KR20170019944A - Method and device for recommendation service of product using relative comparison - Google Patents

Method and device for recommendation service of product using relative comparison Download PDF

Info

Publication number
KR20170019944A
KR20170019944A KR1020150114490A KR20150114490A KR20170019944A KR 20170019944 A KR20170019944 A KR 20170019944A KR 1020150114490 A KR1020150114490 A KR 1020150114490A KR 20150114490 A KR20150114490 A KR 20150114490A KR 20170019944 A KR20170019944 A KR 20170019944A
Authority
KR
South Korea
Prior art keywords
product
user
ranking
recommendation
taste
Prior art date
Application number
KR1020150114490A
Other languages
Korean (ko)
Inventor
정진호
Original Assignee
정진호
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 정진호 filed Critical 정진호
Priority to KR1020150114490A priority Critical patent/KR20170019944A/en
Priority to JP2016079235A priority patent/JP5992122B1/en
Priority to KR1020160102309A priority patent/KR101866514B1/en
Priority to JP2016158334A priority patent/JP6087467B2/en
Priority to PCT/KR2016/008915 priority patent/WO2017026852A1/en
Publication of KR20170019944A publication Critical patent/KR20170019944A/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0254—Targeted advertisements based on statistics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0263—Targeted advertisements based upon Internet or website rating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)

Abstract

The present invention relates to a method and a device for a recommendation service of a product through relative comparison. The method comprises: fixing ranking of the product through relative comparison according to the taste of a user; and determining the user with similar taste based on the ranking of a product to recommend the product based on the ranking of the product decided by the user with similar trend.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and apparatus for recommending goods,

The present invention relates to a product recommendation service method and a recommendation service apparatus for the same, and more particularly, to a recommendation service apparatus for recommending a product by a relative comparison, And recommends a product on the basis of a ranking of a product determined by a user with a similar taste by judging a user with a similar taste through comparison.

A wealth of information is being shared on the Internet, and a user selects a product based on evaluation or recommendation of a product experienced or possessed by another person in a variety of information.

For example, when a product is searched on a search service, an evaluation or recommendation of various products is exposed as a result of the search, and the user selects a product suitable for him based on such information.

However, due to the abuse of such situation, the reliability of the evaluation and recommendation of the product is lowered due to the presence of the information of advertisement, and furthermore, each person has different personality and accordingly, the preference for the preferred product is different accordingly, There is a problem in that when a product is selected according to recommendation, a product that is not suitable for its taste is actually selected.

In addition, a method of recommending a product by displaying a rating of a product as a star number is applied in most cases. In the case of an evaluation using a star number, a user evaluates the feeling of only one product in a situation in which there is no comparison There is a limitation in that it is difficult to consistently evaluate a plurality of evaluations because the same impression is reflected differently at the same time even though the same user evaluates the same product and there is a problem that comparison is impossible between products having the same number of stars .

Patent Publication No. 10-2012-0101188

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems of the prior art, and it is an object of the present invention to solve the problem that the reliability of evaluation or recommendation of a product presented on the Internet is low due to advertisement information or the like.

Particularly, since each person has different personality, the preference for the preferred product differs accordingly, so that the user can trust the evaluation or recommendation of the product, so that when the product is selected, the product which is not suitable for his / .

Further, in the case of the evaluation of the product using the number of stars, there is a limitation that it is difficult to consistently evaluate the same user even though the same user evaluates the same product, and there is a problem that comparison is not possible between products having the same number of stars. And to provide recommended services that can be comparatively evaluated.

According to an aspect of the present invention, there is provided a product recommendation service method, a product recommendation service method, and a product recommendation method for setting a ranking of a product for each user based on a user's preference item selection based on a relative comparison of a plurality of products, Ranking setting step; A similar-taste user determining step of comparing a ranking of a product set by a specific user with a ranking of a product set by one or more other users to determine another user having similar taste to the specific user; And a product recommendation step of recommending the product to the specific user based on the ranking of the product set by another user having a similar taste to the specific user.

Preferably, the merchandise ranking setting step includes: a merchandise list generating step of receiving a plurality of merchandise information from the user and generating a merchandise list; And setting a ranking for the plurality of products based on the user's preference item selection through a relative comparison based on the preference of the user for the plurality of goods included in the goods list, And a product ranking list generation step of generating a product ranking list.

Here, the product ranking list generation step may set ranking by listing sequential sequences for each of the plurality of products.

Further, the similar taste user determining step may include: a product recommendation request step of requesting a product recommendation from a specific user among the plurality of users; A similarity degree calculating step of comparing the commodity ranking list corresponding to the specific user with a commodity ranking list corresponding to at least one of the plurality of users to calculate the similarity degree; And a similar-taste user selecting step of determining one or more other users having a similar taste to the specific user among the one or more other users based on the similarity.

Preferably, the similarity calculating step may include: extracting a product ranking list corresponding to one or more other users whose products included in the product ranking list corresponding to the specific user include the predetermined reference number or more, It is possible to calculate the similarity by cross-comparing the product ranking list corresponding to the extracted user and the product ranking list corresponding to the extracted other user.

Here, the ranking is set by listing the sequential sequences for each of the plurality of products, and the degree of similarity calculating step includes calculating a degree of similarity based on a product ranking list corresponding to the specific user and a product ranking list Classifying a plurality of goods into a plurality of groups according to a sequential sequence order; Comparing the group of the product ranking list corresponding to the specific user with the group of the product ranking list corresponding to the different user on a group basis and comparing the similarity of the other user with respect to the specific user on the basis of the number of the same goods, And a step of calculating the number of steps.

Preferably, the commodity recommending step may include: a list extracting step of extracting a commodity ranking list corresponding to the specific user and a commodity ranking list corresponding to the selected at least one similar favorite user; A new product extracting step of extracting a new product from a product ranking list corresponding to the similar-taste user, the product not included in the product ranking list corresponding to the specific user; A recommended product determination step of determining a recommended product based on a ranking of a new product set by the like user; And a recommendation information providing step of providing recommendation information including the recommendation product to the specific user.

For example, the list extracting step extracts a product ranking list corresponding to a similar-taste user having the highest similarity to the specific user, and the recommendation product determination step may include: ranking the new products in the highest ranking, New products can be selected as recommended products in ascending order.

As another example, the list extracting step extracts a product ranking list corresponding to a similar-taste user up to a predetermined number of degrees of similarity to the specific user, and the recommendation product determination step determines, for each new product, The recommendation score may be calculated based on the similarity degree of the liking taste user and the ranking set by the similar taste user, and the new article may be selected as the recommendation article based on the recommendation score.

In addition, the recommendation service apparatus according to the present invention includes: a ranking setting unit that sets a ranking for a product for each user based on the user's preference item selection through relative comparison of a plurality of items according to a taste of each of the plurality of users; A similar user judging unit for comparing a ranking of a product set by a specific user with a ranking of a product set by one or more other users and judging another user having a similar taste to the specific user; And a product recommendation unit for recommending the product to the specific user based on a ranking of the product set by another user having a similar taste to the specific user.

Preferably, the ranking setting unit generates a plurality of user-specific product lists, sets a ranking for the products on the product list based on the user's preference item selection based on relative comparison according to each user's taste, Wherein the similar user determination unit compares a product ranking list corresponding to a specific user who has requested a product recommendation with a product ranking list corresponding to another user to determine a similarity degree of the other user with respect to the specific user And judges a similar-taste user for the specific user on the basis of the degree of similarity, and the product recommendation unit judges whether or not a product that is not included in the product ranking list corresponding to the specific user in the product ranking list corresponding to the similar- Extracts a new product, It is possible to determine the recommended product based on the ranking of the new product set by the user.

The recommendation service apparatus according to the present invention may be a device in which a computer program for performing each step of the product recommendation service method according to the present invention is recorded.

According to the present invention as described above, a commodity recommendation that can be satisfied by a user can be made by recommending a commodity based on an evaluation of a commodity set by another user similar in taste to the user.

In addition, since the product is recommended by synthesizing the evaluation of a user who requests a product recommendation and a plurality of other users having a similar taste, it is possible to exclude the advertisement information and the like, thereby enhancing the reliability of the recommendation.

In addition, by overcoming the limitations of the simple evaluation of a product using the number of stars, the user can more effectively select a product by recommendation through comparison evaluation among a plurality of products.

1 shows an embodiment of a recommended service system for providing a product recommendation service according to the present invention,
2 is a block diagram of an embodiment of a recommendation service apparatus for providing a product recommendation service according to the present invention,
FIG. 3 shows a schematic flow chart of an embodiment of a product recommendation service method through relative comparison according to the present invention,
4 shows an embodiment of a merchandise ranking setting process in the recommendation service method according to the present invention,
FIG. 5 shows an embodiment of a similar taste user judgment process in the recommendation service method according to the present invention,
6 shows an embodiment of a product recommendation process in the recommendation service method according to the present invention,
FIG. 7 shows an embodiment of recommended product information in the recommendation service method according to the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description of the present invention when taken in conjunction with the accompanying drawings.

First, the terminology used in the present application is used only to describe a specific embodiment, and is not intended to limit the present invention, and the singular expressions may include plural expressions unless the context clearly indicates otherwise. Also, in this application, the terms "comprise", "having", and the like are intended to specify that there are stated features, integers, steps, operations, elements, parts or combinations thereof, But do not preclude the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof.

In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

The present invention is characterized in that a user sets a ranking of a product through relative comparison according to his / her preference, judges a similar-like user through cross-comparison of rankings of products among users, Suggest ways to recommend products.

In the present invention, a commodity to be applied to a recommendation service may be a form or an intangible information. For example, it may include various items such as a smart phone and a car, and may include a place such as a restaurant or a café , And may also include content such as movies and music.

FIG. 1 shows an embodiment of a recommended service system for providing a product recommendation service according to the present invention.

The recommendation service apparatus 100 stores ranking list information of a product determined by each user according to the taste of each of a plurality of users 10a, 10b, ... 10n, and based on the ranking list information of the goods for each user, Another user having a taste similar to that of the user is identified, and the product recommendation service is provided to the specific user based on the ranking information of the product determined by another user having a similar taste.

A plurality of users 10a, 10b,... 10n can access a recommended service device 100 by using the communication terminal of their own and receive a recommended service. The communication terminal may be a smart phone, a PC, May be applied.

The user can be connected to the recommended service device 100 through the network 30 with his / her own communication terminal. Here, the network 30 may include both a wired network and a wireless network as a general Internet line. Further, when the recommendation service according to the present invention is provided in a limited range of a specific company or the like, the network network may be a limited area or a virtual private network or an intranet network accessible only to an authorized person.

The recommendation service apparatus 100 may provide a recommendation service to the users 10a, 10b, ... 10n in cooperation with a general search service server 50. For example, The search service server 50 may request the recommendation service apparatus 100 to provide a product recommendation considering the user's preference in such a case. And the recommendation service apparatus 100 may provide the product recommendation result to the search service server 50 considering the taste for the user.

FIG. 2 shows a configuration diagram of an embodiment of a recommendation service apparatus for providing a product recommendation service according to the present invention.

The recommendation service apparatus 100 may roughly include a ranking setting unit 110, a similar user determination unit 130, a product recommendation unit 150, and may further include a user information DB 170 have.

The ranking setting unit 110 generates a list of goods for each user for each item experienced or possessed by each user and, when each user selects a preferred item through a relative comparison according to his taste, And generates a merchandise ranking list for each user by matching rankings of the merchandise list and the merchandise corresponding thereto. Here, the ranking setting unit 110 provides a service page or a tool that allows a user to input a list of items experienced or possessed by the user, and to determine a preferred product through a relative comparison of each product according to his taste It is possible.

Preferably, the product ranking list generated by the ranking setting unit 110 may be stored in the user information DB 170 in association with the identification information of the corresponding user.

The similar user judging unit 130 judges a similar user based on the user's commodity ranking list generated by the ranking setting unit 110. For example, the similar user judging unit 130 judges whether a commodity ranking list corresponding to a specific user and a commodity ranking And cross-compares the list to determine another user having similar tastes to the particular user. At this time, the similar user determination unit 130 may calculate the degree of similarity according to the cross-comparison of the merchandise ranking list, and may select one other user indicating the highest degree of similarity or a plurality of other users within the similarity range of the predetermined range .

The product recommendation unit 150 identifies one or more other users having similar tastes to the user determined by the similar user determination unit 130 and selects the one or more other users having similar tastes based on the product ranking list determined by another user having similar taste And generates and provides recommendation information for recommending a product that is not held.

The recommendation service apparatus 100 is provided with such a configuration, and the recommendation service according to the present invention can be provided with the functions of the respective configurations. Here, the recommendation service apparatus 100 is implemented as one apparatus including each configuration Alternatively, each configuration may be selectively combined with each individual device or individual module, and the recommended service device 100 may be implemented as a group of configurations. In addition, a server capable of performing a storage function and an arithmetic function can be applied to the recommendation service apparatus 100, and a computer program for performing each step of the product recommendation service method according to the present invention to be described later may be recorded in a recommendation service apparatus have.

A recommendation service apparatus according to the present invention can provide a recommendation service through relative comparison in consideration of a user's taste. A method of providing a recommendation service through a relative comparison according to the present invention is described in .

FIG. 3 shows a schematic flow chart of an embodiment of a method for recommending goods through relative comparison according to the present invention.

Since the product recommendation service method according to the present invention is implemented in the recommendation service apparatus according to the present invention, the recommendation service apparatus will be referred to together.

The recommendation service method according to the present invention includes: a merchandise ranking setting process (S100) for setting a ranking of a merchandise through relative comparison according to a user's taste; A similar taste user judgment process (S200) of judging one or more other users having a taste similar to that of the specific user by cross-comparing the ranking of the product determined by the specific user requesting the recommended service and the rank of the product determined by the other user; And a product recommendation step (S300) of recommending the product to the specific user based on the ranking of the product determined by another user of similar taste.

Each of the above-described steps of the recommendation service method according to the present invention will be described in more detail with reference to the following detailed embodiments.

First, the merchandise ranking setting process (S100) will be described with reference to FIG. 3, with reference to the embodiment of the merchandise ranking setting process in the recommendation service method according to the present invention shown in FIG.

First, the ranking setting unit 110 of the recommendation service apparatus 100 inputs product information experienced or possessed by the user (S110) and generates a product list (S120). 4, the ranking setting unit 110 of the recommendation service apparatus 100 receives the restaurant information that the user A has experienced from the user A, collects the information, a restaurant list 210 is created by combining the restaurant information 215 experienced by the user A as shown in FIG.

The ranking setting unit 110 of the recommendation service apparatus 100 sets a ranking for a product on the basis of the user's preference through a relative comparison between the products included in the product list according to the taste of the user (S130), and generates a merchandise ranking list (S140).

As shown in FIG. 4B, when the user A selects the restaurant 1 (221) and the restaurant 2 (223) on the restaurant list 210 of the user A through a relative comparison according to the taste of the user A The relatively preferred restaurant 2 225 may be selected and the comparative comparison is repeatedly performed so that the ranking setting unit 110 of the recommendation service apparatus 100 searches the list of restaurants And sets a ranking based on the selection of the restaurants on the menu 210 to generate a restaurant ranking list. Here, as shown in FIG. 4 (c), the restaurant ranking list includes all the restaurants 215 on the restaurant list 210 as a sequence (235), and the restaurant ranking list 230 ).

The recommendation service apparatus 100 may provide a service page or an application for setting the ranking and inputting the product information to the user terminal.

In the product ranking setting process S100, a ranking is set for a product through a relative comparison among the products according to a user's taste, and a product ranking setting process S100 is repeatedly performed for each of a plurality of users, A user-specific item ranking list for each user can be generated.

The user-specific merchandise ranking list generated as described above may be stored in the user information DB 170 corresponding to each user.

Further, the user may update the overall product ranking list by adjusting the preference selection of the product according to the re-experience of the existing product existing in the product ranking list, or may update the ranking of the newly- It is also possible to update the product ranking list by newly adding to the ranking list.

Second, a similar-taste user determination process (S200) will be described with reference to FIG. 3 and an embodiment of a similar-taste user determination process in the recommended service method according to the present invention shown in FIG.

The similar user judging unit 130 of the recommendation service apparatus 100 receives the product recommendation request (S210) from the specific user in the state that the product ranking list for a plurality of users is held through the product ranking setting process S100 The similarity degree of the taste for the specific user is calculated (S230) by cross-comparing the merchandise ranking list corresponding to the specific user with the merchandise ranking list corresponding to at least one or more other users (S220). Then, based on the calculated degree of similarity, another user having similar taste to the specific user is determined (S240).

For example, as shown in (a) of FIG. 5, a restaurant ranking list 310a corresponding to the user A and having ranking by sequential order of each of a plurality of restaurants, a restaurant ranking list 310 corresponding to the user N 310n corresponding to the user N from the restaurant ranking list 310b corresponding to the user A and the restaurant ranking list 310b corresponding to the user B when the user A requests the restaurant recommendation, (310n), thereby calculating the similarity of each of the other users to the user A.

At this time, the degree of similarity may be calculated by considering only the restaurant ranking list including the same number of products as the products included in the merchandise ranking list corresponding to the user A among the users B to N.

Referring to the example shown in FIG. 5 (b), a restaurant ranking list in which a ranking is set by an ordered list of a plurality of restaurants, a plurality In FIG. 5B, the restaurants included in the restaurant ranking list corresponding to the user A are classified into groups (320a, 330a) by 10 in the sequence order, and similarly, The restaurants included in the ranking list were also classified into groups (320b, 330b) by ten.

The degree of similarity of the user B with respect to the user A is calculated through cross-comparison between the user A and the user B requesting restaurant recommendation by the restaurant group included in the restaurant ranking list. The upper ranking group 320a corresponding to the user A is referred to as the user B The upper ranking group 320b and the lower ranking group 330b corresponding to the user B and the lower ranking group 330b corresponding to the user B are compared with the upper ranking group 320b and the lower ranking group 330b respectively corresponding to the user B, Gt; 330b < / RTI >

A restaurant 323a included in the upper ranking group 320a corresponding to the user A and a restaurant 323b included in the upper ranking group 320b corresponding to the user B as the similar taste appreciation between the user A and the user B, And compares the number of restaurants belonging to the upper ranking group in the same manner as that of the restaurant 1 (325a, 325b). The restaurant 333a included in the lower ranking group 330a corresponding to the user A is compared with the restaurant 333b included in the lower ranking group 330b corresponding to the user B and the restaurant 333a is compared with the restaurant 335a or 335b Similarly, the number of restaurants belonging to the lower ranking group is grasped.

Also, as an opposite taste between the user A and the user B, the restaurant 323a included in the upper ranking group 320a corresponding to the user A and the restaurant 333b included in the lower ranking group 330b corresponding to the user B And compares the number of restaurants belonging to the opposite ranking group such as restaurant 2 (327a, 337b). The restaurant 333a included in the lower ranking group 330a corresponding to the user A is compared with the restaurant 323b included in the upper ranking group 320b corresponding to the user B and the number of restaurants belonging to the opposite ranking group I understand.

The similarity of the user B to the user A is calculated on the basis of the comparison. Likewise, the restaurant belonging to the upper ranking group has a high likelihood that the user A and the user B have similar tastes. The same weighting is applied to the number of restaurants, and a restaurant belonging to a lower ranking group has the possibility that the taste of the user A and the user B are similar to each other. Therefore, an intermediate weight is applied to the number of restaurants belonging to the lower ranking group , And a restaurant belonging to the opposite ranking group means that there is a possibility that the taste of the user A and the user B may be different. Therefore, a similar weight is calculated by applying a lower weight.

As an example, the similarity degree of the user B to the user A can be calculated by the following equation (1).

S AB = (α × H + β × L + γ × R) / T; (?>?>?) [Formula 1]

Here, S AB is the similarity degree of the user B to the user A, α is the weight value of the commodity that belongs to the same upper ranking group, β is the weight value of the commodity belonging to the lower ranking group, L is the number of products belonging to the same rank in the lower ranking group, R is the number of the products belonging to the opposite ranking group, T is the number of the products belonging to the same ranking group, Represents the number of products obtained by adding the above H, L and R.

This process is repeatedly performed to calculate the degree of similarity of the user A to the user N after the user B shown in FIG. 5 (a).

Then, another user having a high degree of similarity with respect to the user A is selected. At this time, only one other user having the highest degree of similarity may be selected, or a plurality of other users having similarity to predetermined values may be selected.

Third, the product recommendation process (S300) will be described with reference to FIG. 3 and an embodiment of the product recommendation process in the recommendation service method according to the present invention shown in FIG.

If at least one similar taste user having similar taste to a specific user who has requested a product recommendation is selected through the similar taste user determination process (S200), the product recommendation unit 150 of the recommendation service apparatus 100 determines And extracts a product ranking list and a product ranking list corresponding to one or more selected similar taste users (S310).

Next, the product recommendation unit 150 of the recommendation service apparatus 100 compares the product ranking list of the specific user with the product ranking list of the similar-taste user (S320) and compares the product ranking list of the similar user with the product ranking list The new product is extracted from the product not included in the product ranking list corresponding to the specific user (S330).

Then, the product recommendation unit 150 of the recommendation service apparatus 100 determines (S340) a recommended product based on the ranking of the new product set by the similar-taste user, and transmits recommendation information including the recommendation product And provides it to a specific user (S350).

If only one other user with the highest similarity degree to the specific user who has requested the product recommendation is selected as the similar-taste user, a new product is extracted from the ranking list corresponding to one similar-taste user, A new product is selected as a recommended product in the order of products or a predetermined number of ranking ascending order.

Furthermore, a case in which a plurality of other users up to a preset number of similarities are selected as similar-taste users will be described with reference to the embodiment shown in FIG.

FIG. 6 is an example of extracting a recommended restaurant based on the restaurant ranking setting of a plurality of similar-taste users in connection with the restaurant recommendation.

First, the user A and the user B, the user D selected as a similar-taste user, ... A restaurant ranking list corresponding to the user C is extracted and a restaurant not included in the restaurant ranking list corresponding to the user A is extracted as a new restaurant on each restaurant ranking list, And creates a new restaurant table 410 in which new restaurants corresponding to each similar-taste user are arranged in order. In FIG. 6, the portion denoted by X is a restaurant included on the restaurant ranking list corresponding to the user A, and is a portion excluded from the new restaurant.

Based on the new restaurant table 410, the recommendation score is calculated on the basis of the similarity degree of the similar taste user and the ranking set by the similar taste user. In the case of the restaurant 3 (411, 413) , The ranking set by the user B having the highest degree of similarity is ranked second, and the ranking set by the user D having the second highest degree of similarity is ranked first, so that the recommendation score is calculated to be high. In the case of the restaurant 6 (415, 417), since the ranking set by the user B having the highest similarity degree is the third and the ranking set by the user C having the lowest similarity degree is the first rank, .

As an example, a recommendation score for a new product can be calculated by the following equation (2).

Figure pat00001
[Formula 2]

Here, SCORE is the recommendation score for the new product, M is the total number of similar-taste users who set the ranking for the new product, SI is the similarity level of the i-th like taste user, and Rank is the i- Is a ranking set for the new product, and k is a weight that is set as needed.

As described above, each recommendation score is calculated for each new product, and a product to be recommended is selected based on the calculated recommendation score. Only one new product having the highest recommendation score may be selected as a recommendation item, A number of new products may be selected as recommended products up to the higher order.

When the recommended product is selected, the product recommendation unit 150 of the recommended service device 100 generates recommendation information including the recommended product and provides it to the user. For example, in the recommendation service method according to the present invention shown in FIG. 7, Recommendation information 420 including recommended restaurants in a sequential order along with recommendation ranking is provided to the user terminal as in the embodiment of the product information. In this case, various kinds of additional information may be included in the recommendation information. For example, when the restaurant is recommended as shown in FIG. 7, information such as a menu, a price, a location and a telephone number may be included, In addition, a URL to the web page in which the various information is presented may be included.

According to the present invention as described above, a product recommendation can be made satisfactory to a user by recommending a product based on an evaluation of a product set by another user similar in taste to the user.

In addition, since the product is recommended by synthesizing the evaluation of a user who requests a product recommendation and a plurality of other users having a similar taste, it is possible to exclude the advertisement information and the like, thereby enhancing the reliability of the recommendation.

In addition, by overcoming the limitations of the simple evaluation of a product using the number of stars, the user can more effectively select a product by recommendation through comparison evaluation among a plurality of products.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments of the present invention are not intended to limit the scope of the present invention but to limit the scope of the present invention. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents thereof should be construed as being included in the scope of the present invention.

10a, 10b, ... 10n: user,
30: Network,
50: Search service server,
100: Recommended service devices,
110: Ranking setting unit,
130: Pseudo user judgment unit,
150: Product recommendation department,
170: User information DB.

Claims (12)

A product ranking setting step of setting a ranking of a product for each user based on a user's preference item selection based on a relative comparison of the plurality of goods according to a taste of each of the plurality of users;
A similar-taste user determining step of comparing a ranking of a product set by a specific user with a ranking of a product set by one or more other users to determine another user having similar taste to the specific user; And
And recommending a product to the specific user based on a ranking of the product set by another user having a similar taste to the specific user. The method according to claim 1,
Wherein the merchandise ranking setting step comprises:
A product list generating step of receiving a plurality of product information from the user and generating a product list; And
Setting a ranking for the plurality of products based on the user's preference selection of the plurality of products included in the product list through relative comparison according to the preference of the user, And a product ranking list generation step of generating a ranking list. 3. The method of claim 2,
The merchandise ranking list generation step includes:
Wherein ranking is set by listing the sequential sequences for each of the plurality of products. 3. The method of claim 2,
Wherein the similar taste user determination step comprises:
A product recommendation step of requesting a product recommendation from a specific user among the plurality of users;
A similarity degree calculating step of comparing the commodity ranking list corresponding to the specific user with a commodity ranking list corresponding to at least one of the plurality of users to calculate the similarity degree; And
And a similar-taste user selecting step of determining one or more other users having a taste similar to the specific user among the one or more other users based on the similarity. 5. The method of claim 4,
Wherein the similarity calculating step comprises:
Extracting a product ranking list corresponding to one or more other users whose products are the same as the product included in the product ranking list corresponding to the specific user and including a predetermined reference number or more, Wherein the degree of similarity is calculated by cross-comparing the merchandise ranking list corresponding to the user. 5. The method of claim 4,
Wherein the product ranking list is set to ranking by a sequence of sequential sequences for each of a plurality of products,
Wherein the similarity calculating step comprises:
Classifying a plurality of products into a plurality of groups in a sequential sequence order for each of a product ranking list corresponding to the specific user and a product ranking list corresponding to the other user;
Comparing the group of the product ranking list corresponding to the specific user with the group of the product ranking list corresponding to the different user on a group basis and comparing the similarity of the other user with respect to the specific user on the basis of the number of the same goods, And calculating the product recommendation service. 5. The method of claim 4,
The product recommendation step may include:
A list extracting step of extracting a goods ranking list corresponding to the specific user and a goods ranking list corresponding to the selected one or more similar taste users;
A new product extracting step of extracting a new product from a product ranking list corresponding to the similar-taste user, the product not included in the product ranking list corresponding to the specific user;
A recommended product determination step of determining a recommended product based on a ranking of a new product set by the like user; And
And providing recommendation information including the recommended product to the specific user. 8. The method of claim 7,
The list extracting step includes:
Extracting a product ranking list corresponding to a similar-taste user having the highest similarity to the specific user,
In the recommendation product determination step,
And the new product is selected as a recommended product in the order of the highest ranking new product or ranking up to the predetermined number. 8. The method of claim 7,
The list extracting step includes:
Extracting a merchandise ranking list corresponding to a similar taste user up to a predetermined number of similarities for the specific user,
In the recommendation product determination step,
A recommendation score is calculated for each new product based on the degree of similarity of the similar-taste user and the ranking set by the similar-taste user, and a new product is selected as a recommendation product based on the recommendation score Recommended service method. A ranking setting unit configured to set a ranking for a product for each user based on the user's preference item selection based on a relative comparison of the plurality of items according to a taste of each of the plurality of users;
A similar user judging unit for comparing a ranking of a product set by a specific user with a ranking of a product set by one or more other users and judging another user having a similar taste to the specific user; And
And a product recommendation unit for recommending a product to the specific user based on a ranking of the product set by another user having a similar taste to the specific user. 11. The method of claim 10,
The ranking setting unit,
Generating a plurality of user-specific product lists, setting up ranking for the products on the product list based on the user's preference product selection through relative comparison according to each user's preference to generate the per-user product ranking list,
The similar-
The similarity degree of the other user to the specific user is calculated by cross-comparing the product ranking list corresponding to the specific user requesting the product recommendation and the product ranking list corresponding to the other user, Judges a taste user,
The product recommendation unit,
Extracting a new commodity from the commodity ranking list corresponding to the similar preference user, the commodity not included in the commodity ranking list corresponding to the specific user, and selecting a recommendation commodity based on the ranking of the new commodity set by the similar- Wherein the recommendation service apparatus judges whether or not the recommendation service apparatus is operating. 9. A recommendation service apparatus in which a computer program for performing each step of the method for recommending goods described in any one of claims 1 to 9 is recorded.
KR1020150114490A 2015-08-13 2015-08-13 Method and device for recommendation service of product using relative comparison KR20170019944A (en)

Priority Applications (5)

Application Number Priority Date Filing Date Title
KR1020150114490A KR20170019944A (en) 2015-08-13 2015-08-13 Method and device for recommendation service of product using relative comparison
JP2016079235A JP5992122B1 (en) 2015-08-13 2016-04-12 Product recommendation service method based on relative comparison, recommendation service device and program therefor
KR1020160102309A KR101866514B1 (en) 2015-08-13 2016-08-11 Method for recommendation service of product using relative comparison, and device and program for the same
JP2016158334A JP6087467B2 (en) 2015-08-13 2016-08-11 Product recommendation service method based on relative comparison, recommendation service device and program therefor
PCT/KR2016/008915 WO2017026852A1 (en) 2015-08-13 2016-08-12 Method for service of recommending product through relative comparison, and recommendation service apparatus and program therefor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150114490A KR20170019944A (en) 2015-08-13 2015-08-13 Method and device for recommendation service of product using relative comparison

Publications (1)

Publication Number Publication Date
KR20170019944A true KR20170019944A (en) 2017-02-22

Family

ID=56921017

Family Applications (2)

Application Number Title Priority Date Filing Date
KR1020150114490A KR20170019944A (en) 2015-08-13 2015-08-13 Method and device for recommendation service of product using relative comparison
KR1020160102309A KR101866514B1 (en) 2015-08-13 2016-08-11 Method for recommendation service of product using relative comparison, and device and program for the same

Family Applications After (1)

Application Number Title Priority Date Filing Date
KR1020160102309A KR101866514B1 (en) 2015-08-13 2016-08-11 Method for recommendation service of product using relative comparison, and device and program for the same

Country Status (3)

Country Link
JP (2) JP5992122B1 (en)
KR (2) KR20170019944A (en)
WO (1) WO2017026852A1 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11157985B2 (en) * 2017-11-29 2021-10-26 Ditto Technologies, Inc. Recommendation system, method and computer program product based on a user's physical features
CN109919650A (en) * 2019-01-16 2019-06-21 深圳壹账通智能科技有限公司 Multi-stage service promotes management method, device and storage medium, computer equipment
KR102272063B1 (en) * 2019-12-13 2021-07-02 임계수 Apparatus and method for determinating taste similarity of users
CN115699069A (en) * 2020-06-19 2023-02-03 松下知识产权经营株式会社 Information providing method
JP6910515B1 (en) * 2020-07-31 2021-07-28 ＰａｙＰａｙ株式会社 Analytical instruments, analytical methods and analytical programs

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20120101188A (en) 2011-02-01 2012-09-13 케이비에스인터넷 주식회사 System and method for providing information of good food restaurant using smart phone

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3707361B2 (en) * 2000-06-28 2005-10-19 日本ビクター株式会社 Information providing server and information providing method
JP4580604B2 (en) * 2001-12-25 2010-11-17 ぴあ株式会社 Ranking information return system and computer program and method for realizing the same
JP5032477B2 (en) * 2005-08-19 2012-09-26 フォースウォール・メディア・インコーポレーテッド System and method for recommending items of interest to users
KR100811937B1 (en) * 2006-06-30 2008-03-10 현대자동차주식회사 Forming Limit Diagram Tester
JP2008102846A (en) * 2006-10-20 2008-05-01 Dowango:Kk Content recommendation server, content recommendation program, and content recommendation method
KR101415022B1 (en) * 2007-07-24 2014-07-09 삼성전자주식회사 Method and apparatus for information recommendation using hybrid algorithm
KR20100005289A (en) * 2008-07-07 2010-01-15 엘지전자 주식회사 Apparatus for generating vibration
KR101022886B1 (en) * 2008-11-11 2011-03-16 한국과학기술원 Mehod and system for recommending intelligent contents according to user
KR20100091669A (en) * 2009-02-11 2010-08-19 인하대학교 산학협력단 Personalized recommendation system for e-commerce service
JP2011053920A (en) * 2009-09-02 2011-03-17 Fujitsu Ltd Method and apparatus for supporting consolidation of ballot target
KR101095311B1 (en) * 2009-10-22 2011-12-16 성균관대학교산학협력단 User adaptive recommendation system
JP5483576B2 (en) * 2010-06-08 2014-05-07 日本電信電話株式会社 Recommended item filtering method and recommended item filtering program
KR20120076477A (en) * 2010-11-25 2012-07-09 주식회사 케이티 Method and systmem for store recommendation
JP5968665B2 (en) * 2012-04-05 2016-08-10 シャープ株式会社 Similarity calculation device, similarity calculation system, similarity calculation method, and similarity calculation program
KR101647364B1 (en) * 2013-08-26 2016-08-23 네이버 주식회사 System and method for recommending contents based on user characteristics and transactions, and recording media thereof
KR20150080090A (en) * 2013-12-30 2015-07-09 전남대학교산학협력단 System for recommending product based on Hadoop and apparatus and methode for recommending product in the system
KR101579376B1 (en) * 2014-05-11 2015-12-21 이정우 Personalized place recommendation system and method by using subjectivity analysis for user classification

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20120101188A (en) 2011-02-01 2012-09-13 케이비에스인터넷 주식회사 System and method for providing information of good food restaurant using smart phone

Also Published As

Publication number Publication date
WO2017026852A1 (en) 2017-02-16
KR101866514B1 (en) 2018-06-12
JP6087467B2 (en) 2017-03-01
KR20170116924A (en) 2017-10-20
JP2017037650A (en) 2017-02-16
JP5992122B1 (en) 2016-09-14
JP2017037629A (en) 2017-02-16

Similar Documents

Publication Publication Date Title
EP2304619B1 (en) Correlated information recommendation
US9754306B2 (en) Recommendation engine with profile analysis
KR101866514B1 (en) Method for recommendation service of product using relative comparison, and device and program for the same
US10074121B2 (en) Shopper helper
JP5039844B1 (en) Information providing apparatus, information providing method, information providing program, and computer-readable recording medium storing the program
AU2012274726B2 (en) Information Processing Apparatus, Information Processing Method, Information Processing Program, Recording the Medium having Stored therein Information Processing Program
US20110119148A1 (en) Server apparatus, information processing apparatus, and information processing method
US20150169189A1 (en) Media recommendation kiosk
Chiru et al. Movie Recommender system using the user's psychological profile
US20170024783A1 (en) Methods and systems for ranking merchants
KR20130012155A (en) Method and device for providing social network service
JP2001014349A (en) Rating system for collaboration information filtering
US20150248720A1 (en) Recommendation engine
KR101708254B1 (en) Story-based recommendation system and method for movies by character-net and collaborative filtering
KR101350079B1 (en) Device for providing information, method for providing information, and computer-readable recording medium storing program for providing information
KR101507328B1 (en) Apparatus and method for predicting user feed back in collaborative recommendation system
WO2009143109A1 (en) Interest-based shopping lists and coupons for networked devices
JP5223019B2 (en) Information providing apparatus, information providing method, information providing program, and computer-readable recording medium storing the program
JP5451644B2 (en) RECOMMENDATION SYSTEM, RECOMMENDATION METHOD, RECOMMENDATION PROGRAM, AND INFORMATION STORAGE MEDIUM
JP6096007B2 (en) Content search result providing apparatus, content search result providing method, and content search result providing system
Zioutos et al. SHARE: A Framework for Personalized and Healthy Recipe Recommendations
JP6059595B2 (en) Content search result providing apparatus, content search result providing method, and content search result providing system
JP6059596B2 (en) Content search result providing apparatus, content search result providing method, and content search result providing system

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E902 Notification of reason for refusal
E601 Decision to refuse application