JP7482557B1 - Information processing device, information processing method, and program - Google Patents

Abstract

[Problem] To provide an information processing device, information processing method, and program capable of accurately grasping the deep needs of each user and providing optimal information to each user. [Solution] The information processing device according to the present disclosure includes a user deep needs estimation unit that estimates deep needs information of each user based on behavior history information related to the behavior of the user browsing a website and deep product needs information associated with a product stored in a storage unit, and an output data generation unit that generates output data to be output to each user based on the deep needs information of the user. [Selected Figure] Figure 1

Description

The present disclosure relates to an information processing device, an information processing method, and a program.

Conventionally, there is known a technique for acquiring information on the search history and site browsing history of a site visitor who visits a website, and identifying the site visitor's field of interest based on the history information, and displaying advertisements in that field. For example, Patent Document 1 discloses a system that stores and manages the history of articles viewed by a user and related fields, and displays advertisements in a priority order determined based on the user's field of interest and browsing history.

Patent Publication No. 7013054

The technology in Patent Document 1 above is said to be able to display or transmit information of interest to a user in a personalized manner based on the browsing history of articles on a website. However, this is not sufficient in terms of grasping the deep needs of each user and providing optimal information to each individual user, and there is room for improvement.

Therefore, the present disclosure has been made in consideration of the above problems, and its purpose is to provide an information processing device, an information processing method, and a program that can accurately grasp the deep needs of each user and provide each user with the most suitable information.

According to the present disclosure, a user deep needs estimation unit that estimates deep needs information of each user based on behavior history information related to the behavior of the user browsing a website and deep product needs information associated with a product stored in a storage unit;
An information processing device is provided, comprising: an output data generating unit that generates output data to be output to each user based on the deep needs information of the user.

According to the present disclosure, there is also provided a method for estimating deep user needs information of each user based on behavior history information related to the behavior of the user browsing the website and deep product needs information associated with the product, the deep product needs information being stored in a storage unit;
and an output data generation process for generating output data to be output to each user based on the deep needs information of the user.

According to the present disclosure, there is also provided a method for estimating deep user needs information of each user based on behavior history information related to the behavior of the user browsing a website and deep product needs information associated with the product, the deep product needs information being stored in a storage unit;
An output data generating process for generating output data to be output to each user based on the deep needs information of the user is provided.

According to the present disclosure, it is possible to provide an information processing device, an information processing method, and a program that can accurately grasp the deep needs of each user and provide each user with the most suitable information.

FIG. 1 is a diagram illustrating a configuration example of an information processing system according to an embodiment of the present disclosure. FIG. 2 is a diagram illustrating an example of a configuration of an information processing device according to the embodiment. A figure showing an example of deep needs information for each user in the same embodiment. A figure showing another example of deep needs information for each user in the same embodiment. FIG. 11 is a diagram illustrating an example of a display screen of a user terminal according to the embodiment. FIG. 11 is a diagram showing another example of the display screen of the user terminal according to the embodiment. FIG. 11 is a diagram showing an example of a deep product needs database according to the embodiment. A figure showing another example of deep needs information for each user in the same embodiment. FIG. 11 is a diagram showing another example of the display screen of the user terminal according to the embodiment. FIG. 11 is a diagram showing another example of the display screen of the user terminal according to the embodiment. FIG. 11 is a diagram illustrating a configuration example of a user terminal according to the embodiment. FIG. 11 is a flowchart illustrating an information processing method according to the embodiment.

A preferred embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that in this specification and drawings, components having substantially the same functions are designated by the same reference numerals to avoid redundant description.

FIG. 1 shows an example of an information processing system 100 according to the present embodiment. The information processing system 100 includes an information processing device 10 as a system management server, and a user terminal 20 used by a user who is a user of a service using the present system 100. The information processing device 10 and the multiple user terminals 20 are each connected via a network NW. The network NW is configured to include the Internet, an intranet, a wireless LAN (Local Area Network), a WAN (Wide Area Network), a fixed telephone line, a mobile phone line, or a combination of these. In this example, multiple users (site visitors, etc.) communicate with the information processing device 10 via their own user terminals 20 (20a, 20b, 20c), but this is not limited to this, and each user may use the present system via the input and output units of the information processing device 10. In other words, the present system 10 can function as the information processing device 10 alone, without including the user terminals and the network. Alternatively, all the functions of the information processing device 10 can be implemented in the user terminal, allowing the user terminal to function independently.

Figure 2 is a block diagram showing the functional configuration of the information processing device 10. The information processing device 10 is a device used by a system administrator or the like when operating and managing various services, and may be, for example, a general-purpose computer such as a workstation or a personal computer, or may be logically realized by cloud computing technology.

The information processing device 10 of this example has a control unit 11, a storage unit 12, an input unit 13, an output unit 14, and a communication unit 15. The information processing device 10 accepts various input information from the input unit 13 or from an external device via the communication unit 15. Then, the control unit 11 executes processing according to a program corresponding to the input information, and the processing result of the program (e.g., an image, a sound, etc.) is output from the output unit 14 or transmitted to an external information processing device or the like via the communication unit 15. Note that a part of the above program may be transmitted to another information processing device (e.g., a user terminal, another server, etc.) and executed on the other information processing device. In this case, the other information processing device may be, for example, a smartphone, a mobile phone terminal, a tablet terminal, a personal computer, etc., and is connected wirelessly or wired to the information processing device 10 via a network such as the Internet.

The control unit 11 transfers information between each unit and controls the information processing device 10 as a whole, and is realized, for example, by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit) executing a program stored in a predetermined memory. The control unit 11 in this embodiment includes a user deep needs estimation unit 111 and an output data generation unit 112.

The user deep needs estimation unit 111 estimates (determines) the deep needs information of each site visitor based on behavior history information related to the browsing behavior of the site visitor who browses the website and the deep product needs information associated with the product (object of transaction) stored in the memory unit. For example, when a user views a specific product on a website, the user deep needs estimation unit 111 can estimate the deep product needs information associated with the specific product as the deep needs of the user. Specifically, when a user views a product called "Pumps A," the deep product needs information of "emphasis on functionality" and "elegant" associated with "Pumps A" can be estimated as the deep needs of the user.

The behavior history information may include online behavior history and offline behavior history. The online behavior history is a history of information processing executed based on the input operation of each user, and may include, for example, website browsing history, review browsing history, review input history, search history, purchase history (purchased products, number of purchases of each product, purchase frequency, total purchase amount in a specified period such as one month or one year, average purchase amount), various applications installed on the user terminal, email, SNS, etc. execution history. The website browsing history may include, for example, pages (including articles) viewed by the user on the website, page viewing time (stay time), viewing time of each product (transaction object), scroll length, searched keywords, number of searches for each keyword, search frequency (number of times per unit time), selected categories or tags (selected category/tag information), number of selections of each category or tag, viewed product description information, viewed review information, etc. The review input history information is a history of reviews input by each user, and may include, for example, number of inputs, input frequency (number of times within a specified period), input date and time, review object, review content (text, image), graded evaluation parameters (numerical values), etc. The graded evaluation parameter is, for example, a five-point evaluation, with 5 being the highest evaluation and 1 being the lowest evaluation, and is a numerical value selected by the user. The storage unit 12 can store information on the individual evaluations for each user who inputs review information, and the average value for all users who input review information for each review subject. The evaluation is not limited to a five-point scale, and may be any multiple scale, such as three or ten. The information processing device 10 can acquire and store information on the behavioral history of each user by receiving information input by the user via the user terminal.

Offline behavior history is, for example, non-online behavior such as visiting a store or participating in an event. Offline behavior history can be obtained, for example, by a user inputting it via a user terminal, by being generated by a control unit based on information acquired by a camera or sensor installed in a store or event venue, or by being received from another external system.

The behavioral history information preferably includes at least any of the following: search text information entered by the user, search tag information selected by the user, product viewing information related to products viewed by the user (such as product detail pages), review viewing information related to review information viewed by the user, and information related to the selection of products (advertisements) proposed as output data based on the estimated deep needs. The search text information entered by the user is information on the text entered by the user to search for products. The search tag information selected by the user is information on the tags (keywords) selected by the user to search for products. The information related to whether or not a product (advertisement) proposed based on the estimated deep needs was selected is information related to whether or not the proposed product was selected and the number of times it was selected.

The deep product needs information is the deep needs of the customer that each product can satisfy. The deep product needs information is information associated with each product and stored in the storage unit. Each product is associated with one or more pieces of deep needs information. Here, the "deep needs" of the customer can be the desires and wants hidden in the deep psychology of each customer. In the present invention, the deep needs of each user are estimated based on the user's behavior history information and the deep product needs information, and information corresponding to the deep needs is provided. Each user who browses websites and review information has individual deep needs, and performs actions such as selecting and deciding on the content to be browsed or searched based on the deep needs. For example, if the product to be browsed or purchased is "perfume," the deep needs include "I want to try an expensive perfume," "I want to find a perfume that suits me," "I want to treat myself," and "I want to give it to my lover as a present," and each user may have multiple deep needs.

Figures 3 and 4 show an example of deep needs of each user estimated by the user deep needs estimation unit 111. Each user who uses the website is given identification information (such as a personal ID) by the control unit 10. The identification information is information unique to each user for identifying the user, and is expressed as a combination of characters such as numbers and letters. The user deep needs estimation unit 111 can determine one or more deep needs and the importance of each deep need based on the behavioral history information of each user and the product deep needs information, and store them in the memory unit.

In the example of FIG. 3, the identification information for each user, the attribute information of "gender" and "age", and the items of "emphasis on functionality", "for going out", "attention category", and "interest in specific elements" as data on deep needs are stored as a database for each user. The item "emphasis on functionality" is information indicating the degree to which the user attaches importance to the functionality of the product, and is classified into three levels, "high", "medium", and "low", from the highest degree of importance. The item "for going out" is classified into four levels, "high", "medium", and "low", which indicate the degree to which the user wishes to use the product when going out, plus "- (hyphen)" for unknown purposes. Note that the levels for all items can be changed as appropriate, and may be, for example, two levels, "yes" and "no" or "high" and "low", or may be finely classified into four or more levels. For example, the degree of desire for deep needs may be expressed by a number between 0 and 100. The item "attention category" is information on the category (classification) of a specific product that each user is particularly paying attention to (requesting), and includes information such as "pumps" and "yoga mat". The item "Interest in specific elements" is, for example, information that classifies the degree of interest in a specific brand, a specific category, a specific product, a specific store, etc. into three levels. In addition, when there are multiple deep needs items such as "emphasis on functionality" and "for going out", the user deep needs estimation unit 111 may estimate and store their priorities. For example, the priorities of the four items "emphasis on functionality", "for going out", "popular category", and "interest in specific elements" may be estimated from the behavior history information of the user. In this case, for example, the priorities may be set to be higher in the order of "emphasis on functionality", "for going out", "popular category", and "interest in specific elements". According to this, for example, the output data generation unit 112 can preferentially select advertisements related to products related to the item with the highest priority as output data.

As shown in the table of FIG. 4, the storage unit stores identification information (personal ID) for each user and information on "category", "needs", and "importance" as information constituting deep needs in association with each other. The information on "category", "needs", "importance", etc. constituting deep needs may be stored in advance as options in the storage unit, and the user deep needs estimation unit 111 may select deep needs applicable to each user from the options based on the behavior history information of each user. Alternatively, the user deep needs estimation unit 111 may generate individual information on "category", "needs", "importance", etc. constituting deep needs based on the behavior history information of each user, and store the information in the storage unit. Output data such as advertising information may be stored in advance in association with each deep need. A category is a field to which a desired object belongs, and a need is a specific request. Importance is indicated in a number of stages, such as three stages of "high", "medium", and "low", and indicates the priority of the deep needs.

The user deep needs estimation unit 111 may estimate the deep needs of each user based on not only the user's own behavioral history information but also on the behavioral history information of others. For example, the deep needs of each user can be estimated by referring to the behavioral history information and deep needs information of others whose behavioral history information is highly similar to that of the user. The user deep needs estimation unit 111 may estimate the deep needs of another user who has the highest similarity as the user's deep needs, or may estimate the user's deep needs based on the deep needs of multiple other users who have high similarities. The user deep needs estimation unit 111 can calculate the similarity between the site browsing history information of one user and another user.

The user deep needs estimation unit 111 can compare the site browsing history information of one user with the site browsing history information of another user to determine the similarity and store it in the storage unit. The similarity can be expressed, for example, as a numerical value (%) ranging from 0 to 100, and the larger the numerical value, the higher the similarity. The similarity is determined by comparing one or more combinations of the components of the site browsing history information, such as the browsing target (article, product, etc.), the display time (one time, the total of multiple times, the average, etc.), the display time, the number of times of display, and the number of times tags, keywords, etc. are selected. The method of determining the similarity is not particularly limited, but for example, at least one of the number of times the same tag was selected, the number of times the same product was viewed, and the number of times the same page in a website was viewed may be compared to determine the user with the smallest difference. The parameters to be compared are not limited to the above number of times, and may be the length of time the same product, page, etc. were viewed. Viewing means displaying it on the screen. The determination or calculation of the similarity may be based on machine learning using a learning model or other analysis method.

The user deep needs estimation unit 111 can determine the user whose behavioral history information is most similar to a specific user. For example, among multiple users, the other user whose similarity value for the site browsing history information of a specific user is the highest can be determined as the user whose similarity is the highest. The user deep needs estimation unit 111 may also estimate deep needs by referring to information about trading objects such as products, user information such as customers, etc. Information about review objects such as products includes product description text, images, prices, metadata, product reviews, etc. Information about users may include, for example, attribute information, purchase (history) information, behavioral history information, etc. The user deep needs estimation unit 111 may estimate the deep needs of each user based on at least one of review browsing history information and site browsing history information as behavioral history information, and product deep needs information.

The deep user needs estimation unit 111 may estimate the deep needs of each user based on, for example, machine learning using a learning model or other analysis methods. The deep user needs estimation unit 111 may, for example, analyze multiple review information viewed by the user, extract common text (keywords) contained in the review information, calculate the total number of each extracted keyword, the percentage in the whole, and estimate the content and importance of one or more deep needs (for example, the above-mentioned "category", "needs", and "importance") using the keywords as input information. The deep user needs estimation unit 111 may perform deep needs estimation processing based on any one or a combination of information such as the display time of each review information included in the review viewing history information (if displayed multiple times, the total display time or the average display time for one time, etc.), the date and time when the review information was viewed, and the text, image, output voice, and tag displayed as the review information.

Each review information is stored in association with a review subject (such as a product). In addition, multiple pieces of review information are stored in association with one review subject. If no review is input for a review subject, there may be no review information associated with the review subject, or only one piece of review information may be associated with the review subject. Information input by the user via the input unit 23 of the user terminal 20 includes text, audio, images (including still images and videos), graded evaluation values, etc., and is transmitted to the information processing device 10 as a server device via the network NW. The review information storage unit 123 of the information processing device 10 acquires the input information, edits the input information as necessary, and stores it. The review information storage unit 123 can store all review information input by multiple users for one review subject. In this way, review information can be accumulated in the review information storage unit 123.

The user deep needs estimation unit 111 may further estimate the deep needs of each user based on the attribute information of users such as site visitors. The attribute information may include, for example, age, sex, residential area (address), family structure, purchase history, etc. In this case, the similarity of attributes between users may be calculated by comparing each element of the user's attribute information and quantifying the degree of agreement. The user deep needs estimation unit 111 may then determine highly similar users based on either or both of the similarity of behavioral history information and the similarity of attribute information, and estimate the user's deep needs based on the deep needs of other highly similar users.

The output data generating unit 112 generates information (output data) to be output to the user based on various input information. For example, the output data generating unit 112 generates output data to be output to the site viewer based on the deep needs information of each site viewer estimated by the user deep needs estimating unit 111. The output data includes, for example, advertising information (information about the recommended product) of the product associated with the deep needs information, tag information associated with the deep needs information, etc. The output data may be not only the display content of the website, but also data (subject, preheader, text, image, recommended product, etc.) output to various applications launched on the user terminal, communication tools such as email and SNS, etc., or print data (text, image, recommended product, etc.) for objects exchanged in the real world such as advertising pages and direct mail. The preheader is, for example, a short text sentence that is not displayed in the body of the email, but is displayed only on the notification or lock screen of the user terminal such as a smartphone.

The output data generating unit 112 generates output data such as advertisements, for example, based on one or more items of deep needs for each user and their degree (importance). For example, in the example of FIG. 4, for a user with ID number "0001", one or more advertisements can be generated as output data for pumps of a specific brand that are highly functional and stored as items for going out, and that serve as a specific element.

The output data generating unit 112 can also determine which advertising information to present preferentially based on the estimated deep needs of the user and, if necessary, the importance of each item. In other words, the output data generating unit 112 can display advertisements corresponding to deep needs with high importance earlier than advertisements corresponding to deep needs with low importance, or place them in a position where they will be displayed first (such as the top side when scrolling from top to bottom, or the left side when scrolling from left to right), thereby setting priorities.

Figures 5 and 6 show an example of output data for each user displayed on a website. The screen on which the output data is presented is not limited to a shop screen that displays a list of products, and can be any screen. For example, it may be a screen that displays one or more products in a cart that are temporarily stored as products under consideration for purchase (a screen for confirming products added to the cart). Specifically, an item under consideration for purchase is stored as a product by selecting an icon such as "add to cart" associated with the item. Then, in response to an input such as the selection of an icon that instructs the display of the items in the cart, a screen for confirming the items added to the cart is displayed, and advertisements for related products as output data can be displayed on that screen.

In the example of FIG. 5, information (images, prices, product names, brands, etc.) about multiple specific products (pumps) are displayed in order of priority from the left, along with category information (composite information) about deep needs, "Recommended pumps that are great for summer dates and don't tire you out," corresponding to the most important estimated user deep needs information. The sentences (captions, headings, titles, explanations) as the composite information about deep needs may be generated by combining individual elements of deep needs ("summer," "date," "functionality," "pumps," etc.), or may be generated only from individual elements of one deep need (for example, a sentence "For those who love limited items!" may be generated only from the deep need of "I like limited items"). When there are multiple suggested products, the priority of the suggested products (advertisements) as output data is determined in order of the number of individual elements of the deep needs that are satisfied. Furthermore, in the example of FIG. 5, multiple specific products (skirts) are displayed in order of priority from the left, along with category information, "Pretty skirts recommended for summer dates," corresponding to the next most important user deep needs information. In this case, the user's individual deep need elements are "summer," "date," "elegant," and "skirt."

In the example of FIG. 6, multiple pieces of tag information ("#No sore feet", "#Perfect for summer dates", "#Easy to match", "#Doesn't get stuffy") associated with the estimated deep-seated needs of the user are further displayed in a selectable manner, and the user can select any one of the tags to display products associated with that tag. The output data generation unit 112 can generate one or more pieces of such tag information as output data.

The control unit 11 in this example has a deep product needs generation unit 113. The deep product needs generation unit 113 generates deep product needs information associated with a product based on input information including review information input by a user for a product posted on a website, and stores the information in a storage unit (deep product needs storage unit 121). The deep product needs generation unit 113 may generate a database related to deep needs of a product, etc., based on machine learning using a learning model or other analysis methods. The deep product needs generation unit 113 can analyze data related to a product, such as metadata, product description, product review information, and product images associated with the product, by machine learning, and extract (estimate) deep needs satisfied by the product (for example, "pumps A", "comfortable to wear", "perfect for a date"). Note that, as input information, information related to the product (metadata, product description, product review information, product images) from an external website or an external system such as an SNS other than the website in question may be acquired, and the deep product needs information may be generated based on the different website.

Figure 7 is an example of a database. Each product is associated with deep needs information that the product satisfies ("clean", "elegant", "adult", "gentle", "floral"). As shown in Figure 7, the number of deep needs that each product satisfies is not limited to one, and may be multiple. In the example of Figure 7, the identification information of each product is associated with one or more deep needs. Such a database may be set in advance by the service provider. When the product deep needs generation unit 113 generates the database, for example, the deep needs previously associated with the user who purchased each product may be estimated as the deep needs corresponding to the product, or the deep needs corresponding to the product may be estimated based on at least one of the information of each user's site browsing history and review browsing history, and data such as the user's browsing time for the product, the number of searches, and the number of times the tag was selected, and the database may be generated.

Figure 8 is an example of a database in which deep needs are associated with each user (customer). The database can be generated by associating deep needs estimated based on at least one of the site browsing history and review browsing history of each user with each user. The user's deep needs database can also be generated by machine learning based on the deep needs database for products as shown in Figure 7 and information about each user (attribute information, purchase information, behavioral history information, or a combination thereof). The control unit can output the generated database, and can display it on a display device such as a touch panel or monitor of a user terminal. Such a database can be provided to, for example, a product seller, making it possible to make product suggestions according to the user's deep needs.

The output data generation unit 112 may further generate output data based on attribute information of users such as site visitors. Attribute information includes, for example, age, gender, residential area (address), family structure, purchasing history, etc. This makes it possible to provide more accurate output data according to the attribute information of each user.

The output data generating unit 112 may generate output data to highlight the advertisement copy on the page of each individual product. Highlighting can be, for example, but is not limited to, making the text larger than other text, changing the color, making the text thicker, or underlining the text. In addition, the output data generating unit 112 may automatically display recommended areas, review subjects (products), review information, etc. in a pop-up.

The storage unit 12 stores various information. The storage unit 12 stores programs for executing various control processes and functions within the control unit 11, input information, etc., and is configured with one or any combination of RAM (Random Access Memory), ROM (Read Only Memory), flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), and other storage. It is preferable that the program is stored in a non-volatile storage medium among these storage media that configure the storage unit 12.

As shown in FIG. 2, the memory unit 12 includes a deep product needs memory unit 121, a user information memory unit 122, a review information memory unit 123, and an advertisement information memory unit 124. The review information memory unit 123 is not a required component, and the memory unit 12 may include other functional units.

The deep product needs storage unit 121 stores deep needs information associated with each product. For example, deep needs information for each product as shown in FIG. 7 is stored in the deep product needs storage unit 121.

The user information storage unit 122 stores information about users such as site viewers. Information about users includes, for example, each user's identification information, attribute information, behavior history information, etc. Each site viewer may be composed of multiple users, or may be partly or entirely the same user. The attribute information of each user may be generated based on information input by each user, or may be acquired from an external device or the like via a network. For example, the system may cooperate (communicate) with an SNS system other than this system via a network to acquire account information (including attribute information) preregistered in the SNS service from the external system. Information about each user may be automatically generated or updated based on each user's review browsing history information, site browsing history information, or other information. The user information storage unit 122 may store information for each user category.

The memory unit 12 stores information related to websites. The memory unit 12 stores, for example, information related to review subjects posted on websites. The review subjects are not particularly limited as long as they are subject to evaluation, and examples include products, services, applications, stores, websites, people, real estate, etc. Information related to review subjects includes, for example, names, values (monetary amounts, etc.), images, review information, keywords and tags associated with each review subject, and is stored in association with each review subject. Keywords and tags include, for example, words and phrases such as spring, summer, fall, winter, beginners, advanced, stylish, for men, for women, high price, low price, gift, etc.

The review information storage unit 123 stores review information generated based on information input by a user. The review information is stored in association with each product.

The advertisement information storage unit 124 stores advertisement information. The advertisement information stores information related to advertisements as output data to be presented to users within a website. The advertisement information is, for example, the product, service, application, store, website, person, real estate, etc. that is the subject of the advertisement. The information related to the advertisement target is, for example, the name, value (amount, etc.), image, review information on the advertisement target, deep needs associated with each advertisement target, keywords, tags, etc. associated with each advertisement target, and is stored in association with each advertisement target. Examples of keywords and tags are words or phrases such as spring, summer, fall, winter, beginner, advanced, stylish, for men, for women, high price, low price, gift, etc.

The input unit 13 allows a user or system administrator to input various pieces of information as described above, and is realized, for example, by a keyboard, mouse, touch panel, microphone, etc.

The output unit 14 can output information generated by the control unit 11 and information received via the communication unit. The output unit 14 can include, for example, an image output unit such as a liquid crystal display (LCD) or a touch panel, and an audio output unit such as a speaker. It can output various information based on instructions from the control unit 11. Alternatively, the output unit 14 may output (transmit) various information to another information processing device (user terminal) or the like via the communication unit 15.

The communication unit 15 is for communicating with other information processing devices, and has a function as a receiver that receives various data and signals transmitted from other information processing devices, etc., and a function as a transmitter that transmits various data and signals to other information processing devices, etc. in response to commands from the control unit 11.

The control unit 11 in this example further includes a review presentation unit 114. The review presentation unit 114 is not an essential component. The review presentation unit 114 presents review information to a user (such as a site viewer) browsing the website. The review presentation unit 114 transmits the review information stored in the storage unit to the user terminal and displays it on the screen, thereby presenting the review information for the review target to the user. The timing of presenting the review information is not particularly limited, and may be, for example, a timing preset by the system side, or a timing according to the user's request. The preset timing may be, for example, the timing when the user starts browsing the website, or the timing when the user starts browsing a page of a specific review target. In addition, the timing according to the user's request may be, for example, the timing when the user browsing the website or the page of a specific review target selects an icon or the like that requests the display of review information. The review information can be displayed on any page (display screen) within the website. The review information may be displayed as a widget or a pop-up window at any position within the website, or may be fixedly displayed (displayed in an embedded format) on the page of each review target (such as a product). When review information is displayed as a widget or pop-up window, the review information may move in response to a user's scrolling of the display screen, so that the review information is always displayed on the screen.

Here, FIG. 9 shows an example of a screen 201 displayed on the user terminal 20 of a user browsing a website. The screen 201 is the top screen of the online shop's homepage, and displays the store name "Shop A" 202, product information 203 such as images, names, amounts (prices), and descriptions of products sold, and a widget icon 204 that can be selected to display review information. When the user selects the widget icon 204, a review window 205 is displayed as shown in FIG. 10. The review window 205 displays the name of the store to be reviewed, fractional values and images indicating the average value of the graded evaluation (the percentage of the colored parts of the three star-shaped images indicates the average evaluation value), a bar display indicating the percentage of users who have evaluated each grade, numerical values (%), keywords (tags), and part of the review comments. Note that the configuration of the review information presentation screen is not limited to those shown in FIGS. 9 and 10 and can be selected as appropriate. When the user selects a tag indicating a keyword, review information, product information, etc. corresponding to the keyword will be displayed. In this case, the tag indicating the keyword and the review information corresponding to the keyword may be associated with each other, for example, by displaying them in close proximity to each other or in the same window. The keywords may be displayed in order of the number of times they were selected on the website, or only a predetermined number of the top keywords may be displayed. The control unit of the information processing device can calculate the number of times the keyword was selected (which may be the total value for the entire period or the total value for a predetermined period (such as one month, one week, or one day)) from the history information of all viewers of multiple websites. The keyword information may be stored in the storage unit in advance, or may be generated by the generation unit. The control unit (generation unit) of the information processing device can generate keyword information based on any one or a combination of the user's review input information, review browsing history information, and site browsing history information, and store the generated information in the storage unit.

Review viewing history information, which is an example of site viewing history information, is a history of review information that a user has viewed in the past, i.e., that has been displayed on the screen of a user terminal, and is stored in the storage unit as described below. The review viewing history information includes information such as the date and time (date and time) when each user viewed the review information, the display time (total value, average value, individual display time), viewing frequency (number of views in a specified period), text displayed as review information, images, output audio, keywords contained therein, and tags. The viewed review information includes the review subject, comments (evaluation text), information on the review inputter, and the like. The tags are displayed as icons displaying preset keywords. Each tag is associated with a product or the like that is the review subject, and is stored in the storage unit. As a result, for example, when a user selects the tag "for beginners", the control unit 11 of the information processing device 10 can display information associated with the "for beginners" tag (review information, product information, etc.) on the screen of the user terminal. Site browsing history information includes information such as the pages viewed, the date and time (date and time) when each site visitor viewed the website, the display time (total value, average value, individual display time), viewing frequency (number of times viewed in a specified period), displayed text, images, output audio, keywords and tags contained therein, etc.

The user terminal 20 is used by a user who uses the services provided by the system 100 to browse websites, etc. The user terminal 20 can be, for example, an information processing device such as a smartphone, a tablet terminal, a mobile phone, or a personal computer.

Figure 11 is a functional block diagram showing the user terminal 20 of Figure 1. The user terminal 20 has a control unit 21, a storage unit 22, an input unit 23, an output unit 24, and a communication unit 25. The control unit 21, like the above-mentioned control unit 11, transfers information between each unit and controls the entire user terminal 20, and is realized, for example, by a CPU, an MPU, or a GPU executing a program stored in a predetermined memory. The storage unit 22, like the above-mentioned storage unit 12, stores programs for executing various control processes and each function in the control unit 21, input information, etc., and is composed of one or any combination of RAM, ROM, flash memory, HDD, SSD, other storage, etc. The input unit 23, like the above-mentioned input unit 13, is for the user to input various information as described above, and is realized, for example, by a keyboard, mouse, touch panel, microphone, etc. The output unit 24, like the above-mentioned output unit 14, can output information generated by the control unit 21 and information received via the communication unit, and can include, for example, an image output unit such as a liquid crystal display or a touch panel, and an audio output unit such as a speaker. The communication unit 25, like the above-mentioned communication unit 15, is for communicating with other information processing devices, and has a function as a receiving unit that receives various data and signals transmitted from other information processing devices, etc., and a function as a transmitting unit that transmits various data and signals to other information processing devices, etc. in response to commands from the control unit 21. Users input various information via the input unit 23 of the user terminal 20 used by each user, and transmit the input information to the information processing device 10 as a server device via the communication unit 25. In addition, the processing results output from the information processing device 10 are received and confirmed via the output unit 24.

Figure 12 is a flow diagram showing an example of an information processing method executed by this system. The information processing method includes a deep product needs storage process (S1) that stores deep product needs information in a storage unit in association with a product, a deep user needs estimation process (S2) that estimates deep needs information of each user based on behavior history information related to the behavior of the user browsing the website and the deep product needs information associated with the product stored in the storage unit, and an output data generation process (S3) that generates output data to be output to each user based on the deep needs information of the user.

As described above, in the deep product needs storage process (S1), the deep product needs generation unit 113 generates deep product needs information associated with a product based on input information about the product posted on the website, and stores the information in the storage unit (deep product needs storage unit 121). The input information can be, for example, but is not limited to, a title, product description, product image, reviews (already present on existing EC sites, etc.), metadata, and similar data acquired from external sites. Note that the information is not limited to being generated by the deep product needs generation unit 113, and the deep needs information may simply be associated with each product in advance and stored in the storage unit.

In the user deep needs estimation process (S2), the information processing device 10 acquires behavior history information on the behavior of the user browsing the website via the user terminal. For example, from the information on the details page of a product (e.g., the above-mentioned "pumps A" and "skirt A") selected and displayed by the user on the website as behavior history information, a product displayed on the product detail page may be identified, and deep product needs information associated with the product may be acquired from the storage unit and estimated as the deep needs information of the user. In this case, deep product needs information associated with one product (e.g., "summer," "date," "functionality," "pumps," etc.) may be estimated as the deep needs information of the user, or deep product needs information common to deep product needs information associated with multiple products (e.g., "summer," "date," etc.) may be estimated as the deep needs information of the user.

In the output data generation process (S3), the information processing device 10 generates output data to be output to each user based on the deep needs information of the user. For example, one or more products (pumps A, pumps B, skirt A, skirt, etc.) that satisfy all or part of the user's deep needs information ("summer", "date", "functionality", "pumps", etc.), one or more search tags, etc. may be generated and displayed on the user terminal.

The user's deep needs estimation process (S2) and the output data generation process (S3) may be executed repeatedly. In this case, the user's deep needs estimation process (S2) and the output data generation process (S3) may be executed repeatedly at a preset interval, such as 5 seconds, 10 seconds, 30 seconds, 1 minute, 5 minutes, etc. When the process is executed repeatedly at short intervals such as 5 seconds or 10 seconds, personalized output data can be presented to the user in a state substantially close to real time according to the user's behavior history information.

As described above, the information processing device of this embodiment includes a user deep needs estimation unit that estimates deep needs information of each user based on behavior history information related to the behavior of the user browsing a website and deep product needs information associated with a product stored in a storage unit, and an output data generation unit that generates output data to be output to the user based on the deep needs information of each user. In this way, by combining behavior history information related to the user's behavior and deep product needs information associated with a product, it is possible to accurately grasp the deep needs of each user and provide personalized and optimal information to each user.

In addition, in this embodiment, by multiplying the behavioral history information with product deep needs information (database), the deep needs of the customer can be estimated and verbalized, and personalization can be realized. Although there have been services that simply personalize based on behavioral data, they cannot present "Why was that personalization done? Why is that product being recommended?" In this embodiment, by multiplying the behavioral history information with product deep needs information, the intention behind it can be interpreted and verbalized in the form of deep needs. This allows for personalization actions beyond simply presenting products (for example, searching with needs tags, creating captions (headings, titles, descriptions) for recommendations using deep needs, inserting phrases that hit deep needs in appealing messages such as emails, etc.), and therefore the breadth and depth (precision) of personalization can be increased.

The information processing device of this embodiment may further include a deep product needs generation unit that generates the deep product needs information for each of the products based on input information including review information entered by users for the products listed on the website. In this case, for example, by generating deep product needs based on the opinions (review information) of customers evaluating the products, rather than the company selling the products, it is possible to grasp the needs that the products fulfill from the customer's perspective, which is deeper than the existing company's understanding of the products.

In addition, in the information processing device of this embodiment, the user deep needs estimation unit may further estimate the deep needs information of each user based on the attribute information of each user. This makes it possible to estimate the deep needs information based on the attribute information of the user, such as age and place of residence. As a result, it is possible to more accurately grasp the deep needs of the user and provide appropriate information.

In addition, in the information processing device of this embodiment, the output data generation unit may further generate output data to be output to each user based on the attribute information of each user. This makes it possible to generate output data taking into account attribute information such as the user's age and place of residence. As a result, it is possible to provide appropriate information according to the user's attributes.

In addition, in the information processing device of this embodiment, the behavioral history information may include at least any of the following information: search text information input by the user, search tag information selected by the user, product viewing information regarding products viewed by the user, review viewing information regarding review information viewed by the user, and information regarding product selection presented to the user as output data. This makes it possible to estimate the deeper needs of each user based on a combination of one or more pieces of information among the search text information, search tag information, product viewing information, review viewing information, and information regarding product selection presented to the user as output data.

In addition, in the information processing device of this embodiment, the output data may include advertising data to be presented to the user. This makes it possible to present advertising data that corresponds to the deep needs of each user. As a result, for example, information on products desired by each user can be presented.

In the above embodiment, the advertising data including the suggested product information is generated as the output data, but the title (subject) and text of the email may be generated as the output data. That is, the output data generating unit 112 can determine the title and text of the email to be sent to each user based on the deep needs of the user. This makes it possible to automatically create and send emails to email addresses stored in advance in the storage unit by registration of each user. As a result, emails with content according to the deep needs of each user can be sent individually, making it easier to attract the user's interest than emails with uniform text. In addition, the title and text of the email can include the keywords used as tag information in the previous embodiment, or text according to the deep needs can be generated. Machine learning technology using a learning model may be used to generate specific text.

In the user information storage process, when a user browses a website provided by the information processing device 10 via the user terminal 20b, history information on the browsing behavior is stored. For example, the user browses review information about a product they are considering purchasing to help them make a purchase decision. Specifically, the user can refer to the average rating on a 5-point scale, whether the comments written in the reviews meet their needs, and comments on reviews that have been given low ratings, such as 1 or 2, the lowest rating on a 5-point scale, to check whether there are any specific issues that do not meet their needs. In addition, in the user information storage process, other information such as the user's site browsing history information and user attribute information may be stored.

In the generation process, output data relating to the user may be generated based on the user's site browsing history information and deep product needs information. The control unit of the information processing device can then transmit the determined advertising content or information generated based on the advertising content to the user terminal and display it on the screen of the user terminal. With this configuration, advertising information according to the deep needs of the user can be presented to each user.

Although the preferred embodiment of the present disclosure has been described in detail above with reference to the attached drawings, the technical scope of the present disclosure is not limited to such examples. It is clear that a person with ordinary knowledge in the technical field of the present disclosure can conceive of various modified or revised examples within the scope of the technical ideas described in the claims, and it is understood that these also naturally fall within the technical scope of the present disclosure.

The device described in this specification may be realized as a single device, or may be realized by multiple devices (e.g., cloud servers) some or all of which are connected via a network. For example, the control unit 11 and the storage unit 12 of the information processing device 10 may be realized by different servers connected to each other via a network.

The series of processes performed by the device described in this specification may be realized using software, hardware, or a combination of software and hardware. A computer program for realizing each function of the information processing device 10 according to this embodiment can be created and implemented in a PC or the like. A computer-readable recording medium on which such a computer program is stored can also be provided. Examples of the recording medium include a magnetic disk, an optical disk, a magneto-optical disk, and a flash memory. The above computer program may also be distributed, for example, via a network, without using a recording medium.

In addition, the processes described in this specification using flowchart diagrams do not necessarily have to be performed in the order shown. Some processing steps may be performed in parallel. Also, additional processing steps may be employed, and some processing steps may be omitted.

Furthermore, the effects described in this specification are merely descriptive or exemplary and are not limiting. In other words, the technology disclosed herein may achieve other effects that are apparent to a person skilled in the art from the description in this specification, in addition to or in place of the above effects.

Note that the following configurations also fall within the technical scope of the present disclosure.
(Item 1)
a user deep needs estimation unit that estimates deep needs information of each user based on behavior history information related to the behavior of the user browsing the website and deep product needs information associated with the product stored in a storage unit;
an output data generation unit that generates output data to be output to each user based on the deep needs information of the user.
(Item 2)
The information processing device according to claim 1 , further comprising a deep product needs generating unit configured to generate the deep product needs information for each of the products based on input information related to the products posted on the website.
(Item 3)
The information processing device according to claim 1 , wherein the user deep needs estimation unit estimates deep needs information of each user based on attribute information of each user.
(Item 4)
The information processing apparatus according to claim 1 , wherein the output data generating unit further generates output data to be output to each user based on attribute information of each user.
(Item 5)
The information processing device of claim 1 or 2, wherein the behavioral history information includes at least any of the following information: search text information entered by the user, search tag information selected by the user, product viewing information regarding products viewed by the user, review viewing information regarding review information viewed by the user, and information regarding product selection presented to the user as output data.
(Item 6)
The information processing device according to claim 1 , wherein the output data includes advertisement data to be presented to a user.
(Item 7)
a user deep needs estimation process for estimating deep needs information of each user based on behavior history information related to the behavior of the user browsing the website and deep product needs information associated with the product stored in a storage unit;
and an output data generation process for generating output data to be output to each user based on the deep needs information of the user.
(Item 8)
a user deep needs estimation process for estimating deep needs information of each user based on behavior history information related to the behavior of the user browsing the website and deep product needs information associated with the product stored in a storage unit;
and an output data generation process for generating output data to be output to each user based on the deep needs information of the user.

Reference Signs List 100 Information processing system 10 Information processing device 20 User terminal

Claims (9)

a user deep needs estimation unit that estimates deep needs information indicating the desires of each user based on behavior history information related to the behavior of the user browsing the website and deep product needs information associated with the product stored in a storage unit;
an output data generating unit that generates output data including advertisement data or message data for each user according to the deep needs information of the user,
The deep product needs information includes need information indicating user needs to be satisfied by each product;
The behavior history information includes product viewing information indicating products viewed by the user and the viewing time or number of times each product is viewed,
The user deep needs estimation unit estimates a category and importance of a need as the deep needs information of each user based on the product viewing information and the need information associated with a product viewed by the user included in the product viewing information, and
the output data generation unit generates output data including text to be presented to each user using machine learning based on a predetermined learning model that generates text based on the category and importance of the request without using word-of-mouth information about the product ;
An information processing device , wherein the output data includes sentences generated by the output data generation unit so as to include words indicating categories of requests as the deep needs information of each user . The behavioral history information includes website browsing information indicating websites visited by the user and the browsing time or number of times each website was visited,
The information processing device according to claim 1 , wherein the user deep needs estimation unit further estimates the deep needs information of each user based on text information extracted from the website browsing information. a deep product needs generating unit that generates the deep product needs information for each of the products based on input information regarding the products posted on the website;
the input information includes text information associated with the product on the website or an external website;
The information processing device according to claim 1 , wherein the product deep needs generation unit estimates a category of the need related to the product based on text information associated with the product on the website or an external website. The information processing device according to claim 1 or 2, wherein the user deep needs estimation unit further estimates deep needs information of each user based on attribute information of each user. The information processing device according to claim 1 or 2, wherein the output data generating unit further generates output data to be output to each user based on attribute information of each user. The information processing device according to claim 1 or 2, wherein the user deep needs estimation unit estimates deep needs information of each user based on information regarding whether the user selected a product presented to the user as output data. The information processing device according to claim 1 or 2, wherein the output data includes advertising data to be presented to the user. A user deep needs estimation process that estimates deep needs information indicating the desires of each user based on behavior history information related to the behavior of the user browsing the website and deep product needs information associated with the product stored in a storage unit;
an output data generation process for generating output data including advertisement data or message data for each user according to the deep needs information of the user, the output data including advertisement data corresponding to the request of the user or message data for the user being generated by the information processing device;
The deep product needs information includes need information indicating user needs to be satisfied by each product;
The behavior history information includes product viewing information indicating products viewed by the user and the viewing time or number of times each product is viewed,
The user deep needs estimation process estimates a category and importance of a need as deep needs information of each user based on the product browsing information and the need information associated with a product browsed by the user included in the product browsing information,
the output data generation process generates output data including text to be presented to each user using machine learning based on a predetermined learning model that generates text based on the category and importance of the request without using word-of-mouth information about the product ;
An information processing method , wherein the output data includes a sentence generated by the output data generation process so as to include words indicating categories of requests as the deep needs information of each user . A user deep needs estimation process that estimates deep needs information indicating the desires of each user based on behavior history information related to the behavior of the user browsing the website and deep product needs information associated with the product stored in a storage unit;
an output data generating process for generating output data including advertisement data or message data for each user according to the deep needs information of the user, the output data including advertisement data or message data for the user according to the deep needs information of the user;
The deep product needs information includes need information indicating user needs to be satisfied by each product;
The behavior history information includes product viewing information indicating products viewed by the user and the viewing time or number of times each product is viewed,
The user deep needs estimation process estimates a category and importance of a need as deep needs information of each user based on the product browsing information and the need information associated with a product browsed by the user included in the product browsing information,
the output data generation process generates output data including text to be presented to each user using machine learning based on a predetermined learning model that generates text based on the category and importance of the request without using word-of-mouth information about the product ;
A program , wherein the output data includes sentences generated in the output data generation process so as to include words indicating categories of requests as the deep needs information of each user .