KR20150020390A - Content recommendation method, and apparatas and system for providing the method - Google Patents

Abstract

The purpose of the present invention is to provide a content recommending method, and a content recommending apparatus and system for providing the same, which generate content recommendation information that can lead actual purchases of users. The content recommending system according to the present invention comprises: multiple content receiving devices which receive content recommendation information from a content recommending apparatus; and the content recommending apparatus which stores content purchase history information of the multiple content receiving devices, analyzes user purchase characteristics of each of categories of content referring to the content purchase history information, determines recommendation logic for the categories of the content, each of which corresponds to each of the categories of the content, in accordance with a result of the analysis, wherein each of the recommendation logic includes one or more recommending methods and the priorities of the one or more recommending methods, generates recommendation information including at least one set of content based on the determined recommendation logic, and provides the recommendation information to the content receiving devices.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a content recommendation method,

The present invention relates to a content recommendation method and apparatus and system for providing the same, and more particularly, to a content recommendation method for implementing a content recommendation algorithm optimized for a content receiving apparatus such as a smart phone, a tablet PC, To a content receiving apparatus, and to an apparatus and a system for providing the content recommendation method.

With the recent development of mobile communication technology and the spread of smart phones, there has been a demand for users of various high-quality multimedia services using mobile terminals such as smart phones and tablet PCs, A variety of techniques are being developed to provide content that can be matched to a user.

The most appropriate way to induce the purchase of content to the user of the mobile terminal is to recommend content that the user is expected to use or view.

However, in providing such content recommendation information, it is important to develop an algorithm that can determine the optimal content by appropriately considering the profile, purchase history, and current situation of each mobile terminal user.

For example, there has been a collaborative filtering algorithm (Collaborate Filtering Algorithm) and an Associate Rule method for recommending an application as a method for determining an optimum content for a user.

The collaborative filtering algorithm is a method of identifying a user's tendency through data mining and recommending a content product with reference to a content preferred by another user having a similar tendency to an identified user's tendency, Based on the fact that it is highly likely to prefer the past favorite products in the future, it is a method of collecting user's purchasing history and recommending the contents based on the purchase history.

However, contents products such as broadcasts, movies, music, e-books, cartoons, etc. are different in structure of other applications and product meta data, and it is also confirmed that there are different purchasing characteristics in each category.

As a result, it may not be appropriate to provide content information to a user using the same algorithm for a content item having various attributes.

Therefore, for each digital content product, there is a need for a content recommendation methodology that is differentiated from the existing recommendation methodology and is specialized for the corresponding content item based on the meta data characteristic of the product and data analysis.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and it is an object of the present invention to provide content recommendation information to be provided to a user, in which, in order to select a content, A content recommendation method for recommending content to be mapped optimally with an actual preference of a user as a result of determining a recommendation method by analyzing the characteristics and generating recommendation information of the determined content according to the recommendation method, The purpose of the system is to provide.

The above object is achieved by a content recommendation apparatus according to the present invention, comprising: a purchase history storage unit for collecting and storing content purchase history information of a plurality of content receiving apparatuses; A purchasing characteristic analyzer for analyzing purchase characteristics of a user for each category of contents by referring to the purchase history information; A recommendation logic for each content category corresponding to each category of the content according to an analysis result of the purchase characteristics, the recommendation logic determining at least one recommendation method and a priority of the at least one recommendation method; A recommendation information generation unit for generating recommendation information including at least one content based on the determined recommendation logic; And a recommendation information providing unit for providing the generated recommendation information to the content receiving apparatus.

Here, the recommendation information generation unit may assign weights according to priorities of at least one recommendation method included in the recommendation logic, multiply the scores of the contents selected using each recommendation method by the weights, Can be selected.

Here, the recommendation information generation unit may generate the recommendation information using a recommendation method in which the priority order of the recommendation method is within a predetermined range.

The recommendation method may include at least one of continuity-based recommendation, genre-based recommendation, person similarity-based recommendation, and purchase history-based recommendation. The recommendation method may include at least one of a broadcast, movie, music, e-book, .

Here, the continuity-based recommendation method may be to recommend the latest turnover when there is a latest turnover added within a predetermined period after the user purchases the last turnover.

Here, the genre-based recommendation method may recommend at least one of the same genre contents when the user purchases the same genre of content over a predetermined number of times for a predetermined period of time.

Here, the personality similarity-based recommendation method may be a method in which at least one of a plurality of purchased content and an author, a publisher, and a publisher recommends the same content according to the purchase history information of the user.

Here, the purchase characteristic analyzing unit may update the purchase characteristics for each category based on content purchase history information of a plurality of users.

The content providing apparatus may further include a content providing unit for providing the content receiving apparatus with the content selected based on the provided recommendation information.

According to another aspect of the present invention, there is provided a content recommendation method comprising: collecting and storing content purchase history information of a plurality of content receiving apparatuses; Analyzing a purchase characteristic of a user for each category of contents by referring to the purchase history information; Determining recommendation logic for each content category corresponding to each category of the content according to an analysis result of the purchase characteristics, the recommendation logic including at least one recommendation method and a priority of the at least one recommendation method; Generating content recommendation information based on the determined recommendation logic; And providing the generated recommendation information to the content receiving apparatus.

Here, the step of generating the content recommendation information may be performed by assigning weights according to priorities of at least one recommendation method included in the recommendation logic, multiplying the scores of the contents selected using the recommendation methods by the weights , And selecting at least one content included in the recommendation information.

Here, the step of generating the content recommendation information may include generating the recommendation information using a recommendation method in which the priority of the recommendation method is within a predetermined range.

The recommendation method may include at least one of continuity-based recommendation, genre-based recommendation, person similarity-based recommendation, and purchase history-based recommendation. The recommendation method may include at least one of a broadcast, movie, music, e-book, .

Here, the continuity-based recommendation method may be to recommend the latest turnover when there is a latest turnover added within a predetermined period after the user purchases the last turnover.

Here, the genre-based recommendation method may recommend at least one of the same genre contents when the user purchases the same genre of content over a predetermined number of times for a predetermined period of time.

Here, the personality similarity-based recommendation method may be a method in which at least one of a plurality of purchased content and an author, a publisher, and a publisher recommends the same content according to the purchase history information of the user.

Here, the method may further include updating the purchase characteristics of each category based on content purchase history information of a plurality of users.

The method may further include providing the selected content to the content receiving apparatus based on the provided recommendation information.

According to another aspect of the present invention, there is provided a content recommendation system comprising: a plurality of content receiving apparatuses for receiving content recommendation information from a content recommendation apparatus; And storing content purchase history information of the plurality of content receiving apparatuses, analyzing a purchase characteristic of a user for each category of content by referring to the purchase history information, Wherein the recommendation logic determines at least one recommendation method and a priority of the at least one recommendation method based on the recommended recommendation logic, and based on the determined recommendation logic, recommendation information including at least one content And a content recommendation apparatus for providing the content recommendation system to the content reception apparatus.

As described above in detail, in the present invention, in generating content recommendation information to be provided to a user, in order to select a content that an actual user prefers and can lead to purchase, A content recommendation method for recommending contents to be mapped optimally with an actual preference of a user and a content recommendation apparatus and a content recommendation system for providing the content recommendation method can be provided have.

1 is a block diagram of a content providing system including a content recommendation apparatus and a plurality of content receiving apparatuses according to the present invention.
2 is a flowchart of a content providing method according to the present invention.

It is noted that the technical terms used herein are used only to describe specific embodiments and are not intended to limit the invention. It is also to be understood that the technical terms used herein are to be interpreted in a sense generally understood by a person skilled in the art to which the present invention belongs, Should not be construed to mean, or be interpreted in an excessively reduced sense. Further, when a technical term used herein is an erroneous technical term that does not accurately express the spirit of the present invention, it should be understood that technical terms that can be understood by a person skilled in the art are replaced. In addition, the general terms used in the present invention should be interpreted according to a predefined or prior context, and should not be construed as being excessively reduced.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to like or similar elements throughout the several views, and redundant description thereof will be omitted. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. It is to be noted that the accompanying drawings are only for the purpose of facilitating understanding of the present invention, and should not be construed as limiting the scope of the present invention with reference to the accompanying drawings. The spirit of the present invention should be construed as extending to all modifications, equivalents, and alternatives in addition to the appended drawings.

1 is a block diagram of a content recommendation system according to the present invention.

As shown in the figure, the content recommendation system according to the present invention may include a content recommendation apparatus 100 and a plurality of content receiving apparatuses 200.

The content receiving apparatus 200 can be implemented as a smart phone, a tablet PC, a desktop PC, a laptop PC, a PDA, a digital TV, or the like, as an apparatus that can receive and execute contents.

The content receiving apparatus 200 can access the web server of the content recommendation apparatus 100 using an IP (internet protocol) wired / wireless communication network, receives recommendation information to be described later, The content recommendation apparatus 100 can receive the content.

The content referred to in the present invention may include an application, a broadcast, a movie, a music, a comic, etc., and may include any kind of application program or file that can be executed in the content receiving apparatus 200.

The content recommendation apparatus 100 is implemented as a server that plays a role of providing content recommendation information and contents to a plurality of content receiving apparatuses 200 connected through an IP network and collects and analyzes information for generating content recommendation information Algorithm.

Hereinafter, the detailed configuration of the content recommendation apparatus 100 will be described in detail.

1, the content recommendation apparatus 100 includes a database 110, a purchase characteristic analyzer 120, a recommendation information generator 130, a recommendation information provider 140, a content provider 150 ).

According to the embodiment of the present invention, even if a part of the configuration shown in FIG. 1 is omitted, there is no problem in implementing the content recommendation apparatus 100 according to the present invention.

The database unit 110 stores a database related to content recommendation in the content recommendation apparatus and includes a user information storage unit 112, a purchase history storage unit 114, a recommendation history storage unit 116, (118).

The user information storage unit 112 stores a profile of a user of the content receiving apparatus 200 for purchasing the content.

For example, user information such as sex, age, access time zone, preferred content category, etc. of the user of the content receiving apparatus 200 can be stored.

The purchase history storage unit 114 collects and stores content purchase history information of a plurality of content receiving apparatuses 200.

Specifically, the purchase history of each content receiving apparatus 200 can be stored by date, time, or category.

The recommendation record storage unit 116 may store the history of recommendation information provided to each content receiving apparatus 200 by the recommendation apparatus 100. [

Specifically, history of contents recommended for each category of contents, information on whether the user has purchased actual contents corresponding to recommendation information, and the like can be stored.

The content storage unit 118 stores content files including broadcasting, movies, music, e-books, cartoons, and the like.

The purchase characteristic analyzing unit 120 analyzes the purchasing characteristics of the user for each content category by referring to the content purchase history information of the content receiving apparatus 200 stored in the purchase history storing unit 114. [

The conventional content recommendation apparatus 100 may include a collaborative filtering algorithm for recommending a content item with reference to a content preferred by another user having a tendency similar to a tendency of the user of the identified content receiving apparatus 200, Based on the fact that there is a high likelihood that the preferred product will be preferred in the future, the recommendation information is generated according to the purchase association method in which the purchase history of the user is collected and the content item is recommended based on the purchase history.

The content recommendation apparatus 100 according to the present invention may be configured such that the user has different purchasing characteristics for each category of content, for example, broadcasting, movie, music, e-book, (120), it is analyzed what kind of purchasing characteristic the user has for each category of contents.

The analysis result of the purchase characteristic analyzing unit 120 is as follows.

In the case of broadcast and comic contents, it is general that the user wants to purchase the next time of the content that has been watched recently. Therefore, the purchase continuity can be a main factor of recommending the content.

In addition, in the case of comic books and e-books, there is a tendency to purchase other contents produced by the same author as contents already purchased, so that the degree of similarity of the characters of the artist and the like can be a main factor of content recommendation.

On the other hand, the purchase history storage unit 114 continuously collects and stores the content purchase history information of the plurality of content receiving apparatuses 200, and the purchasing characteristic analyzing unit 120 determines, based on the updated content purchase history information, You can update purchase characteristics by category.

Accordingly, it is possible to generate appropriate content recommendation information according to the purchasing characteristics of the changing user.

The recommendation information generating unit 130 generates content recommendation information for instructing the user of the content receiving apparatus 200 to purchase the content.

The content recommendation information may include at least one content, and may include information such as a content name, a category, a brief content, a number of downloads, and evaluation of other users.

The content recommendation information determines recommendation logic for each content category corresponding to each content category according to the analysis of the purchase characteristics analyzed by the purchase characteristics analyzer 120.

Here, the recommendation logic may select at least one recommendation method and may include the priority of the selected recommendation method.

For example, for the content included in the broadcast category, the analysis result of the purchase characteristic analyzer 120, the continuity-based recommendation method, the purchase history-based recommendation method, and the gender or age-based group recommendation method are selected according to priorities And can generate the recommendation information including the content selected by each recommendation method according to the selected recommendation method and priority.

That is, the recommendation logic is for selecting the most appropriate content for each category, focusing on the fact that the user exhibits different purchasing characteristics according to the category of the content.

In the present invention, the recommendation method may include a purchase history based recommendation method, a group recommendation method, a continuity based recommendation method, a genre based recommendation method, and a person similarity recommendation method.

The purchase history based recommendation method may be a known purchase related method in a manner of selecting and recommending contents similar to the contents purchased in the content receiving apparatus 200 on the basis of the purchase history information of the user.

The group recommendation method is a method of recommending contents with reference to a user's personal profile, and recommends popular contents to users belonging to a group having similar age, age, and access time.

Continuity based recommendation method is recommended based on continuity with recently purchased content.

For example, in the case of broadcast contents, a plurality of times are uploaded at predetermined intervals, and when the user has a latest uploaded uploaded within a predetermined period after purchasing the last uploaded content, the latest uploaded content can be recommended .,

Typically, in the case of broadcast or comic content, the user tends to purchase a particular broadcast or comic book in order of each turn, and this continuity based recommendation method can be analyzed as being the highest priority in the purchase characteristics analysis have.

The genre-based recommendation method recommends at least one of the contents of the same genre when the user purchases the same genre of contents over a predetermined period of time.

Typically, in the case of movies or music content, users tend to prefer content of the same genre, and such a genre-based recommendation method can be analyzed as having the highest priority as a result of purchasing characteristic analysis.

The personality similarity-based recommendation method is a method in which at least one of a content purchased by a user and a writer, a publisher, and a publisher recommends other contents according to the purchase history information of the user.

Generally, in the case of an e-book or a cartoon content, a user tends to prefer content written by the same author or content produced by the same manufacturer or publisher. Such a personality similarity- It can be analyzed as being a priority.

Meanwhile, as described above, the recommendation information generation unit 130 determines recommendation logic for each category of content, and the recommendation logic includes at least one recommendation method and includes priority of each recommendation method.

In addition, the recommendation information generation unit 130 can generate the recommendation information using the recommendation method in which the priority is within a predetermined range.

Specifically, when the top three methods among the recommendation methods are determined according to the priority of the recommendation method, the recommendation information can be generated by selecting three contents that are most appropriate according to each recommendation method.

For example, when the recommendation logic is determined in the order of the analysis of the purchase characteristics regarding the broadcast content category, the continuity based recommendation, the purchase history based recommendation, and the person similarity based recommendation, Based on the purchase history-based recommendation method, content related to the content recently purchased according to the purchasing history-based recommendation method, and content similar to that of the author or the publisher Can be selected and recommended.

In another embodiment, the recommendation information generation unit 130 assigns weights according to the determined priorities of the recommendation methods, multiplies the scores of the contents selected using the recommendation methods by the weights, and stores at least one Can be selected.

Specifically, the recommendation score score (j) of the specific content j is determined by the following formula, and recommendation information can be generated by selecting a predetermined number of contents having the highest recommendation score.

Here, i is the identifier of the recommendation method, n is the number of recommendation methods determined according to the recommendation logic, w (i) is the weight of the recommendation method i, p (i, j) it means.

The recommendation information providing unit 140 provides the content providing apparatus with the content recommendation information generated by the recommendation information generating unit 130. [

The recommendation information providing unit 140 may provide recommendation information corresponding to each content receiving apparatus 200 through the IP network.

When the content receiving apparatus 200 receives the recommendation information, the content receiving apparatus 200 displays a user interface for purchasing the content based on the received recommendation information, and when the user requests content purchase through the user interface The content recommendation apparatus 100 may request the content recommendation apparatus 100 to transmit the content.

As described above, the recommendation information received by the content receiving apparatus 200 includes information on at least one content, and may include the priority of each content. Depending on the setting of the content receiving apparatus 200 Only the contents corresponding to the predetermined number of the priorities can be displayed through the user interface.

In addition, the content receiving apparatus 200 may display information such as name, category, brief content, number of downloads, evaluation of other users according to recommendation information, and may induce the user to purchase the content.

The content providing apparatus 150 transmits the requested content to the content receiving apparatus 200 at the request of the content receiving apparatus 200.

The content providing unit 150 may transmit the content stored in the content storage unit 118 or the content received from the external content server through the IP network to the content receiving apparatus 200. [

Hereinafter, an example of recommendation logic determined for each category of contents will be described in detail.

As described above, the content category includes at least one of broadcasting, movie, music, e-book, and comic, and recommendation methods include at least one of continuity based recommendation, genre based recommendation, . ≪ / RTI >

The recommendation information generation unit 130 determines the recommendation logic by referring to the analysis result of the purchase characteristic analysis unit 120. This is because the recommendation information generation unit 130 determines the recommendation logic in the order of contents determined according to the recommendation method, It is for recommending contents.

First, in the case of the cartoon category, recommendation logic can be determined in the order of continuity based recommendation, person similarity based recommendation, purchase history based recommendation, genre based recommendation, and sex / age based group recommendation.

For example, based on the continuity-based recommendation, if there is a latest latest registered within the last 60 days since the last purchased purchase based on the recent 60-day purchase history of the content receiving apparatus 200, I can recommend it by priority

Next, according to the popularity similarity-based recommendation, it is possible to recommend content produced by the same author as the author of the cartoon content that the content receiving apparatus 200 has purchased a lot.

Next, according to the genre-based recommendation, when the user purchases the same genre, for example, comedy genre content five or more times in the last 60 days, other contents in the comedy genre can be recommended.

In the case of the broadcast category, the recommendation logic may be determined in the order of the continuity based recommendation, the purchase history based recommendation, and the sex / age based group recommendation in the analysis result of the purchase characteristics analyzer 120.

For example, when there is a latest latest registered content within the last 30 days since the last purchased content based on the latest 30-day purchase history of the content receiving apparatus 200, the content of the latest content can be recommended as a top priority .

In the case of the e-book category, recommendation logic can be determined in order of recommendation based on person similarity, purchase history based recommendation, and sex / age based group recommendation.

In the case of the movie and music category, recommendation logic can be determined in the order of genre-based recommendation, purchasing history-based recommendation, and sex / age-based group recommendation.

The recommendation logic for each category may be different according to the analysis result of the purchasing characteristic analyzer 120 and the purchasing characteristic analyzer 120 may calculate the recommendation logic based on the content purchase history information of a plurality of users , And can update the purchase characteristics by category.

According to the present invention, the recommendation method is determined by analyzing the purchase characteristics of users according to the category of the content, and the recommendation information of the determined content is generated. As a result, the content recommendation apparatus 100 < / RTI >

2 is a flowchart of a content recommendation method according to the present invention.

Hereinafter, description of the same technical features as those of the present invention described with reference to FIG. 1 will be omitted.

A content receiving apparatus 200 according to the present invention can be implemented as a smart phone, a tablet PC, a desktop PC, a laptop PC, a PDA, a digital TV, and the like, May be implemented as a server for providing content recommendation information and contents to a plurality of content receiving apparatuses 200 connected through an IP network.

The content recommendation apparatus 100 collects and stores content purchase history information of a plurality of content receiving apparatuses 200 (S110).

The content recommendation apparatus 100 refers to the stored purchase history information and analyzes the purchase characteristics of the user for each category of the content (S120).

Here, the category of the content may include at least one of broadcast, movie, music, e-book, and comic.

If there is a request for providing recommendation information from the content receiving apparatus 200, the recommendation apparatus 100 determines recommendation logic for each content category according to the analysis of the purchase characteristics (S130).

Wherein the recommendation logic includes at least one recommendation method corresponding to each category of content and a priority of the at least one recommendation method.

In the present invention, the recommendation method may include a purchase history based recommendation method, a group recommendation method, a continuity based recommendation method, a genre based recommendation method, and a person similarity recommendation method.

The purchase history based recommendation method may be a known purchase related method in a manner of selecting and recommending contents similar to the contents purchased in the content receiving apparatus 200 on the basis of the purchase history information of the user.

The group recommendation method is a method of recommending contents with reference to a user's personal profile, and recommends popular contents to users belonging to a group having similar age, age, and access time.

Continuity based recommendation method is recommended based on continuity with recently purchased content.

The genre-based recommendation method recommends at least one of the contents of the same genre when the user purchases the same genre of contents over a predetermined period of time.

The personality similarity-based recommendation method is a method in which at least one of a content purchased by a user and a writer, a publisher, and a publisher recommends other contents according to the purchase history information of the user.

An example of the recommendation method is as described above with reference to FIG.

The content recommendation apparatus 100 selects at least one content included in the recommendation information according to the determined recommendation logic.

In this case, at least one content can be selected based on the weight given in accordance with the priority of the recommendation method (S141).

Specifically, the recommendation score score (j) of the specific content j is determined by the following formula, and recommendation information can be generated by selecting a predetermined number of contents having the highest recommendation score.

Here, i is the identifier of the recommendation method, n is the number of recommendation methods determined according to the recommendation logic, w (i) is the weight of the recommendation method i, p (i, j) it means.

In another embodiment, at least one content may be generated according to each recommendation method using a recommendation method having a priority within a predetermined range (S142).

Specifically, when the top three methods among the recommendation methods are determined according to the priority of the recommendation method, the recommendation information can be generated by selecting three contents that are most appropriate according to each recommendation method.

For example, when the recommendation logic is determined in the order of the analysis of the purchase characteristics regarding the broadcast content category, the continuity based recommendation, the purchase history based recommendation, and the person similarity based recommendation, Based on the purchase history-based recommendation method, content related to the content recently purchased according to the purchasing history-based recommendation method, and content similar to that of the author or the publisher Can be selected and recommended.

The content recommendation apparatus 100 generates recommendation information including at least one content selected in accordance with the recommendation logic (S150).

The content recommendation apparatus 100 provides the generated recommendation information to the content receiving apparatus 200 (S160).

The content receiving apparatus 200 receiving the recommendation information displays a user interface capable of purchasing the content based on the received recommendation information. When the user requests content purchase through the user interface, the content recommendation apparatus 100 And may request the transmission of the content.

The content recommendation apparatus 100 may provide the content according to a request from the content receiving apparatus 200 (S170).

According to the present invention, a recommendation method is determined by analyzing purchase characteristics of users according to a content category, and as a result of generating recommendation information of the determined content, a content recommendation method, which is preferred by an actual user, .

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

According to the content recommendation apparatus and the content recommendation method of the present invention, the recommendation method is determined by analyzing the purchase characteristics of the users for each category of the content, and the recommendation information of the determined content is generated. As a result, It is not only the use of the related technology but also the possibility of commercialization or operation of the applied device is sufficient and it is practically possible to carry out clearly, It is an invention.

100: content recommendation apparatus 110:
112: user information storage unit 114: purchase history storage unit
116: a recommendation history storage unit 118: a content storage unit
120: purchase characteristic analyzing unit 130: recommendation information generating unit
140: Recommendation information Offering 150: Offering contents
200: Content receiving device

Claims (19)

A content recommendation apparatus comprising:
A purchase history storage unit for collecting and storing content purchase history information of a plurality of content receiving apparatuses;
A purchasing characteristic analyzer for analyzing purchase characteristics of a user for each category of contents by referring to the purchase history information;
A recommendation logic for each content category corresponding to each category of the content according to an analysis result of the purchase characteristic, the recommendation logic determining at least one recommendation method and a priority of the at least one recommendation method; A recommendation information generation unit for generating recommendation information including at least one content based on the determined recommendation logic; And
And a recommendation information providing unit for providing the generated recommendation information to the content receiving apparatus. The method according to claim 1,
Wherein the recommendation information generation unit assigns weights according to priorities of at least one recommendation method included in the recommendation logic, multiplies the scores of the contents selected using each recommendation method by the weights, And the content recommendation apparatus selects the at least one content. The method according to claim 1,
And the recommendation information generation unit generates the recommendation information by using a recommendation method in which the priority order of the recommendation method is within a predetermined range. 4. The method according to any one of claims 1 to 3,
Wherein the category of the content includes at least one of a broadcast, a movie, a music, an e-book, and a comic, and the recommendation method includes at least one of continuity based recommendation, genre based recommendation, Content recommendation apparatus. 5. The method of claim 4,
Wherein the continuity-based recommendation method recommends the latest occurrence when there is a latest occurrence of an addition within a predetermined period of time after the user purchases the last occurrence. 5. The method of claim 4,
Wherein the genre-based recommendation method recommends at least one of the same genre content when the user purchases the same genre of content over a predetermined number of times for a predetermined period of time. 5. The method of claim 4,
Wherein the recommendation method is based on recommendation of at least one of a plurality of purchased contents and at least one of an author, a publisher, and a publisher based on purchase history information of a user. The method according to claim 1,
Wherein the purchasing characteristic analyzing unit comprises:
And updates the purchase characteristics for each category based on content purchase history information of a plurality of users. The method according to claim 1,
And a content providing unit for providing the content receiving apparatus with the content selected based on the provided recommendation information. In the content recommendation method,
Collecting and storing content purchase history information of a plurality of content receiving apparatuses;
Analyzing a purchase characteristic of a user for each category of contents by referring to the purchase history information;
Determining recommendation logic for each content category corresponding to each category of the content according to an analysis result of the purchase characteristics, the recommendation logic including at least one recommendation method and a priority of the at least one recommendation method;
Generating content recommendation information based on the determined recommendation logic; And
And providing the generated recommendation information to the content receiving apparatus. 11. The method of claim 10,
Wherein the step of generating the content recommendation information comprises:
Assigning weights according to priorities of at least one recommendation method included in the recommendation logic, multiplying a score of the selected content by each weight using the recommendation method, and calculating at least one content included in the recommendation information And selecting the content. 11. The method of claim 10,
Wherein the step of generating the content recommendation information comprises:
And generating the recommendation information by using a recommendation method in which a priority of the recommendation method is within a predetermined range. 13. The method according to any one of claims 10 to 12,
Wherein the category of the content includes at least one of a broadcast, a movie, a music, an e-book, and a comic, and the recommendation method includes at least one of continuity based recommendation, genre based recommendation, How to recommend content. 14. The method of claim 13,
Wherein the continuity based recommendation method recommends the latest occurrence if there is a latest occurrence that has been added within a predetermined period of time after the user purchases the last occurrence. 14. The method of claim 13,
Wherein the genre-based recommendation method recommends at least one of the content of the same genre when the user purchases the same genre of content for a predetermined period of time or more. 14. The method of claim 13,
The method of recommending a content similarity based on at least one of a plurality of purchased contents and at least one of an author, a publisher, and a publisher recommends the same contents according to purchase history information of a user. 11. The method of claim 10,
Further comprising updating the purchase characteristics of each category based on content purchase history information of a plurality of users. 11. The method of claim 10,
And providing the content selected based on the provided recommendation information to a content receiving apparatus. A content recommendation system comprising:
A plurality of content receiving apparatuses for receiving content recommendation information from a content recommendation apparatus; And
Storing content purchase history information of the plurality of content receiving apparatuses, analyzing purchase characteristics of a user for each category of content by referring to the purchase history information, analyzing purchase characteristics of each content category corresponding to each category of the content A recommendation logic for each content category, the recommendation logic determining at least one recommendation method and a priority of the at least one recommendation method, and based on the determined recommendation logic, recommendation information including at least one content And provides the content recommendation apparatus to the content receiving apparatus.

Images