KR101177768B1 - Product and service recommendation method based on self-expression on the digital communication tools - Google Patents

Abstract

The present invention relates to a product and service recommendation method based on self-expression on a digital communication tool, comprising: a characteristic value classification step of classifying characteristic values by modeling a user's state; A keyword extraction step of extracting a keyword stored in an FTR (feature) database from the input magnetic expression; A product and service classification step of classifying a product and a service according to a business knowledge or requirement of a corresponding product and service provider after selecting a specific domain; A characteristic value matching product and service according to the analysis result of the characteristic value and a product and service matching step; The product and service recommendation step of outputting and displaying related product and service recommendation results identified from the matching database using the user status as an input value, and based on self-expression that can be set and changed by the individual as a user at any time in the digital communication tool. By inferring the user's current status and recommending appropriate products and services, the user can not only improve the effectiveness and increase the commercial profits compared to the existing mass marketing techniques, but also if there is no or insufficient accumulated member information. It is a useful invention that has a particular advantage that can be easily employed even when there is no information about the behavior pattern for.

Description

Product and service recommendation method based on self-expression on the digital communication tools}

The present invention relates to a method for recommending goods and services, and more particularly, based on a self-expression that can be set and changed by an individual as a user on a digital communication tool (messenger, PDA, smartphone, etc.). The present invention relates to a method of recommending products and services based on self-expression in digital communication tools that infers and recommends appropriate products and services.

In general, a product recommendation management system is a personalized information filtering technology that makes a list of recommended products to customers to help customers easily find possible products. Collaborative filtering is known as the most successful product recommendation technique and is widely used.

As an example of such a product recommendation management system, a technology related to a conventional product recommendation system is disclosed in Korean Patent Application Publication No. 2005-0017534, customized clothes recommendation system using the avatar costume purchase information, and its recommendation method (hereinafter, “prior art”). And a number of applications and registered status.

The prior art was developed as a marketing strategy for recommending a product by grasping a behavioral pattern of a product buyer through an avatar. As illustrated in FIG. 1, an internet site providing an avatar decorating service and a clothing recommendation service to a user is provided. Internet server 1 for driving and managing, shopping mall clothing information collection server 2 for collecting clothing product information on clothes sold in a plurality of internet clothing shopping malls operated on the Internet, and avatars using the avatar decorating service Analyzing clothing purchasing preferences of the avatar decorating service users using the avatar costume information management server 3 collecting the costume purchasing information and the avatar costume purchasing information, and the garments highly related to the clothing purchasing preferences are selected from the clothing product information. Search for actual clothing A clothing recommendation server 4 for providing the recommended clothing recommendation service and a database 5 for storing the avatar clothes purchase information, the clothing product information, and information on the clothing purchase preference are provided.

As described above, in the prior art, when a user purchases an avatar costume to decorate an avatar with himself on the Internet, the user provides a tailored clothing recommendation service for the user through the avatar costume purchase information, but after decorating the avatar, Since there is a recommendation, there is a problem that the width of clothing that can be selected by the user can be limited to avatar costumes only.

In addition, since the prior art can confirm the user's clothing preference only through the avatar costume purchase information, there is a problem that additional cost and time are required by using the avatar decorating service to provide a customized clothing recommendation service.

On the other hand, avatars currently used in cyberspace represent themselves in cyberspace, but the avatars are represented by icons including accessories or clothes, rather than realistically represented by the user's body shape, taste, or characteristics. Even if the clothes were recommended according to their taste based on the clothes, it was not possible to determine whether they were suitable for the user (buyer).

In other words, even if the user purchases the clothes according to the user's preference, there is a problem in that the purchased clothes are not suitable for checking their body shape in advance.

In addition, a method for recommending a product of an electronic commerce system is disclosed in the Patent Publication No. 2002-0014332.

The product recommendation method of the electronic commerce system of Patent Publication No. 2002-0014332 is the first step of analyzing the psychology or taste of the buyer based on the buyer's profile and the results of the survey of the buyer as shown in FIG. S101, S102; A second step (S103 to S108) of analyzing the psychology or taste of the gift recipient based on the present use, the profile of the gift recipient, and the result of the survey of the buyer on the gift recipient; The third step (S109-S110) of selecting a suitable product from the product database and presenting it as a recommended product according to the analysis of the psychology or taste of the buyer or the gifted person is performed. After analyzing the preferences and psychology of the current buyer based on the rhythm and so on, based on the result of the analysis, the product suitable for the buyer is recommended.

However, such a product recommendation method is based on the buyer's information, that is, the member's profile, which is difficult to employ when there is no existing or insufficient profile information of the buyer.

As described above, the conventional product recommendation technologies are used in online businesses, and constitute a recommendation marketing strategy for products and services based on member information and behavior patterns. However, this includes a lot of information about members (buyers) (such as personal information and preferences). , Purchase history, behavior patterns, etc.), there is a problem that it is difficult to employ when there is no existing or insufficient information.

With the recent rapid development of information and communication technology, various communication tools (messenger, PDA, etc.) are expanding from one-to-one communication methods using telephone lines to one-to-many and many-to-many communication through the Internet, wireless network, and messenger. , Smartphones, etc.) is increasingly used in real life.

Various advertising messages are randomly output in a specific manner in such a communication tool at all times in a push manner, and are currently being used for recommendation of products and services, but this is not related to the characteristics of individual users. As a mass marketing method, there is a problem that the effect cannot be expected in terms of influence on the user.

On the other hand, people can express their feelings through self-expression functions such as messengers, blogs, and mini homepages, and self-expression functions provided by various communication tools (messenger, PDA, smartphone, etc.). It can be easily shared with others.

Accordingly, the inventors of the present invention have completed the present invention by focusing on the fact that inferring the current state of the user based on the self-expression function provided by various communication tools, he can recommend products and services suitable for the user. .

The present invention has been invented to solve various defects and problems caused by the conventional product recommendation method in view of the above situation, the object of which is a user who is often a user on a digital communication tool (messenger, PDA, smartphone, etc.) Based on the self-expression that can be set and changed, it is possible to deduce the current state of users and recommend appropriate products and services to digital communication tools that can improve effectiveness and increase commercial profits compared to existing mass marketing techniques. It provides a method of recommending products and services based on self-expression.

Another object of the present invention is to infer the current state of the user based on the self-expression on the digital communication tool and recommend the appropriate goods and services to the self in the digital communication tool that can be employed even if there is no or lack of accumulated member information. It is to provide a method of recommending goods and services based on expression.

Another object of the present invention is to infer the current state of the user based on the self-expression on the digital communication tool and recommend appropriate products and services to the digital communication tool that can be employed even when there is no information on the behavior pattern for the user It is to provide a product and service recommendation method based on the self-expression of the prize.

Product and service recommendation method based on the self-expression on the present invention digital communication tool to achieve the above object by modeling the user's state according to the characteristics of the user's interests A characteristic value classification step of classifying; A keyword extraction step of extracting, as a keyword, an independently meaningful noun stored in an FTR database from an input self-expression phrase; A product and service classification step of classifying a product and a service according to a business knowledge or requirement of a corresponding product and service provider after selecting a specific domain; A characteristic value matching product and service according to the classification result of the characteristic value and a product and service matching step; And a product and service recommendation step of outputting and displaying the related product and service recommendation result identified from the matching database using the user state as an input value.

The present invention is based on the self-expression that can be set and changed by the individual as a user on the digital communication tool, and inferring the current state of the user and recommending appropriate products and services to the target marketing (Target Marketing). ), And increase the commercial profits, and there is a particular advantage that can be easily employed even when there is no or lack of existing accumulated member information and there is no information about the behavior pattern for the user .

Hereinafter, with reference to the accompanying drawings will be described in detail a preferred embodiment of the product and service recommendation method based on the self-expression on the present invention digital communication tool.

3 is a conceptual diagram of a product and service recommendation model based on self-expression on the digital communication tool employed in the method of the present invention, and FIG. 4 is a flowchart illustrating a product and service recommendation method based on self-expression on the digital communication tool of the present invention. The product and service recommendation model based on self-expression on the digital communication tool employed in the method of the present invention comprises a feature value classifier [10] comprising user state modeling means 11 for modeling a user's state as shown in FIG. Feature categorization]; A feature database (20) for storing the classification result of the feature value classification unit (10); The keyword is extracted from the feature database 20 using category comparison extracting means 31 and NLP (Natural Language Processing), which extracts the keyword from the feature database 20 in comparison with the set category. The keyword extracting unit 30 which extracts an independent noun stored in the FTR database 20 as a keyword from the input self-expressing 20a phrase consisting of NLP extracting means 32 for extracting as a keyword. Wow; A commodity and service classifying unit (40) comprising commodity and service sorting means (42) for classifying commodities and services according to the business knowledge or requirements of the commodity and service providers; PRD / SRV (product / service) Categorization]; A product / service (PRD / SRV) database 50 for storing a classification result of the product and service classification unit 40; Characteristic values and products and services for matching the recommended products and services according to the analysis result of the characteristic value consisting of a pre-designated matching means 61 previously specified by the product and service provider and a user-set matching means 62 freely set by the users A matching unit 60; A matching database (70) for storing a matching result of the characteristic value and the product and service matching unit (60); And a product and service recommendation unit 80 including display means 81 for displaying and displaying related product and service recommendation results identified from the matching database 70 using the user state as an input value.

The product and service recommendation method based on self-expression on the digital communication tool according to the present invention comprises: a characteristic value classification step (S1 step) of modeling a user's state and classifying it according to a characteristic of a user's interest; A keyword extraction step (S2 step) of extracting a keyword stored in an FTR (feature) database from the input magnetic expression; A product and service classification step (S3 step) of classifying goods and services according to business knowledge or requirements of the corresponding goods and service providers after selecting a specific domain; A characteristic value matching product and service according to the classification result of the characteristic value and a product and service matching step (step S4); And a product and service recommendation step (step S5) of outputting and displaying a related product and service recommendation result identified from the matching database using the user state as an input value.

The modeling in the characteristic value classification step (S1 step) is to derive a state (for example, emotion, interest, plan, etc.) that can be used by collecting self-expression of various users and to define a general hierarchy predefined using the concept of ontology. Modeling is based on the designation and hierarchical classification of the advertisement category from a theoretical perspective that provides a categorical classification and a practical perspective that provides a specialized hierarchical classification. In the characteristic value classification step (S1 step), the classification result of the characteristic value is FTR (feature). The step of storing the classification result of the characteristic value stored in the database.

In the keyword extraction step (S2 step), the keyword is extracted from the feature database using a category comparison extraction step of extracting a keyword from the feature (FTR) database and a natural language processing (NLP) by comparing with a set category. NLP extraction step of extracting.

In addition, the product and service classification step (S3 step) includes a classification result storage step of the goods and services to store the product and service classification results in the PRD / SRV (product / service) database.

In the characteristic value and product and service matching step (step S4), a pre-designation step previously designated by the product and service provider and a user setting step freely set by the user and a result of matching the characteristic value and the product and service are stored in a matching database. Storing the matching result of the feature value and the goods and services.

The product and service recommendation step (S5 step) includes an alignment step of the recommended product and service.

Here, the sorting step may be a variety of sorting methods such as the order of relevance, date order.

Next, a product and service recommendation method based on self-expression on the digital communication tool of the present invention made as described above will be described in more detail.

In order to recommend products and services by the method of recommending goods and services based on self-expression on the digital communication tool of the present invention, as shown in FIGS. 3 and 4, the characteristic value classifier 10 The state of the user is modeled by the user state modeling means 11. In other words, the self-expression of various users is collected to derive common states (e.g. emotions, interests, plans, etc.) and hierarchically modeled from the theoretical and practical point of view using the ontology concept, and the result is FTR. (feature) is stored in the database 20, the keyword extraction from the FTR (feature) database 20 compared to the category set by the category comparison extraction means 31 in the keyword extraction step (step S2) and NLP It is stored in the FTR (feature) database 20 from the input self-expression through a method of extracting a keyword from the feature database 20 using NLP (Natural Language Processing) by the extraction means 32. Extract the keyword.

Subsequently, in the product and service classification step (step S3), the goods and services are classified by the product and service classification means 42 according to the business knowledge or requirements of the corresponding product and service provider, and the classified results are classified as PRD / SRV (product / service) to the database 50.

Subsequently, the product and the service provider pre-specify and match the property value with the pre-designated matching means 61 in the product and service matching step (step S4), or the users freely set and match the user setting matching means 62. The recommended products and services are matched according to the analysis result of the characteristic value, and the matching result is stored in the matching database 70.

Next, in the product and service recommendation step (S5 step), the user state is used as an input value, and the related product and service recommendation results identified from the matching database 70 are outputted and displayed on the display means 81 to display the products and services. You will complete the recommendation.

Figure 5 is a schematic diagram showing a comparison between the advertising method according to the existing product recommendation method and the product and service recommendation method of the present invention, as can be seen from the existing advertising method for any user connected to the arbitrary advertising Although the present invention is made in a manner of outputting, the present invention extracts a keyword from a self-expression phrase written by the user and outputs an advertisement for recommending products and services based on user interests.

While the present invention has been described as a preferred embodiment, the present invention is not limited thereto, and various modifications can be made without departing from the gist of the invention.

1 is a block diagram showing a customer-customized clothing recommendation system using the conventional avatar costume purchase information,

2 is a signal flow diagram of a product recommendation method of a conventional electronic commerce system;

3 is a conceptual diagram of a product and service recommendation model based on self-expression on a digital communication tool employed in the method of the present invention;

4 is a flowchart of a product and service recommendation method based on self-expression on the digital communication tool of the present invention;

5 is a schematic diagram showing a comparison between the advertisement method according to the existing product recommendation and the product and service recommendation method of the present invention.

Description of the Related Art

10: characteristic value classifier 11: user state modeling means

20: FTR (feature) database 20a: Input self expression

30: keyword extraction unit 31: category comparison extraction means

32: NLP extraction means 40: Goods and services classification unit

41 domain selection means 42 product and service classification means

50: PRD / SRV (product / service) database
60: characteristic value and product and service matching unit

61: pre-designated matching means 62: user-set matching means

70: matching database 80: product and service recommendation

81: display means

Claims (8)

A characteristic value classification step (step S1) of modeling the user's state with the user state modeling means 11 of the characteristic value classification unit 10 and classifying the user's state according to the characteristics of the user's interests; The keyword extraction unit extracts an independent meaning noun stored in a FTR (feature) database from the input self-expression phrase as a keyword by the category comparison extraction unit 31 and the NLP extraction unit 32 of the keyword extraction unit 30 as a keyword. Step (step S2); A product and service classification step of selecting a specific domain as the product and service classification means 41 of the product and service classification unit 40 and classifying the goods and services according to the business knowledge or requirements of the corresponding product and service provider (step S3). )Wow; A characteristic value and a product and service matching step of matching the recommended product and service according to the classification result of the characteristic value with the predetermined value matching means 61 and the user setting matching means 62 of the characteristic value and the product and service matching unit 60. (Step S4) and; The product and service recommendation step (step S5) of displaying the result of recommendation of the related goods and services identified from the matching database using the user state as an input value to the display means 81 of the product and service recommendation unit 80. under; The modeling in the characteristic value classification step (S1 step) derives a state that can be used by collecting self-expression of various users, and provides a general hierarchical classification which is predefined using an ontology concept. Modeling the designation and hierarchical classification of advertising categories from a practical perspective of providing hierarchical classification; In the keyword extraction step (S2 step), the keyword is extracted from the feature database using a category comparison extraction step of extracting a keyword from the FTR (feature) database and NLP (Natural Language Processing) by comparing with a set category. An NLP extraction step of extracting; The product and service recommendation step (S5 step) is a product and service recommendation method based on the self-expression on the digital communication tool, characterized in that the alignment step of the recommended products and services. delete 2. The ego of the digital communication tool according to claim 1, wherein the step of classifying the characteristic values (step S1) includes a classifying result storing step of storing characteristic values in a feature database. How to recommend products and services based on expression. delete delete delete delete delete

Images