JP2021064028A - Management server and product search method - Google Patents

Abstract

To provide a product search system capable of developing so that products that match the user's tastes and similar or related products can be recommended by continuing to use them.SOLUTION: A product search system comprises a user terminal 100, a server 110 that stores big data, and a management server 120 that is connected via a network. The management server 120 includes: a correlation coefficient information analysis unit 150 for analyzing a correlation coefficient of products based on a search pattern included in a search history provided from a user information storage unit 130, and extracting product information about the products concerning the analysis from the server 110; and a search unit 160 for extracting the product information having a degree of relevance corresponding to the acquired user information from a personal product DB 140.SELECTED DRAWING: Figure 1

Description

The present invention relates to a management server and a product search method.

With the progress of information technology, it has become possible to easily search and purchase products that match individual tastes from innumerable products in the world. However, individual tastes vary, and it is difficult for a person with little knowledge of interiors to find an interior product that matches his or her tastes. In addition, it is difficult for even a person with abundant knowledge about interiors to find a product that suits his or her taste from unknown products.

JP-A-2007-269491

For example, Patent Document 1 discloses a recommendation system that quantifies and records individual taste characteristics and characteristics of wine as a product, and automatically selects and proposes wine that matches individual tastes. ..

However, in Patent Document 1, once personal preference information is registered in the system, it cannot be changed unless the user manually corrects it. That is, since the conventional recommendation system does not have a learning function, it does not develop so that a product more suitable for the user's taste can be recommended even if the user continues to use the system.

An object of the present invention is to provide a technique capable of recommending a product that is more suitable for a user's taste or a similar or related product by continuing to use the product.

A brief description of typical inventions disclosed in the present application is as follows.

One embodiment of the present invention is a management server connected to a user terminal and a server storing big data via a network, and is a search pattern included in a search history provided by a user information storage unit. It has a correlation coefficient information analysis unit that analyzes the correlation coefficient of products based on the basis and extracts product information about products involved in the analysis from a server in which big data is stored. Further, the correlation coefficient information analysis unit overwrites and updates the correlation coefficient information of the analyzed product with the correlation coefficient information included in the extracted product information. In addition, the management server has a personal product DB that stores the updated product information. In addition, the management server has a search unit that extracts product information having a relevance degree 1 corresponding to the acquired user information from the personal product DB. In addition, the search unit generates a search screen based on the attribute data and the image included in the extracted product information. Further, the search unit receives from the user the focus reference product determined by dragging the desired product from the search screen displayed on the user terminal and the input of the narrowing tab on the search screen. Product information having a similarity level of 1 corresponding to the additional condition determined by the above is extracted from the personal product DB. In addition, the search unit generates a search screen based on the extracted product information. In addition, the search unit provides the generated search screen to the user terminal.

According to the present invention, it is possible to recommend a product that is more suitable for the user's taste or a similar or related product by continuing to use the product.

It is a figure which shows the outline of the configuration example of the product search system including the management server in one Embodiment of this invention. It is a figure which shows the outline of the user information stored in the user information storage part of the management server in one Embodiment of this invention. It is a figure which shows the outline of the whole processing in one Embodiment of this invention. It is a figure which shows the outline of the user information acquisition processing and the user information storage processing in one Embodiment of this invention. It is a figure which shows the outline of the product information and the correlation coefficient information in one Embodiment of this invention. It is a figure which shows the outline of the correlation coefficient information analysis processing in one Embodiment of this invention. It is a figure which shows the outline of the degree of similarity and the degree of relevance in one Embodiment of this invention. It is a figure which shows the outline of the configuration example of the search screen displayed on the display of a user terminal in one Embodiment of this invention. It is a figure which shows the outline of the configuration example of the search screen displayed on the display of a user terminal in one Embodiment of this invention. It is a figure which shows the outline of the focus search process in one Embodiment of this invention. It is a figure which shows the outline of the re-search process in one Embodiment of this invention. It is a figure which shows the outline of the configuration example of the search screen displayed on the display of a user terminal in one Embodiment of this invention. It is a figure which shows the outline of the near-focus search process in one Embodiment of this invention. It is a figure which shows the outline of the configuration example of the search screen displayed on the display of a user terminal in one Embodiment of this invention. It is a figure which shows the outline of the coordinate search process in one Embodiment of this invention. It is a figure which shows the outline of the configuration example of the search screen displayed on the display of a user terminal in one Embodiment of this invention. It is a figure which shows the outline of the separate search process in one Embodiment of this invention. It is a figure which shows the outline of the configuration example of the purchase screen displayed on the display of the user terminal in one Embodiment of this invention. It is a figure which shows the outline of the purchase screen providing processing in one Embodiment of this invention.

Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. It should be noted that this is only an example, and the technical scope of the present invention is not limited to this. In addition, in all the drawings for explaining the embodiment, the same parts are in principle the same reference numerals, and the repeated description thereof will be omitted.
<System configuration>
FIG. 1 is a diagram showing an outline of a configuration example of a product search system according to an embodiment of the present invention.

As shown in FIG. 1, the product search system stores the user terminal 100, the management server 120 connected to the user terminal 100 via the network, and big data connected to the management server 120 via the network. It has a server 110 and the like. That is, the management server 120 is connected to the user terminal 100 and the server 110 via a network.

The user terminal 100 indicates a terminal such as a smartphone or a PC owned by the user. Further, the server 110 in which big data is stored indicates big data that is generally shared and is connected to the Internet.
As shown in FIG. 1, the server 110 in which big data is stored may be connected to the outside of the management server 120. The server 110 in which big data is stored may be included inside the management server 120.

The management server 120 includes a user information storage unit 130, a personal product DB 140 (an abbreviation for a database; hereinafter abbreviated as DB in the same manner), a correlation coefficient information analysis unit 150, a search unit 160, and a purchase screen generation. It has a unit 170 and a purchase screen providing unit 180.

User information (described later, FIG. 2) is stored in the user information storage unit 130. Product information (described later, FIG. 5) is stored in the personal product DB 140.

The correlation coefficient information analysis unit 150 analyzes the correlation coefficient of the product based on the search pattern included in the search history 210 provided by the user information storage unit 130. Next, the correlation coefficient information analysis unit 150 extracts product information for each product involved in the analysis from the server in which big data is stored. Next, the correlation coefficient information analysis unit 150 updates the correlation coefficient information included in the extracted product information by overwriting the correlation coefficient of the analyzed product. After that, the correlation coefficient information analysis unit 150 transmits the product information including the updated correlation coefficient information to the personal product DB 140.

The search unit 160 generates a search screen 700 (described later, FIG. 7).

The purchase screen generation unit 170 generates the purchase screen 1800. The purchase screen generation unit 170 first extracts the product information about the product desired to be purchased transmitted from the user terminal 100 from the server in which the big data is stored. After that, the purchase screen generation unit 170 generates the purchase screen 1800 based on the attribute data (details will be described later), the image, and the specification explanation among the extracted product information.

The purchase screen providing unit 180 provides the purchase screen 1800 to the user terminal 100. After that, the user terminal 100 displays the provided purchase screen 1800 on the display.
<User information storage unit>
FIG. 2A is a diagram showing an outline of a configuration example of user information 200 stored in the user information storage unit 130 of the management server 120 according to the embodiment of the present invention.

As shown in FIG. 2A, the user information 200 is composed of a user ID, a name, contact information, friend information, and data items such as a search history 210.

The user ID indicates a code for the management server 120 to identify the user. The name indicates the name of the user. The contact information indicates the user's e-mail address, telephone number, or the like. The search history 210 indicates a history of searches by the user (details will be described later).

The friend information indicates information such as the name, name, address, contact information, etc. of the recipient who presented the product purchased by the user using the present invention by processing on the Web (details are omitted because it is a known means). ..
By including the friend information in the user information 200, the history presented by the user and the characteristics (age, gender, etc.) of the friend can be converted into big data and reflected in the search conditions.

FIG. 2B is a diagram showing an outline of a configuration example of a search history 210 included in the user information 200 stored in the user information storage unit 130 of the management server 120 according to the embodiment of the present invention. The search history 210 indicates information such as a user ID, a date and time, a search pattern, search conditions, and purchased products.

The "date and time" indicates the date and time when the management server 120 receives the input from the user.

The "search pattern" indicates information on the type and number of searches corresponding to each search in the search history 210 included in the user information 200 that the management server 120 has received input from the user.

The "search condition" indicates the information of the product to be searched corresponding to each search of the search history 210 included in the user information 200 received by the management server 120 from the user. For example, the search condition is composed of "genre", "category", "product name", "brand", "feature", "price" and the like.
<Overall processing>
FIG. 3 is a diagram showing an outline of the overall processing according to the embodiment of the present invention.

First, in S301, the management server 120 performs a user information acquisition process (described later in FIG. 4A). Next, in S302, the management server 120 performs user information storage processing (described later in FIG. 4B). The process of S302 is performed only when the user uses the system according to the present invention for the first time.

Next, in S303, the management server 120 performs a correlation coefficient information analysis process (described later in FIG. 6).

Next, in S304, the management server 120 performs a search process (described later in FIGS. 8 to 17). Next, in S305, the management server 120 causes the user to determine whether or not to perform a search again. When the user determines that the search is to be performed again, the management server 120 performs the search process (described later in FIG. 11) in S306.

When the user determines that the search is not performed again, the management server 120 causes the user to determine whether or not to purchase the product in S307. When the user determines that the product is to be purchased, the management server 120 performs a purchase screen provision process (described later in FIG. 19) in S308. If the user decides not to purchase the product, the management server 120 ends this process.
<User information acquisition processing and user information storage processing>
FIG. 4A is a diagram showing an outline of a user information acquisition process and a user information storage process according to an embodiment of the present invention. Hereinafter, a method in which the management server 120 acquires the user information 200 will be described.

First, in S401, the management server 120 provides the user information input screen to the user terminal 200.
Next, in S402, the user terminal 200 displays the user information input screen on the display.

After that, when the user uses the system according to the present invention for the first time, the user terminal 100 receives the input of the user information 200 from the user in S403.
The user information 200 is composed of a user ID, a name, a contact, and data items such as a search history 210.
Next, in S404, the user terminal 100 transmits the user information 200 that has received the input in S403 to the management server 120.

Next, in S405, the management server 120 acquires the user information 200 by receiving the user information 200 transmitted in S404.
Next, in S406, the management server 120 attaches a user ID to the received user information 200, and stores the user information 200 received in S403 in the user information storage unit 130.
<User information acquisition process>
FIG. 4B is a diagram showing an outline of a user information acquisition process according to an embodiment of the present invention. Hereinafter, a method in which the management server 120 acquires the user information 200 will be described.

When the user uses the system according to the present invention for the second time or later, the user terminal 100 receives the input of the user ID from the user in S407.
The user ID is included in the user information 200. Next, in S408, the user terminal 100 transmits the user ID that received the input in S407 to the management server 120.

After that, in S409, the management server 120 acquires the user information 200 corresponding to the user ID transmitted in S408 from the user information storage unit 130.
<Correlation coefficient information analysis processing>
FIG. 5 is a diagram showing an outline of product information and correlation coefficient information according to the embodiment of the present invention. Further, FIG. 6 is a diagram showing an outline of the correlation coefficient information analysis process according to the embodiment of the present invention. Hereinafter, a method in which the management server 120 analyzes the correlation coefficient information will be described with reference to FIGS. 5 to 6.

FIG. 5A shows an outline of product information. Product information is composed of "attribute data", "image", "specification explanation", and "correlation coefficient information".

Attribute data is composed of "genre", "category", "product name", "brand", "feature", and "price". The feature is composed of features that make up the product, such as "color", "size", and "material".

For example, the attribute data of the product information 502 of the product A (501) has a genre of "interior", a category of "cushion", a product name of "product A", a color of "gray", and the like. Similarly, product D (505) has unique product information 506.

The “image” indicates image data representing the appearance of a product, for example, data such as jpg. "Specification description" indicates text data or the like for explaining the specifications of the product.

"Correlation coefficient information" indicates information such as a pattern in which a user searches for a product and a correlation coefficient link. The correlation coefficient indicates the degree of relevance between products by a numerical value from 0 to 1. The correlation coefficient is determined by how relevant each product is relative to the other products. When the correlation coefficient is 0, it indicates that the degree of relevance is the lowest, and when it is 1, it indicates that the degree of relevance is the highest. Then, as the correlation coefficient approaches 0 to 1, the degree of relevance increases. Further, even for the same product, the product has a different correlation coefficient for each user depending on the age, gender, region, etc. of the user. FIG. 5B shows an outline of the correlation coefficient information.

FIG. 5B shows a search pattern 510 when the user searches for products in the order of product A (501), product B, product C, and product D (505). For example, the search pattern 510 at this time includes the route 511 from the product A to the product B.

Further, FIG. 5B shows how the correlation coefficient link 520 is generated by reflecting the search pattern 510 described above. For each product (node), a correlation coefficient is defined with each other for a route (link) connecting each product (between nodes).
Then, based on the search pattern 510, the correlation coefficient information analysis unit 150 increases the correlation coefficient of each product (between nodes). More specifically, the correlation coefficient information analysis unit 150 increases the correlation coefficient of the route (link connecting each product) included in the search pattern 510. As a result, the correlation function of the searched route (link connecting each product) can be increased.
For example, it is assumed that the product C and the product D are different in color and size, and the correlation coefficient between the product C and the product D before the search is "0.5". Further, the correlation coefficient 521 between arbitrary products not included in the route 511 is "0.4". At this time, the correlation coefficient 522 between the product C and the product D included in the path 511 connecting the product C and the product D after the search increases from "0.5" to "0.7". That is, the correlation coefficient information analysis unit 150 adds a weight vector to the degree of relevance of the product by the search, and raises the correlation coefficient 522. The correlation coefficient 521 not included in the path 511 remains "0.4" because the weight vector is not added.

As shown in FIG. 6, first, in S601, the correlation coefficient information analysis unit 150 extracts the search history 210 corresponding to the user ID to be analyzed from the user information storage unit 130. The search history 210 is composed of information such as a user ID, a date and time, a search pattern, search conditions, and purchased products.
Next, the correlation coefficient information analysis unit 150 provides the correlation coefficient information analysis unit 150 with the search history 210 extracted from the user information storage unit 130.
Next, in S603, the correlation coefficient information analysis unit 150 analyzes the correlation coefficient of the product based on the search pattern included in the provided search history 210. Specifically, the correlation coefficient information analysis unit 150 extracts the (specific) correlation coefficient information unique to each user, which is associated with each product constituting the route 511 included in the search pattern 510. Analyze the correlation coefficient.

Next, in S604, the correlation coefficient information analysis unit 150 extracts product information for each product involved in the analysis from the server 110 in which big data is stored. Specifically, the correlation coefficient information analysis unit 150 analyzes the correlation coefficient by extracting the (universal) correlation coefficient information that is associated with each product and is common to all users.
Next, in S605, the correlation coefficient information analysis unit 150 overwrites the correlation coefficient information included in the extracted product information with the correlation coefficient of the analyzed product and updates it. That is, the correlation coefficient information analysis unit 150 reflects the search pattern 510 obtained by the search performed by the user in the universal correlation coefficient information extracted from the server 110 in which the big data is stored, and for each user. Overwrite and update the unique (specific) correlation coefficient information.

After that, in S606, the product information including the updated correlation coefficient information is transmitted to the personal product DB 140. Next, in S607, the personal product DB 140 stores the updated product information. The product information is composed of attribute data and the like and correlation coefficient information. The personal product DB 140 updates and stores the correlation coefficient information in the product information.
<Similarity and relevance>
FIG. 7 is a diagram showing an outline of the degree of similarity and the degree of relevance in one embodiment of the present invention.

As shown in FIG. 7A, each product is classified according to the degree of similarity based on any product. Regarding the degree of similarity, there are several items in which the parameters of each item of the attribute data of the product information of the product are the same or similar, and the parameters of each item of the attribute data of the product information of the product are the same or similar. It is determined by. That is, the similarity indicates the number of items in which the parameters of the attribute data (indicating the attribute) of the product are the same or similar. For example, when the similarity is 1, it means that the number of items having the same or similar parameters is one. It is assumed that the similarity n + 1 is always included in the similarity n. Then, the larger the value of the degree of similarity, the higher the degree of similarity between the products.

For example, goods are classified according to similarity 1 (710), similarity 2 (720), and similarity 3 (730) with the product A (700) as a base point. Similarity 1 includes products having the same genre as product A as a base point. When the genre of the product A is "interior", the product 711 is included in the similarity 1 because it is the same "interior" product. That is, a product having one item number of items having the same or similar parameters as a product serving as a base point has a similarity level of 1.

The similarity level 2 includes products having the same category as the product A as the base point. When the category of the product A is "cushion", the product 721 is included in the similarity 2 because it is a product of the same "cushion". That is, a product that serves as a base point and a product that has two items with the same or similar parameters have a similarity level of 2.
The similarity level 3 includes a product having the same color as the product A as the base point. When the color of the product A is "gray", the product 731 is included in the similarity 3 because it is the same "gray" product. That is, a product having three items having the same or similar parameters as the product serving as the base point has a similarity level of 3.

By classifying each product according to the degree of similarity in this way, the search unit 160 can allow the user to gradually narrow down the products having high similarity. That is, the search unit can provide a focus search (described later, FIG. 10 and the like) and a near focus search (described later, FIG. 13 and the like).

In the focus search, the search unit 160 extracts the product information of "similarity 1" corresponding to the focus reference product 810 desired by the user and the additional condition (details will be described later) from the personal product DB 140 and searches. It is provided to the user by generating a screen 840.

Further, in the near focus search, the search unit 160 extracts product information of "similarity 2" corresponding to a plurality of focus reference products 1210 desired by the user and additional conditions (details will be described later) from the personal product DB 140. Then, the search screen 1240 is generated and provided to the user.

As shown in FIG. 7B, each product is classified according to the degree of relevance based on any product. The degree of relevance is determined according to the height of the correlation coefficient included in the correlation coefficient information of the product information possessed by the product. The larger the value of the correlation coefficient, the higher the degree to which the products are related to each other. As the number of searches increases, the correlation coefficient increases, so the degree of relevance also increases.

For example, goods are classified according to the degree of relevance 1 (750), the degree of relevance 2 (760), and the degree of relevance 3 (770) with the product A (700) as a base point. For example, the degree of relevance 1 includes products having a correlation coefficient of 0.1 or more and less than 0.3 with the product A at the base point. For example, the product 751 is included in the degree of relevance 1 because it is a product having a correlation coefficient of "0.2" with the product A.

The relevance degree 2 includes, for example, a product having a correlation coefficient of 0.3 or more and less than 0.7 with the product A at the base point. For example, product 761 is included in the degree of relevance 2 because it is a product having a correlation coefficient of "0.4" with product A.
The relevance degree 3 includes, for example, a product having a correlation coefficient of 0.7 or more and less than 1.0 with the product A at the base point. For example, product 771 is included in the degree of relevance 3 because it is a product having a correlation coefficient of "0.8" with product A.

By classifying each product according to the degree of relevance in this way, the search unit 160 narrows down the products that are highly relevant to the user step by step by referring to the degree of relevance, that is, a coordinated search (described later, FIG. 15, etc.). Can be made to.

In the coordinated search, the search unit 160 extracts highly relevant product information corresponding to the coordinated standard product 1510 desired by the user and additional conditions (details will be described later) from the personal product DB 140, and the search screen 1440. Is provided to the user by generating.
[Focus search]
<Search screen>
8 and 9 are diagrams showing an outline of a configuration example of a search screen displayed on the display of the user terminal 100 according to the embodiment of the present invention.

As shown in FIG. 8A, the search screen 800 includes an icon 810 indicating a “focus reference product”. The focus reference product 810 indicates a product that serves as a base point when the search unit 160 performs a focus search. The focus reference product 810 is displayed in the center frame (center frame) of the 3 × 3 frame. Therefore, icons 831 to 838 indicating the other eight "recommended products" are displayed above, below, left, right and left obliquely upward, right obliquely upward, left obliquely downward, and right obliquely below the focus reference product 810. Then, icons 831 to 838 indicating the other eight "recommended products" are displayed in a state of surrounding the focus reference image 810. Further, the focus reference product 810 is determined by accepting an input from the user to be dragged from the "arbitrary frame other than the central frame" to the central frame.

The search screen 800 is displayed on the icon displayed in the "arbitrary frame other than the central frame" and the icon displayed in the central frame when the user receives an input to be dragged from the "arbitrary frame other than the central frame" to the central frame. Replace the displayed icon and display it. That is, the center frame (center frame) of the 3 × 3 frame and eight “recommended products” above, below, left, right and left diagonally above, right diagonally above, left diagonally below, and right diagonally below are shown. Icons 831 to 838 are always displayed without being hollow.

The search screen 800 includes an enlarged display tab 811 of the focus reference product 810. The image of the focus reference product 810 is enlarged and displayed on the enlarged display tab 811. The search screen 800 is generated by the search unit 160 and displayed by the user terminal 100.

The search screen 800 includes a narrowing tab 812. In the narrowing tab 812, the "genre", "feature", and the like of the product can be set as additional conditions for the product search.

The search screen 800 includes a focus tab 813. The focus tab 813 can perform a focus search (described later, FIG. 10) by accepting an input pressed by the user.

The search screen 800 includes a re-search tab 820. The re-search tab 820 can be re-searched (described later in FIG. 11) by accepting an input pressed by the user.

The search screen 800 includes a front screen display tab 821. When the front screen display tab 821 is pressed by the user, the user terminal 100 causes the user terminal 100 to display the front screen on the display. The "previous screen" means, for example, the "before switching" screen when the screen is switched by pressing the re-search tab 820.

The search screen 800 includes a keyword search tab 822. The keyword search tab 822 can directly search for a product desired by the user by accepting an input of a specific keyword that the user wants to search from the user.

The search screen 800 includes a plurality of icons 831 to 838 indicating "recommended products". For the recommended product, the search unit 160 extracts the product information of "relevance degree 1" corresponding to the age, gender, etc. of the user from the user information 200 obtained by the user information acquisition process (S301 or S302) from the personal product DB. It is generated by. The icons 831 to 838 are randomly displayed in eight frames excluding the central frame of the 3 × 3 frame.

As shown in FIG. 8B, the search screen 840 includes a focus reference product 810, a re-search tab 820, a front screen display tab 821, a keyword search tab 822, and the like.

The search screen 840 includes a plurality of icons 841 to 848 indicating “recommended products”. Recommended products can be rephrased as "search result products". That is, the icons 841 to 848 indicate the products of the search result obtained by the search unit 160 performing the focus search. The icons 841 to 848 are randomly displayed by eight frames excluding the central frame of the 3 × 3 frame.

Further, on the search screen 840, the display of the user terminal 100 is switched from the search screen 800 by causing the user to press the re-search tab 820 on the search screen 800 (by activating the focus search process).

It should be noted that the management server 120 has a billing function by a banner advertisement for the product corresponding to the icon of 9 squares displayed on the search screen 800 when the input by tapping the re-search tab 820 is received from the user terminal 100. You can do it.
Since the re-search tab 820 has a banner advertisement function in this way, the management server 120 can also provide the seller of the product with the merit of using the present invention.

As shown in FIG. 9A, the search screen 850 includes a focus reference product 810, a re-search tab 820, a front screen display tab 821, and the like.

The search screen 850 includes a plurality of icons 851 to 858 indicating “recommended products”. Recommended products can be rephrased as "search result products". That is, the icons 851 to 858 indicate the products of the search result obtained by the search unit 160 re-searching the focus search. The icons 851 to 858 are randomly displayed by eight frames excluding the central frame of the 3 × 3 frame.

The search screen 850 includes a "fixed product" selection icon 900. The fixed product indicates a product (for example, product 851 and product 856) that the user desires to fix the display among the recommended products 851 to 858. That is, as shown in FIG. 9B, the product 851 and the product 856 with the fixed product selection icon 900 are always displayed in a fixed manner even after the user presses the search tab 820. That is, the product selected as the fixed product and displaying the fixed product selection icon 900 cannot be switched even after the re-search tab 820 is pressed.
The icon 900 can be determined by holding down the icon desired by the user as a fixed product for a certain period of time (for example, 3 seconds).

As shown in FIG. 9B, the search screen 860 includes a focus reference product 810, a re-search tab 820, a front screen display tab 821, and the like.

The search screen 860 includes a plurality of icons 861 to 868 indicating “recommended products”. Recommended products can be rephrased as "search result products". That is, the icons 861 to 868 indicate the products of the search result obtained by the search unit 160 re-searching the focus search. The icons 861 to 868 are randomly displayed by eight frames excluding the central frame of the 3 × 3 frame.

The search screen 860 includes a "fixed product" selection icon 900. That is, the product 861 and the product 866 to which the fixed product selection icon 900 is attached are fixedly displayed as the same as the product 851 and the product 856 before the input that the user presses the search tab 820 is received.
<Focus search process>
FIG. 10 is a diagram showing an outline of a focus search process according to an embodiment of the present invention. Hereinafter, a method in which the search unit 160 generates the search screens 800 and 840 will be described.

First, in S1001, the search unit 160 extracts the product information of "relevance degree 1" corresponding to age, gender, etc. from the user information 200 acquired in S301 or S302 from the personal product DB 140. The product having a relevance degree of 1 means, for example, a product having a correlation coefficient of 0.1 or more and less than 0.3 with the product A at the base point.
Next, in S1002, the search unit 160 generates the search screen 800 based on the extracted product information.

Specifically, the search unit 160 generates the search screen 800 based on the "product name", "brand", "feature", "price", and the image among the attribute data included in the extracted product information. ..

Next, in S1003, the search unit 160 provides the generated search screen 800 to the user terminal 100.
Next, in S1004, the user terminal 100 displays the provided search screen 800 on the display.

Next, in S1005, the user terminal 100 determines the focus reference product 810 by accepting an input for causing the user to drag a desired product from the displayed search screen 800.
Further, in S1006, the user terminal 100 determines additional conditions by accepting the input of the narrowing down tab 812 on the search screen 800 from the user. The additional condition indicates a condition for narrowing down the search by having the user add and set the "genre", "feature", etc. of the product when searching for the product.
After that, in S1007, the user terminal 100 transmits the determined focus reference product 810 and additional conditions to the search unit 160.

Next, in S1008, the search unit 160 extracts the product information of "similarity 1" corresponding to the received focus reference product 810 and the additional condition from the personal product DB 140. The product information is composed of attribute data and the like and correlation coefficient information. The search unit 160 extracts the product information of the corresponding product from the personal product DB 140.
Next, in S1009, the search unit 160 generates a search screen 840 based on the extracted product information.

Specifically, the search unit 160 includes a search screen 840 that includes "product name", "brand", "feature", "price", and an image among the attribute data included in the extracted product information. To generate.

Next, in S1010, the search unit 160 provides the generated search screen 840 to the user terminal 100.
Next, in S1011, the user terminal 100 displays the provided search screen 840 on the display.

By performing the focus search in this way, the management server 120 can make recommendations according to a specific product feature.
<Research process>
FIG. 11A is a diagram showing an outline of the re-search process according to the embodiment of the present invention. Hereinafter, a method in which the search unit 160 generates the search screen 850 will be described.

First, in S1101, the user terminal 100 causes the user to determine whether or not to change the focus reference product 810 or the additional condition. When accepting the input to change the focus reference product 810 or the additional condition, the user terminal 100 and the management server 120 repeat the steps S1005 to S1011. When the focus reference product 810 or the additional condition is not changed, the user terminal 100 proceeds to the process of S1102.

In S1102, the user terminal 100 starts the re-search while maintaining the focus reference product 810 or the additional condition by accepting the input pressed by the user on the re-search tab 820. The additional condition indicates a condition for narrowing down the search by having the user add and set the "genre", "feature", etc. of the product when searching for the product.
Next, in S1103, the search unit 160 obtains product information excluding products having "similarity 2" corresponding to the maintained focus reference product 810 and the additional condition and which have already been provided to the user terminal 100. Extracted from personal product DB 140.
For example, when the additional condition is "color", the search unit 160 excludes products having the same "color" from the products stored in the personal product DB and already provided to the user terminal 100. Product information is extracted from the personal product DB 140.
Further, the similarity 2 includes products having the same category as the maintained focus reference product 810. For example, if the category of the maintained focus reference product 810 is "cushion", the products with the same "cushion" are included in the similarity 2. That is, a product having two items having the same or similar parameters as the maintained focus reference product 810 has a similarity level of 2.
Next, in S1104, the search unit 160 generates a search screen 850 based on the extracted product information.

Specifically, the search unit 160 includes a search screen 850 that includes "product name", "brand", "feature", "price", and an image among the attribute data included in the extracted product information. To generate.

Next, in S1105, the search unit 160 provides the generated search screen 850 to the user terminal 100.
Next, in S1106, the user terminal 100 displays the provided search screen 850 on the display.

Next, in S1107, the user terminal 100 causes the user to determine whether or not to perform a re-search. When the input to perform the re-search is further received, the user terminal 100 and the management server 120 repeat the steps S1101 to S1107. If no further search is performed, the user terminal 100 ends this process.

Note that S1103 in the nth re-search processes the process with "similarity n + 1". That is, in S1107, when the user terminal 100 causes the user to determine whether or not to perform a re-search and then accepts an input to perform a re-search, the user terminal 100 first repeats the steps S1101 to S1102. .. It is obvious that this re-search is a "second re-search". That is, the similarity increases with each re-search.
Next, the search unit 160 repeats the process of S1103. At this time, the search unit 160 is a product having "similarity 3" corresponding to the maintained focus reference product 810 and the additional condition, and has already been provided to the user terminal 100. Product information excluding those is extracted from the personal product DB 140. The reason for the "similarity 3" is that the re-search is a "second re-search".
Further, the similarity 3 includes products having the same color as the maintained focus reference product 810. For example, when the color of the maintained focus reference product 810 is "gray", the same "gray" product is included in the similarity 3. That is, the maintained focus reference product 810 and a product having three items having the same or similar parameters have a similarity level of 3.
Next, the search unit 160 repeats the steps S1104 to S1105. That is, the search screen 850 is generated based on the extracted product information and provided to the user terminal 100.
After that, the user terminal 100 repeats the steps S1106 to S1107.

FIG. 11B is a diagram showing an outline of the re-search process when a fixed product is selected. Hereinafter, a method in which the search unit 160 generates the search screen 860 will be described.

In S1108, the user terminal 100 accepts an input for determining a fixed product by causing the user to select the fixed product selection icon 900. The fixed product is not limited to a single item. Next, in S1109, the user terminal 100 transmits the determined fixed product data to the search unit 160. The fixed product data indicates information on which product (for example, product 851 and product 856) the user wants to fix the display among the recommended products 851 to 858. That is, the information about the product 851 and the product 856 accompanied by the fixed product selection icon 900 is shown.

Next, in S1110, the search unit 160 provides information on which of the products 851 to 858 recommended by the user, which is included in the received fixed product data, the product for which the display is desired to be fixed. The steps S1103 to S1105 are performed for the products in the "frame in which the fixed product is not selected" (that is, the frame in which the fixed product selection icon 900 is not attached). As a result, the search unit 160 generates the search screen 860 and provides it to the user terminal 100.

After that, in S1111, the user terminal 100 displays the provided search screen 860 on the display.

By performing the re-search in this way, the management server 120 can recommend products that are more suitable for the user's taste and products that are similar or related to the user's taste by continuing the search by the user.
[Near focus search]
<Search screen>
FIG. 12 is a diagram showing an outline of a configuration example of a search screen displayed on the display of the user terminal 100 according to the embodiment of the present invention.

As shown in FIG. 12 (a), the search screen 1200 includes icons 1210 and 1212 indicating "focus reference products". The focus reference products 1210 and 1212 indicate products that serve as a base point when the search unit 160 performs a near focus search.
In addition, any one of the focus reference products 1210 and 1212 (for example, 1210) is displayed by the central frame of the 3 × 3 frame.

Any one of the focus reference products 1210 and 1212 (eg, 1210) can be determined by accepting an input that causes the user to drag from an "arbitrary frame other than the central frame" to the central frame. The other one of the focus reference products 1210 and 1212 (1212) can be determined by tapping the desired product after dragging to the center frame.

The search screen 1200 includes an enlarged display tab 1211 of the focus reference product 1210. The enlarged display tab 1211 enlarges and displays the image of the focus reference product 1210.

The search screen 1200 includes a narrowing tab 812, a focus tab 813, a research tab 820, a front screen display tab 821, and a keyword search tab 822.

The search screen 1200 includes a plurality of icons 1231 to 1238 indicating "recommended products". For the recommended product, the search unit 160 extracts the product information of "relevance degree 1" corresponding to the age, gender, etc. of the user from the user information 200 obtained by the user information acquisition process (S301 or S302) from the personal product DB. It is generated by. The icons 1231 to 1238 are randomly displayed by eight frames excluding the central frame of the 3 × 3 frame. For example, the product 1238 becomes the focus reference product 1212 by accepting an input to be tapped after dragging to the center frame of the focus reference product 1210 as described above.

As shown in FIG. 12B, the search screen 1240 includes focus reference products 1210 and 1212, a search tab 820, and the like.

The search screen 1240 includes a plurality of icons 1241 to 1247 indicating "recommended products". Recommended products can be rephrased as "search result products". That is, the icons 1241 to 1247 indicate the products of the search result obtained by the search unit 160 performing the near-focus search. The icons 1241 to 1247 are randomly displayed by the frames excluding all the frames selected as the focus reference products among the 3 × 3 frames.

Further, on the search screen 1240, the display of the user terminal 100 is switched from the search screen 1200 by causing the user to press the re-search tab 820 on the search screen 1200 (by activating the near focus search process).

In addition, the management server 120 has a billing function by a banner advertisement for the product corresponding to the icon of 9 squares displayed on the search screen 1200 when the input by tapping the re-search tab 820 is received from the user terminal 100. You can do it.
Since the re-search tab 820 has a banner advertisement function in this way, the management server 120 can also provide the seller of the product with the merit of using the present invention.
<Near focus search processing>
FIG. 13 is a diagram showing an outline of a near-focus search process according to an embodiment of the present invention. Hereinafter, a method in which the search unit 160 generates the search screens 1200 and 1240 will be described.

First, in S1301, the search unit 160 generates the search screen 1200 by performing the steps S1001 to S1004.
Next, in S1302, the search unit 160 provides the generated search screen 1200 to the user terminal 100.
Next, in S1303, the user terminal 100 displays the provided search screen 1200 on the display.

Next, in S1304, the user terminal 100 receives an input for causing the user to drag a desired product from the displayed search screen 1200 from the "arbitrary frame other than the central frame" to the central frame, thereby causing the focus reference. The product 1210 can be determined. Further, the user terminal 100 can determine the focus reference product 1212 by tapping the desired product after dragging to the central frame.
Next, in S1305, the user terminal 100 determines additional conditions by accepting the input of the narrowing down tab 812 on the search screen 1200 from the user.
After that, in S1306, the user terminal 100 transmits the determined plurality of focus reference products 1210 and 1212 and additional conditions to the search unit 160.

Next, in S1307, the search unit 160 extracts the product information of "similarity 1" corresponding to the received plurality of focus reference products 1210 and 1212 and the additional condition from the personal product DB 140. Next, in S1308, the search unit 160 generates a search screen 1240 based on the extracted product information.

Specifically, the search unit 160 generates a search screen 1240 based on the "product name", "brand", "feature", "price", and the image among the attribute data included in the extracted product information. ..

Next, in S1309, the search unit 160 provides the generated search screen 1240 to the user terminal 100.
Next, in S1310, the user terminal 100 displays the provided search screen 1240 on the display.

By performing the near-focus search in this way, the management server 120 can make recommendations that take into account the features common to two or more products.
[Coordinated search]
<Search screen>
FIG. 14 is a diagram showing an outline of a configuration example of a search screen displayed on the display of the user terminal 100 according to the embodiment of the present invention.

As shown in FIG. 14A, the search screen 1400 includes an icon 1410 indicating a “coordinated reference product”. The coordinated reference product 1410 indicates a product that serves as a base point when the search unit 160 performs a coordinated search. The coordinated standard product 1410 is displayed by the central frame of the 3 × 3 frame.

The coordination reference product 1410 can be determined by accepting an input for the user to drag from "an arbitrary frame other than the central frame" to the central frame.

The search screen 1400 includes an enlarged display tab 1411 of the focus reference product 1410. The enlarged display tab 1411 enlarges and displays the image of the focus reference product 1410.

The search screen 1400 includes a coordinate tab 1412. The coordination tab 1412 can perform a coordination search (described later, FIG. 15) by receiving an input pressed by the user.

The search screen 1400 includes a narrowing tab 812, a focus tab 813, a research tab 820, a front screen display tab 821, and a keyword search tab 822.

The search screen 1400 includes a plurality of icons 1431 to 1438 indicating "recommended products". For the recommended product, the search unit 160 extracts the product information of "relevance degree 1" corresponding to the age, gender, etc. of the user from the user information 200 obtained by the user information acquisition process (S301 or S302) from the personal product DB. It is generated by.
The icons 1431 to 1438 are randomly displayed by eight frames excluding the central frame of the 3 × 3 frame.

As shown in FIG. 14B, the search screen 1440 includes a focus reference product 1410, a re-search tab 820, and the like.

The search screen 1440 includes a plurality of icons 1441 to 1448 indicating "recommended products". Recommended products can be rephrased as "search result products". That is, the icons 1441 to 1248 indicate the products of the search result obtained by the search unit 160 performing the coordinated search.
The icons 1441 to 1448 are randomly displayed in the 3 × 3 frames excluding the central frame selected as the coordination reference product.

Further, on the search screen 1440, the display of the user terminal 100 is switched from the search screen 1400 by causing the user to press the re-search tab 820 on the search screen 1400 (by activating the coordinated search process).

In addition, the management server 120 has a billing function by a banner advertisement for the product corresponding to the icon of 9 squares displayed on the search screen 1400 when the input by tapping the re-search tab 820 is received from the user terminal 100. You can do it.
Since the re-search tab 820 has a banner advertisement function in this way, the management server 120 can also provide the seller of the product with the merit of using the present invention.
<Coordinated search process>
FIG. 15 is a diagram showing an outline of a coordinated search process according to an embodiment of the present invention. Hereinafter, a method in which the search unit 160 generates the search screens 1400 and 1440 will be described.

First, in S1501, the search unit 160 generates the search screen 1400 by performing the steps S1001 to S1004.
Next, in S1502, the search unit 160 provides the generated search screen 1400 to the user terminal 100.
Next, in S1503, the user terminal 100 displays the provided search screen 1400 on the display.

Next, in S1504, the user terminal 100 receives an input for causing the user to drag a desired product from the displayed search screen 1400 from the "arbitrary frame other than the central frame" to the central frame, thereby performing the coordination standard. Product 1410 can be determined.
Next, in S1505, the user terminal 100 determines additional conditions by accepting the input of the narrowing down tab 812 on the search screen 1400 from the user.
After that, in S1506, the user terminal 100 transmits the determined coordination reference product 1410 and additional conditions to the search unit 160. The coordinated reference product 1410 indicates a product that serves as a base point when the search unit 160 performs a coordinated search.

Next, in S1507, the search unit 160 extracts highly relevant product information corresponding to the received coordination reference product 1510 and the additional condition from the personal product DB 140. The product information is composed of attribute data and the like and correlation coefficient information. The search unit 160 extracts the product information of the corresponding product from the personal product DB 140.
Next, in S1508, the search unit 160 generates a search screen 1440 based on the extracted product information.

Specifically, the search unit 160 generates a search screen 1440 based on the "product name", "brand", "feature", "price", and the image among the attribute data included in the extracted product information. ..

Next, in S1509, the search unit 160 provides the generated search screen 1440 to the user terminal 100. Next, in S1510, the user terminal 100 displays the provided search screen 1440 on the display.

By performing the coordinated search in this way, the management server 120 can recommend a product having a compatible combination from products in another category of the same genre as a specific product.
[Separate search]
<Search screen>
FIG. 16 is a diagram showing an outline of a configuration example of a search screen displayed on the display of the user terminal 100 according to the embodiment of the present invention.

As shown in FIG. 16A, the search screen 1600 includes an icon 1610 indicating a focus reference product or a coordination reference product. In addition, the search screen 1600 includes the "combination icon" 1638. The braid icon 1638 displays a plurality of products as a set of "braids" with icons for one product.

The search screen 1600 includes a plurality of icons 1631 to 1638 indicating "recommended products". For the recommended product, the search unit 160 extracts the product information of "relevance degree 1" corresponding to the age, gender, etc. of the user from the user information 200 obtained by the user information acquisition process (S301 or S302) from the personal product DB. It is generated by. The icons 1631 to 1638 are randomly displayed by eight frames excluding the central frame of the 3 × 3 frame.

As shown in FIG. 14B, the search screen 1640 includes a separate reference product 1638, a re-search tab 820, and the like.

The search screen 1640 includes a plurality of icons 1641 to 1648 indicating "recommended products". Recommended products can be rephrased as "search result products". That is, the icons 1641 to 1648 indicate the products of the search result obtained by the search unit 160 performing the separate search. The icons 1641 to 1648 are randomly displayed in the 3 × 3 frames excluding the central frame selected as the separate reference product. The separate reference product 1638 indicates a product that serves as a base point when the search unit 160 performs a separate search. The separate reference product 1638 can be determined by causing the user to drag the braid icon 1638 from the search screen 1600 to the center frame.

Further, on the search screen 1640, the display of the user terminal 100 is switched from the search screen 1600 by causing the user to press the re-search tab 820 on the search screen 1600 (by invoking the separate search process).

In addition, the management server 120 has a billing function by a banner advertisement for the product corresponding to the icon of 9 squares displayed on the search screen 1600 when the input by tapping the re-search tab 820 is received from the user terminal 100. You can do it.
Since the re-search tab 820 has a banner advertisement function in this way, the management server 120 can also provide the seller of the product with the merit of using the present invention.
<Separate search processing>
FIG. 17 is a diagram showing an outline of a separate search process according to an embodiment of the present invention. Hereinafter, a method in which the search unit 160 generates the search screens 1600 and 1640 will be described.

First, in S1701, the search unit 160 generates the search screen 1600 by performing the steps S1001 to S1004.
Next, in S1702, the search unit 160 provides the generated search screen 1600 to the user terminal 100.
Next, in S1703, the user terminal 100 displays the provided search screen 1600 on the display.

Next, in S1704, the user terminal 100 can determine the separate reference product 1638 by accepting an input for causing the user to drag the braid icon 1638 from the displayed search screen 1600 to the center frame.
After that, in S1705, the user terminal 100 transmits the determined separate reference product 1638 to the search unit 160.

Next, in S1706, the search unit 160 extracts information on any eight highly relevant products included in the assembly, which is the received separate reference product 1638, from the personal product DB 140. In addition, the "combination" defines a plurality of (8 or more) products selected in advance by the person who provides the advertisement as one product. In addition, the plurality of products included in this assembly have the same idea and common characteristics.
Next, in S1707, the search unit 160 generates a search screen 1640 based on the extracted product information.

Specifically, the search unit 160 generates a search image 1640 based on the "product name", "brand", "feature", "price", and the image among the attribute data included in the extracted product information. ..

Next, in S1708, the search unit 160 provides the generated search screen 1640 to the user terminal 100.
Next, in S1709, the user terminal 100 displays the provided search screen 1640 on the display.

By performing the separate search in this way, the management server 120 can decompose the image photograph of the world view coordinated by some products into each product and recommend it.
[Inspiration Search]
For example, in the focus search process described above (the same applies to the near focus search, the coordinated search, and the separate search), when both the focus tab 813 and the coordinated tab 1412 included in the search screen 800 are not selected, the search is re-searched. Tab 820 transforms into an "inspiration tab".

At this time, the icon display of the focus reference product 810 is deleted from the center frame of the 3 × 3 frame. That is, only the icons 831 to 838 indicating the eight "recommended products" of the focus reference product 810, which are above, below, left, right and left obliquely upward, right obliquely upward, left obliquely downward, and right obliquely downward, are displayed. Then, only the icons 831 to 838 indicating the other eight "recommended products" are displayed in a state of surrounding the hollow focus reference image 810.

After that, the focus reference product 810 is determined by accepting an input to be dragged from the icon 831 to 838 indicating the eight "recommended products" displayed in the "arbitrary frame other than the central frame" from the user. ..

Further, the icons 831 to 838 indicating the above eight "recommended products" do not extract information from the personal product DB 140 based on the search conditions, for example. That is, the icons 831 to 838 indicating the above eight "recommended products" are randomly selected and displayed regardless of the search conditions.
<Purchase screen>
FIG. 18 is a diagram showing an outline of a configuration example of a purchase screen 1800 displayed on the display of the user terminal 100 according to the embodiment of the present invention.

FIG. 18 (a) is the same as that shown in FIG. 8 (a). The search screen 800 includes a focus reference product 810, a re-search tab 820, a front screen display tab 821, and the like.

As shown in FIG. 18B, the purchase screen 1800 includes a specification explanation display area 1810 for the desired product, a purchase tab 1820, and a cancellation tab 1830.
<Purchase screen provision process>
FIG. 19 is a diagram showing an outline of a purchase screen providing process according to an embodiment of the present invention. Hereinafter, a method in which the management server 120 provides the purchase screen 1800 will be described.

First, in S1901, the user terminal 100 can determine the desired purchase product by letting the user tap the enlarged display tab 811 included in the displayed search screen 800 or the like.

The management server 120 may have a billing function by a banner advertisement when receiving an input by tapping the enlarged display tab 811 from the user terminal 100 in S1901.
Since the enlarged display tab 811 has a banner advertisement function in this way, the management server 120 can also provide the seller of the product with the merit of using the present invention.

Next, in S1902, the user terminal 100 transmits the data of the determined purchase desired product to the management server 120.
Next, in S1903, the management server 120 extracts the received product information about the desired product from the server in which the big data is stored.
After that, in S1904, the management server 120 generates a purchase screen 1800 based on the extracted product information.

Specifically, the search unit 160 includes the "product name", "brand", "feature", "price" of the attribute data included in the extracted product information, and the purchase screen 1800 including these based on the image. To generate.

Next, in S1905, the management server 120 provides the generated purchase screen 1800 to the user terminal 100.
Next, in S1906, the user terminal 100 displays the provided purchase screen 1800 on the display.

After that, in S1907, the user terminal 100 causes the user to determine whether or not to decide to purchase the desired product. When accepting the input to the effect that the purchase is decided, the user terminal 100 decides the purchase by tapping the purchase tab 1820 included in the purchase screen 1800. If the purchase is not decided, the user terminal 100 ends this process.
<Effect of this embodiment>

According to the embodiment of the present invention described above, the management server 120 generates a search screen 800 or the like based on the user information 200 received from the user terminal 100 and the product information received from the server 110 and displays the search screen 800 or the like on the display. Therefore, it is possible to recommend products that are more suitable for the user's taste and similar or related products.

Although the invention made by the present inventor has been specifically described above based on the embodiment, the present invention is not limited to the embodiment and can be variously modified without departing from the gist thereof. Needless to say. For example, the customer terminal includes all various types of customer terminals such as notebook PCs and tablet terminals in addition to smartphones.

Further, the above-described embodiment has been described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the described configurations. Further, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. .. In addition, other configurations may be added, deleted, or replaced with respect to a part of the configurations of each embodiment.

Further, each of the above-mentioned configurations, functions, and processing units may realize a part or all of them by hardware (for example, an integrated circuit). In addition, each of the above configurations, functions, and processing units is installed-type software via a network or by a storage medium such as a disk, or a network-type application such as an ASP, in which a processor interprets and executes a program that realizes each function. It may be realized. Information such as programs, tables, and files that realize each function can be placed in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

100 ... User terminal 110 ... Server 120 ... Management server 130 ... User information storage unit 140 ... Personal product DB
150 ... Correlation coefficient information analysis unit 160 ... Search unit 170 ... Purchase screen generation unit 180 ... Purchase screen provision unit 800 ... Search screen 1800 ... Purchase screen

Claims (15)

A management server that is connected to a user terminal and a server that stores big data via a network.
It has a correlation coefficient information analysis unit that analyzes the product correlation coefficient based on the search pattern included in the search history provided by the user information storage unit and extracts product information about the products involved in the analysis from the server. ,
The correlation coefficient information analysis unit overwrites and updates the correlation coefficient information of the analyzed product with the correlation coefficient information included in the extracted product information.
A personal product DB that stores the updated product information, and
A search unit that extracts product information of the degree of relevance corresponding to the acquired user information from the personal product DB, and
Have,
The search unit generates a search screen based on the attribute data and the image included in the extracted product information.
The search unit receives input from the user for a focus reference product determined by accepting input from the user for a desired product from the search screen displayed on the user terminal, and input of a narrowing tab on the search screen. Product information of the degree of similarity corresponding to the determined additional condition is extracted from the personal product DB, and the product information is extracted from the personal product DB.
The search unit generates a search screen based on the extracted product information, and generates a search screen.
The search unit provides the generated search screen to the user terminal, and provides the user terminal with the generated search screen.
The degree of similarity is determined by whether the parameters of each item of the attribute data of the product information of the product are the same or similar, and how many items have the same or similar parameters, and increases each time the re-search is repeated. And
The degree of relevance is determined according to the height of the correlation coefficient included in the correlation coefficient information of the product information possessed by the product, and increases each time the re-search is repeated.
The correlation coefficient is determined by a numerical value from 0 to 1 as to how much each product is relatively related to other products.
Management server. In the management server according to claim 1,
The search unit causes the user to determine whether or not to change the focus reference product or the additional condition, and if the change is not made, the focus reference product and the product having a similarity degree 2 corresponding to the additional condition are already present. Product information excluding those provided to the user terminal is extracted from the personal product DB, and
The search unit includes a search unit that generates a search screen based on the extracted product information.
The search unit provides the generated search screen to the user terminal, and provides the user terminal with the generated search screen.
When the user is made to judge whether or not to perform the re-search further, and then the re-search is performed, the search screen is generated with the similarity n + 1 in the nth re-search.
Management server. In the management server according to claim 1,
The search unit has a degree of similarity corresponding to a plurality of focus reference products determined from the search screen displayed on the user terminal and additional conditions determined by accepting the input of the narrowing tab on the search screen from the user. Extract the product information of 2 from the personal product DB,
The search unit generates a search screen based on the extracted product information, and generates a search screen.
The search unit provides the generated search screen to the user terminal.
Management server. In the management server according to claim 1,
The search unit has a high degree of relevance corresponding to the coordinated standard product determined from the search screen displayed on the user terminal and the additional condition determined by accepting the input of the narrowing tab on the search screen from the user. Extract product information from personal product DB,
The search unit generates a search screen based on the extracted product information, and generates a search screen.
The search unit provides the generated search screen to the user terminal.
Management server. In the management server according to claim 1,
The search unit extracts highly relevant product information corresponding to the separate standard product determined by the user by dragging the braid icon to the center frame from the search screen displayed on the user terminal from the personal product DB. ,
The search unit generates a search screen based on the extracted product information, and generates a search screen.
The search unit provides the generated search screen to the user terminal.
Management server. In the management server according to claim 1,
The search unit does not extract the product information from the personal product DB for the search screen displayed on the user terminal.
The search unit erases the display from the central frame of the 3 × 3 frame, generates a search screen that randomly displays products other than the central frame, and generates a search screen.
The search unit provides the generated search screen to the user terminal.
Management server. In the management server according to claim 1,
Receives the desired purchase product determined by letting the user tap the enlarged display tab included in the search screen displayed on the user terminal.
Extract the received product information about the desired product from the server and
A purchase screen generator that generates a purchase screen based on the extracted product information,
It has a purchase screen providing unit that provides the generated purchase screen to the user terminal.
Management server. In the management server according to claim 1,
It also has a billing function by banner advertisement when the user taps the re-search tab or the enlarged display tab included in the search screen displayed on the user terminal to re-search or accept the input of the product to be purchased.
Management server. A method for searching for a product having a user terminal, a server that stores big data, and a management server that is wirelessly connected to the user terminal and the server via a network.
A process in which the management server acquires and stores user information from the user terminal, and
The management server analyzes the correlation coefficient of the product based on the search pattern included in the search history provided from the user information storage unit, and extracts the product information about the product involved in the analysis from the server.
A process in which the management server overwrites, updates, and stores the correlation coefficient information of the analyzed product on the correlation coefficient information included in the extracted product information.
A process in which the management server extracts product information having a degree of relevance corresponding to the acquired user information from the personal product DB, and
A process in which the management server generates a search screen based on the attribute data and images included in the extracted product information.
The management server determines the focus reference product determined by dragging the desired product from the search screen displayed on the user terminal to the user, and receives the input of the narrowing tab on the search screen from the user. The process of extracting the product information of the degree of similarity corresponding to the additional conditions made from the personal product DB, and
A process in which the management server generates a search screen based on the extracted product information, and
The management server has a step of providing the generated search screen to the user terminal.
How to search for products. In the product search method according to claim 9,
The management server causes the user to determine whether or not to change the focus reference product or the additional condition, and if the change is not made, the maintained focus reference product and the product having a similarity degree of 2 corresponding to the additional condition are used. The process of extracting product information from the personal product DB, excluding those already provided to the user terminal,
A process in which the management server generates a search screen based on the extracted product information, and
The process of providing the generated search screen to the user terminal by the management server, and
The management server has a step of generating a search screen with a similarity n + 1 in the nth re-search when the user is made to determine whether or not to perform a re-search and the re-search is performed.
How to search for products. In the product search method according to claim 9,
Similarity corresponding to a plurality of focus reference products determined by the management server from the search screen displayed on the user terminal and additional conditions determined by accepting the input of the narrowing tab on the search screen from the user. The process of extracting product information of degree 2 from the personal product DB,
A process in which the management server generates a search screen based on the extracted product information, and
The management server has a step of providing the generated search screen to the user terminal.
How to search for products. In the product search method according to claim 9,
The degree of relevance corresponding to the coordination standard product determined by the management server from the search screen displayed on the user terminal and the additional condition determined by accepting the input of the narrowing tab on the search screen from the user. The process of extracting high-quality product information from the personal product DB,
A process in which the management server generates a search screen based on the extracted product information, and
The management server has a step of providing the generated search screen to the user terminal.
How to search for products. In the product search method according to claim 9,
The management server extracts highly relevant product information corresponding to the separate standard product determined by the user by dragging the braid icon to the center frame from the search screen displayed on the user terminal from the personal product DB. And the process to do
A process in which the management server generates a search screen based on the extracted product information, and
The management server has a step of providing the generated search screen to the user terminal.
How to search for products. In the product search method according to claim 9,
A process in which the management server does not extract product information from the personal product DB for the search screen displayed on the user terminal.
A process in which the management server erases the display from the central frame of the 3 × 3 frame and generates a search screen that randomly displays products other than the central frame.
The management server has a step of providing the generated search screen to a user terminal.
How to search for products. In the product search method according to claim 9,
The process of receiving the purchase desired product determined by the management server by causing the user to tap the enlarged display tab included in the search screen displayed on the user terminal.
A process in which the management server extracts the received product information about the desired product from the server in which big data is stored, and
A process in which the management server generates a purchase screen based on the extracted product information,
The management server has a step of providing the generated purchase screen to the user terminal.
How to search for products.

Images