Virtual Signage System

Abstract

A virtual sign system suitable for evaluating or improving advertisements is provided. [Solution] A V signboard providing server 100 receives location information of a mobile terminal 200, acquires AR content data and anchor information of V signs installed within a predetermined range from the location of the mobile terminal 200 based on the received location information, and transmits the acquired AR content data and anchor information to the mobile terminal 200. It also receives terminal information, etc., and calculates the degree of attention that the user has paid to the V signboard based on the received terminal information, etc.

Description

[Technical Field]

[0001] The present invention relates to a system relating to a virtual sign, and more particularly to a virtual sign system suitable for evaluating or improving advertisements. [Background technology]

[0002] 2. Description of the Related Art Conventionally, the techniques described in Patent Documents 1 and 2 and Non-Patent Document 1 are known as techniques for displaying virtual signs or advertisements.

[0003] The technologies described in Patent Documents 1 and 2 display virtual billboards as advertisements within a virtual city, and charge advertisers for the display of the virtual billboards.

[0004] The technology described in Non-Patent Document 1 superimposes store advertisements onto the camera image of a smartphone. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2001-331813 [Patent Document 2] Japanese Patent Application Laid-Open No. 2001-338037 [Non-patent literature]

[0006] [Non-Patent Document 1] "What is AR advertising and AR promotion? Introducing interesting use cases and how to create them in companies," [online], February 21, 2025, Cloud Circus, [Retrieved April 1, 2025], Internet<URL:https: / / less-ar.jp / media / column / ar-advertising> Summary of the Invention [Problem to be solved by the invention]

[0007] However, the techniques described in Patent Documents 1 and 2 and the technique described in Non-Patent Document 1 cannot evaluate or improve advertisements on virtual signboards or stores.

[0008] Therefore, the present invention has been made with a focus on the unresolved issues of the conventional technology, and aims to provide a virtual sign system that is suitable for evaluating or improving advertisements. [Means for solving the problem]

[0009] [Invention 1] In order to achieve the above object, the virtual sign system of Invention 1 is a virtual sign system that is communicatively connected to a mobile terminal having a camera, and includes: location information receiving means for receiving location information of the mobile terminal; virtual sign information acquisition means for acquiring, based on the location information received by the location information receiving means, virtual sign information and location information of a virtual sign installed within a predetermined range from the location of the mobile terminal from a storage means that stores virtual sign information related to the content of a virtual sign, which is a virtual sign, and location information related to the installation location of the virtual sign; virtual sign information transmission means for transmitting the virtual sign information and location information acquired by the virtual sign information acquisition means to the mobile terminal; terminal information etc. acquisition means for acquiring terminal information indicating the movement or stay state of the mobile terminal, gaze information related to the user's gaze at a display screen displayed on the mobile terminal based on the virtual sign information and the location information, operation information related to the user's operation on the display screen, or activity information related to the amount of activity of the user using the mobile terminal; and attention level calculation means for calculating the level of attention the user has paid to the virtual sign based on the terminal information, gaze information, operation information, or activity information acquired by the terminal information etc. acquisition means.

[0010] With this configuration, when the location information of the mobile terminal is received by the location information receiving means, the virtual sign information acquisition means acquires virtual sign information and location information of virtual signs installed within a specified range from the location of the mobile terminal based on the received location information, and the virtual sign information transmission means transmits the acquired virtual sign information and location information to the mobile terminal.

[0011] In addition, the terminal information acquisition means acquires terminal information, gaze information, operation information or activity information, and the attention level calculation means calculates the level of attention the user has paid to the virtual sign based on the acquired terminal information, gaze information, operation information or activity information.

[0012] Here, signs include, for example, signs, signs, symbols, and other displays. The same applies to the virtual sign systems of Inventions 5 to 7 below.

[0013] Furthermore, the terminal information etc. acquisition means may, for example, input terminal information etc. from an input device etc., acquire or receive terminal information etc. from an external terminal etc., read terminal information etc. from a storage device or storage medium etc., or generate or calculate terminal information etc. by information processing etc. Therefore, acquisition includes at least input, acquisition, reception, reading (including search), generation and calculation. The same concept of acquisition applies hereinafter.

[0014] The storage means stores the virtual sign information and location information by any means and at any time, and may store the virtual sign information and location information in advance, or may store the virtual sign information and location information by external input during operation of the system without storing the virtual sign information and location information in advance. The same applies to other storage means below. The same applies to the virtual sign systems of Inventions 5 to 7 below.

[0015] Furthermore, this system may be realized as a single device, apparatus, terminal, or other device, or as a network system in which multiple devices, apparatus, terminals, or other devices are communicatively connected. In the latter case, each component may belong to any of the multiple devices as long as they are communicatively connected. The same applies to the virtual sign systems of Inventions 5 to 7 below.

[0016] [Invention 2] Furthermore, the virtual sign system of Invention 2 is the virtual sign system of Invention 1, and further comprises a preference calculation means for calculating the user's preference for the virtual sign based on the terminal information, gaze information, operation information or activity information acquired by the terminal information acquisition means.

[0017] With this configuration, the favorability rating calculation means calculates the user's favorability rating for the virtual sign based on the acquired terminal information, line-of-sight information, operation information, or activity information.

[0018] [Invention 3] Furthermore, the virtual sign system of Invention 3 is a virtual sign system of either Invention 1 or 2, and further comprises an estimation means for estimating the content or installation location of the virtual sign so as to enhance the scenic effect based on the terminal information, line of sight information, operation information or activity information acquired by the terminal information acquisition means, and a suggestion means for suggesting the content or installation location of the virtual sign based on the estimation result of the estimation means.

[0019] With this configuration, the estimation means estimates the content or installation location of the virtual sign based on the acquired terminal information, gaze information, operation information, or activity information so as to enhance the scenic effect, and the suggestion means suggests the content or installation location of the virtual sign based on the estimation result of the estimation means.

[0020] [Invention 4] Furthermore, the virtual sign system of Invention 4 is a virtual sign system of either Invention 1 or 2, and further comprises an estimation means for estimating the content or installation location of the virtual sign based on the virtual sign information and location information in the storage means so as to enhance the scenic effect, and a suggestion means for suggesting the content or installation location of the virtual sign based on the estimation result of the estimation means.

[0021] With this configuration, the estimation means estimates the content or installation location of the virtual sign based on the virtual sign information and location information in the storage means so as to enhance the scenic effect, and the suggestion means suggests the content or installation location of the virtual sign based on the estimation result of the estimation means.

[0022] [Invention 5] Furthermore, the virtual sign system of Invention 5 is a virtual sign system communicatively connected to a mobile terminal having a camera, and comprises: location information receiving means for receiving location information of the mobile terminal; virtual sign information acquiring means for acquiring virtual sign information and location information of a virtual sign installed within a predetermined range from the location of the mobile terminal from storage means for storing virtual sign information relating to the content of a virtual sign, which is a virtual sign, and location information relating to the installation location of the virtual sign, based on the location information received by the location information receiving means; virtual sign information transmitting means for transmitting the virtual sign information and location information acquired by the virtual sign information acquiring means to the mobile terminal; terminal information etc. acquiring means for acquiring terminal information indicating the movement or stay state of the mobile terminal, gaze information relating to the user's gaze at a display screen displayed on the mobile terminal based on the virtual sign information and the location information, operation information relating to the user's operation on the display screen, or activity information relating to the amount of activity of a user using the mobile terminal; and preference level calculation means for calculating the user's preference level for the virtual sign based on the terminal information, gaze information, operation information, or activity information acquired by the terminal information etc. acquiring means.

[0023] [Invention 6] Furthermore, a virtual sign system of Invention 6 is a virtual sign system communicably connected to a mobile terminal having a camera, comprising: location information receiving means for receiving location information of the mobile terminal; virtual sign information acquiring means for acquiring virtual sign information and location information of a virtual sign installed within a predetermined range from the location of the mobile terminal from a storage means for storing virtual sign information relating to the content of a virtual sign, which is a virtual sign, and location information relating to an installation location of the virtual sign, based on the location information received by the location information receiving means; and virtual sign information transmitting means for transmitting the virtual sign information and location information acquired by the virtual sign information acquiring means to the mobile terminal. The device is equipped with a terminal information acquisition means for acquiring terminal information indicating the movement or stay state of the mobile terminal, gaze information regarding the user's gaze at a display screen displayed on the mobile terminal based on the virtual sign information and the location information, operation information regarding the user's operation on the display screen, or activity information regarding the amount of activity of the user using the mobile terminal, an estimation means for estimating the content or installation location of the virtual sign so as to enhance the scenic effect based on the terminal information, gaze information, operation information, or activity information acquired by the terminal information acquisition means, and a suggestion means for suggesting the content or installation location of the virtual sign based on the estimation result of the estimation means.

[0024] [Invention 7] Furthermore, the virtual sign system of Invention 7 is a virtual sign system that is communicatively connected to a mobile terminal having a camera, and includes: location information receiving means for receiving location information of the mobile terminal; virtual sign information acquisition means for acquiring virtual sign information and location information of a virtual sign that is installed within a predetermined range from the location of the mobile terminal from a storage means that stores virtual sign information regarding the content of a virtual sign, which is a virtual sign, and location information regarding the installation location of the virtual sign, based on the location information received by the location information receiving means; virtual sign information transmission means for transmitting the virtual sign information and location information acquired by the virtual sign information acquisition means to the mobile terminal; estimation means for estimating the content or installation location of the virtual sign based on the virtual sign information and location information in the storage means so as to enhance the scenic effect; and suggestion means for suggesting the content or installation location of the virtual sign based on the estimation result of the estimation means. [Effects of the Invention]

[0025] As described above, according to the virtual sign system of invention 1, the degree of attention that a user has paid to a virtual sign is calculated, and therefore, advertisements can be evaluated more effectively than in the past.

[0026] Furthermore, according to the virtual sign system of the second or fifth invention, the user's favorability rating for the virtual sign is calculated, so that the advertisement can be evaluated.

[0027] Furthermore, according to the virtual sign system of Inventions 3, 4, 6 or 7, the content or installation location of the virtual sign is suggested, which allows for improvement of advertising. [Brief explanation of the drawings]

[0028] [Figure 1] 1 is a block diagram showing a configuration of a network system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a diagram showing the hardware configuration of the V signboard provider 100. [Figure 3]4 shows the data structures of an advertiser table 400, a store table 402, an advertisement table 404, a scenery table 406, a charge setting table 408, and an advertisement history table 410. FIG. [Figure 4] FIG. 1 is a functional block diagram of a generation AI server 120. [Figure 5] 10 is a flowchart showing an advertisement information registration process. [Figure 6] 10 is a flowchart showing a V signboard providing process. [Figure 7] 10 is a flowchart showing an advertisement evaluation process. [Figure 8] 10 is a flowchart showing an advertisement suggestion process. [Figure 9] 10 is a display screen of an advertiser terminal. [Figure 10] 10 is a flowchart showing a charging process. DETAILED DESCRIPTION OF THE INVENTION

[0029] An embodiment of the present invention will be described below, with reference to Figures 1 to 10 showing the embodiment.

[0030] First, the business model of this embodiment will be described. An advertising agency accepts advertising applications from advertisers. The advertising agency advertises by installing a virtual signboard (hereinafter referred to as a "V signboard") that corresponds to the location of a real store using AR (Augmented Reality). When a general user takes a photo of the target store with a camera such as a smartphone, the V signboard appears in the camera image at a location corresponding to the target store (for example, the exterior wall of the store's building). The advertiser is charged based on the number of times the V signboard is displayed. In addition, the degree of attention that the user paid to the V signboard and the level of favorability of the V signboard are calculated, and the content or installation location of the V signboard are evaluated based on the calculated attention and favorability. In addition, the advertising agency uses AI (Artificial Intelligence) to suggest the content or installation location of the V signboard to the advertiser to enhance the scenic effect in the surrounding environment (hereinafter simply referred to as the "surrounding environment") where the V signboard is installed.

[0031] 〔composition〕 Next, the configuration of this embodiment will be described. FIG. 1 is a block diagram showing the configuration of a network system according to this embodiment.

[0032] 1, connected to the Internet 199 are a V signboard providing server 100 that provides V signboards, a generation AI server 120 that generates answer information using an AI model in response to a request, and a base station 210. The base station 210 is wirelessly connected to a plurality of mobile terminals 200 so that they can communicate with each other, and relays communication between the mobile terminals 200 and the Internet 199.

[0033] [V signboard provision server] Next, the configuration of the V signboard provider 100 will be described. FIG. 2 is a diagram showing the hardware configuration of the V signboard provider 100. As shown in FIG.

[0034] As shown in Figure 2, the V signboard provider 100 is composed of a CPU (Central Processing Unit) 30 that controls calculations and the entire system based on a control program, a ROM (Read Only Memory) 32 that stores the control program etc. of the CPU 30 in advance in a specified area, a RAM (Random Access Memory) 34 for storing data read from the ROM 32 etc. and the calculation results required in the calculation process of the CPU 30, and an I / F (Interface) 38 that mediates the input and output of data to external devices, and these are connected to each other and to be able to send and receive data by a bus 39, which is a signal line for transferring data.

[0035] The I / F 38 is connected to external devices such as an input device 40 consisting of a keyboard, mouse, etc. that can input data as a human interface, a memory device 42 that stores data, tables, etc. as files, a display device 44 that displays a screen based on an image signal, and a signal line for connecting to the Internet 199.

[0036] [Data Structure] Next, the data structure of the storage device 42 will be described. FIG. 3 shows the data structures of an advertiser table 400, a store table 402, an advertisement table 404, a scenery table 406, a charge setting table 408, and an advertisement history table 410. As shown in FIG.

[0037] The storage device 42 stores AR content data for constructing each VR signboard. The camera application of the mobile terminal 200 can superimpose the V signboard on the camera image based on the AR content data and anchor information including the position information of the V signboard.

[0038] As shown in FIG. 3, the storage device 42 stores an advertiser table 400, a store table 402, an advertisement table 404, a scenery table 406, a charge setting table 408, and an advertisement history table 410.

[0039] The advertiser table 400 is a table for registering advertiser information related to advertisers. As shown in Fig. 3(a), the advertiser table 400 is configured with a column for registering an advertiser ID for uniquely identifying an advertiser, a column for registering the company name of the advertiser, and a column for registering other information. The advertisement ID is the primary key.

[0040] The store table 402 is a table for registering store information about stores of advertisers. As shown in FIG. 3(b), the store table 402 is configured to have a column for registering a store ID for uniquely identifying a store, a column for registering an advertiser ID, a column for registering the latitude indicating the store's location, a column for registering the longitude indicating the store's location, and columns for registering other information. The store ID is the primary key, and the advertiser ID is the foreign key. The store table 402 and the advertiser table 400 have a many-to-one relationship.

[0041] The advertisement table 404 is a table for registering advertisement information related to advertisements. As shown in FIG. 3(c), the advertisement table 404 is configured to have a column for registering an advertisement ID for uniquely identifying an advertisement, a column for registering an advertiser ID, a column for registering a path name of AR content data, a column for registering a latitude indicating the installation location of a V signboard, a column for registering a longitude indicating the installation location of a V signboard, a column for registering a display range in which the V signboard is displayed, and columns for registering other information. The advertisement ID is the primary key, and the advertiser ID is the foreign key. The advertisement table 404 and the advertiser table 400 have a many-to-one relationship.

[0042] The landscape table 406 is a table for registering landscape information related to landscapes. As shown in Figure 3(d), the landscape table 406 is configured with a column for registering an area ID for uniquely identifying an area to which environmental standards apply, a column for registering the center latitude of the area, a column for registering the center longitude of the area, a column for registering the area range, a column for registering landscape standards, and a column for registering other information. The area ID is the primary key.

[0043] Charging setting table 408 is a table for registering charging setting information related to charging settings. As shown in FIG. 3(e), charging table 408 is configured with a column for registering a charging ID for uniquely identifying a charging setting, a column for registering an advertising ID, a column for registering a charging unit price, and columns for registering other information. The charging ID is the primary key, and the advertising ID is the foreign key. There is a one-to-one relationship between charging setting table 408 and advertising table 404.

[0044] The advertisement history table 410 is a table for registering advertisement history information related to advertisement history. As shown in FIG. 3(f), the advertisement history table 410 is configured to have a column for registering a log ID, a column for registering an advertisement ID, a column for registering a terminal ID for uniquely identifying the mobile terminal 200, a column for registering the date and time when the V sign was displayed, a column for registering the latitude indicating the location of the mobile terminal 200, a column for registering the longitude indicating the location of the mobile terminal 200, a column for registering the attention level at which the user paid attention to the V sign, and a column for registering the user's favorability rating for the V sign. The log ID is the primary key, and the advertisement ID is the foreign key. The advertisement history table 410 and the advertisement table 404 have a many-to-one relationship.

[0045] [Generation AI Server] Next, the configuration of the generation AI server 120 will be described. The generation AI server 120 has the same hardware configuration as the V signboard providing server 100, and is configured as, for example, a cloud server.

[0046] FIG. 4 is a functional block diagram of the generation AI server 120. As shown in Figure 4, the generation AI server 120 is configured to include multiple base models 50, a base model control unit 52 that controls the base models 50, and an RDS (Relational Database Service) 54, which is a knowledge base that registers data that the base models 50 refer to for inference.

[0047] The base model 50 is an AI model trained on a large data set and is a highly versatile model capable of performing a variety of tasks. For example, a large language model can be used as the base model 50. A large language model is a deep learning model that pre-trains a language model, which models human-spoken language based on its occurrence probability, from a massive amount of data. When a prompt is input, the large language model statistically estimates the probability of generating the next word from the sentence included in the input prompt and outputs the estimation result. For example, known technologies described on the internet sites "https: / / chatgpt-lab.com / n / n418d3aa56f0b" and "https: / / agirobots.com / chatgpt-mechanism-and-problem / " can be used as the large language model. More specifically, the base models 50 include, for example, Titan Text G1 - Express, Titan Text G1 - Lite, Titan Image Generator G1, Titan Embeddings G1 - Text, Titan Embeddings Text V2, Titan Multimodal Embeddings G1, Claude, Claude Instant, Claude 3 Sonnet, Claude 3 Haiku, Claude 3 Opus, Jurassic-2. Mid, Jurassic-2 Ultra, Command, Command Light, Command R, Command R+, Embed English, Embed Multilingual, Llama 2 Chat 13B, Llama 2 Chat 70B, Llama 2 13B, Llama 2 70B, Llama 3 8b Instruct, Llama 3 70b Instruct, Mistral 7B Instruct, Mixtral 8X7B Instruct, Mistral Large, Stable Diffusion XL can be adopted.

[0048] The base model control unit 52 selects one of multiple base models 50 to be used for inference in response to a selection request from the prompt processing unit 60. Also, when a reference request is input from the prompt processing unit 60, it causes the selected base model 50 (hereinafter referred to as the "selected base model") to reference the data in the RDS 54 in response to the input reference request. Also, when a prompt is input from the prompt processing unit 60, it inputs the input prompt to the selected base model. Then, when an execution request is input from the prompt processing unit 60, it causes the selected base model to execute inference in response to the input execution request, obtains the inference result from the selected base model, and outputs the obtained inference result to the prompt processing unit 60.

[0049] The RDS 54 can register reference information to be referenced in inference. The reference information in the RDS 54 is in a data format (for example, vector data) that can be referenced by the base model 50.

[0050] The generation AI server 120 is further configured to include a request receiving unit 56 that receives a request, a prompt generating unit 58 that generates a prompt based on the request received by the request receiving unit 56, a prompt processing unit 60 that processes the prompt generated by the prompt generating unit 58, and an answer information sending unit 62 that sends answer information to the V signboard providing server 100 in response to the request from the V signboard providing server 100.

[0051] The request receiving unit 56 receives a request for generating answer information from the V signboard providing server 100 and outputs the received request to the prompt generating unit 58 .

[0052] The prompt generation unit 58 generates a prompt that instructs the base model 50 based on the request received by the request reception unit 56. Then, the prompt generation unit 58 outputs the generated prompt to the prompt processing unit 60 together with the parameters included in the request received by the request reception unit 56.

[0053] When the prompt processing unit 60 receives a prompt and parameters from the prompt generation unit 58, it performs the following processing. First, it outputs a selection request to select the base model 50 to the base model control unit 52. Next, when the V signboard providing server 100 requests reference information, it outputs a reference request to the base model control unit 52 requesting reference information in the RDS 54. Then, it outputs the prompt and execution request received from the prompt generation unit 58 to the base model control unit 52, and when it receives an inference result from the base model control unit 52 in response to the execution request, it outputs the received inference result to the answer information sending unit 62.

[0054] The answer information transmitting unit 62 transmits answer information including the inference result input from the prompt processing unit 60 to the V signboard providing server 100 .

[0055] The generation AI server 120 further comprises a request receiving unit 64 that receives requests, and a reference information registration unit 66 that registers reference information in the RDS 54.

[0056] The request receiving unit 64 receives a request for registering reference information from the V signboard providing server 100 and outputs the received request to the reference information registering unit 66 .

[0057] The reference information registration unit 66 stores the reference information included in the request received by the request receiving unit 64 in storage (not shown) and converts it into a data format (e.g., vector data) that can be referenced by the base model 50. Vector data can be generated by a technology (embedding) that converts data including characters, images, audio, etc. into a numerical vector. The converted reference information is then registered in the RDS 54. The base model control unit 52 causes the selected base model to refer to the reference information in response to a reference request from the prompt processing unit 60.

[0058] [Mobile terminal 200] Next, the configuration of the mobile terminal 200 will be described. The mobile terminal 200 is composed of a portable terminal such as a smartphone or tablet. The hardware configuration is made up of a CPU, ROM, RAM, I / F, etc. connected via a bus. A touch panel, a storage device, a camera, a GPS, an acceleration sensor, a gyro sensor, a wireless communication device, etc. are connected to the I / F.

[0059] [Operation] Next, the operation of this embodiment will be described. [Advertising information registration process] First, a case where an advertisement application is received from an advertiser will be described.

[0060] FIG. 5 is a flowchart showing the advertisement information registration process. The CPU 30 is comprised of an MPU (Micro-Processing Unit) or the like, and starts a predetermined program stored in a predetermined area of ​​the ROM 32, and in accordance with the program, executes the advertisement information registration process shown in the flowchart of Fig. 5. The advertisement information registration process is executed in response to an application request from an advertiser terminal used by an advertiser, and when executed by the CPU 30, the process first proceeds to step S100 as shown in Fig. 5.

[0061] In step S100, advertiser information, store information, and advertising information are received from the advertiser terminal. The store information is information about the advertiser's store, and the range of the V signboard installation location (for example, a 50-meter radius from the store's center location) is determined based on the store's location information (latitude and longitude). The advertising information includes information about the content and installation location of the V signboard that the advertiser wishes to install, and the V signboard installation location is set within the determined range. The installation location may be set arbitrarily by the advertiser, or the V signboard providing server 100 may automatically set it to an optimal location. The charging unit price is determined based on the content or installation location of the V signboard. For example, the charging unit price can be set higher for V signboards with more conspicuous content, in locations with higher traffic, or on lower floors. For this reason, charging setting information is generated based on the advertising information.

[0062] Next, the process proceeds to step S102, where a record is registered in the advertiser table 400 based on the received advertiser information (advertiser ID, company name, and other information).

[0063] Next, the process proceeds to step S104, where a record is registered in the store table 402 based on the received store information (store ID, advertiser ID, store location information (latitude and longitude) and other information).

[0064] Next, in step S106, a record is registered in the advertisement table 404 based on the received advertisement information (advertisement ID, advertiser ID, AR content data, location information of the V signboard (latitude and longitude), display range of the V signboard, and other information). The AR content data is stored in the storage device 42, and its path name is registered in the advertisement table 404.

[0065] Next, the process proceeds to step S108, where a record is registered in the charging setting table 406 based on the generated charging setting information (charging ID, advertisement ID, charging unit price, and other information), and the series of processes ends.

[0066] [V signboard provision processing] Next, a case where a user views a V signboard will be described. FIG. 6 is a flowchart showing the V signboard providing process.

[0067] The CPU 30 starts a predetermined program stored in a predetermined area of ​​the ROM 32, and executes the V signboard providing process shown in the flowchart of Fig. 6 in accordance with the program. The V signboard providing process is a process executed in response to a provision request from the mobile terminal 200, and when executed by the CPU 30, the process first proceeds to step S150 as shown in Fig. 6.

[0068] When the camera application is started, the mobile terminal 200 acquires the location information of the mobile terminal 200 from the GPS and transmits the acquired location information to the V signboard providing server 100.

[0069] In step S150, location information of mobile terminal 200 is received from mobile terminal 200, and the process proceeds to step S152, where, based on the received location information, a search is made for advertising information of V-signboards installed within a predetermined range from the location of mobile terminal 200. Since the advertising information includes a path name of the AR content data, the AR content data is read from storage device 42 based on the path name.

[0070] Next, the process proceeds to step S154, where the read AR content data and anchor information including the position information of the retrieved VR signboard are transmitted to the mobile terminal 200, and the series of processes is terminated.

[0071] When the mobile terminal 200 receives the AR content data and anchor information, the camera application displays a V signboard superimposed on a camera image based on the received AR content data and anchor information.

[0072] [Advertisement evaluation processing] Next, the case of evaluating an advertisement will be described. FIG. 7 is a flowchart showing the advertisement evaluation process.

[0073] The CPU 30 starts a predetermined program stored in a predetermined area of ​​the ROM 32, and in accordance with the program, executes the advertisement evaluation process shown in the flowchart of Fig. 7. The advertisement evaluation process is executed in response to a tracking notification from the mobile terminal 200, and when executed by the CPU 30, the process first proceeds to step S200, as shown in Fig. 7.

[0074] When a user takes a picture of a target store with a camera on the mobile terminal 200, the mobile terminal 200 displays a V signboard at a position corresponding to the target store in the camera image. When the V signboard is displayed, the mobile terminal 200 transmits terminal information, gaze information, operation information, or activity information of the mobile terminal 200 to the VR signboard providing server 100 as a tracking notification. The terminal information includes GPS position information, acceleration information from an acceleration sensor, or gyro information from a gyro sensor. The gaze information includes information about the user's gaze on a display screen (hereinafter simply referred to as the "display screen") on which the V signboard is displayed. The operation information includes information about user operations on the display screen (e.g., tap, swipe, pinch in, pinch out). The activity information includes information about the amount of activity (e.g., number of steps, distance traveled, calories burned, heart rate) of the user using the mobile terminal 200, and for example, the amount of activity collected by a wearable device worn by the user can be acquired by a healthcare app or the like on the mobile terminal 200.

[0075] In step S200, terminal information, line-of-sight information, operation information, or activity information is received from the mobile terminal 200.

[0076] Next, the process proceeds to step S202, where the degree of attention that the user has paid to the V signboard is calculated based on the received terminal information, line-of-sight information, operation information, or activity information. As a method for calculating the degree of attention, for example, the following configuration can be adopted.

[0077] 1. Configuration for calculating attention level based on device information (1) Calculation of attention level based on location information The system analyzes the user's route based on location information and calculates the time spent within the V sign's display area. The attention level is calculated based on the time spent there. The longer the time spent there, the higher the calculated value of the attention level.

[0078] (2) Calculation of attention level based on acceleration information The fluctuation range of acceleration in a certain time window is calculated. If the fluctuation range continues to be equal to or less than a predetermined value, it is determined that the mobile terminal 200 is stationary, and the time during which it is determined to be stationary is calculated. The attention level is calculated based on the time of stationary. The longer the time of stationary, the higher the calculated value of the attention level.

[0079] (3) Calculation of attention level based on gyro information The attitude of the mobile terminal 200 is analyzed based on the gyro information, and the direction maintenance time during which the mobile terminal 200 maintains an orientation that matches the display direction of the V signboard is calculated. The attention level is calculated based on the direction maintenance time. The longer the direction maintenance time, the higher the calculated attention level.

[0080] (4) Calculating attention levels based on multiple pieces of information The attention level can also be calculated based on a combination of two or more of the information used to calculate the attention level in (1) to (3).

[0081] 2. Configuration for calculating attention level based on gaze information (1) Calculation of attention level based on dwell time Based on the line-of-sight information, the time that the line of sight remains on the V signboard on the display screen is calculated. The attention level is calculated based on the time of the line of sight. The longer the time of the line of sight, the higher the calculated value of the attention level.

[0082] (2) Calculation of attention level based on gaze movement patterns Based on the gaze information, the speed, distance, or trajectory of gaze movement relative to the V-sign on the display screen is analyzed to detect gaze movement patterns (for example, looking at the entire V-sign evenly, or concentrating on a specific part). The attention level is calculated based on the gaze movement pattern. For example, if the viewer looks at the entire V-sign slowly, the attention level is high, and if the viewer only looks quickly at one point, the attention level is low.

[0083] (3) Calculating attention level based on a combination of gaze and operation When a user is looking at the V signboard (their line of sight is on the V signboard on the display screen) and performs an operation such as tapping, swiping, pinching in, or pinching out, the attention level is increased based on the operation. For example, an additional value is set according to the operation, such as +1 for a tap and +2 for a pinch out. This allows the attention level to reflect the user's active interaction, rather than simply looking at the V signboard.

[0084] (4) Calculating attention levels by combining gaze and emotion analysis The system analyzes the user's facial expressions captured by the camera of the mobile terminal 200 in real time to detect expressions that show interest or concern (e.g., smiles, frowns, etc.). If these positive emotions are detected while the user is looking at the V signboard, the attention level is increased. By combining the results of the emotion analysis with the gaze information, a higher attention level is assigned if the user is likely to have a positive interest in the V signboard. For example, if a smile is detected while gazing at the V signboard, the attention level is weighted by doubling.

[0085] (5) Calculating attention levels based on multiple pieces of information The attention level can also be calculated based on a combination of two or more of the information used to calculate the attention level in (1) to (4). For example, one possible method is to weight the dwell time to 0.4, the eye movement pattern to 0.3, the operation content to 0.2, and the emotion analysis result to 0.1, and then multiply each piece of information by a weight and add them up. This makes it possible to calculate the attention level from a more multifaceted perspective that cannot be captured by a single piece of information alone.

[0086] 3. Configuration for calculating attention level based on operation information (1) Calculation of attention level based on the number of operations Based on the operation information, the number of operations by the user such as tapping on the V signboard on the display screen is calculated. The attention level is calculated based on the number of operations. The more operations there are, the higher the calculated attention level is.

[0087] (2) Calculation of attention level based on operation time Based on the operation information, the operation time during which the user taps on the V signboard on the display screen is calculated. The attention level is calculated based on the operation time. The longer the operation time, the higher the calculated attention level.

[0088] (3) Calculation of attention level based on operation patterns Based on the operation information, the operation pattern of the V signboard on the display screen is detected. The attention level is calculated based on the operation pattern. The more a specific operation pattern (for example, tapping to display details, pinching in to enlarge the display, or pinching in after tapping) is used, the higher the calculated attention level is.

[0089] (4) Calculating attention levels based on multiple pieces of information The attention level can also be calculated based on a combination of two or more of the information used to calculate the attention level in (1) to (3).

[0090] 4. Configuration for calculating attention level based on activity information (1) Calculation of attention level based on number of steps and time spent The number of steps taken by the user is calculated based on the activity information. The duration of stay is also calculated as described in 1(1) above. The attention level is then calculated based on the number of steps and duration of stay. For example, if the duration of stay is a certain period of time or more and the number of steps taken during the stay is small, the attention level is calculated as a high value.

[0091] (2) Calculation of attention level based on movement distance and movement speed The distance traveled by the user is calculated based on the activity information. The speed of movement is calculated based on the location information. The attention level is then calculated based on the distance traveled and the speed of movement. For example, if the speed of movement decreases as the user approaches the display range of the V signboard, and the user temporarily stops or moves extremely slowly within the display range, the attention level is calculated as a high value.

[0092] (3) Calculation of attention level based on calorie consumption and location information The system calculates the user's calorie consumption based on activity information. The attention level is calculated based on calorie consumption and location information. For example, if the increase in calorie consumption temporarily stagnates or decreases within the display range of the V sign, it is possible that the user's attention has been drawn to some object, causing a decrease in activity, and the attention level is calculated as a high value.

[0093] (4) Calculation of attention level based on heart rate and time spent The user's heart rate is calculated based on the activity information. The time spent there is also calculated as described in 1(1) above. The attention level is then calculated based on the heart rate and the time spent there. For example, the heart rate before and after entering the display range of the V sign is compared, and if a significant change (e.g., an increase or a temporary decrease) is observed, it is possible that there was an emotional reaction to the V sign, and the attention level is calculated as a high value.

[0094] (5) Calculating attention levels based on multiple pieces of information The attention level can also be calculated based on a combination of two or more of the information used to calculate the attention level in (1) to (4).

[0095] Next, the process proceeds to step S204, where the user's favorability rating for the V signboard is calculated based on the received terminal information, line-of-sight information, operation information, or activity information. As a method for calculating the favorability rating, for example, the following configuration can be adopted.

[0096] 1. Configuration for calculating favorability based on device information (1) Calculation of favorability based on location information The user's route is analyzed based on location information, and the time spent within the V sign's display area is calculated. The favorability rating is calculated based on the time spent there. The longer the time spent there, the higher the favorability rating is calculated.

[0097] (2) Calculation of favorability based on acceleration information The fluctuation range of acceleration in a certain time window is calculated. If the fluctuation range continues to be equal to or less than a predetermined value, it is determined that the mobile terminal 200 is stationary, and the time during which it is determined to be stationary is calculated. The favorability rating is calculated based on the time of stationary. The longer the time of stationary, the higher the value of the favorability rating calculated.

[0098] (3) Calculation of favorability based on gyro information The attitude of the mobile terminal 200 is analyzed based on the gyro information, and the direction maintenance time during which the mobile terminal 200 maintains an orientation that matches the display direction of the V signboard is calculated. The favorability rating is calculated based on the direction maintenance time. The longer the direction maintenance time, the higher the value of the favorability rating is calculated.

[0099] (4) Calculating favorability based on multiple pieces of information The favorability rating can also be calculated based on a combination of two or more pieces of information used to calculate the favorability rating in (1) to (3).

[0100] 2. Configuration for calculating favorability based on gaze information (1) Calculating favorability based on dwell time Based on the line-of-sight information, the time that the line of sight remains on the V signboard on the display screen is calculated. The favorability rating is calculated based on the time of the line of sight. The longer the time of the line of sight, the higher the value of the favorability rating is calculated.

[0101] (2) Calculation of favorability based on gaze movement patterns Based on the gaze information, the speed, distance, or trajectory of gaze movement relative to the V sign on the display screen is analyzed to detect gaze movement patterns (for example, looking at the entire V sign evenly, or concentrating on a specific part). The likeability rating is calculated based on the gaze movement pattern. For example, if the viewer looks at the entire V sign slowly, the likeability rating will be high, and if the viewer only looks quickly at one point, the likeability rating will be low.

[0102] (3) Calculating favorability based on a combination of gaze and operation When a user is looking at the V signboard (their line of sight is on the V signboard on the display screen) and performs an operation such as tapping, swiping, pinching in, or pinching out, the favorability rating is increased based on the operation. For example, an additional value is set according to the operation, such as +1 for a tap and +2 for a pinch out. This allows the favorability rating to reflect the user's active interaction, rather than simply looking at the V signboard.

[0103] (4) Calculating favorability by combining gaze and emotion analysis The system analyzes the user's facial expressions captured by the camera of the mobile terminal 200 in real time to detect expressions that show interest or concern (e.g., smiles, frowns, etc.). If these positive emotions are detected while the user is looking at the V signboard, the system increases the likeability rating. By combining the results of the emotion analysis with the gaze information, a higher likeability rating is assigned if the user is likely to have a positive interest in the V signboard. For example, if a smile is detected while gazing at the V signboard, the likeability rating is weighted by doubling.

[0104] (5) Calculation of favorability based on multiple pieces of information The favorability rating can also be calculated based on a combination of two or more of the information used to calculate the favorability rating in (1) to (4). For example, one possible method would be to weight the dwell time to 0.4, the eye movement pattern to 0.3, the operation content to 0.2, and the emotion analysis result to 0.1, and then multiply each piece of information by a weight and add them up. This makes it possible to calculate the favorability rating from a more multifaceted perspective than can be captured by a single piece of information alone.

[0105] 3. Configuration for calculating favorability based on operation information (1) Calculation of favorability based on the number of operations Based on the operation information, the number of operations by the user such as tapping on the V signboard on the display screen is calculated. The favorability rating is calculated based on the number of operations. The more operations there are, the higher the favorability rating is calculated as the value.

[0106] (2) Calculation of favorability based on operation time Based on the operation information, the operation time during which the user taps on the V signboard on the display screen is calculated. The favorability rating is calculated based on the operation time. The longer the operation time, the higher the favorability rating is calculated.

[0107] (3) Calculation of favorability based on operation patterns Based on the operation information, the operation pattern of the V signboard on the display screen is detected. The favorability rating is calculated based on the operation pattern. The more specific operation patterns (e.g., tapping for detailed display, pinching in for enlarged display, pinching in after tapping) are used, the higher the favorability rating is calculated.

[0108] (4) Calculating favorability based on multiple pieces of information The favorability rating can also be calculated based on a combination of two or more pieces of information used to calculate the favorability rating in (1) to (3).

[0109] 4. Configuration for calculating favorability based on activity information (1) Calculation of favorability based on number of steps and time spent The number of steps taken by the user is calculated based on the activity information. The duration of stay is also calculated as described in 1(1) above. The favorability rating is then calculated based on the number of steps and duration of stay. For example, if the duration of stay is a certain time or more and the number of steps taken during the stay is small, the favorability rating is calculated as a high value.

[0110] (2) Calculation of favorability based on movement distance and movement speed The distance traveled by the user is calculated based on the activity information. The speed of travel is calculated based on the location information. The favorability rating is then calculated based on the distance traveled and the speed of travel. For example, if the user's speed decreases as they approach the display range of the V signboard, and they temporarily stop or move extremely slowly within the display range, the favorability rating is calculated as a high value.

[0111] (3) Calculation of favorability based on calorie consumption and location information The system calculates the user's calorie consumption based on activity information. The likeability rating is calculated based on calorie consumption and location information. For example, if the increase in calorie consumption temporarily stagnates or decreases within the display range of the V sign, it is possible that the user's attention has been drawn to some object, causing a decrease in activity, and the system calculates the likeability rating as a high value.

[0112] (4) Calculation of favorability based on heart rate and stay time The user's heart rate is calculated based on the activity information. The time spent is also calculated as described in 1(1) above. The likeability rating is then calculated based on the heart rate and time spent. For example, the heart rate before and after entering the display range of the V sign is compared, and if a significant change (e.g., an increase or a temporary decrease) is observed, it is possible that there was an emotional reaction to the V sign, and the likeability rating is calculated as a high value.

[0113] (5) Calculation of favorability based on multiple pieces of information The favorability rating can also be calculated based on a combination of two or more pieces of information used to calculate the favorability rating in (1) to (4).

[0114] Next, the process proceeds to step S206, where a record is registered in the advertising history table 410 based on the terminal information, gaze information, operation information, or activity information received in step S200 and the attention level and favorability level calculated in steps S202 and S204, and the process ends.

[0115] The attention level or favorability level can be displayed on the advertiser terminal together with the V signboard in response to a display request from the advertiser terminal.

[0116] [Advertisement proposal processing] Next, the case of improving an advertisement will be described. FIG. 8 is a flowchart showing the advertisement suggestion process.

[0117] The CPU 30 starts a predetermined program stored in a predetermined area of ​​the ROM 32, and in accordance with the program, executes the advertisement proposal process shown in the flowchart of Fig. 8. The advertisement proposal process is a process executed in response to a proposal request from an advertiser terminal, and when executed by the CPU 30, the process first proceeds to step S250 as shown in Fig. 8.

[0118] In step S250, advertising information corresponding to the advertiser's advertiser ID is searched from the advertising table 404, and the corresponding AR content data is read from the storage device 42.Then, in step S252, landscape information corresponding to the location information (latitude and longitude) of the V signboard from the retrieved advertising information is searched from the landscape table 406, and the process proceeds to step S254.

[0119] In step S254, a request including a request to propose the content or installation location of the V signboard to enhance the scenic effect is sent to the generation AI server 120. The request includes the advertising information and AR content data retrieved and read in step S250, and the scenic information retrieved in step S252.

[0120] Next, proceed to step S256, where response information is received from the generation AI server 130 in response to the request sent in step S254, and proceed to step S258, where, based on the received response information, proposed information regarding the content or installation location of the V signboard to be changed is sent to the advertiser terminal, and the series of processes is completed.

[0121] As a method for proposing a V signboard, for example, the following configuration can be adopted. 1. Harmony with the surrounding environment (1) Color suggestions The AI ​​model analyzes the surrounding environment and proposes colors for the V sign that conform to the landscape standards. The analysis of the surrounding environment can be performed in cooperation with a street view service, etc. For example, it proposes calm colors for historic cityscapes and earth tones for places rich in nature. In this case, the request to the generation AI server 120 includes a generation request to perform these operations. The same applies to (2), (3), and 2 to 4 below.

[0122] (2) Proposal of shape or texture The AI ​​model analyzes the surrounding environment and proposes shapes and textures for V-signs that conform to landscape standards. For example, in areas with many Japanese-style buildings, it proposes shapes and textures using wood and washi paper, while in areas with many modern buildings, it proposes shapes and textures using metal and glass.

[0123] (3) Brightness suggestions The AI ​​model analyzes the surrounding environment at night and proposes lighting brightness and color temperature for the V sign to comply with landscape standards. It takes into consideration the nighttime landscape, reduces unnecessary light output, and minimizes impact on the surrounding environment.

[0124] 2. Visibility and information transmission (1) Gaze analysis The AI ​​model analyzes the gaze of passersby within the V sign's display range and suggests the most effective content or location for the V sign. For example, it uses eye tracking with passersby's smartphone cameras to suggest displaying important information where passersby's eyes naturally go, or suggesting ways to catch the information while waiting at a traffic light.

[0125] (2) Readability optimization The AI ​​model optimizes text size, font, line spacing, etc., and suggests content that is easy to read even from a distance, with particular consideration given to the elderly and visually impaired.

[0126] (3) Multilingual support In tourist areas, the AI ​​model analyzes the nationalities of tourists within the area where the V sign is displayed and suggests information in multiple languages ​​as the content of the V sign. The AI ​​model can also suggest translation accuracy.

[0127] 3. Reflection of regional characteristics (1) Incorporating local culture The AI ​​model suggests information about the region's history, culture, and local specialties as content for the V sign, bringing out the unique charm of the region.

[0128] (2) Linking with event information The AI ​​model suggests information about local events and seasonal information as content for the V sign, attracting the interest of tourists and residents.

[0129] (3) Cooperation with local residents The AI ​​model will suggest the content and location of the V sign based on feedback from local residents, including through surveys and social media.

[0130] 4.Improvement (1) Effectiveness measurement and optimization The AI ​​model evaluates the visibility and effectiveness of V-signs and proposes improvements to the content or location of V-signs, for example by analyzing passersby's time spent on the sign, their behavioral patterns, and reactions on social media.

[0131] (2) Design diversity The AI ​​model presents multiple V-sign design proposals and predicts the effectiveness of each.

[0132] (3) Landscape simulation This simulates the landscape when a V-sign is actually installed, allowing you to check the impact on the landscape before installation.

[0133] FIG. 9 shows the display screen of the advertiser terminal. When the advertiser terminal accesses the V signboard providing server 100 to receive a V signboard proposal, an image of the area where the V signboard is installed is displayed, as shown in Figure 9. Proposals for attention level, favorability rating, content of the V signboard, and installation location are also displayed. The advertiser can use this as a reference to change the content or installation location of the V signboard.

[0134] [Charging process] Next, the case where billing is performed will be described. FIG. 10 is a flowchart showing the billing process.

[0135] The CPU 30 starts a predetermined program stored in a predetermined area of ​​the ROM 32, and in accordance with the program, executes the billing process shown in the flowchart of Fig. 10. The billing process is executed at predetermined billing times (for example, on a predetermined day of each month), and when executed by the CPU 30, the process first proceeds to step S300 as shown in Fig. 10.

[0136] In step S300, the advertiser ID of the advertiser to be charged is searched from advertiser table 400, and the process proceeds to step S302, where the charging setting information corresponding to the found advertiser ID is searched from charging table 408, and the process proceeds to step S304.

[0137] In step S304, the advertising history information corresponding to the advertiser ID retrieved in step S300 is searched from the advertising history table 410, and the process proceeds to step S306, where the charging amount is calculated based on the charging setting information and advertising history information retrieved in steps S302 and S304, and the process proceeds to step S308.

[0138] In step S308, payment processing is carried out based on the calculated charge amount, and the series of processing steps is terminated.

[0139] 〔effect〕 Next, the effects of this embodiment will be described. In this embodiment, the V signboard providing server 100 receives location information of the mobile terminal 200, acquires AR content data and anchor information of V signs installed within a predetermined range from the location of the mobile terminal 200 based on the received location information, and transmits the acquired AR content data and anchor information to the mobile terminal 200. It also receives terminal information and the like, and calculates the degree of attention that the user has paid to the V signboard based on the received terminal information and the like.

[0140] This allows advertisements to be evaluated more effectively than ever before. Furthermore, in this embodiment, the V signboard providing server 100 calculates the user's favorability rating for the V signboard based on the received terminal information and the like.

[0141] This allows the advertisement to be evaluated. Furthermore, in this embodiment, the V signboard providing server 100 estimates the content or installation location of the V signboard based on the received terminal information, etc., so as to enhance the scenic effect, and suggests the content or installation location of the V signboard based on the estimation result.

[0142] This allows for improvements to be made to the advertisements. In this embodiment, the storage device 42 corresponds to the storage means of invention 1, 5 or 6, step S150 corresponds to the location information receiving means of invention 1, 5 or 6, step S152 corresponds to the virtual sign information acquiring means of invention 1, 5 or 6, and step S154 corresponds to the virtual sign information transmitting means of invention 1, 5 or 6. Also, step S200 corresponds to the terminal information acquiring means of inventions 1 to 3, 5 or 6, step S202 corresponds to the attention level calculating means of invention 1, step S204 corresponds to the favorability level calculating means of invention 2 or 5, and steps S254 and S256 correspond to the estimation means of invention 3 or 6.

[0143] In this embodiment, step S258 corresponds to the proposed means of invention 3 or 6.

[0144] [Modification] In the above embodiment and its variants, the V signboard providing server 100 estimated the content or installation location of the V signboard based on the terminal information of the mobile terminal 200, etc., so as to enhance the scenic effect, but this is not limited to this, and the following configuration can also be adopted.

[0145] The first configuration estimates the content or installation location of a V signboard based on the AR content data and anchor information of the V signboard to enhance the scenic effect.

[0146] The second configuration estimates the content or installation location of the V signboard based on terminal information of the mobile terminal 200, etc., to enhance advertising effectiveness, customer experience, engagement, and brand image.

[0147] The third configuration estimates the content or installation location of the V signboard based on the AR content data and anchor information of the V signboard to enhance advertising effectiveness, customer experience, engagement, and brand image.

[0148] Furthermore, in the above embodiment and its modified examples, the content or installation location of the V signboard is estimated using an AI model, but this is not limiting and estimation can be performed using any method.

[0149] Furthermore, in the above embodiment and its variations, the generation AI server 120 may be configured with the functions 56 to 66 integrated as in the above embodiment, or some of the functions may be configured by a separate server or the like.

[0150] Furthermore, in the above embodiment and its modifications, the system is realized as a network system, but the present invention is not limited to this and can be realized as a single device or application.

[0151] Furthermore, in the above embodiment and its modifications, the case where the present invention is applied to a network system consisting of the Internet 199 has been described, but the present invention is not limited to this, and may be applied, for example, to a so-called intranet that communicates using the same method as the Internet 199. Of course, the present invention is not limited to a network that communicates using the same method as the Internet 199, and may be applied to a network of any communication method.

[0152] Furthermore, in the above embodiment and its variants, when executing the processes shown in the flowcharts of Figures 5 to 8 and 10, the case where a program pre-stored in ROM 32 is executed has been described, but this is not limited to this, and the program showing these procedures may be read into RAM 34 from a storage medium on which the program is stored and executed.

[0153] In the above embodiment and its modifications, the present invention is applied to the case where a V signboard is provided, but it is not limited to this and can be applied to other cases without departing from the spirit of the present invention. For example, instead of a V signboard, a sign, a symbol, or other display can be provided virtually. [Explanation of symbols]

[0154] 100...V signboard providing server, 30...CPU, 32...ROM, 34...RAM, 38...I / F, 39...bus, 40...input device, 42...storage device, 44...display device, 120...generation AI server, 50...basic model, 52...basic model control unit, 54...RDS, 56, 64...request receiving unit, 58...prompt generating unit, 60...prompt processing unit, 62...answer information sending unit, 66...reference information registration unit, 200...mobile terminal, 199...Internet, 400...advertising Main The Table, 402...store Pavilion Table 404: Advertisement table, 406: Scenery table, 408: Charge setting table, 410: Advertisement history table

Claims

1. A virtual sign system communicably connected to a mobile terminal having a camera, a location information receiving means for receiving location information of the mobile terminal; a virtual sign information acquiring means for acquiring, based on the location information received by the location information receiving means, virtual sign information and installation location information of the virtual sign installed within a predetermined range from the location of the mobile terminal from a storage means for storing virtual sign information, which is content data for configuring a virtual sign, and installation location information indicating the installation location of the virtual sign in a virtual space corresponding to a real space; a virtual sign information transmitting means for transmitting the virtual sign information and installation location information acquired by the virtual sign information acquiring means to the mobile terminal; a request input means for inputting a request to the trained AI model, the request including the virtual sign information and landscape information indicating a landscape standard, and requesting the generation of a proposed change to the content of the virtual sign so as to conform to the landscape standard; an answer information acquisition means for acquiring answer information from the AI ​​model, the answer information being a result of the AI ​​model inferring content of a new virtual sign, including color, shape, texture, brightness, or color temperature, as a proposed change to make the content of the virtual sign conform to the landscape standard, in response to the input of the request; A virtual sign system characterized by comprising a proposal means for providing the content of the new virtual sign indicated by the answer information acquired by the answer information acquisition means as proposal information indicating the content of the virtual sign to be changed.

2. In claim 1, the request input means inputs a request to the AI ​​model, the request including the virtual sign information, the installation position information, and the landscape information, requesting the generation of a proposal to change the content and installation position of the virtual sign so as to conform to the landscape standard; The answer information acquisition means acquires, in response to the input of the request, answer information from the AI ​​model, which is a result of the AI ​​model inferring content and installation position of a new virtual sign, including color, shape, texture, brightness, or color temperature, as a proposed change to make the content and installation position of the virtual sign conform to the landscape standard; A virtual sign system characterized in that the proposal means provides the content and installation location of the new virtual sign indicated by the response information acquired by the response information acquisition means as proposal information indicating the content of the virtual sign to be changed.

3. In any one of claims 1 and 2, a terminal information acquiring means for acquiring terminal information indicating the movement or stay state of the mobile terminal, gaze information indicating the behavior of the user's gaze with respect to the virtual sign on a display screen displayed on the mobile terminal based on the virtual sign information and the location information, operation information indicating the manner of operation of the user with respect to the virtual sign on the display screen, or activity information indicating the amount of activity of the user within the predetermined range; A virtual sign system characterized by comprising: (1) calculating the time the mobile terminal stays in the display range of the virtual sign based on terminal information acquired by the terminal information acquisition means, etc.; (2) calculating the time the gaze stays on the virtual sign based on gaze information acquired by the terminal information acquisition means, etc.; (3) calculating the number or time of operations on the virtual sign based on operation information acquired by the terminal information acquisition means, etc.; or (4) calculating the time the mobile terminal stays in the display range of the virtual sign based on activity information acquired by the terminal information acquisition means, etc., and calculating an index for evaluating the virtual sign based on the calculation result.

Images