Display support device, display support method, and recording medium

Abstract

This display support device includes a book information acquiring unit, an identifying unit, and an output unit. The book information acquiring unit acquires book information relating to a book of interest to be displayed on a shelf. The identifying unit inputs the acquired book information into a learning model that has learned a relationship between a time-series change in a display state, including a display position and a display method, of each book on the shelf, and the book information relating to the books displayed on the shelf, and identifies a candidate for the display position and display method for displaying the book of interest on the shelf, and a candidate for a book to be removed from the shelf. The output unit outputs the candidate for the display position and display method for displaying the book of interest, and the candidate for the book to be removed.

Description

Display support device, display support method, and recording medium

[0001] The present disclosure relates to a display support device and the like.

[0002] Deciding how to display products is time-consuming and laborious. Therefore, for example, Patent Literature 1 describes a technology for determining product positions based on relationship information that indicates the relationship between the product and the placement position in a placement area where the product is placed.

[0003] International Publication No. 2022 / 190294

[0004] Books are published in large quantities and delivered to bookstores one after another. For this reason, the shelves at fairs and other venues are often changed. Since book sales depend on the shelves, it is difficult to decide how to display books.

[0005] An example of an object of the present disclosure is to provide a display support device or the like that can facilitate the display of books.

[0006] A display support device in one aspect of the present disclosure includes a book information acquisition means for acquiring book information regarding target books to be displayed on a shelf, an identification means for inputting the acquired book information into a learning model that has learned the relationship between the time series changes in the display situation, including the display position and display method of each book on the shelf, and the book information regarding the books displayed on the shelf, and identifying candidate display positions and display methods for displaying the target books on the shelf and candidate books to be removed from the shelf, and an output means for outputting the candidate display positions and display methods for displaying the target books and the candidate books to be removed.

[0007] In one aspect of the present disclosure, a display support method involves a computer acquiring book information about target books to be displayed on a shelf, inputting the acquired book information into a learning model that has learned the relationship between the time series changes in the display situation, including the display position and display method of each book on the shelf, and the book information about the books displayed on the shelf, identifying candidate display positions and display methods for displaying the target books on the shelf and candidate books to remove from the shelf, and performing a process of outputting the candidate display positions and display methods for displaying the target books and the candidate books to remove.

[0008] A program in one aspect of the present disclosure causes a computer to acquire book information regarding target books to be displayed on a shelf, input the acquired book information into a learning model that has learned the relationship between time-series changes in the display situation, including the display position and display method of each book on the shelf, and the book information regarding the books displayed on the shelf, identify candidate display positions and display methods for displaying the target books on the shelf and candidate books to be removed from the shelf, and execute a process of outputting the candidate display positions and display methods for displaying the target books and the candidate books to be removed.

[0009] Each program may be stored in a non-transitory computer-readable recording medium.

[0010] According to the present disclosure, it is possible to facilitate the display of books.

[0011] 1 is a first block diagram showing an example configuration of a display support device according to the present disclosure. FIG. 2 is a flowchart showing an example operation of a display support device according to the present disclosure. FIG. 3 is an explanatory diagram showing each display position on a shelf. FIG. 4 is an explanatory diagram showing display method example 1. FIG. 5 is an explanatory diagram showing display method example 2. FIG. 6 is an explanatory diagram showing display method example 3. FIG. 7 is an explanatory diagram showing display method example 4. FIG. 8 is an explanatory diagram showing an example connection between a display support device and another device. FIG. 9 is a second block diagram showing an example configuration of a display support device according to the present disclosure. FIG. 10 is an explanatory diagram showing an example visualization of a display situation. FIG. 11 is an explanatory diagram showing an example of acquiring book information from the book JAN code of a book. FIG. 12 is an explanatory diagram showing example 1 of displaying candidate display positions and display methods for a target book on a terminal device. FIG. 13 is an explanatory diagram showing example 2 of displaying candidate display positions and display methods for a target book on a terminal device. FIG. 14 is a flowchart showing an example operation related to generation and learning of display information by a display support device according to the present disclosure. FIG. 15 is a flowchart showing an example operation related to identification of a display position and display method for a target book by a display support device according to the present disclosure. FIG. 16 is an explanatory diagram showing an example hardware configuration of a computer.

[0012] Hereinafter, with reference to the drawings, embodiments of a display support device, a display support method, a program, and a non-transitory recording medium for recording the program according to the present disclosure will be described in detail. The disclosed technology is not limited to these embodiments.

[0013] 1 is a block diagram illustrating a configuration example of a display support device according to the present disclosure. The display support device 10 includes a book information acquisition unit 101, an identification unit 102, and an output unit 103.

[0014] The book information acquisition unit 101 acquires book information about a target book to be displayed on a shelf. The target book may be, for example, a book to be newly displayed. The book information includes, for example, at least one of the following: the book's name, the book's author, the book's first publication date, the book's category, the book's cover artist, the number of copies of the book in stock, information about the book's sales, the book's media information, the display location and display method of other books by the author, information about the sales of other books by the author, and information about the book's size. The size information may be, for example, information about the specific length and width, or information indicating whether the book is a hardback or a paperback. The media information may indicate at least one of the degree of attention on the Internet and the degree to which the book is featured in media. The Internet may include SNS (Social Networking Service) and the like. Media media include newspapers, television, magazines, and the like. The book sales information may indicate the number of copies of the book sold or the attributes of customers who purchased the book. The attribute may be at least one of age, sex, and occupation.

[0015] Next, the identification unit 102 inputs the acquired book information into the learning model to identify candidate display positions and display methods for displaying the target book on the shelf and candidate books to remove from the shelf. The learning model is a model that has learned the relationship between changes in the display situation, including the display position and display method of each book on the shelf, and book information about the books displayed on the shelf. The display situation may be the display situation when a specific person, such as an expert, displays the books. A change in the display situation is a change in the arrangement of books on the shelf. For example, changes in the display situation include newly displayed books, changes in the display position and display method of those books, and changes in removed books, and changes in the display position and display method of the removed books. In other words, the learning model is a model that has learned how a specific person, such as an expert, rearranges books according to book information. The display method is, for example, how books are displayed and how they are placed. Specific examples of display positions and display methods will be described in the second embodiment.

[0016] The learning model may be generated using inverse reinforcement learning or intention learning. This allows the learning model, reflecting the intentions of the person who arranged the shelves, to identify candidate display positions and display methods for the target products and candidate books to remove from the shelves. Intention learning can learn which perspectives a person prioritizes based on their decision-making history. The decision-making history is the display information that represents the actual display situation of books on the shelves. Examples of perspectives include the store's customer demographics, book categories, media coverage, number of books in stock, sales, and author popularity. The store's customer demographics refer to the attributes of customers who purchase books sold in the store. Attributes include age, gender, and occupation. In other words, intention learning determines a weighting coefficient for each perspective. This allows the creation of shelves that look like they were arranged by a skilled store clerk. Constraints are not specified, but may include the number of types of books to be displayed on the shelves, the number of books in stock, and the target number of books sold. The number of types of books may be the number of different types of books, such as 10 types, if the same book is considered to be one type.

[0017] The output unit 103 outputs candidate display positions and display methods for displaying the target books, and candidate books to be extracted. The output method by the output unit 103 is not particularly limited to audio output, display, etc. The output destination by the output unit 103 is not particularly limited to a terminal device of a store clerk, a terminal device installed in the store, etc. For example, the output unit 103 may display candidate display positions and display methods for displaying the target books, and candidate books to be extracted, on the terminal device of the store clerk.

[0018] (Flowchart) Figure 2 is a flowchart showing an example of operation of the display support device 10 according to the present disclosure. The book information acquisition unit 101 acquires book information about target books to be displayed on a shelf (step S101). The identification unit 102 inputs the acquired book information into a learning model to identify candidate display positions and display methods for the books and candidate books to be extracted (step S102). The output unit 103 outputs candidate display positions and display methods for the books and candidate books to be extracted (step S103). The display support device 10 ends the series of processes.

[0019] While a large number of new books are delivered to bookstores, the delivered books need to be removed. The removed books may be returned to their publishers. For example, an inexperienced store clerk may decide which books to remove based on the book's sales ranking. However, in reality, customers consider purchasing a book by comparing books on the shelves. Therefore, even a book with low sales may increase sales by arranging it with other books. It is expected that an experienced store clerk will consider factors other than rankings when determining the display position and display method of books and which books to remove. In the first embodiment, the display support device 10 inputs book information about the target books to be displayed on the shelves into a learning model that has learned the relationship between changes in the display situation and books, and identifies candidate display positions and display methods for the books and candidate books to remove. The display support device 10 then outputs candidate display positions and display methods for the books and candidate books to remove. This facilitates book display. Furthermore, the display support device 10 determines which books to extract, taking into account the perspective of an expert who takes into account sales and other factors, thereby improving sales.

[0020] Second Embodiment Next, a second embodiment will be described in detail with reference to the drawings. In the second embodiment, a process for generating display information and a process for generating a learning model will be described. Below, a description of content that overlaps with the above description will be omitted to the extent that the description of the second embodiment is not unclear.

[0021] 3 is an explanatory diagram showing the display positions on a shelf, and in FIG. 3, the display positions will be explained using a shelf used at a fair or the like as an example.

[0022] In Figure 3, the display positions on the shelf include the area on the shelf platform, the area on the platform in front of the shelf, the area at eye level on the shelf, the area on the shelf higher than eye level, and the area on the shelf lower than eye level. Note that the display positions may be differentiated in more detail. Eye level may be the average height of the eye level.

[0023] 4A to 4D are explanatory diagrams showing examples of display methods. As shown in FIG. 4A, the display method may be flat stacking. Flat stacking is a display method in which books are stacked vertically with their covers on top. Flat stacking is performed, for example, on a flat surface area of ​​a shelf or on a flat surface area in front of a shelf. Flat stacking may be further divided into a display method in which the front covers of the books are visible, a display method in which the spines of the books are visible, a display method in which the back covers of the books are visible, and a display method in which the books are open. In the display method in which the books are open, only the topmost book may be open.

[0024] 4B, the display method may be shelf-mounting. Shelf-mounting is a display method in which books are placed upright on a shelf with their spines visible. Shelf-mounting is performed in an area at eye level on the shelf, an area higher than eye level on the shelf, an area lower than eye level on the shelf, or the like.

[0025] 4C, the display method may be a surface display. Surface display is a display method in which books are placed upright on a shelf and the covers and the like are visible. Surface display may be further divided into a display method in which the covers of the books are visible, a display method in which the back covers are visible, and the like. Surface display is carried out in an area at eye level on the shelf, an area on the shelf higher than eye level, an area on the shelf lower than eye level, and the like.

[0026] 4D, the display method may be a multi-sided display, which is a display method that combines at least two of the following display methods: a display method that shows the cover of the book, a display method that shows the spine, a display method that shows the back cover, and a display method that shows the book in an open state.

[0027] FIG. 5 is an explanatory diagram showing an example of a connection between the display support device 20 and another device. The display support device 20 is connected to a terminal device 21, for example, via a communication network. For example, the terminal device 21 may be pre-installed with an application program capable of outputting information from the display support device 20 or transmitting information to the display support device 20. For example, the terminal device 21 may access the website of the display support device 20 via the communication network NT. The type of the terminal device 21 is not particularly limited, and may be a personal computer (PC), a smartphone, a tablet device, or the like. The number of terminal devices 21 may be provided for each user, and is not particularly limited. Note that the following description will be given taking a store clerk as an example of a user. The terminal device 21 may be, for example, a terminal device 21 owned by a store clerk or a terminal device 21 installed in the store.

[0028] 6 is a second block diagram showing an example configuration of the display assistance device 20 according to the present disclosure. In FIG. 6, the display assistance device 20 includes a book information acquisition unit 201, an identification unit 202, an output unit 203, a learning data acquisition unit 204, a learning unit 205, a shelf image acquisition unit 206, and a display information generation unit 207.

[0029] The book information acquisition unit 201 may have, as a basic function, the function of the book information acquisition unit 101 shown in Fig. 1. The identification unit 202 may have, as a basic function, the function of the identification unit 102 shown in Fig. 1. The output unit 203 may have, as a basic function, the function of the output unit 103 shown in Fig. 1.

[0030] The display support device 20 may also include a display DB (DataBase) 2000 and a book DB 2001 .

[0031] The display DB 2000 stores, for example, display information that indicates the display status of books on shelves at each date and time. For example, the display DB 2000 may store the display information so that the person who decided on the shelf display can be identified. Furthermore, for example, the display DB 2000 may store the display information in association with shelf images. In this way, for example, the display DB 2000 makes it possible to identify the chronological display status of a specific person.

[0032] The book DB 2001 stores information about books for each book. The book DB 2001 may store book identification information for identifying a book in association with information about the book. The book identification information may be, for example, a book code such as an ISBN (International Standard Book Number) included in a book JAN (Japanese Article Number) code. For example, a barcode representing the book JAN code is printed on a book. For example, when the barcode is read by a reading device or an imaging device, information about the book associated with the book code included in the book JAN code represented by the barcode is identified from the book DB 2001.

[0033] Next, each functional unit will be described.

[0034] <Generation of Display Information> In a store, shelf allocation information, such as where each product is displayed, is created. However, while the shelf allocation for books may register which shelf each book is displayed on, it may not register the position on the shelf where each book is displayed. Therefore, the display support device 20 may generate display information representing the display situation, including the display position and display method of each book on the shelf, from the shelf image. The display information may also include information such as the positional relationship between books and the display area of ​​each book.

[0035] For example, the shelf image acquisition unit 206 acquires an image of a shelf. The imaging device that images the shelf may be a surveillance camera installed in the store so that it can capture an image of the shelf, or may be an imaging device provided in the clerk's terminal device 21. For example, when the clerk has finished arranging books on the shelf, the clerk may operate the terminal device 21 to capture a shelf image using the imaging device of the terminal device 21. Then, the shelf image acquisition unit 206 acquires from the terminal device 21, via the clerk's terminal device 21, a shelf image of the shelf captured by the clerk's operation. Note that a single shelf image may be generated by capturing multiple images of the shelf.

[0036] The display information generation unit 207 generates display information representing the display situation, including the display position and display method of each book on the shelf, based on the acquired shelf image. As a method of generating the display information, for example, the display information generation unit 207 generates display information representing the display situation, including the display position and display method of each book on the shelf, by performing image recognition of each book from the shelf image. Note that existing technology may be used for the image recognition. The display information generation unit 207 may associate clerk identification information identifying the clerk who decided to display the books, date and time, display information, and shelf image, and store them in the display DB 2000.

[0037] The output unit 203 may also output at least a part of the display information. For example, the output unit 203 may display on the terminal device 21 a display status indicating the display position of each book.

[0038] 7 is an explanatory diagram showing an example of visualization of a display situation. For example, a store clerk captures an image of a shelf via the terminal device 21. The terminal device 21 transmits the shelf image to the display support device 20. The shelf image acquisition unit 206 then receives the shelf image from the terminal device 21. The display information generation unit 207 generates display information based on the shelf image. The output unit 203 may visualize the display situation according to the display information and output it to the terminal device 21 in the store.

[0039] In this way, every time a store clerk completes a new display, an image of the shelf is taken and display information is generated, and the display information is stored in the display DB 2000. This makes it possible to identify changes in the display status of the shelf over time.

[0040] <Learning> Next, the learning phase will be described.

[0041] The learning data acquisition unit 204 acquires chronological display information and book information about each book. The learning data acquisition unit 204 acquires the chronological display information from the display DB 2000. Note that, for example, the learning data acquisition unit 204 may acquire chronological display information about a specific person. The learning data acquisition unit 204 acquires book information about books displayed in the display situation represented by the chronological display information from the book DB 2001.

[0042] The learning unit 205 learns the relationship between time-series changes in the display situation, including the display position and display method of each book on the shelf, and book information about the books displayed on the shelf. The learning unit 205 trains a learning model, for example, based on display information representing each time-series display situation acquired by the learning data acquisition unit 204 and book information about the books displayed on the shelf in the time-series display situation. The learning unit 205 may perform, for example, inverse reinforcement learning. This generates a learning model that reflects the intention of the person who displayed the books.

[0043] The timing at which the learning unit 205 generates a learning model is not particularly limited. For example, the learning unit 205 may perform learning every time new display information is generated, may perform learning at a timing designated by a user such as a store clerk, or may perform learning at predetermined intervals. The predetermined interval may be particularly limited, such as one week, two weeks, one month, or one year.

[0044] <Inference> Next, the inference phase will be described.

[0045] The book information acquisition unit 201 acquires book information about a target book to be displayed on a shelf. The book information is as described in the first embodiment. If the target book is a newly published book, there is no sales, so a predicted or expected value of sales may be used. The predicted or expected value may be determined, for example, based on the sales of past books by the same author as the target book. Furthermore, the target book is not limited to a newly published book or a book to be delivered, but may also be a book already displayed on another shelf.

[0046] As an example of acquiring book information related to a target book, the book information acquisition unit 201 acquires, from the book DB 2001, book information stored in association with a target book designated by a store clerk. The method of designating the target book is not particularly limited to inputting a book JAN code or a book name, selecting a book from a list of books, etc. Also, for example, the book information acquisition unit 201 may acquire, from the book DB 2001, book information stored in association with a book code included in a book JAN code represented by a barcode of a book read by the store clerk via the terminal device 21 or a reading device.

[0047] Next, the identification unit 202 inputs the acquired book information into the learning model to identify candidate display positions and display methods for displaying the target book on the shelf, and candidate books to be removed from the shelf. The display positions may be those shown in FIG. 3. The display positions may be multiple different positions on the shelf. As multiple different candidate display positions, for example, both a platform area and an area at eye level may be identified. In other words, a reputation display may be performed. The display method may be the display method shown in FIGS. 4A to 4D. The display method may also be the number of faces or the number of displays. The number of displays is the number of books to be displayed.

[0048] For example, the book information acquisition unit 201 may acquire book information for each of the plurality of target books based on the book JAN code of each of the plurality of target books, and the identification unit 202 may identify candidate display positions and display methods for each of the plurality of target books when the plurality of target books are to be displayed on the same shelf, and candidate books to be removed from the shelf.

[0049] The output unit 203 outputs candidates for display positions and display methods for displaying the target books, and candidates for books to be extracted.

[0050] 8 is an explanatory diagram showing an example of acquiring book information from a book's book JAN code. In FIG. 8, for example, a store clerk operates the terminal device 21 to read the barcode of the book JAN code from the book. The terminal device 21 transmits the book code included in the read book JAN code to the display support device 20. The acquisition unit then acquires book information associated with the book code from the book DB 2001. The identification unit 202 inputs the book information into the learning model and identifies candidate display positions and display methods for the target book and candidate books to be removed from the shelf.

[0051] FIG. 9 is an explanatory diagram showing Example 1 in which candidate display positions and display methods for the target book are displayed on the terminal device 21. The output unit 203 displays candidate display positions and display methods for the target book and candidate books to be extracted on the terminal device 21. For example, in FIG. 9, the output unit 203 may superimpose candidate display positions and display methods for the target book on a shelf image. The shelf image may be a shelf image showing the current display status, or may be a shelf image of a shelf on which no books are displayed. In FIG. 9, the output unit 203 displays images of the target book as candidate display methods on the shelf image, in addition to candidate display positions for the target book.

[0052] For example, for a book with the title "xxx", an area at eye level is listed as a display position candidate. For a book with the title "xxx", a face display with the number of faces set to 2, the number of books displayed to 10, and a face display with the front cover showing are listed as display method candidates.

[0053] For example, for a book with the title "yyy," the display position can be a platform area. For the book with the title "yyy," the display method can be a flat display with two faces, 40 books in total, and both front and back covers showing.

[0054] The books to be removed from the shelf are listed as having the book title "zzz" and the book title "xyz." Note that images of the books to be removed from the shelf may be displayed so that the store clerk can easily confirm the books.

[0055] 10 is an explanatory diagram showing Example 2 in which candidate display positions and display methods for a target book are displayed on the terminal device 21. The output unit 203 may display a route from a predetermined position to a shelf on a store map, and the display position and display method on the shelf. The predetermined position may be the position of a store clerk within the store, or a specific position such as the store entrance or the backroom where the book was delivered. The position of the store clerk may be the position of the terminal device 21. Existing technology may be used to identify the route.

[0056] 10, a store map is displayed, with the positions of store clerks indicated by circles and the positions of shelves indicated by stars. The route from the positions of the store clerks to the positions of the shelves is also displayed on the store map.

[0057] 10 also shows the location of the return box. The output unit 203 may display the destination of the book along with the name of the book to be removed from the shelf. The removed book is likely to be returned to the publisher, etc. For this reason, in FIG. 10, the destination of the book is the return box R.

[0058] 11 is a flowchart showing an example of operation related to generation and learning of display information by the display support device 20 according to the present disclosure. The shelf image acquisition unit 206 acquires a current shelf image by photographing the shelf using the store clerk's terminal device 21 (step S201). Then, the display information generation unit 207 generates display information representing the display situation, including the display position and display method of each book displayed on the shelf, by performing image recognition on the shelf image (step S202).

[0059] Next, the learning data acquisition unit 204 acquires the time-series display information and the book information of the books displayed in the display situations represented by each display information (step S203).Then, the learning unit 205 performs inverse reinforcement learning based on the time-series display information and the book information (step S204).This allows the display assistance device 20 to generate a learning model.

[0060] 12 is a flowchart showing an example of an operation of the display support device 20 according to the present disclosure for identifying the display position and display method of a target book. For example, the book information acquisition unit 201 reads the book JAN code of the target book via the terminal device 21 (step S211). Then, the book information acquisition unit 201 acquires, from the book DB 2001, book information of the target book associated with the book code included in the book JAN code (step S212).

[0061] The identification unit 202 inputs the book information of the target book into the learning model to identify the display position and display method of the target book and the book to be extracted (step S213). The output unit 203 inputs the book information of the target book and displays the display position and display method of the target book and the book to be extracted on the terminal device 21 (step S214). This completes the series of processes of the display support device 20.

[0062] As described above, in the second embodiment, the display assistance device 20 learns a learning model based on display information representing each of the time-series display situations and book information about books displayed on shelves in the time-series display situations. Here, the display assistance device 20 generates the learning model by inverse reinforcement learning.

[0063] Furthermore, the display support device 20 acquires images of the shelves and generates display information that indicates the display situation, including the display position and display method of each book on the shelf, based on the acquired images. This makes it possible to specify the display situation of the books in more detail than just shelf allocation information, such as which shelf the books are displayed on.

[0064] The display position may be at least one of an area on the shelf platform, an area at the height of the line of sight of the shelf, an area higher than the line of sight of the shelf, and an area lower than the line of sight of the shelf. This allows the display position to be specified so that the product can be easily displayed.

[0065] The display method may be any of flat stacking, face display, and shelf display. The display method may include at least one of the number of faces and the number of books. Flat stacking is any of the display methods that show the cover of the book, the display method that show the spine of the book, the display method that show the back cover of the book, and the display method that show the book in an open state. Face display is further any of the display methods that show the cover of the book, the display method that show the spine, and the display method that show the back cover. This allows the store clerk to check the display method in more detail. This makes it easier to display books.

[0066] The display positions may also be different positions on a shelf, thereby allowing reputation display.

[0067] The display support device 20 may also display candidate display positions and display methods for the target book on the shelf image. That is, the display support device 20 may highlight candidate display positions for the target book on the shelf image. The display support device 20 may also display on the shelf image the display state of the target book when the target book is displayed using the candidate display positions and display methods for the target book. The display support device 20 may also display on the shelf image an image representing the target book as the candidate display positions and display methods for the target book. In this case, an image of the target book may be used, or an image the same size as the target book may be used. This allows the store clerk to more easily grasp the image of the target book when displayed. For example, even a store clerk who is unfamiliar with display can have an image of the display. Therefore, it is possible to facilitate the display of books.

[0068] This concludes the description of each embodiment. Furthermore, each embodiment may be combined. The display support devices 10 and 20 may be configured to include some of the functional units and information. For example, the learning model may be created in another system. Therefore, the display support device 20 may be configured to include a book information acquisition unit 201, an identification unit 202, an output unit 203, a shelf image acquisition unit 206, and a display information generation unit 207.

[0069] Furthermore, the embodiments are not limited to the examples described above and can be modified in various ways. Furthermore, the configuration of the display support devices 10 and 20 is not particularly limited. For example, the functional units of the display support devices 10 and 20 may be implemented by a single device. Alternatively, for example, each functional unit or DB of the display support devices 10 and 20 may be implemented by a different device, and configured as a system. For example, each functional unit of the display support device 20 may be implemented by multiple servers, and configured as a system. For example, it may be implemented by a database server including each DB and a server having each functional unit.

[0070] In the embodiment, each DB may include part of the above-mentioned information. Also, each piece of information may include information other than the above-mentioned information.

[0071] The process of generating information to be displayed on the terminal device 21 may be performed by the output unit. This process may also be performed by the terminal device 21. That is, the terminal device 21 generates information for a screen to be displayed on the terminal device 21 based on data received from the display support devices 10 and 20, and displays the screen.

[0072] Furthermore, in each embodiment, an example of displaying books has been described, but if the present invention is applicable to products other than books, candidate display positions and display methods for the products may be identified.

[0073] (Example of Computer Hardware Configuration) Next, an example of a hardware configuration in which each device, such as the display support devices 10 and 20 and the terminal device 21, is realized by a computer will be described.

[0074] 13 is an explanatory diagram showing an example of the hardware configuration of a computer. For example, some or all of the devices can be realized using any combination of a computer 80 and a program as shown in FIG.

[0075] The computer 80 includes, for example, a processor 801, a ROM (Read Only Memory) 802, a RAM (Random Access Memory) 803, and a storage device 804. The computer 80 also includes a communication interface 805 and an input / output interface 806. The components are connected to each other, for example, via a bus 807. The number of each component is not particularly limited, and there may be one or more of each component.

[0076] The processor 801 controls the entire computer 80. The processor 801 may be, for example, a central processing unit (CPU), a digital signal processor (DSP), a graphics processing unit (GPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, or a combination thereof, and is not particularly limited.

[0077] The computer 80 also includes a ROM 802, a RAM 803, and a storage device 804. Examples of the storage device 804 include a semiconductor memory such as a flash memory, a hard disk drive (HDD), and a solid state drive (SSD). For example, the storage device 804 stores an operating system (OS) program, application programs, and programs related to the embodiments. Alternatively, the ROM 802 stores application programs and programs related to the embodiments. The RAM 803 is used as a work area for the processor 801.

[0078] The processor 801 also loads programs stored in the storage device 804, ROM 802, etc. The processor 801 then executes each process coded in the program. The processor 801 may also download various programs via the communication network NT. The processor 801 also functions as a part or all of the computer 80. The processor 801 may then execute the processes or instructions in the illustrated flowchart based on the program.

[0079] The communication interface 805 is connected to a communication network NT such as a LAN (Local Area Network) or a WAN (Wide Area Network) via a wireless or wired communication line. The communication network NT may be composed of multiple communication networks NT. As a result, the computer 80 is connected to external devices and external computers 80 via the communication networks NT. The communication interface 805 serves as an interface between the communication network NT and the inside of the computer 80. The communication interface 805 also controls the input and output of data from external devices and external computers 80.

[0080] Furthermore, the input / output interface 806 is connected to at least one of an input device, an output device, and an input / output device. The connection method may be wireless or wired. Examples of the input device include a keyboard, a mouse, and a microphone. Examples of the output device include a display device, a lighting device, and an audio output device that outputs audio. Examples of the input / output device include a touch panel display. Note that the input device, output device, and input / output device may be built into the computer 80 or may be external.

[0081] The hardware configuration of the computer 80 is an example. The computer 80 may have some of the components shown in FIG. 3 . The computer 80 may have components other than those shown in FIG. 13 . For example, the computer 80 may have a drive device or the like. The processor 801 may then read programs and data stored on a recording medium attached to the drive device or the like into the RAM 803. Examples of non-transitory tangible recording media include optical disks, flexible disks, magneto-optical disks, and USB (Universal Serial Bus) memories. As described above, the computer 80 may have input devices such as a keyboard and a mouse. The computer 80 may have an output device such as a display. The computer 80 may also have an input device, an output device, and an input / output device.

[0082] The computer 80 may also include various sensors (not shown). The types of sensors are not particularly limited. The computer 80 may also include an imaging device capable of capturing images or videos.

[0083] This concludes the description of the hardware configuration of each device. There are various variations in the method of realizing each device. For example, each device may be realized by any combination of a different computer and program for each component. Furthermore, multiple components of each device may be realized by any combination of a single computer and program.

[0084] Furthermore, some or all of the components of each device may be realized by circuits for specific applications. Furthermore, some or all of the components of each device may be realized by general-purpose circuits such as FPGAs (Field Programmable Gate Arrays). Furthermore, some or all of the components of each device may be realized by a combination of circuits for specific applications and general-purpose circuits. These circuits may be a single integrated circuit. Alternatively, these circuits may be divided into multiple integrated circuits. The multiple integrated circuits may be connected via a bus or the like.

[0085] Furthermore, when some or all of the components of each device are realized by a plurality of computers, circuits, etc., the plurality of computers, circuits, etc. may be centrally located or distributed.

[0086] The display support method described in the embodiment may be realized by being executed by a computer such as the display support device 10 or 20 .

[0087] Each program, such as the formulation program and optimization program described in the embodiments, is recorded on a computer-readable recording medium such as an HDD, SSD, flexible disk, optical disk, magneto-optical disk, or USB memory. Each program is executed by being read from the recording medium by a computer. Each program may also be distributed via a communication network NT.

[0088] The functions of each of the components of the display support device 10 and the display support device 20 described above may be realized by dedicated hardware, such as a computer. Alternatively, each component may be realized by software. Alternatively, each component may be realized by a combination of hardware and software.

[0089] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above embodiments. The configuration and details of each of the present disclosures may include embodiments to which various modifications that would be apparent to those skilled in the art are applied within the scope of the present disclosure. The present disclosure may include embodiments in which the details described herein are appropriately combined or substituted as necessary. For example, details described using a particular embodiment may also be applied to other embodiments to the extent that no contradiction occurs. For example, although multiple operations are described in sequence in the form of a flowchart, the order of description does not limit the order in which the multiple operations are performed. Therefore, when implementing the embodiments, the order of the multiple operations may be changed as long as it does not interfere with the content.

[0090] Some or all of the above-described embodiments can be described as follows: However, some or all of the above-described embodiments are not limited to the following.

[0091] (Supplementary Note 1) A display support device comprising: a book information acquisition means for acquiring book information about target books to be displayed on a shelf; an identification means for inputting the acquired book information into a learning model that has learned the relationship between time-series changes in the display situation, including the display position and display method of each book on the shelf, and the book information about the books displayed on the shelf, and identifying candidate display positions and display methods for displaying the target books on the shelf and candidate books to be removed from the shelf; and an output means for outputting the candidate display positions and display methods for displaying the target books and the candidate books to be removed.

[0092] (Supplementary Note 2) The display assistance device according to Supplementary Note 1, wherein the learning model is a model generated by inverse reinforcement learning.

[0093] (Supplementary Note 3) A display support device as described in Supplementary Note 1 or Supplementary Note 2, comprising: a shelf image acquisition means for acquiring an image of the shelf; and a display information generation means for generating, based on the acquired image, display information representing the display situation including the display position and display method of each book on the shelf.

[0094] (Appendix 4) The display support device described in any one of Appendix 1 to Appendix 3, wherein the display position is at least one of an area on the platform of the shelf, an area at line-of-sight height of the shelf, an area higher than line-of-sight of the shelf, and an area lower than line-of-sight of the shelf.

[0095] (Supplementary Note 5) The display support device according to any one of Supplementary Note 1 to Supplementary Note 4, wherein the display method is one of flat stacking, surface display, and shelf display.

[0096] (Supplementary Note 6) The display support device according to Supplementary Note 5, wherein the display method includes at least one of the number of faces and the number of volumes of the books.

[0097] (Appendix 7) The display support device described in Appendix 5 or Appendix 6, wherein the flat stacking is one of a display method that shows the cover of the book, a display method that shows the spine of the book, a display method that shows the back cover of the book, and a display method that shows the book in an open state.

[0098] (Supplementary Note 8) The display support device according to any one of Supplementary Note 5 to Supplementary Note 7, wherein the face display is further one of a display method showing the cover of the book, a display method showing the spine, and a display method showing the back cover.

[0099] (Supplementary Note 9) The display assistance device according to any one of Supplementary Notes 1 to 8, wherein the display positions are a plurality of different positions on the shelf.

[0100] (Appendix 10) A display support device as described in any one of Appendices 1 to 9, comprising: a learning means for learning the learning model based on display information representing each of the display situations in chronological order and book information regarding the books displayed on the shelves in the display situations in chronological order.

[0101] (Appendix 11) A display support device as described in any of Appendices 1 to 10, wherein the book information includes at least one of the following: the name of the book, the author of the book, the first publication date of the book, the category of the book, the artist of the book cover, the number of books in stock, information about sales of the book, media information about the book, the display location and display method of other books by the author, information about sales of other books by the author, and information about the size of the book.

[0102] (Supplementary Note 12) The display support device according to any one of Supplementary Note 1 to Supplementary Note 11, wherein the output means displays the display positions and the display method candidates for the target books on the shelf image.

[0103] (Supplementary Note 13) The display support device according to Supplementary Note 12, wherein the output means highlights the display position candidates for the target book on the shelf image.

[0104] (Appendix 14) A display support method that executes processing in which a computer acquires book information about target books to be displayed on a shelf, inputs the acquired book information into a learning model that has learned the relationship between time-series changes in the display situation, including the display position and display method of each book on the shelf, and the book information about the books displayed on the shelf, identifies candidate display positions and display methods for the target books on the shelf and candidate books to be removed from the shelf, and outputs the candidate display positions and display methods for the target books and the candidate books to be removed.

[0105] (Supplementary Note 15) The display assistance method according to Supplementary Note 14, wherein the learning model is a model generated by inverse reinforcement learning.

[0106] (Appendix 16) A display support method according to appendix 14 or appendix 15, in which the computer executes a process of acquiring an image of the shelf, and generating, based on the acquired image, display information representing the display situation including the display position and display method of each book on the shelf.

[0107] (Appendix 17) A display support method described in any one of Appendices 14 to 16, wherein the display position is at least one of an area on the platform of the shelf, an area at line-of-sight height of the shelf, an area higher than line-of-sight of the shelf, and an area lower than line-of-sight of the shelf.

[0108] (Supplementary Note 18) The display support method according to any one of Supplementary Note 14 to Supplementary Note 17, wherein the display method is one of flat stacking, surface display, and shelf display.

[0109] (Supplementary Note 19) The display support method according to Supplementary Note 18, wherein the display method includes at least one of the number of faces and the number of volumes of the books.

[0110] (Appendix 20) The display support method described in Appendix 18 or Appendix 19, wherein the flat stacking is one of a display method that shows the cover of the book, a display method that shows the spine of the book, a display method that shows the back cover of the book, and a display method that shows the book in an open state.

[0111] (Appendix 21) The display support method according to any one of Appendices 18 to 20, wherein the face display is further one of a display method showing the cover of the book, a display method showing the spine, and a display method showing the back cover.

[0112] (Supplementary Note 22) The display assistance method according to any one of Supplementary Note 14 to Supplementary Note 21, wherein the display positions are a plurality of different positions on the shelf.

[0113] (Appendix 23) A display support method according to any one of appendices 14 to 22, in which the computer executes a process to learn the learning model based on display information representing each of the display situations in chronological order and the book information relating to the books displayed on the shelves in the display situations in chronological order.

[0114] (Appendix 24) A display support method as described in any of Appendices 14 to 23, wherein the book information includes at least one of the following: the name of the book, the author of the book, the first publication date of the book, the book category, the artist of the book cover, the number of books in stock, information about book sales, media information for the book, the display location and display method of other books by the author, information about sales of other books by the author, and information about the size of the book.

[0115] (Supplementary Note 25) The display support method according to any one of Supplementary Note 14 to Supplementary Note 24, wherein in the output, the display positions and the display method candidates for the target books are displayed on the shelf image.

[0116] (Supplementary Note 26) The display support method according to Supplementary Note 25, wherein in the output, the candidate display positions for the target books are highlighted on the shelf image.

[0117] (Appendix 27) A non-transitory computer-readable recording medium that records a program for causing a computer to execute the following processes: acquire book information about target books to be displayed on a shelf; input the acquired book information into a learning model that has learned the relationship between time-series changes in the display situation, including the display position and display method of each book on the shelf, and the book information about the books displayed on the shelf; identify candidate display positions and display methods for displaying the target books on the shelf and candidate books to be removed from the shelf; and output the candidate display positions and display methods for displaying the target books and the candidate books to be removed.

[0118] (Supplementary Note 28) The recording medium according to Supplementary Note 27, wherein the learning model is a model generated by inverse reinforcement learning.

[0119] (Appendix 29) The recording medium described in Appendix 27 or Appendix 28, wherein the computer acquires an image of the shelf, and generates display information representing the display situation, including the display position and display method of each book on the shelf, based on the acquired image.

[0120] (Appendix 30) The recording medium described in any one of Appendices 27 to 29, wherein the display position is at least one of an area on the platform of the shelf, an area at line-of-sight height of the shelf, an area higher than line-of-sight of the shelf, and an area lower than line-of-sight of the shelf.

[0121] (Supplementary Note 31) The recording medium according to any one of Supplementary Note 27 to Supplementary Note 30, wherein the display method is one of flat stacking, face display, and shelf display.

[0122] (Supplementary Note 32) The recording medium according to Supplementary Note 31, wherein the display method includes at least one of the number of faces and the number of volumes of the books.

[0123] (Appendix 33) The recording medium described in Appendix 31 or Appendix 32, wherein the flat stacking is a display method that shows the cover of the book, a display method that shows the spine of the book, a display method that shows the back cover of the book, or a display method that shows the book in an open state.

[0124] (Appendix 34) The recording medium according to any one of appendices 32 to 34, wherein the face display is further any one of a display method showing the cover of the book, a display method showing the spine, and a display method showing the back cover.

[0125] (Supplementary Note 35) The recording medium according to any one of Supplementary Notes 27 to 34, wherein the display positions are a plurality of different positions on the shelf.

[0126] (Appendix 36) A recording medium described in any of Appendices 27 to 35, which records a program that causes the computer to execute a process of learning the learning model based on display information representing each of the display situations in chronological order and the book information regarding the books displayed on the shelves in the display situations in chronological order.

[0127] (Appendix 37) A recording medium described in any of Appendices 27 to 36, wherein the book information includes at least one of the following: the name of the book, the author of the book, the first publication date of the book, the category of the book, the artist of the book cover, the number of books in stock, information about sales of the book, media information for the book, the display location and display method of other books by the author, information about sales of other books by the author, and information about the size of the book.

[0128] (Supplementary Note 38) The recording medium according to any one of Supplementary Note 27 to Supplementary Note 37, wherein in the output, the display position and the display method candidates for the target book are displayed on the shelf image.

[0129] (Supplementary Note 39) The recording medium according to Supplementary Note 38, wherein in the output, the candidate display positions for the target book are highlighted on the shelf image.

[0130] (Appendix 40) A program for a computer that: acquires book information regarding target books to be displayed on a shelf; inputs the acquired book information into a learning model that has learned the relationship between time-series changes in the display situation, including the display position and display method of each book on the shelf, and the book information regarding the books displayed on the shelf; identifies candidate display positions and display methods for displaying the target books on the shelf and candidate books to remove from the shelf; and outputs the candidate display positions and display methods for displaying the target books and the candidate books to remove.

[0131] 10, 20 Display support device 21 Terminal device 80 Computer 101, 201 Book information acquisition unit 102, 202 Identification unit 103, 203 Output unit 204 Learning data acquisition unit 205 Learning unit 206 Shelf image acquisition unit 207 Display information generation unit 801 Processor 802 ROM 803 RAM 804 Storage device 805 Communication interface 806 Input / output interface 807 Bus 2000 Display DB 2001 Book DB NT Communication network R Return box

Claims

1. A display support device comprising: a book information acquisition means for acquiring book information on target books to be displayed on a shelf; an identification means for inputting the acquired book information into a learning model which has learned the relationship between the time series changes in the display situation, including the display position and display method of each book on the shelf, and the book information on the books displayed on the shelf, and identifying candidate display positions and display methods for displaying the target books on the shelf and candidate books to be removed from the shelf; and an output means for outputting the candidate display positions and display methods for displaying the target books and the candidate books to be removed.

2. The display assistance device according to claim 1, wherein the learning model is a model generated by inverse reinforcement learning.

3. A display support device as described in claim 1 or claim 2, comprising: a shelf image acquisition means for acquiring an image of the shelf; and a display information generation means for generating display information representing the display situation including the display position and display method of each book on the shelf based on the acquired image.

4. A display support device as described in any one of claims 1 to 3, wherein the display position is at least one of an area on the platform of the shelf, an area at line-of-sight height of the shelf, an area higher than line-of-sight of the shelf, and an area lower than line-of-sight of the shelf.

5. A display support device according to any one of claims 1 to 4, wherein the display method is flat stacking, surface display, or shelf display.

6. The display assistance device according to claim 5, wherein the display method includes at least one of the number of faces and the number of volumes of the book.

7. A display support device as described in claim 5 or claim 6, wherein the stacking is any one of a display method that shows the cover of the book, a display method that shows the spine of the book, a display method that shows the back cover of the book, and a display method that shows the book in an open state.

8. A display support device according to any one of claims 5 to 7, wherein the face display is further one of a display method showing the cover of the book, a display method showing the spine, and a display method showing the back cover.

9. A display assistance device according to any one of claims 1 to 8, wherein the display positions are a plurality of different positions on the shelf.

10. A display support device as described in any one of claims 1 to 9, comprising a learning means for learning the learning model based on display information representing each of the display situations in chronological order and the book information regarding the books displayed on the shelves in the display situations in chronological order.

11. A display support device as described in any one of claims 1 to 10, wherein the book information includes at least any of the following: the name of the book, the author of the book, the first publication date of the book, the book category, the artist of the book cover, the number of books in stock, information regarding sales of the book, media information of the book, the display position and display method of other books by the author, information regarding sales of other books by the author, and information regarding the size of the book.

12. A display support device according to any one of claims 1 to 11, wherein the output means displays the display positions and display methods of the target books on the shelf image.

13. The display support device according to claim 12, wherein the output means highlights the candidate display positions for the target book on the image of the shelf.

14. A display support method in which a computer executes a process to acquire book information regarding target books to be displayed on a shelf, input the acquired book information into a learning model that has learned the relationship between time-series changes in the display situation, including the display position and display method of each book on the shelf, and the book information regarding the books displayed on the shelf, to identify candidate display positions and display methods for displaying the target books on the shelf and candidate books to be removed from the shelf, and output the candidate display positions and display methods for displaying the target books and the candidate books to be removed.

15. A non-transitory recording medium readable by a computer that records a program for causing a computer to execute the following processes: acquire book information about target books to be displayed on a shelf; input the acquired book information into a learning model that has learned the relationship between time-series changes in the display situation, including the display position and display method of each book on the shelf, and the book information about the books displayed on the shelf; identify candidate display positions and display methods for displaying the target books on the shelf and candidate books to be removed from the shelf; and output the candidate display positions and display methods for displaying the target books and the candidate books to be removed.

Images