KR101020843B1 - Contents and/or channel recommendation method by consumer sensitivity and system thereof - Google Patents

Abstract

Disclosed are a method and system for recommending content and / or channel according to consumer sentiment. The content and / or channel recommendation method includes receiving consumer emotion information including an emotion ratio for at least one emotion generated from a consumer; And a content recommendation degree for each of the plurality of contents based on the at least one metadata including the recommendation ratio for each corresponding emotion among the plurality of contents and the emotion ratio, and at least based on the calculation result. Outputting one piece of content as recommended content. According to the present invention there is an effect that can automatically recommend the content and / or channel in accordance with the consumer sentiment.

Emotion, content, channel

Description

Contents and / or channel recommendation method by consumer sensitivity and system according to consumer emotion

The present invention relates to a method of recommending content and / or a channel, and more particularly, to a method and a system for recommending content and / or a channel according to a consumer's emotion.

With the recent development of digital broadcasting, consumers can watch various contents through a plurality of channels. In addition, with the development of network and multimedia technologies, consumers can enjoy various contents such as movies, music, or text anytime, anywhere.

However, since the channels and contents are created innumerably, it may be difficult for consumers to find the channels and contents that they want, and it is difficult to enjoy the channels and contents that match their emotions.

In particular, when there is no channel or content that a consumer specifically desires in the flood of channels and content, it may be difficult for a consumer to select a channel or content that matches the emotion of the consumer.

For example, when a consumer inadvertently turns on a television, it may not be easy to find a channel that matches his emotion among numerous channels, and when the user visits a specific content server through the Internet, the content that fits his emotion Finding it can be difficult.

Therefore, there is a need for a method and a system capable of automatically providing a channel or content according to emotion even if a consumer does not find a desired channel or content.

Accordingly, the technical problem to be achieved by the present invention relates to a method and system for recommending content and / or channel according to consumer emotion.

The technical problem to be achieved by the present invention relates to a method and system for recommending content and / or channel in accordance with the changing consumer emotion in real time.

In addition, the technical problem of the present invention is to recommend content and / or channel that can provide more suitable content and / or channel to consumers by using metadata including the recommendation ratio by emotion for the content and / or channel And a system thereof.

In accordance with an aspect of the present invention, there is provided a method of recommending content in accordance with consumer emotion, the method comprising: receiving consumer emotion information including an emotion ratio of at least one emotion generated from a consumer; And a content recommendation degree for each of the plurality of contents based on the at least one metadata including the recommendation ratio for each corresponding emotion among the plurality of contents and the emotion ratio, and at least based on the calculation result. Outputting one piece of content as recommended content.

The at least one emotion may include at least one of joy, sadness, displeasure, serenity, and pleasure.

The metadata may further include at least one of a title of the content and an attribute of the content.

(여기서 상기 P'_i는 상기 콘텐츠 추천도, 상기 S_i는 상기 적어도 하나의 감성에 대한 비율, 및 상기 P_i는 상기 적어도 하나의 감성에 대한 추천비율이다.)일 수 있다.The content recommendation degree,

(Wherein P ' _i is the content recommendation degree, S _i is a ratio for the at least one emotion, and P _i is a recommendation ratio for the at least one emotion.).

The consumer sentiment information includes a real-time consumer sentiment rate that changes in real time, and the outputting of the recommendation content includes the at least one metadata for each of the plurality of contents based on the at least one metadata and the real-time runner sentiment rate. Calculating a content recommendation degree and outputting the at least one content as the recommendation content based on a calculation result.

The content recommendation method according to the emotion of the consumer may further include recording, in the metadata, the recommendation ratio for each emotion for each of the plurality of contents before receiving the emotion information.

The outputting of the at least one content as the recommendation content may include calculating at least the content recommendation degree for each of the plurality of contents, and based on the calculated content recommendation degree, the at least one content falling within a predetermined ranking among the plurality of contents. One piece of content can be output as the recommended content.

The content recommendation method according to the emotion of the consumer may further include generating the emotion information based on at least one of a voice, an electrocardiogram, and an EEG of the consumer before receiving the emotion information.

The content may include at least one of music, video, or text.

According to an aspect of the present invention, there is provided a content recommendation system according to consumer emotion, comprising: an emotion information receiver configured to receive consumer emotion information including an emotion ratio of at least one emotion generated from a consumer; And a content recommendation degree for each of the plurality of contents based on the at least one metadata including the recommendation ratio for each corresponding emotion among the plurality of contents and the emotion ratio, and at least based on the calculation result. It may include a content recommendation unit for outputting one piece of content as recommended content.

The at least one emotion may include at least one of joy, sadness, displeasure, serenity, and pleasure.

The metadata may further include at least one of a title of the content and an attribute of the content.

(여기서 상기 P'_i는 상기 콘텐츠 추천도, 상기 S_i는 상기 적어도 하나의 감성에 대한 비율, 및 상기 P_i는 상기 적어도 하나의 감성에 대한 추천비율이다.)일 수 있다.The content recommendation degree,

(Wherein P ' _i is the content recommendation degree, S _i is a ratio for the at least one emotion, and P _i is a recommendation ratio for the at least one emotion.).

The consumer sentiment information includes a real-time consumer sentiment rate that changes in real time, and the content recommendation unit is configured to calculate the content recommendation for each of the plurality of contents based on the at least one metadata and the real-time runner sentiment rate. The at least one content may be output as the recommended content based on the calculation result.

The content recommendation unit may record the recommendation ratio for each emotion for each of the plurality of contents in the metadata before receiving the emotion information.

The content recommendation unit calculates the content recommendation degree for each of the plurality of contents and outputs at least one content falling within a predetermined rank among the plurality of contents as the recommended content based on the calculated content recommendation degree. Can be.

The content recommendation system may further include a consumer emotion detector that generates the emotion information based on at least one of voice, electrocardiogram, and brain wave of the consumer.

The content may include at least one of music, video, or text.

The content recommendation unit may include: a content library configured to receive information about each of the plurality of contents and to generate and store at least one metadata including a recommendation ratio for each corresponding emotion among the plurality of contents; And a content recommendation module that calculates a content recommendation degree for each of the plurality of contents based on the at least one metadata and the emotion ratio, and outputs at least one content as recommended content based on a calculation result. have.

The content recommendation system according to the consumer emotion may be implemented in at least one of a set top box, a TV, a PC, a portable terminal, a PMP, and a notebook computer.

According to an aspect of the present invention, there is provided a channel recommendation method according to consumer emotion, comprising: receiving consumer emotion information including an emotion ratio of at least one emotion generated from a consumer; And calculating channel recommendation for each of the plurality of channels based on the at least one metadata including the recommendation ratio for each corresponding emotion among the plurality of channels and the emotion ratio, and based on the calculation result. And outputting one channel as a recommendation channel.

The at least one emotion may include at least one of joy, sadness, displeasure, serenity, and pleasure.

The metadata may further include at least one of a title of the channel and an attribute of the channel.

(여기서 상기 Q'_i는 상기 채널 추천도, 상기 S_i는 상기 적어도 하나의 감성에 대한 비율, 및 상기 Q_i는 상기 적어도 하나의 감성에 대한 추천비율이다.)일 수 있다.The channel recommendation is

(Wherein Q ' _i is the channel recommendation, S _i is the ratio for the at least one emotion, and Q _i is the recommendation ratio for the at least one emotion.).

According to an aspect of the present invention, there is provided a channel recommendation system according to consumer emotion, comprising: an emotion information receiver configured to receive consumer emotion information including an emotion ratio of at least one emotion generated from a consumer; And calculating channel recommendation for each of the plurality of channels based on the at least one metadata including the recommendation ratio for each corresponding emotion among the plurality of channels and the emotion ratio, and based on the calculation result. It may include a channel recommendation unit for outputting one channel as a recommendation channel.

The at least one emotion may include at least one of joy, sadness, displeasure, serenity, and pleasure.

The metadata may further include at least one of a title of the channel and an attribute of the channel.

(여기서 상기 Q'_i는 상기 채널 추천도, 상기 S_i는 상기 적어도 하나의 감성에 대한 비율, 및 상기 Q_i는 상기 적어 도 하나의 감성에 대한 추천비율이다.)일 수 있다.The channel recommendation is

Where Q ' _i is the channel recommendation, S _i is the ratio for the at least one emotion, and Q _i is the recommendation ratio for the at least one emotion.

The channel recommendation unit may include: a channel information storage unit configured to receive information about each of the plurality of channels and to generate and store at least one metadata including an emotion ratio recommendation ratio for a corresponding channel among a plurality of channels; And a channel recommendation module configured to calculate a channel recommendation for each of the plurality of channels based on the at least one metadata and the emotion ratio, and output at least one channel as a recommendation channel based on a calculation result. have.

The channel recommendation system according to the consumer emotion may be implemented in at least one of a set top box, a TV, a PC, a portable terminal, a PMP, and a notebook computer.

As described above, the method and system for recommending content and / or channel according to the present invention have an effect of automatically recommending content and / or channel according to consumer emotion.

The method and system for recommending the content and / or the channel according to the present invention has the effect of recommending the content and / or the channel according to the consumer's emotion in real time.

In addition, according to the present invention there is an effect that can provide a more suitable content and / or channel to the consumer by using the metadata including the recommendation ratio for each content and / or channel when the content and / or channel recommendation.

In order to fully understand the present invention, the operational advantages of the present invention, and the objects achieved by the practice of the present invention, reference should be made to the accompanying drawings which illustrate preferred embodiments of the present invention and the contents described in the accompanying drawings. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Like reference numerals in the drawings denote like elements.

1 is a block diagram of a content recommendation system according to consumer emotion according to an embodiment of the present invention, FIG. 2 is a diagram for explaining emotion information detected by the consumer emotion detector of FIG. 1, and FIG. 3 is the content of FIG. 1. Represents the configuration of metadata stored in the library.

4 is a view for explaining a process of outputting a list of recommended content in the content recommendation system of FIG. 1. 1 to 4, a content recommendation system 10 (hereinafter, referred to as a “content recommendation system”) according to consumer emotion is a PC, a server, a set-top box, a TV, a notebook, and a portable multimedia player (PMP). The emotion information receiver 12 and the content recommender 14 constituting the content recommendation system 10 may be implemented in hardware (H / W), software (S / W), and / or a combination thereof. Can be.

The emotion information receiver 12 may receive consumer emotion information (sen-info) including an emotion ratio for at least one emotion generated from the consumer.

More specifically, the emotion information receiver 12 may receive the consumer emotion information sen-info including an emotion ratio for the at least one emotion from the consumer emotion detector 5.

The consumer emotion detector 5 may generate the consumer emotion information sen-info based on at least one of voice and biometric information (eg, electrocardiogram, electrocardiogram, skin resistance, brain wave, etc.) of the consumer 3. Can be.

The at least one emotion may include at least one of joy, displeasure, sadness, serenity, and enjoyment, and the consumer emotion detector 5 includes a plurality of emotions based on the voice and biometric information. Consumer sentiment information (sen-info) including the ratio of each of the emotions (joy: S ₁ %, displeasure: S ₂ %, sadness: S ₃ %, ..., and calm: S _k %) Can be generated.

In this case, the emotion of the consumer 3 may be expressed by the following equation 1 when expressed as a plurality of emotions.

(여기서, 상기 S_i는 상기 적어도 하나의 감성에 대한 비율을 나타낸다.)

(S _i represents a ratio for the at least one emotion.)

For example, the consumer emotion detector 5 generates a voice signal based on the voice of the consumer 3 (voice information in FIG. 2), and the ratio of each of the emotions based on the frequency and magnitude of the generated voice signal (Fig. 2). Consumer sentiment information (sen-info) including joy of S: ₁ %, displeasure: S ₂ %, sadness: S ₃ %, ..., and calm: S _k %).

In addition, the consumer emotion detector 5 detects a biosignal based on the biometric information (eg, electrocardiogram, electrocardiogram, skin resistance, and brain wave, etc.) of the consumer 3 and detects the biosignal. Compare with the patterns of each of the predetermined emotions based on and the ratio of each of the emotions based on the comparison result (joy: S ₁ %, discomfort: S ₂ %, sadness: S ₃ %, ..., And tranquility: S _k %) may be generated.

The consumer sentiment detector 5 may be implemented as a device outside the content recommendation system 10, but may also be implemented internally as part of the content recommendation system 10.

The content recommendation unit 14 calculates a content recommendation degree for each of the plurality of contents based on at least one metadata including the recommendation ratio for each corresponding emotion among the plurality of contents and the emotion ratio. At least one content may be output as a recommended content (reco-cont) based on the calculation result.

The content may include at least one of music, video, or text, and may include all media playable by a multimedia device.

The meta data may include a recommendation ratio for each emotion stored in at least one of the content providing server 30 and the content library 16. In this case, the metadata may further include at least one of a title of the content and an attribute of the content.

For example, as shown in FIG. 3, the metadata includes the title of the content (for example, the matrix 4), the recommendation rate by emotion (the recommendation rate is 50% in case of joy, the recommendation rate is 5% in case of displeasure, and the recommendation rate is 20 in case of sadness. %, In the case of calm, the recommended rate may be 20%).

In addition, although not shown in FIG. 3, the metadata further includes attribute information (eg, file format: MPEG-4, Width: 800, Height: 600, Bit rate: 200, and width: 256K) of the corresponding content. Of course it can include.

The content recommendation unit 14 may record the recommendation ratio for each emotion for each of the plurality of contents in the metadata, and may store metadata including the recommendation ratio for each emotion input from the outside.

The content recommendation degree P ′ _i may be calculated by Equation 2 below.

(여기서 상기 P'_i는 상기 콘텐츠 추천도, 상기 S_i는 상기 적어도 하나의 감성에 대한 비율, 및 상기 P_i는 상기 적어도 하나의 감성에 대한 추천비율이다.)

Where _P'i is the content recommendation, S _i is the ratio for the at least one emotion, and P _i is the recommendation ratio for the at least one emotion.

Hereinafter, when the ratio of each of the emotions received by the consumer emotion detector 5 is joy: 50%, discomfort: 30%, sadness: 10%, and calm: 10%, the content recommendation unit 14 recommends content. The process of calculating the degree (P ' _i ) and outputting the recommended content (reco-cont) based on the calculation result will be described in detail.

The content recommendation unit 14 may include a recommendation ratio for the emotion included in the metadata for the content “Matrix 4” of FIG. 3 (for example, in the case of pleasure, the recommendation ratio is 50%, in the case of displeasure, the recommendation ratio is 5%, In the case of sadness, the recommendation ratio is 20%, and in the case of calm, the recommendation ratio is 20%). The recommendation degree _P'i1 for the content “Matrix 4” may be calculated as in Equation 3 below.

Recommendation (P ' _i1 ) of the content “Matrix 4” = 0.5 * 0.5 + 0.3 * 0.05 + 0.1 * 0.2 + 0.1 * 0.2 = 0.585 (i.e. 58.5%)

In addition, the content recommendation unit 14 may include a recommendation ratio (e.g., 60% recommendation rate in the case of joy, 3% recommendation rate in the case of discomfort, 3%, sadness) of the emotion included in the meta data (not shown). If recommended ratio is recommended when the ratio of 10%, and calmness can be based on 50%) to calculate the recommendation level (P _'i2) for the di of the war, as shown in the following equation (4).

Recommend (P ' _i ) of content “D War” = 0.5 * 0.6 + 0.3 * 0.03 + 0.1 * 0.1 + 0.1 * 0.5 = 0.369 (i.e. 36.9%)

In this case, the content recommendation unit 14 compares the recommendation degree (P ' _i1 = 58.5%) of the content “Matrix 4” with the recommendation degree (P ′ _i2 = 36.9%) for the content “D War”. The higher content "Matrix 4" can be output as recommended content (reco-cont).

In addition, when the consumer sentiment information (sen-info) includes a real-time consumer sentiment rate that changes in real time, the content recommendation unit 14 is configured to generate the plurality of pieces based on the at least one metadata and the real-time consumer sentiment rate. The content recommendation degree for each of the contents may be calculated and the at least one content may be output as the recommendation content (reco-cont) based on a calculation result.

That is, according to the embodiment of the present invention, there is an effect of automatically providing recommended content (reco-cont) according to the emotional change of the consumer 3.

In addition, the content recommendation unit 14 calculates the recommendation for each of the plurality of contents and based on the recommended recommendation, at least one of the contents belonging to a predetermined ranking among the plurality of the recommended contents. You can output it as (reco-cont).

For example, the content recommendation unit 14 may output the top 10 contents as recommended content (reco-cont, for example, the list of recommended contents of FIG. 4) based on the recommendation degree for each of the plurality of contents.

The content recommendation unit 14 may include a content library 16 and a content recommendation module 18. The content library 16 may receive information cnt about each of the plurality of contents and generate and store at least one metadata including a recommendation ratio for each corresponding emotion among the plurality of contents. .

For example, the content library 16 receives at least information cnt about each of the plurality of contents from the content providing server 30 and includes at least a recommendation ratio for each of the plurality of contents. You can create and store a single piece of metadata.

Alternatively, the content library 16 may directly receive and store at least one metadata including an externally generated recommendation ratio for each emotion.

The content recommendation module 18 calculates a content recommendation degree for each of the plurality of contents based on the at least one metadata and the emotion ratio, and recommends at least one content based on the calculated result. cont).

5 is a block diagram of a channel recommendation system according to consumer sentiment according to an embodiment of the present invention, FIG. 6 shows a configuration of metadata stored in the channel information storage unit of FIG. 5, and FIG. 7 shows the channel recommendation of FIG. 5. A diagram for describing a process of outputting a channel list in a system.

FIG. 8 illustrates a channel list output from the channel recommendation system of FIG. 5. 5 to 8, a channel recommendation system 20 (hereinafter, referred to as a "channel recommendation system") according to consumer emotion is a PC, a server, a set-top box, a TV, a notebook, and a portable multimedia player (PMP). The emotion information receiver 22 and the channel recommender 24 constituting the channel recommendation system 20 may be implemented in hardware (H / W), software (S / W), and / or a combination thereof. Can be.

The emotion information receiver 22 may receive consumer emotion information (sen-info) including an emotion ratio for at least one emotion generated from the consumer.

Since the emotional information receiver 22 has the same function as the emotional information receiver 12 of FIG. 1, a detailed description thereof will be omitted.

In addition, since the consumer sentiment detector 5, which may be implemented inside the channel recommendation system 10 as part of the channel recommendation system 10, has been described in detail with reference to FIG. 1, a detailed description thereof will be omitted.

The channel recommendation unit 24 calculates a channel recommendation for each of the plurality of channels based on at least one metadata including the recommendation ratio for each corresponding emotion among the plurality of channels and the emotion ratio. At least one channel may be output as an r-channel based on the calculation result.

Each of the plurality of channels is a transmission path of radio waves allocated according to a frequency band provided by a broadcaster server 40 or a broadcasting station transmitter, and a consumer may receive or watch various contents through each of the plurality of channels.

The metadata may include a recommendation ratio for each emotion for each of the plurality of channels received from the broadcaster server 40. In this case, the metadata may further include at least one of a title of a channel and an attribute of the channel.

For example, the metadata may include the title of the channel (eg, M-net), the recommendation ratio by emotion (the recommendation rate is 50% in case of joy, the recommendation rate is 5% in case of displeasure, and the recommendation rate in case of sadness. 20%, in the case of tranquility may include 20%).

In addition, although not shown in FIG. 6, the metadata may further include attribute information (eg, frequency band: 180 to 186 MHz and frequency transmission rate: 64 KbpsD, etc.) for the corresponding channel.

The channel recommender 24 may record the recommendation ratio for each emotion for each of the plurality of channels in the metadata, and may store metadata including the recommendation ratio for each emotion input from the outside.

Wherein the channel like part 24 may calculate the (Q _'i) like the channel by the following equation (5) of.

(여기서 상기 Q'_i는 상기 채널 추천도, 상기 S_i는 상기 적어도 하나의 감성에 대한 비율, 및 상기 Q_i는 상기 적어도 하나의 감성에 대한 추천비율이다.)

Where _Q'i is the channel recommendation, S _i is the ratio for the at least one emotion, and Q _i is the recommendation ratio for the at least one emotion.

The process of calculating the channel recommendation by the channel recommender 24 is the same as or similar to the process by which the content recommender 14 of FIG. 1 calculates the content recommendation P ' _i , and thus a detailed description thereof will be omitted. do.

In addition, when the consumer sentiment information (sen-info) includes a real-time consumer sentiment rate that is changed in real time, the channel recommendation unit 24 based on the at least one metadata and the real-time consumer sentiment ratio The channel for each of the channels may be calculated and the at least one channel may be output as the recommended channel based on the calculation result.

That is, according to the embodiment of the present invention, there is an effect of automatically providing a recommendation channel (r-channel) according to the emotional change of the consumer 3.

In addition, the channel recommendation unit 24 calculates the recommendation for each of the plurality of channels, and based on the calculated recommendation, the recommendation channel among at least one channel belonging to a predetermined rank among the plurality of channels. Can output as (r-channel).

For example, the channel recommendation unit 24 may output the upper m channels as a recommendation channel (r-channel, for example, the recommendation channel list of FIG. 7) based on the channel recommendation for each of the plurality of channels. .

Accordingly, the consumer 3 may select one of the recommended channel lists from the recommended channel list according to the emotion of the consumer using the up / down or left / right buttons of the remote controller as shown in FIG. 8. Can receive channel service according to the emotion of 3).

In this case, when the consumer 3 changes the channel through the remote controller, the channel recommendation unit 24 may control the channel to be changed in order of the channel with the highest channel recommendation.

The channel recommendation unit 24 may include a channel information storage unit 26 and a channel recommendation module 28. The channel information storage unit 26 receives information cnt about each of the plurality of channels and generates and stores at least one metadata including emotion recommendation ratios for the corresponding channels among the plurality of channels. Can be.

For example, the channel information storage unit 26 receives the chan-info for each of the plurality of channels from the broadcaster server 40 and includes a recommendation ratio for each of the plurality of channels for the corresponding content. At least one metadata may be generated and stored.

Alternatively, the channel information storage unit 26 may receive and store at least one metadata including an externally generated recommendation ratio for each emotion.

The channel recommendation module 28 calculates a channel recommendation for each of the plurality of channels based on the at least one metadata and the emotion ratio, and recommends at least one channel based on a result of the calculation. channel).

9 is a flowchart illustrating a content recommendation method according to consumer emotion according to an embodiment of the present invention. 1 and 9, the content library 16 receives content information from the content providing server 30 (S10), and includes at least one recommendation ratio for each corresponding emotion among the plurality of contents. Generate the metadata of (S12).

The consumer sentiment detector 5 receives the consumer sentiment from the consumer 3 (S14) and detects the consumer sentiment information sen-info including the sentiment ratio for the at least one sentiment based on the received consumer sentiment. (S16).

The content recommendation module 18 receives the consumer sentiment information sen-info from the consumer sentiment detector 5 through the sentiment information receiver 22 (S18), and responds to the received consumer sentiment information sen-info. Request and receive the at least one metadata from the content library 16 (S20).

The content recommendation module 18 calculates a content recommendation degree for each of the plurality of contents based on the at least one metadata and the emotion ratio, and recommends at least one content based on the calculated result. (S22).

The content recommendation module 18 outputs information on the recommended content (reco-cont) by the step S22 to the consumer 3 or a consumer multimedia device (S24). In this case, the content recommendation module 18 may directly transmit the recommended content detected by the step S22 among the plurality of contents stored in the content library 16 to the consumer 3.

Alternatively, the content recommendation module 18 transmits the information on the recommended content (reco-cont) in step S22 to the content providing server 30 (S26), and the content providing server 30 sends the recommended content ( Based on the information on the reco-cont, among the plurality of contents stored in the content providing server 30, the recommended content corresponding to the information on the recommended content (reco-cont) may be directly transmitted to the consumer 3 ( S28).

10 is a flowchart illustrating a channel recommendation method according to consumer sentiment according to an embodiment of the present invention. 5 and 10, the channel information storage unit 26 receives channel information (chan-info) from the broadcaster server 40 (S40), and recommends for each channel a corresponding channel among emotions. At least one meta data including the ratio is generated (S42).

The consumer sentiment detector 5 receives the consumer sentiment from the consumer 3 (S44), and detects consumer sentiment information (sen-info) including the sentiment ratio for the at least one sentiment based on the received consumer sentiment. (S46).

The channel recommendation module 28 receives the consumer sentiment information sen-info from the consumer sentiment detector 5 through the sentiment information receiver 22 (S48), and responds to the received consumer sentiment information (sen-info). In step S50, the channel information storage unit 26 requests and receives the at least one metadata.

The channel recommendation module 28 calculates a channel recommendation for each of the plurality of channels based on the at least one meta data and the emotion ratio, and recommends at least one channel based on the result of the calculation. (S52).

The channel recommendation module 28 outputs information on the recommendation channel in step S52 to the consumer 3 or a consumer multimedia device (S54).

Alternatively, the channel recommendation module 18 transmits information on the recommendation channel in step S52 to the broadcaster server 40 (S56), and the broadcaster server 40 information on the recommendation channel (r-channel). Based on the broadcast of the recommendation channel (r-channel) corresponding to the information (r-channel) of the recommended channel among the plurality of channels stored in the broadcaster server 40 can be directly transmitted to the consumer (3) S58).

1 and 5 illustrate an independent content recommendation system 10 or a channel recommendation system 20, respectively, but the content recommendation system 10 and the channel recommendation system 20 may be implemented as one system. Of course it can. At this time, the consumer emotion detector 5 may also be implemented in the one system.

The present invention can be embodied as computer readable codes on a computer readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, optical data storage, and the like. The computer readable recording medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion. And functional programs, codes and code segments for implementing the present invention can be easily inferred by programmers in the art to which the present invention belongs.

Although the present invention has been described with reference to one embodiment shown in the drawings, this is merely exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Therefore, the true technical protection scope of the present invention will be defined by the technical spirit of the appended claims.

BRIEF DESCRIPTION OF THE DRAWINGS In order to better understand the drawings cited in the detailed description of the invention, a brief description of each drawing is provided.

1 is a block diagram of a content recommendation system according to consumer sentiment according to an embodiment of the present invention.

FIG. 2 is a diagram for describing emotion information detected by the consumer emotion detector of FIG. 1.

3 illustrates a configuration of meta data stored in the content library of FIG. 1.

4 is a view for explaining a process of outputting a list of recommended content in the content recommendation system of FIG. 1.

5 is a block diagram of a channel recommendation system according to consumer sentiment according to an embodiment of the present invention.

FIG. 6 illustrates a configuration of metadata stored in the channel information storage of FIG. 5.

FIG. 7 is a diagram for describing a process of outputting a channel list in the channel recommendation system of FIG. 5.

FIG. 8 illustrates a channel list output from the channel recommendation system of FIG. 5.

9 is a flowchart illustrating a content recommendation method according to consumer emotion according to an embodiment of the present invention.

10 is a flowchart illustrating a channel recommendation method according to consumer emotion according to an embodiment of the present invention.

Claims (31)

In the content recommendation method according to the emotion of the consumer in the content recommendation system having an emotional information receiving unit and the content recommendation unit, Receiving consumer emotion information including an emotion ratio indicating a ratio of each of two or more emotions generated from the consumer; Calculating a content recommendation degree for each of the plurality of contents based on the emotion ratio and at least one metadata including emotion recommendation ratios for the corresponding contents among a plurality of contents; And Outputting, as recommended content, at least one content that falls within a predetermined rank among the plurality of contents based on the calculated content recommendation degree, Before the step of receiving the consumer emotion information, The consumer emotion information is generated by a consumer emotion detector based on at least one of the voice, electrocardiogram, or brain wave of the consumer, and the consumer's recommendation ratio for each of the plurality of contents is recorded in the metadata. How to recommend content based on emotion. The method of claim 1, wherein the two or more emotions, A method of recommending content according to a consumer's emotion including at least two of joy, sadness, displeasure, serenity, and enjoyment. The method of claim 1, wherein the metadata is The content recommendation method according to the emotion of the consumer further comprises at least one of the title of the content and the attribute of the content. The method of claim 1, wherein the content recommendation degree is

Wherein P ' _i is the content recommendation degree, S _i is the ratio of each of the two or more emotions, and P _i is the recommendation ratio for each of the two or more emotions. The method of claim 1, wherein the consumer emotion information, Includes real-time consumer sentiment rates, The step of calculating the content recommendation, Calculating the content recommendation for each of the plurality of contents based on the at least one metadata and the real-time consumer sentiment rate; The real-time consumer sentiment ratio Content recommendation method according to the consumer emotion that is the ratio of each of the emotions generated in real time by the consumer. delete delete delete The method of claim 1, wherein the content is: A content recommendation method comprising at least one of music, video, or text. A computer readable recording medium for performing the method of claim 1. An emotion information receiver configured to receive consumer emotion information including an emotion ratio indicating a ratio of each of two or more emotions generated from a consumer; And A content recommendation for each of the plurality of contents is calculated based on at least one metadata including emotion recommendation ratios for the corresponding contents among the plurality of contents and the emotion ratio, and the calculated content recommendation A content recommendation unit configured to output, as recommended content, at least one content within a predetermined ranking among the plurality of contents based on the result; Before the emotional information receiver receives the consumer emotional information, The consumer emotion information is generated by a consumer emotion detector based on at least one of the voice, electrocardiogram, or brain wave of the consumer, and the consumer's recommendation ratio for each of the plurality of contents is recorded in the metadata. Content recommendation system based on emotion. The method of claim 11, wherein the two or more emotions, A content recommendation system according to the consumer's emotion, including at least two of joy, sadness, displeasure, serenity, and enjoyment. The method of claim 11, wherein the metadata, Content recommendation system according to the consumer emotion further comprises at least one of the title of the content and the attributes of the content. The method of claim 11, wherein the content recommendation degree,

Wherein P ' _i is the content recommendation degree, S _i is the ratio of each of the two or more emotions, and P _i is the recommendation ratio for each of the two or more emotions. The method of claim 11, wherein the consumer emotion information, Includes real-time consumer sentiment rates, The content recommendation unit, Calculate the content recommendation for each of the plurality of contents based on the at least one metadata and the real-time consumer emotion ratio, The real-time consumer sentiment ratio Content recommendation system according to the consumer emotion that is the ratio of each of the emotions generated in real time by the consumer. delete delete delete The method of claim 11, wherein the content is: A content recommendation system comprising at least one of music, video, or text. The method of claim 11, wherein the content recommendation unit, A content library that receives information about each of the plurality of contents and generates and stores the at least one metadata including a recommendation ratio for each corresponding emotion among the plurality of contents; And A consumer emotion module including a content recommendation module for calculating a content recommendation degree for each of the plurality of contents based on the at least one metadata and the emotion ratio, and outputting at least one content as recommended content based on a calculation result Content recommendation system according to. The system of claim 11, wherein the content recommendation system according to the consumer's emotion is provided. Content recommendation system according to the consumer emotion implemented in at least one of a set-top box, a TV, a PC, a portable terminal, a PMP, and a laptop. In the channel recommendation method according to the emotion of the consumer in the channel recommendation system having an emotional information receiving unit and a channel recommendation unit, Receiving consumer emotion information including an emotion ratio indicating a ratio of each of two or more emotions generated from the consumer; Calculating a channel recommendation for each of the plurality of channels based on at least one metadata including emotion recommendation ratios for the corresponding channels among the plurality of channels and the emotion ratios; And Outputting at least one channel falling within a predetermined rank among the plurality of channels based on the calculated channel recommendation as a recommendation channel, Before the step of receiving the consumer emotion information, The consumer sentiment information is generated by a consumer sentiment detector based on at least one of the voice, electrocardiogram, or brain wave of the consumer, and the recommendation ratio for each sentiment for each of the plurality of channels is recorded in the metadata. Channel recommendation method based on emotion. The method of claim 22, wherein the two or more emotions, At least two of joy, sadness, displeasure, serenity, and pleasure, When the consumer changes the channel through the remote control, the consumer sentiment controlled by the channel recommender to change the channel in the order of the upper m (m is an integer of 1 or more) belonging to the predetermined ranking based on the channel recommendation How to recommend a channel according to. The method of claim 22, wherein the metadata, The channel recommendation method according to the emotion of the consumer further comprises at least one of the title of the channel and the attribute of the channel. The channel recommendation of claim 22,

Where _Q'i is the channel recommendation, S _i is the ratio of each of the two or more emotions, and Q _i is the recommendation ratio for each of the two or more emotions. An emotion information receiver configured to receive consumer emotion information including an emotion ratio indicating a ratio of each of two or more emotions generated from a consumer; And A channel recommendation for each of the plurality of channels is calculated based on at least one metadata including emotion recommendation ratios for the corresponding channels among the plurality of channels and the emotion ratio, and the calculated channel recommendation is calculated. A channel recommendation unit configured to output, as a recommendation channel, at least one channel belonging to a predetermined rank among the plurality of channels based on the result; Before the emotional information receiver receives the consumer emotional information, The consumer sentiment information is generated by a consumer sentiment detector based on at least one of the voice, electrocardiogram, or brain wave of the consumer, and the recommendation ratio for each sentiment for each of the plurality of channels is recorded in the metadata. Channel recommendation system according to emotion. The method of claim 26, wherein the two or more emotions, At least two of joy, sadness, displeasure, serenity, and pleasure, When the consumer changes the channel through the remote control, the consumer sentiment controlled by the channel recommender to change the channel in the order of the upper m (m is an integer of 1 or more) belonging to the predetermined ranking based on the channel recommendation Channel recommendation system according to. The method of claim 26, wherein the metadata, The channel recommendation system according to the emotion of the consumer further comprises at least one of the title of the channel and the attribute of the channel. The channel recommendation of claim 26,

Where _Q'i is the channel recommendation, S _i is the ratio of each of the two or more emotions, and Q _i is the recommendation ratio for each of the two or more emotions. The channel recommendation unit of claim 26, A channel information storage unit for receiving information on each of the plurality of channels and generating and storing the at least one meta data including a recommendation ratio for each corresponding channel among the plurality of channels; And A consumer sentiment comprising a channel recommendation module for calculating a channel recommendation for each of the plurality of channels based on the at least one metadata and the sentiment ratio and outputting at least one channel as a recommendation channel based on a result of the calculation Channel recommendation system according to. The channel recommendation system according to claim 26, wherein Channel recommendation system according to consumer sentiment implemented in at least one of a set-top box, a TV, a PC, a portable terminal, a PMP, and a laptop.

Images