice recognition and content playback device determines whether an advertisement is stored.

If the advertisement is stored as a result of the determination, step 427 is performed.

In step 427, the voice recognition and content playback device selects content and advertisement to be played and proceeds to step 439. The voice recognition and content reproducing apparatus selects a content to be reproduced using the user control information, and selects an advertisement to be reproduced using the user characteristic information. In addition, the voice recognition and content playback device may select an advertisement by further considering content to be played upon selecting the advertisement.

If the advertisement is not stored as a result of the determination, step 423 is performed.

In step 423, the voice recognition and content reproducing apparatus transmits the reproduced content information and the user characteristic information to the service providing server and proceeds to step 425. The voice recognition and content reproducing apparatus selects the content to be reproduced using the user control information, and transmits the reproduction content information, which is information for recognizing the content to be reproduced, to the service providing server. If the advertisement providing server does not select the advertisement in consideration of the reproduction content information, the reproduction content information may not be transmitted.

In operation 425, the apparatus for recognizing speech and contents reproduces an advertisement selected according to the user characteristic information and proceeds to operation 439.

If the content is not stored as a result of the check, the process proceeds to step 419.

In step 419, the voice recognition and content playback device checks whether an advertisement is stored in the voice recognition and content playback device.

If the advertisement is stored as a result of the inspection, the process proceeds to step 429.

In step 429, the voice recognition and content playback device selects an advertisement using the user characteristic information and proceeds to step 431.

In step 431, the voice recognition and content reproducing apparatus transmits content request information for requesting content provision to the service providing server, and proceeds to step 433.

In step 433, the voice recognition and content reproducing apparatus receives the content according to the content providing request, and proceeds to step 439. If the voice recognition and content reproducing apparatus selects an advertisement by further considering content information provided from the service providing server, step 429 may be performed after step 433.

If the advertisement is not stored as a result of the inspection, the flow proceeds to step 435.

In step 435, the voice recognition and content reproducing apparatus transmits content request information and the user characteristic information requesting to provide content, and proceeds to step 437.

In step 437, the voice recognition and content playback device receives an advertisement corresponding to the requested content and user characteristic information from the service providing server and proceeds to step 439.

In operation 439, the apparatus for recognizing speech and contents reproduces the content and the advertisement stored or received from the service providing server. The speech recognition and content playback apparatus may play back at least one time point before, during, or after playback of the content.

Next, the operation of the service providing server according to an exemplary embodiment of the present invention will be described with reference to FIG. 5.

5 is a flowchart illustrating an operation of a service providing server according to an exemplary embodiment of the present invention.

Referring to FIG. 5, in step 511, the service providing server checks whether only content request information is received from the voice recognition and content reproducing apparatus.

If only the content request information is received as a result of the checking, the process proceeds to step 515. When only the content request information is received, an advertisement is stored in the voice recognition and content reproducing apparatus to request only content.

In step 515, the service providing server transmits the corresponding content requested from the voice recognition and content reproducing apparatus.

If only the content request information is not received, the process proceeds to step 515.

In step 513, the service providing server determines whether both the content request information and the user characteristic information have been received.

If both the content request information and the user characteristic information are received as a result of the determination, step 523 is performed. When both the content request information and the user characteristic information are received, it is a case where both the content and the advertisement should be transmitted to the mobile terminal.

In step 523, the service providing server selects content to be transmitted to the voice recognition and content reproducing apparatus according to the content request information, and proceeds to step 525.

In step 525, the service providing server selects an advertisement to be provided to the voice recognition and content player according to the user characteristic information, and proceeds to step 527. The service providing server may select the advertisement by further considering the selected content information when selecting the advertisement.

In step 527, the service providing server transmits the selected advertisement to the voice recognition and content playback device.

If it is determined that neither the content request information nor the user characteristic information is received, the process proceeds to step 517. When neither the content request information nor the user characteristic information is received, the content is stored in the voice recognition and content reproduction device and only an advertisement is requested.

In step 517, the service providing server checks whether content information and user characteristic information to be played are received.

If neither the content information to be reproduced nor the user characteristic information is received as a result of the inspection, step 519 is performed. In this case, the service providing server receives only user characteristic information.

When the content information to be reproduced and the user characteristic information are received as a result of the inspection, the process proceeds to step 519.

In step 519, the service providing server selects an advertisement corresponding to user characteristic information, and proceeds to step 521. The service providing server selects the advertisement by further considering the content information when the content information to be reproduced is received.

In step 521, the service providing server transmits the selected advertisement to the voice recognition and content reproduction apparatus.

The voice recognition and content playback device may store content and advertisement in advance, and may receive and store the content and the advertisement from a service providing server. In this case, the voice recognition and content reproducing apparatus may provide content and an advertisement in the voice recognition and content reproducing apparatus without receiving data separately from the service providing server.

In the present invention, it is possible to provide an optimized kind of target advertisement for each user through extraction of user characteristic information. In particular, by extracting user characteristic information from a user's voice input through voice recognition, a target advertisement can be provided to a user without pre-registration or authentication of user information.

Meanwhile, in the detailed description of the present invention, specific embodiments have been described, but various modifications are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined not only by the scope of the following claims, but also by the equivalents of the claims.

The advertisement providing method of the present invention described above may be applied to a communication system, and is usefully used to provide a target advertisement to a user without a user authentication procedure such as pre-registration of user information or login to a user having a terminal capable of speech recognition. do.

1 is a diagram showing the structure of an advertisement providing system according to an embodiment of the present invention;

2 is a diagram illustrating a structure of a voice recognition and content playback device according to an embodiment of the present invention;

3 is a diagram showing the structure of a service providing server according to an embodiment of the present invention;

4 is a flowchart illustrating an operation of a voice recognition and content playback device according to an embodiment of the present invention;

5 is a flowchart illustrating an operation of a service providing server according to an exemplary embodiment of the present invention.

<Description of Symbols for Main Parts of Drawings>

110: speech recognition and content playback device

120: service providing server

211: speech recognition unit 213: user characteristic information extraction unit

215: playback unit 217: communication unit

219: content selection unit 221: storage unit

223: Ad selection unit

311: communication unit 313: database

315: ad selection unit

Claims (25)

A voice recognition and content reproducing apparatus that extracts user characteristic information using the user's voice and plays an advertisement corresponding to the user characteristic information along with the requested content when a user's voice requesting content provision is input; And a service providing server connected to the voice recognition and content reproducing apparatus through a communication network to provide contents and advertisements. Communication unit for transmitting and receiving data, A storage unit for storing voice characteristic information corresponding to a user voice; A user characteristic information extraction unit for extracting user characteristic information using the voice characteristic information when a user voice requesting content provision is input; A content selection unit configured to voice-recognize the user's voice and select content requested by the user; And a playback unit for playing an advertisement selected according to user characteristic information together with the selected content. The method of claim 2, And an advertisement selector for selecting an advertisement to be provided to the user according to the user characteristic information. The method of claim 2, And the communication unit transmits the user characteristic information to the service provision server and receives an advertisement selected according to the user characteristic information. The method of claim 2, And the user characteristic information includes at least one of user gender information, age information, and emotion information. The method of claim 2, The user characteristic extractor detects a fundamental frequency and a formant frequency from the user voice and obtains user characteristic information corresponding to the detected frequencies using the speech characteristic information modeled as the basic frequency and the formant frequency. A speech recognition and content playback device. The method of claim 2, And the played advertisement is an advertisement selected in consideration of the played content. The method of claim 2, The voice recognition and content reproducing apparatus extracts user characteristic information using the input user image data. The method of claim 8, And the user characteristic information includes at least one of user location information, personnel information, physique information, motion information, used article information, gender information, age information, and emotion information. Communication unit for transmitting and receiving data, A database that stores content and ads, And an advertisement selector for receiving an advertisement corresponding to the user characteristic information from the voice recognition and content reproducing apparatus and selecting the advertisement corresponding to the user characteristic information and transmitting the advertisement to the voice recognition and content reproducing apparatus. The method of claim 10, And the user characteristic information includes at least one of user gender information, age information, and emotion information. The method of claim 10, The selected advertisement is a service providing server, characterized in that the selected advertisement in consideration of the content requested from the user. The method of claim 10, When the user characteristic information is user characteristic information extracted from user image data, the user characteristic information includes at least one of user location information, personnel information, physique information, motion information, use article information, gender information, age information, and emotion information. As a service provision server. In the speech recognition and content providing apparatus advertisement providing method, Extracting user characteristic information using the inputted user voice when a user voice requesting content provision is input; And playing the advertisement corresponding to the user characteristic information together with the requested content. The method of claim 14, The user characteristic information includes at least one of user gender information, age information, emotion information. The method of claim 14, Extracting the user characteristic information; Detecting a fundamental frequency and a formant frequency from the user's voice, and acquiring user characteristic information corresponding to the detected frequencies using voice characteristic information modeled as the fundamental frequency and the formant frequency. . The method of claim 14, Playing the advertisement corresponding to the user characteristic information together with the requested content; Selecting an advertisement to be provided to the user according to the user characteristic information; Playing the selected advertisement with the requested content. The method of claim 14, Playing the advertisement corresponding to the user characteristic information together with the requested content; Transmitting the user characteristic information to the service providing server; Receiving an advertisement selected according to the user characteristic information from the service providing server; Playing the received advertisement with the requested content. The method of claim 14, The advertisement to be played is characterized in that the advertisement is selected in consideration of the content to be played. The method of claim 14, Extracting the user characteristic information; And extracting user characteristic information using the input user image data. The method of claim 20, The user characteristic information includes at least one of user location information, personnel information, physique information, motion information, use article information, gender information, age information, emotion information. In the advertisement providing method of the service providing server, Receiving user characteristic information extracted from the user's voice from the voice recognition and content playback device; Selecting an advertisement corresponding to the user characteristic information from among advertisements stored in the database and transmitting the selected advertisement to the voice recognition and content reproduction apparatus. The method of claim 22, The user characteristic information includes at least one of user gender information, age information, emotion information. The method of claim 22, The selected advertisement is an advertisement providing method characterized in that the selected advertisement in consideration of the content requested from the user. The method of claim 22, When the user characteristic information is user characteristic information extracted from user image data, the user characteristic information includes at least one of user location information, personnel information, physique information, motion information, use article information, gender information, age information, and emotion information. Ad serving method.

Images