WO2023080215A1 - Programme, dispositif de recommandation de produit, procédé de recommandation de produit, et système de recommandation de produit - Google Patents

Programme, dispositif de recommandation de produit, procédé de recommandation de produit, et système de recommandation de produit Download PDF

Info

Publication number
WO2023080215A1
WO2023080215A1 PCT/JP2022/041246 JP2022041246W WO2023080215A1 WO 2023080215 A1 WO2023080215 A1 WO 2023080215A1 JP 2022041246 W JP2022041246 W JP 2022041246W WO 2023080215 A1 WO2023080215 A1 WO 2023080215A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
user
information
evaluation
tendency
Prior art date
Application number
PCT/JP2022/041246
Other languages
English (en)
Japanese (ja)
Inventor
俊二 菅谷
Original Assignee
株式会社オプティム
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社オプティム filed Critical 株式会社オプティム
Publication of WO2023080215A1 publication Critical patent/WO2023080215A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0204—Market segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y10/00—Economic sectors
    • G16Y10/45—Commerce
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • G16Y20/40—Information sensed or collected by the things relating to personal data, e.g. biometric data, records or preferences
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/20—Analytics; Diagnosis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y40/00—IoT characterised by the purpose of the information processing
    • G16Y40/30—Control

Definitions

  • the present disclosure relates to a program, product recommendation device, product recommendation method, and product recommendation system.
  • Patent Literature 1 describes presenting to the user the purchase results of shoes of other users who have a similar feeling of wearing shoes or a similar distance between the foot and the inside of the shoe.
  • Patent Document 1 is based on comparing the feeling of wearing the same shoes. In other words, with the technique of Patent Document 1, it is theoretically impossible to search for other users who are potentially similar to the user in terms of the feeling of wearing the shoes, etc., even though they have never worn the same shoes as the user.
  • the purpose of this disclosure is to recommend appropriate products to users.
  • a program provides a computer with means for obtaining a review by a first user on a first product experienced by a first user, objective evaluation of each product with respect to one or more evaluation items defined for each product category, and Based on a product database storing information on evaluation values and reviews, the first user's sensitivity tendency is estimated for at least one evaluation item defined for the product category to which the first product belongs.
  • FIG. 1 is an explanatory diagram of one aspect of the present embodiment;
  • FIG. It is a figure which shows the data structure of the category database of this embodiment. It is a figure which shows the data structure of the 1st example of the goods database of this embodiment. It is a figure which shows the data structure of the 2nd example of the goods database of this embodiment. It is a figure which shows the data structure of the user database of this embodiment.
  • good can include any type of product (that is, goods), services, or goods used in providing services.
  • product can also include a partner introduced by a matching service (for example, a person, a store, a facility, or content). Humans may include potential friends or potential lovers mediated by the Matchin service. Stores and establishments may include places where services are provided, such as restaurants or lodging facilities, for example.
  • Content may include, for example, video content, music content, e-book content, still image content, or text content.
  • experience means various actions that affect the formation of a user's subjective evaluation of a product. For example, any product purchased, rented, used, used, viewed, consumed, or met (when the product is human) by the user can be interpreted as the product experienced by the user.
  • FIG. 1 is a block diagram showing the configuration of the product recommendation system of this embodiment.
  • the product recommendation system 1 includes a client device 10 and a server 30 .
  • the client device 10 and server 30 are connected via a network (for example, the Internet or an intranet) NW.
  • NW a network
  • the client device 10 is an example of an information processing device that transmits requests to the server 30 .
  • the client device 10 is, for example, a smart phone, a tablet terminal, or a personal computer.
  • the server 30 is an example of an information processing device that provides the client device 10 with a response in response to a request sent from the client device 10 .
  • Server 30 is, for example, a server computer.
  • the server 30 can also be called by other names such as, for example, a product recommendation device.
  • FIG. 2 is a block diagram showing the configuration of the client device of this embodiment.
  • the client device 10 includes a storage device 11, a processor 12, an input/output interface 13, and a communication interface .
  • the client device 10 is connected to the display 21 .
  • the storage device 11 is configured to store programs and data.
  • the storage device 11 is, for example, a combination of ROM (Read Only Memory), RAM (Random Access Memory), and storage (eg, flash memory or hard disk).
  • Programs include, for example, the following programs. ⁇ OS (Operating System) program ⁇ Application (for example, web browser) program that executes information processing
  • the data includes, for example, the following data. ⁇ Databases referenced in information processing ⁇ Data obtained by executing information processing (that is, execution results of information processing)
  • the processor 12 is a computer that implements the functions of the client device 10 by activating programs stored in the storage device 11 .
  • Processor 12 is, for example, at least one of the following: ⁇ CPU (Central Processing Unit) ⁇ GPU (Graphic Processing Unit) ⁇ ASIC (Application Specific Integrated Circuit) ⁇ FPGA (Field Programmable Array)
  • the input/output interface 13 acquires information (for example, user instructions) from an input device connected to the client device 10 and outputs information (for example, an image) to an output device connected to the client device 10.
  • Information for example, user instructions
  • Input devices are, for example, keyboards, pointing devices, touch panels, or combinations thereof.
  • Output devices are, for example, the display 21, speakers, or a combination thereof.
  • the communication interface 14 is configured to control communication between the client device 10 and the server 30 .
  • the display 21 is configured to display images (still images or moving images).
  • the display 21 is, for example, a liquid crystal display or an organic EL display.
  • FIG. 3 is a block diagram showing the configuration of the server of this embodiment.
  • the server 30 includes a storage device 31, a processor 32, an input/output interface 33, and a communication interface .
  • the storage device 31 is configured to store programs and data.
  • Storage device 31 is, for example, a combination of ROM, RAM, and storage (eg, flash memory or hard disk).
  • Programs include, for example, the following programs. ⁇ OS program ⁇ Application program that executes information processing
  • the data includes, for example, the following data. ⁇ Databases referenced in information processing ⁇ Execution results of information processing
  • the processor 32 is a computer that implements the functions of the server 30 by activating programs stored in the storage device 31 .
  • Processor 32 is, for example, at least one of the following: ⁇ CPU ⁇ GPU ⁇ ASICs ⁇ FPGA
  • the input/output interface 33 is configured to acquire user instructions from input devices connected to the server 30 and to output information to output devices connected to the server 30 .
  • Input devices are, for example, keyboards, pointing devices, touch panels, or combinations thereof.
  • An output device is, for example, a display.
  • the communication interface 34 is configured to control communication between the server 30 and the client device 10 .
  • FIG. 4 is an explanatory diagram of one aspect of the present embodiment.
  • the server 30 estimates the sensitivity tendency of the user US1 based on the review of the product IT1 by the user US1 and the product database IDB. The details of the sensibility tendency will be described later.
  • the product database IDB stores information (hereinafter referred to as “product information”) on each product (including product IT1) belonging to the product group GIT.
  • the product information includes objective evaluation value information (hereinafter referred to as “objective evaluation information”) for each evaluation item of each product.
  • the server 30 extracts objective evaluation information of the product IT1 from the product database IDB in order to estimate the user's US1 sensitivity tendency.
  • the server 30 identifies other users (hereinafter referred to as “similar users”) who are similar to the user US1 in their emotional tendencies based on the user US1's emotional tendencies and the user database UDB.
  • the user database UDB stores information on each user belonging to the user group GUS (hereinafter referred to as "user information").
  • the user information includes information on the sensitivity tendency of each user (hereinafter referred to as “sensitivity tendency information”) and information on the action history (hereinafter referred to as “action history information”).
  • the server 30 extracts the emotional tendency information of users other than the user US1 from the user database UDB in order to identify similar users.
  • the server 30 extracts behavior history information of similar users from the user database UDB.
  • the server 30 determines products to be recommended to the user US1 (hereinafter referred to as "recommended products") based on the behavior history information of similar users.
  • the server 30 presents recommended product information (for example, product information) to the user US1.
  • the server 30 estimates the user US1's emotional tendency based on the review of the product IT1 by the user US1, identifies similar users who have similar emotional tendencies (that is, how the user perceives the product) to the user US1, A recommended product is determined based on the behavior history of the similar user. Therefore, according to the server 30, it is possible to determine the recommended product for the user US1 based on the action history of similar users who have an emotional tendency close to that of the user US1. That is, it is possible to recommend an accurate product that matches the sensibility of the user US1, improve the satisfaction of the user US1, and promote sales of the product.
  • a user who has never experienced the product IT1 can be a candidate for a similar user if the user has experienced a product belonging to the same product group GIT as the product IT1. That is, even if the number of users who have experienced the product IT1 is small, such as when the product IT1 is a new product, it is possible to recommend an appropriate product to the user US1.
  • the database of this embodiment will be described.
  • the following databases are stored in the storage device 31.
  • at least one of the following databases may be stored in a storage device connected to the server 30 via a network, or in a storage device provided in an external system connected to the server 30 via a network.
  • the external system is, for example, an EC system, a SaaS (Software as a Service) system, a subscription system, a matching platform system, or the like. That is, the server 30 may access a database managed by the external system in response to a request from the external system, and respond with information on recommended products for the user of the external system.
  • FIG. 5 is a diagram showing the data structure of the category database of this embodiment.
  • Category information is stored in the category database.
  • the category information is information about product categories.
  • the product category means a range to which products that are common in evaluation items belong among products handled by the product recommendation system 1 . However, if all the products handled by the product recommendation system 1 belong to the same category, the category database can be omitted.
  • the category database includes a "category ID” field and a “category name” field. Each field is associated with each other.
  • a category ID is stored in the "category ID" field.
  • the category ID is information that identifies the product category.
  • the "category name” field stores category name information.
  • Category name information is information about the name of the product category.
  • FIG. 6 is a diagram showing the data structure of a first example of the product database of this embodiment.
  • FIG. 7 is a diagram showing the data structure of a second example of the product database of this embodiment.
  • the product database includes a "product ID” field, a "product name” field, and an "objective evaluation value” field. Each field is associated with each other.
  • the product database is associated with the category ID of the category database (Fig. 5).
  • the product ID is stored in the "product ID" field.
  • the product ID is information that identifies the product.
  • the "product name” field stores product name information.
  • the product name information is information regarding the name of the product.
  • the objective evaluation information is stored in the "objective evaluation value" field.
  • the objective evaluation information is information regarding objective evaluation values of products for each of one or more evaluation items.
  • objective evaluation information is defined for each product category.
  • items subject to objective evaluation may differ depending on the product category.
  • the objective evaluation value of each item may be defined as a one-dimensional value or as a multi-dimensional value (that is, vector).
  • Items subject to objective evaluation may be defined by humans (for example, designers of sensory tests for products or administrators of the product recommendation system 1), or may be defined by algorithms.
  • text mining may be performed on reviews of products belonging to a certain product category to extract evaluation items of high interest to the user.
  • the objective evaluation value may be a value based on at least one of the result of measuring the physical quantity or chemical quantity of the product by a measuring device, or the result of a human sensory test on the product.
  • the measuring device is, for example, a taste sensor, a ranging sensor (eg Lidar (Light Detection and Ranging)), a color sensor, a microphone, and the like.
  • the objective evaluation value may be a result of inference (for example, prediction or classification) performed by the trained model based on the measured value by the measuring device.
  • the trained model may be built on the measuring device or server 30, or may be built on an external device (for example, a cloud server).
  • the subject of the sensory test may be an expert such as a sommelier, or a survey population selected for the sensory test.
  • the results of statistical analysis of the reviews of multiple users who have actually experienced the product can be used as the result of the sensory test, and in this case, the objective evaluation value can fluctuate as product reviews accumulate.
  • the objective evaluation information can include appearance information, aroma information, taste information, stickiness information, and hardness information.
  • Appearance information is information about the objective evaluation value of the appearance of the product.
  • the scent information is information about the objective evaluation value of the scent of the product.
  • the taste information is information about the objective evaluation value of the taste of the product.
  • the stickiness information is information about the objective evaluation value of the stickiness of the product.
  • Hardness information is information about the objective evaluation value of the hardness of the product.
  • the objective evaluation information may include sourness information, sweetness information, and tannin content information.
  • the sourness information is information on the objective evaluation value of the sourness of the product.
  • Sweetness information is information about an objective evaluation value of the sweetness of a product.
  • the tannin content information is information on the objective evaluation value of the tannin content of the product.
  • FIG. 8 is a diagram showing the data structure of the user database of this embodiment.
  • the user database includes a "user ID” field, a "user name” field, an emotional tendency field, and an action history field. Each field is associated with each other.
  • a user ID is stored in the "user ID" field.
  • a user ID is information for identifying user information.
  • User name information is stored in the "user name" field.
  • the user name information is information regarding the name of the user.
  • the "Kansei tendency” field stores the Kansei tendency information.
  • the sensibility tendency information is information about the user's sensibility tendency.
  • the sensibility tendency indicates the difference between the user's subjective evaluation and the objective evaluation for one or more evaluation items. For example, if a user evaluates a product whose sourness is “strong” in objective evaluation as having “normal” sourness, it can be said that the user has a sensory tendency to hardly perceive sourness. In addition, if the user evaluates the sweetness of the product as "extremely strong” for a product whose sweetness is "slightly strong” in objective evaluation, it can be said that the user has an emotional tendency to easily perceive sweetness.
  • the sensibility tendency information includes a one-dimensional numerical value or a multi-dimensional vector for each evaluation item.
  • the sensibility tendency information may be defined for each product category. As a result, for example, it is possible to estimate the user's sensibility tendency by distinguishing between how sweetness is perceived in fruit and how sweetness is perceived in alcoholic beverages.
  • Action history information is stored in the "action history" field.
  • the action history information is information related to the user's action history.
  • the action history is the history of experiences or reviews of various products by the user.
  • the action history information includes the following elements. ⁇ Information that can identify when the user has experienced or reviewed a product ⁇ Information that can identify which product the user has experienced or reviewed ⁇ Information that can identify the content of the user’s product experience or review
  • the content of the experience may include quantitative information such as product quantity, experience time, and price.
  • the content of the review may be, for example, a comprehensive evaluation of the product.
  • the product recommendation process is, for example, a process of recommending a product different from the product to a user who has experienced a certain product.
  • FIG. 9 is a flow chart of product recommendation processing according to the present embodiment.
  • FIG. 10 is a diagram showing an example of a review input screen displayed in the product recommendation process of this embodiment.
  • FIG. 11 is a diagram showing an example of a product recommendation screen displayed in the product recommendation process of this embodiment.
  • the product recommendation process starts after a user (an example of a "first user") experiences a product (an example of a "first product", hereinafter referred to as a "target product").
  • the product recommendation process may be started when any of the following start conditions are satisfied.
  • the product recommendation process was called by other information processing.
  • the user performed an operation for calling the product recommendation process (for example, an operation for starting product review on a UI (User Interface) not shown).
  • the client device 10 has entered a predetermined state (for example, activation of a predetermined application (e.g., EC application) or access to a predetermined website (e.g., matching platform website)).
  • a predetermined amount of time has elapsed since a predetermined event (eg, a user's experience of a product).
  • the server 30 presents a review input UI (S130). Specifically, the server 30 presents to the user via the client device 10 a UI for inputting a user's review of the target product. As an example, the server 30 causes the display 21 of the client device 10 to display a review input screen.
  • the review input screen P10 includes a display object A10 and operation objects B10a to B10c.
  • an object group including the display object A10 and the operation objects B10a and B10b is provided for each of one or more evaluation items defined for the product category to which the target product belongs.
  • the display object A10 displays information (for example, the name of the evaluation item) regarding the evaluation item corresponding to the display object A10.
  • the operation object B10a receives an operation for expressing whether the user is satisfied or dissatisfied with the product from the viewpoint of the evaluation item corresponding to the operation object B10a.
  • An evaluation item with which the user expresses satisfaction or dissatisfaction is considered to be an item of high interest to the user.
  • the user if the user satisfies the sourness of the target product, the user selects the thumbs-up button of the operation object B10a corresponding to the evaluation item "sourness”.
  • the user selects the thumbs down button of the operation object B10a corresponding to the evaluation item "sourness”.
  • the operation object B10b is an object that receives an operation for designating subjective evaluation of a product by the user with respect to the evaluation item corresponding to the operation object B10b.
  • the user feels that the product has a strong sour taste, the user moves rightward the slider of the operation object B10b corresponding to the evaluation item “sour taste”.
  • the user feels that the sourness of the product is weak, the user moves the slider of the operation object B10b corresponding to the evaluation item "sourness" to the left.
  • an object representing the objective evaluation value of the product for the evaluation item corresponding to the operation object B10b may be displayed superimposed on the operation object B10b.
  • the initial position of the slider of the operational object B10b may be determined so as to represent the objective evaluation value of the product for the evaluation item corresponding to the operational object B10b.
  • the operation object B10b covering a plurality of evaluation items may be represented using a graph such as a radar chart.
  • the user can specify a subjective evaluation of the product by changing the state of the graph (for example, the position of each vertex on the radar chart, the length of the bars on the graph).
  • the initial state of this graph may be determined so as to represent the objective evaluation value of the product for each evaluation item.
  • the review input screen P10 may further include another graph expressing objective evaluation values for each evaluation item of the product.
  • the operation object B10c accepts an operation to confirm the input state of the operation objects B10a to B10b corresponding to each evaluation item.
  • the client device 10 transmits to the server 30 the information indicating the input state of the operation objects B10a to B10b corresponding to each evaluation item as the product review by the user.
  • step S130 the server 30 executes review acquisition (S131). Specifically, the server 30 acquires from the client device 10 a review based on the user's operation of the review input UI presented in step S130.
  • the server 30 specifies subjective evaluation values (S132). Specifically, the server 30 identifies the user's subjective evaluation value for at least one evaluation item (hereinafter referred to as "target item") of the target product based on the review acquired in step S131. As an example, when the review input screen P10 is presented in step S130, the server 30 can specify a numerical value according to the input state of the operation object B10b corresponding to each evaluation item as the user's subjective evaluation value for the item. is.
  • the server 30 performs sensitivity tendency estimation (S133). Specifically, the server 30 extracts the objective evaluation information of the target product from the product database (FIGS. 6 and 7). The server 30 estimates the user's sensitivity tendency based on the comparison between the objective evaluation value indicated by the objective evaluation information and the subjective evaluation value specified in step S132. As an example, the server 30 may estimate the user's sensitivity tendency based on the difference obtained by subtracting the objective evaluation value from the subjective evaluation value for each target item (hereinafter referred to as "evaluation difference"). The server 30 associates the emotional tendency information that can identify the estimated emotional tendency with the user ID corresponding to the user and stores it in the user database (FIG. 8).
  • the server 30 further based on this emotional tendency information.
  • a sensitivity tendency may be estimated.
  • the server 30 calculates the weighted sum (however, the weight may be 1:1) of the evaluation difference and the previously estimated sensitivity tendency for the target item, and calculates the user's current It may be estimated that the sensibility tendency of
  • weighting may be changed between evaluation items for which the user expresses satisfaction or dissatisfaction and evaluation items for which he is not. For example, evaluation items for which the user has expressed satisfaction or dissatisfaction may be given greater weight to evaluation differences than evaluation items for which the user is not.
  • the server 30 identifies similar users (S134). Specifically, the server 30 identifies another user (an example of a “second user”) who is similar to the user in terms of emotional tendencies. As an example, the server 30 refers to the user database (FIG. 8) to search for similar users who have an emotional tendency similar to the emotional tendency estimated in step S133 for the target item. The server 30 may search for one similar user whose emotional tendency is the most similar, may search for a predetermined number of similar users in order of similar emotional tendency, or may search for a predetermined number of similar users in order of similarity in their emotional tendency. Any number of similar users may be searched for.
  • the degree of similarity of sensibility tendencies can be defined using, for example, the distance between numerical values or vectors representing sensibility tendencies.
  • the difference in sensitivity tendency for each evaluation item may be equally evaluated, or may be weighted for evaluation. Specifically, the kansei of each evaluation item is adjusted so that the difference in the kansei tendencies of the evaluation items for which the user expresses satisfaction or dissatisfaction has a greater effect on the similarity than the difference in the kansei tendencies of the other evaluation items. Differences in trends may be weighted.
  • the server 30 determines recommended products (S135). Specifically, the server 30 refers to the user database (FIG. 8) and extracts the action history information of the similar user identified in step S134. The server 30 determines a recommended product (an example of a “second product”) based on the extracted action history information. The server 30 may determine one recommended product, or may determine a plurality of recommended products.
  • the server 30 may determine the following products as recommended products. ⁇ Products that belong to the same product category as the target product and for which at least one of the frequency, number, quantity, or payment amount of experience by similar users is above the threshold ⁇ Belongs to the same product category as the target product and by similar users Products whose evaluation is above the threshold value in the review ⁇ Products that belong to the same product category as the target product and that similar users have expressed satisfaction with respect to the evaluation items for which the user has expressed satisfaction or dissatisfaction
  • the number of experiences, quantity, Alternatively, the payment amount may be a value per experience, or may be a total value of experiences over a plurality of times.
  • the evaluation in reviews by similar users is, for example, a comprehensive evaluation of a product.
  • a threshold value to be compared with evaluations in reviews by similar users may be a common value among users, or may be determined individually for each user.
  • the threshold may be an evaluation in past reviews of the target product by similar users.
  • this threshold may be a statistical value (for example, average value, median value, or mode value) of evaluations in past reviews by similar users for each product belonging to the same product category as the target product.
  • the server 30 may calculate a recommendation score for each of other products belonging to the same product category as the target product, and determine a predetermined number of products as recommended products in descending order of the recommendation scores.
  • a product with a score equal to or higher than a threshold value may be determined as a recommended product.
  • the recommendation score may be calculated based on at least one of the frequency, number, quantity, or payment amount of experience by the similar user, may be calculated based on the evaluation of the product by the similar user, or may be calculated based on the evaluation of the product by the similar user. It may be calculated based on the number of similar users expressing satisfaction with respect to the evaluation items expressing satisfaction or dissatisfaction.
  • the server 30 may calculate the recommendation score further considering the evaluation items that the user expresses satisfaction or dissatisfaction.
  • the server 30 may increase the recommendation score of the other product as the difference between the objective evaluation value of the target product and the objective evaluation value of the other product becomes smaller for the evaluation item for which the user expresses satisfaction.
  • the server 30 may decrease the recommendation score of the other product as the difference between the objective evaluation value of the target product and the objective evaluation value of the other product becomes smaller for the evaluation item for which the user expresses dissatisfaction.
  • the server 30 presents recommended product information (S136). Specifically, the server 30 generates information on the recommended product determined in step S135 and presents the information to the user via the client device 10 .
  • the server 30 can refer to product databases (FIGS. 6 and 7) to generate information on recommended products.
  • the server 30 causes the display 21 of the client device 10 to display a product recommendation screen.
  • the product recommendation screen P11 includes a display object A11.
  • the display object A11 is provided for each recommended product group.
  • the display object A11 displays information about recommended products.
  • Information about the recommended product can include, for example, information about the name, appearance, production area, raw materials, ingredients, specifications, price, producer, or provider of the recommended product.
  • the information about the recommended product can include a graph (a radar chart as an example) that expresses the objective evaluation information of the target product and the objective evaluation information of the recommended product.
  • step S136 the server 30 ends the product recommendation process (FIG. 9).
  • the server 30 obtains user reviews of target products, and based on the reviews and product databases (FIGS. 6 and 7), evaluates the user's sensitivity to target items. presume.
  • the server 30 identifies similar users who are close to the user in terms of emotional tendencies, and determines products to recommend to the user based on the behavior history of the similar users.
  • the server 30 by considering the action history of various products by similar users who have a similar way of thinking about products as the user, it is possible to select products that are highly likely to be liked by the user. Therefore, according to the server 30, it is possible to improve user satisfaction and promote sales of products.
  • the server 30 specifies the user's subjective evaluation value of the target item of the target product based on the review, and based on the comparison between the subjective evaluation value and the objective evaluation value of the target product, the user's sensitivity tendency of the target item. can be estimated. As a result, it is possible to organize the user's sensibility tendency on an item-by-item basis and reasonably estimate it.
  • the server 30 may present a user interface that includes information about the target item, and obtain reviews based on the user's operation received by the user interface. As a result, it is possible to present the user with a point of view for reviewing the product, and obtain a review that reflects the user's subjective evaluation without omission or duplication.
  • the server 30 may present a user interface that further includes an objective evaluation value for the target item of the target product. Thereby, the user can be urged not to make an extreme subjective evaluation.
  • the server 30 may present a user interface including a graph-type object that accepts an operation of designating subjective evaluations of a plurality of target items of a target product by a user. This allows the user to intuitively make a subjective evaluation of the product.
  • the server 30 may present a user interface including an object that accepts an operation of designating an evaluation item with which the user feels satisfied or unsatisfied. This makes it possible to select products that are more likely to be liked by the user, taking into consideration the items that the user is highly interested in.
  • Target products are products purchased, rented, used, used, viewed, consumed, or met by users. This makes it possible to reasonably estimate the user's sensitivity tendency based on subjective evaluations formed by the user by actually experiencing the target product.
  • the objective evaluation value of each product for the target item may be a value based on at least one of the result of measuring the physical quantity or chemical quantity of the product by a measuring device, or the result of a human sensory test of the product. . This makes it possible to increase the reliability of the objective evaluation value of the product.
  • the other user's action history may include at least one of the purchase, rental, use, use, viewing, consumption, meeting, or review history of the product by the other user. This makes it possible to select products that are more likely to be liked by the user in consideration of the actual experience or review history of products by similar users.
  • the server 30 may determine, as a recommended product, a product that belongs to the same product category as the target product and for which at least one of the frequency, number, quantity, and payment amount of experiences by similar users is equal to or greater than a threshold. This makes it possible to recommend to the user products that similar users have actually actively experienced.
  • the server 30 may determine, as a recommended product, a product that belongs to the same product category as the target product and that has been evaluated in reviews by similar users with a threshold value or higher. As a result, it is possible to recommend to the user products that are actually highly rated by similar users.
  • the server 30 may identify similar users based on the user database (FIG. 8). Accordingly, it is possible to efficiently search for similar users.
  • the storage device 11 may be connected to the client device 10 via the network NW.
  • the display 21 may be mounted on the client device 10 .
  • Storage device 31 may be connected to server 30 via network NW.
  • Each step of the product recommendation process described above can be executed by either the client device 10 or the server 30 .
  • the execution order of each step is not limited to the example described as long as there is no dependency.
  • the first information processing device is part of the product recommendation system 1 and part of an external system (for example, an EC system, a SaaS system, a subscription system, a matching platform system).
  • the first information processing apparatus presents a review input UI to the user of the external system via the client device 10 and acquires a review from the user.
  • the first information processing device transmits the obtained review to the second information processing device.
  • the second information processing device executes steps S132 to S135 of the product recommendation process (FIG. 9).
  • the second information processing device transmits information about recommended products to the first information processing device.
  • the first information processing device presents information on recommended products to the user via the client device 10 . In this way, the product recommendation system 1 can also be used to assist external systems in providing services to users.
  • the product database (Figs. 6 and 7) and the user database (Fig. 8) was explained.
  • the user database can also function as a product database.
  • the user information stored in the user database may comprise objective evaluation information of the corresponding user.
  • the server 30 may specify the user's subjective evaluation value for each evaluation item by performing natural language processing such as semantic analysis on the sentences included in the review.
  • the server 30 may use a trained model that predicts a subjective evaluation value with sentences as input.
  • the review of the target product by the user and the presentation of information on the recommended product may be discontinuous.
  • the recommended product information may be presented when the client device 10 first launches a predetermined application or accesses a predetermined website.
  • information on the recommended product may be sent to the client device 10 in the form of a push notification, e-mail, or message, for example, after a predetermined period of time has elapsed after the user has reviewed the target product.
  • the predetermined period may be determined, for example, based on the average experience cycle of products belonging to the same consumption category as the target product by the user.
  • (Appendix 1) a computer (30); means for acquiring a review by the first user on the first product experienced by the first user (S131); At least one evaluation defined for the product category to which the first product belongs, based on a product database storing information on objective evaluation values of each product for one or more evaluation items defined for each product category, and reviews.
  • Appendix 2 further functioning the computer as a means (S132) for specifying a subjective evaluation value by the first user for the target item of the first product based on the review;
  • the means for estimating the sensibility tendency estimates the first user's sensibility tendency for the target item based on a comparison between the objective evaluation value and the subjective evaluation value for the target item of the first product.
  • Appendix 3 further functioning the computer as a means (S130) for presenting a user interface including information on at least one of the target item or the objective evaluation value of the target item of the first product;
  • the means for acquiring reviews acquires reviews based on operations received from the first user by the user interface.
  • the means for presenting information presents a user interface including a graph-type object that accepts an operation of designating a subjective evaluation of a plurality of target items of the first product by the first user;
  • the means for presenting information presents a user interface including an object that accepts an operation of designating an evaluation item or an objective evaluation value that the first user feels satisfied or dissatisfied with,
  • Appendix 6 The means for obtaining reviews obtains reviews by the first user on products purchased, rented, used, used, viewed, consumed, or met by the first user; The program according to any one of Appendices 1 to 5.
  • the objective evaluation value of each product for the target item is a value based on at least one of the result of measuring the physical quantity or chemical quantity of the product by a measuring device, or the result of a human sensory test of the product.
  • the program according to any one of Appendices 1 to 6.
  • the second user's action history includes at least one history of purchase, rental, use, use, viewing, consumption, meeting, or review of the product by the second user;
  • the program according to any one of Appendices 1 to 7.
  • the means for determining belongs to the same product category as the first product, and at least one of frequency, number, quantity, or payment amount of purchase, rental, use, use, appreciation, consumption, or meeting by the second user is a threshold Determine the above product as the second product, A program according to Appendix 8.
  • the determining means determines, as the second product, a product that belongs to the same product category as the first product and that has been evaluated by the second user above a threshold, A program according to Appendix 8.
  • Appendix 11 The means for identifying the second user identifies the second user based on a user database that stores information about the sensibility tendencies of a plurality of users including the second user. 11. The program according to any one of appendices 1 to 10.
  • (Appendix 12) means for obtaining a review by the first user on the first product experienced by the first user (S131); At least one evaluation defined for the product category to which the first product belongs, based on a product database storing information on objective evaluation values of each product for one or more evaluation items defined for each product category, and reviews.
  • a product recommendation device (30) comprising:
  • (Appendix 13) a computer (30) Acquiring a review by the first user on the first product experienced by the first user (S131); At least one evaluation defined for the product category to which the first product belongs, based on a product database storing information on objective evaluation values of each product for one or more evaluation items defined for each product category, and reviews. estimating the sensitivity tendency of the first user for the target item which is the item (S133); identifying a second user who is similar to the first user in terms of sensitivity (S134); Determining a second product to be recommended to the first user based on the behavior history of the second user (S135); A product recommendation method comprising:
  • a product recommendation system comprising a first information processing device (10) and a second information processing device (30) different from the first information processing device,
  • the first information processing device comprises means for obtaining a review by the first user on the first product experienced by the first user
  • the second information processing device is At least one evaluation defined for the product category to which the first product belongs, based on a product database storing information on objective evaluation values of each product for one or more evaluation items defined for each product category, and reviews.
  • the first information processing device further comprises means for presenting information about the second product to the first user, A product recommendation system (1).

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Computing Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

L'invention aborde le problème de la recommandation d'un produit approprié à un utilisateur. La solution selon un aspect de l'invention porte sur un programme qui amène un ordinateur à fonctionner comme : un moyen pour acquérir un avis d'un premier utilisateur concernant un premier produit expérimenté par le premier utilisateur ; un moyen pour déduire, sur la base de l'avis et d'une base de données de produits qui stocke des informations à propos de valeurs d'évaluation de clients de chaque produit, pour un ou plusieurs éléments d'évaluation définis pour chaque catégorie de produit, une tendance de sensibilité du premier utilisateur concernant un élément cible, qui est au moins un élément d'évaluation défini pour une catégorie de produits auquel appartient le premier produit ; un moyen pour identifier un deuxième utilisateur, qui est similaire au premier utilisateur en termes de tendances à la sensibilité ; et un moyen pour déterminer un deuxième produit à recommander au premier utilisateur sur la base d'un historique de comportement du deuxième utilisateur.
PCT/JP2022/041246 2021-11-04 2022-11-04 Programme, dispositif de recommandation de produit, procédé de recommandation de produit, et système de recommandation de produit WO2023080215A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-180597 2021-11-04
JP2021180597A JP7101438B1 (ja) 2021-11-04 2021-11-04 プログラム、商品推薦装置、商品推薦方法、および商品推薦システム

Publications (1)

Publication Number Publication Date
WO2023080215A1 true WO2023080215A1 (fr) 2023-05-11

Family

ID=82446210

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/041246 WO2023080215A1 (fr) 2021-11-04 2022-11-04 Programme, dispositif de recommandation de produit, procédé de recommandation de produit, et système de recommandation de produit

Country Status (2)

Country Link
JP (2) JP7101438B1 (fr)
WO (1) WO2023080215A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3056168B2 (ja) * 1998-08-20 2000-06-26 株式会社プロムナード 番組編成方法および番組編成装置
JP2008158823A (ja) * 2006-12-25 2008-07-10 Dainippon Printing Co Ltd 情報提供システム
JP2011253243A (ja) * 2010-05-31 2011-12-15 Nippon Telegr & Teleph Corp <Ntt> 情報提供装置、情報提供方法、及び情報提供プログラム
JP5866256B2 (ja) * 2012-05-28 2016-02-17 富士フイルム株式会社 印刷管理装置及び方法、印刷管理システム、印刷システム、情報処理装置並びにプログラム

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002074142A (ja) 2000-08-30 2002-03-15 Toyota Motor Corp 商品推薦システム
JP4240096B2 (ja) 2006-09-21 2009-03-18 ソニー株式会社 情報処理装置および方法、プログラム並びに記録媒体

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3056168B2 (ja) * 1998-08-20 2000-06-26 株式会社プロムナード 番組編成方法および番組編成装置
JP2008158823A (ja) * 2006-12-25 2008-07-10 Dainippon Printing Co Ltd 情報提供システム
JP2011253243A (ja) * 2010-05-31 2011-12-15 Nippon Telegr & Teleph Corp <Ntt> 情報提供装置、情報提供方法、及び情報提供プログラム
JP5866256B2 (ja) * 2012-05-28 2016-02-17 富士フイルム株式会社 印刷管理装置及び方法、印刷管理システム、印刷システム、情報処理装置並びにプログラム

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ABE MASARU, KIYOSHI SAKAI, YUKI MATSUNAMI, SHINSUKE NAKAJIMA: "Proposal of hotel recommendation method using score for each review evaluation item. ", 11TH FORUM ON DATA ENGINEERING AND INFORMATION MANAGEMENT DEIM 2019. (17TH ANNUAL CONFERENCE OF DATABASE SOCIETY OF JAPAN)., 1 January 2019 (2019-01-01), XP093062999, Retrieved from the Internet <URL:https://db-event.jpn.org/deim2019/post/papers/85.pdf> [retrieved on 20230711] *
TANIGUCHI YUNA, YUKI MATSUNAMI, ASAMI OKUDA, MAYUMI UEDA, SHINSUKE NAKAJIMA: "Proposal of a Score Estimation Method for Empty Review Evaluation Items in Cosmetics Recommendation", 11TH FORUM ON DATA ENGINEERING AND INFORMATION MANAGEMENT DEIM 2019. (17TH ANNUAL CONFERENCE OF DATABASE SOCIETY OF JAPAN), 1 January 2019 (2019-01-01), XP093063005, Retrieved from the Internet <URL:https://db-event.jpn.org/deim2019/post/papers/75.pdf> [retrieved on 20230711] *

Also Published As

Publication number Publication date
JP2023070027A (ja) 2023-05-18
JP2023069041A (ja) 2023-05-18
JP7101438B1 (ja) 2022-07-15

Similar Documents

Publication Publication Date Title
Akoglu et al. The effect of brand experiences on brand loyalty through perceived quality and brand trust: a study on sports consumers
US11580586B2 (en) Real-time recommendation monitoring dashboard
CA3111139C (fr) Determination des mots-cles de recherche recommandes pour un utilisateur d`un systeme de conciergerie
KR102321987B1 (ko) 온라인 쇼핑몰 관리 시스템 및 방법
JPWO2005024689A1 (ja) 消費者の購買行動分析方法及び装置
US10592918B2 (en) Predictive recommendation system using tiered feature data
Situmorang et al. The Influence Of Brand Ambassador and Brand Image On Purchase Decisions For L'ORÉAL Paris Products In Medan City
CN111815405A (zh) 一种基于人工智能的商品购买方法
JP7423994B2 (ja) レコメンド装置及びレコメンド方法
Huseynov et al. Food decision-making under time pressure
JP2016081199A (ja) 広告配信システム
Płonka et al. Conjoint analysis models of digital packaging information features in customer decision-making
WO2023080215A1 (fr) Programme, dispositif de recommandation de produit, procédé de recommandation de produit, et système de recommandation de produit
JP7240065B1 (ja) 酒類情報処理装置及びプログラム並びに記憶媒体
Widyastuti SHOPPING ANXIETY AND “FEAR OF MISSING OUT”(FOMO) FOR PURCHASE INTENTION OF E-COMMERCE DURING PANDEMIC COVID-19
WO2021199541A1 (fr) Dispositif d&#39;évaluation de conception, dispositif d&#39;apprentissage, programme et procédé d&#39;évaluation de conception
US20140129329A1 (en) Server, analysis method and computer program product
JP7042787B2 (ja) 判定装置、判定方法、および判定プログラム
JP2021039735A (ja) 情報処理装置、及びプログラム
Sekarlingga et al. Analysis of factors that influence purchase intentions for skintific products using Tiktok shop Indonesia with online trust as mediator variable
CN110799093B (zh) 信息处理装置、客户装置以及记录介质
WO2019159288A1 (fr) Système de traitement d&#39;informations, procédé de traitement d&#39;informations et programme
Anjelita et al. How Does Personalization by Artificial Intelligence on TikTok Influence Purchase Intention?
JP7485203B2 (ja) 商品デザイン生成支援装置、商品デザイン生成支援方法およびコンピュータプログラム
WO2023062864A1 (fr) Dispositif et programme de traitement d&#39;informations de boisson alcoolisée, et modèle entraîné

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22890035

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE