JP7420307B1 - Display system, information processing device, evaluation method, and computer-readable recording medium - Google Patents

Abstract

The present invention provides a display system, an information processing device, an evaluation method, and a recording medium that are advantageous in accurately evaluating the effectiveness of content displayed in a facility for users. A display system 100 that displays information on a floor or a wall includes a first content display device 10 that displays first content at a first position P1 in a facility to induce a predetermined action by a user. , a first imaging device 12 that outputs first image data capturing images of users around the first position, and a first imaging device 12 that outputs first image data capturing images of users around the first position, and a second imaging device 12 that outputs images of users around second positions P2a and P2b that are different from the first position in the facility. A second imaging device 22a, 22b outputs two image data, analyzes the user's behavior based on the first image data and the second image data, and controls the display of the first content based on the analyzed user's behavior. and a content server 30 for determining validity. [Selection diagram] Figure 1

Description

The present disclosure relates to a technology for a display system that displays information on a floor or wall.

Patent Document 1 discloses a technology related to a projection system. This projection system displays product information on a first projection device installed in a shopping mall, for example, and identifies people who are interested in the projected image based on the stop time of the person viewing the projected image. Then, the projection system guides the identified person to a store etc. that sells the product using a floor display using the second projection device.

JP2021-89436A

With the technique disclosed in Patent Document 1, the installer of the projection system cannot determine whether the dynamic content projected and displayed within the facility is effective for the user.

The present disclosure has been made in order to solve the above-mentioned problems, and aims to provide technology that is advantageous in accurately evaluating the effectiveness of content displayed in facilities for users. shall be.

The display system of the present disclosure includes a first content display device that displays first content for inducing a predetermined action by a user at a first position in a facility, and a first content display device that images users around the first position. A first imaging device that outputs one image data, a second imaging device that outputs second image data that captures an image of a user in the vicinity of a second location different from the first location in the facility, and a second imaging device that outputs the first image data and an analysis section that analyzes the user's behavior based on the second image data; a judgment section that judges the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis section; a content server comprising: an alternative content generation unit that generates alternative content to be displayed in a first position in place of the first content when it is determined that display of the content is not effective ; The alternative content generation unit acquires the first content, the first image data, and the second image data. The data acquisition unit includes a data acquisition unit, and an inference unit that uses the learned model to output alternative content based on the first image data, second image data, and first content acquired by the data acquisition unit.
The display system of the present disclosure also includes a first content display device that displays first content at a first position in a facility to induce a predetermined action by a user, and a first content display device that images users around the first position. a first imaging device that outputs first image data that captures images of a user at a second location in the facility that is different from the first location; Content that includes an analysis section that analyzes the user's behavior based on the data and the second image data, and a judgment section that determines the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis section. The analysis unit includes a server and a second content display device that displays second content in a second position to induce a predetermined action by the user, and the analysis unit includes at least one of the first image data and the second image data. or configured to analyze the attributes of the user based on both, and the determination unit is configured to determine the effectiveness of displaying the second content based on the attributes and behavior of the user analyzed by the analysis unit. It is something that will be done.

Further, the information processing device of the present disclosure is an information processing device that is displayed to a user at a first position in a facility and determines the effectiveness of first content for inducing a predetermined action by the user. the at least one processor; and a memory storing at least one program; the at least one processor executes the at least one program to generate a first image of a user around the first position; Acquisition processing that acquires one image data and second image data of a user in the vicinity of a second position different from the first position in the facility; an analysis process for analyzing behavior; a judgment process for determining the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis process; In this case, the alternative content generation process is configured to execute an alternative content generation process that generates an alternative content to be displayed in the first position instead of the first content, and the alternative content generation process includes the first content, the first image data, and the first image data. The acquired first image data is acquired using a learned model generated in advance by learning the relationship between the first content, the first image data, the second image data, and the alternative content. This includes a process of outputting alternative content based on the image data, the second image data, and the first content .
Further, the information processing device of the present disclosure is an information processing device that is displayed to a user at a first position in a facility and determines the effectiveness of first content for inducing a predetermined action by the user. the at least one processor; and a memory storing at least one program; the at least one processor executes the at least one program to cause the first content to be displayed in the vicinity of the first location; The first image data of the user and the user in the vicinity of the second position, which is a different position from the first position in the facility and where the second content for inducing the user to take a predetermined action, is displayed. an acquisition process that acquires second image data obtained by capturing the image; an analysis process that analyzes the user's behavior based on the first image data and the second image data; and an analysis process that analyzes the user's behavior based on the user's behavior analyzed by the analysis process. and a determination process for determining the effectiveness of displaying the first content, and the analysis process analyzes attributes of the user based on at least one or both of the first image data and the second image data. The determination process is configured to determine the effectiveness of displaying the second content based on the attributes and behavior of the user analyzed by the analysis process.

Further, the evaluation method of the present disclosure includes an evaluation that is executed by a computer, is displayed to a user at a first position in a facility, and evaluates the effectiveness of the first content for inducing a predetermined action by the user. The method includes an acquisition step of acquiring first image data capturing images of users around a first location and second image data capturing images of users surrounding a second location different from the first location in the facility. an analysis step for analyzing the user's behavior based on the first image data and the second image data; and a judgment for determining the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis step. and an alternative content generation step for generating alternative content to be displayed in the first position instead of the first content when it is determined in the judgment step that displaying the first content is not effective, the alternative content generation step , a step of acquiring first content, first image data, and second image data, and learning generated in advance by learning the relationship between the first content, first image data, and second image data, and alternative content. and outputting alternative content based on the acquired first image data, second image data, and first content using the acquired model .
Furthermore, the evaluation method of the present disclosure includes an evaluation that is executed by a computer, is displayed to the user at a first position in the facility, and evaluates the effectiveness of the first content for inducing a predetermined action by the user. The method includes an acquisition step of acquiring first image data capturing images of users around a first location and second image data capturing images of users surrounding a second location different from the first location in the facility. an analysis step for analyzing the user's behavior based on the first image data and the second image data; and a judgment for determining the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis step. and a step of displaying second content in a second position for inducing a predetermined action by the user, and the analyzing step is based on at least one or both of the first image data and the second image data. The determination step is configured to determine the effectiveness of displaying the second content based on the user attributes and behavior analyzed in the analysis step. be.

Furthermore, the computer-readable recording medium of the present disclosure is displayed to a user at a first location in a facility, and is configured to determine the effectiveness of the first content for inducing a predetermined action by the user. A computer-readable recording medium that records a program to be executed by a computer, the program includes first image data of a user in the vicinity of a first location and a second location in the facility different from the first location. Obtaining second image data of surrounding users, analyzing the user's behavior based on the first image data and second image data, and displaying the first content based on the analyzed user's behavior. If it is determined that the display of the first content is not valid, the first content, first image data, and second image data are acquired, and the first content, first image data, and second image data are The first image data, the second image data, and the first image data obtained using a learned model generated in advance by learning the relationship between The computer is configured to cause a computer to generate alternative content based on the content .
Further, the computer-readable recording medium of the present disclosure is displayed to a user at a first position in a facility, and is configured to determine the effectiveness of the first content for inducing a predetermined action by the user. A computer-readable recording medium that records a program to be executed by a computer, the program includes first image data of a user in the vicinity of a first location and a second location in the facility different from the first location. Obtaining second image data of surrounding users, analyzing the user's behavior based on the first image data and second image data, and displaying the first content based on the analyzed user's behavior. the user's attributes based on at least one or both of the first image data and the second image data. The computer is configured to analyze the content and determine the effectiveness of displaying the second content based on the analyzed attributes and behavior of the user.

According to the technology of the present disclosure, it is possible to accurately evaluate the effectiveness of content displayed in a facility for users.

FIG. 1 is a diagram illustrating a configuration example of a display system in an embodiment. FIG. 1 is a block diagram showing an example of the configuration of a display system according to an embodiment. FIG. 2 is a block diagram showing functions realized by a processor of the content server executing a program. FIG. 7 is a diagram for explaining a specific example of determination processing. FIG. 3 is a diagram for explaining a first example of determination processing. It is a figure for explaining the second example of judgment processing. FIG. 7 is a diagram for explaining a third specific example of determination processing. FIG. 2 is a functional block diagram showing internal functions of an alternative content generation section. 3 is a flowchart showing a routine of alternative content generation processing executed in an alternative content generation unit. FIG. 2 is an internal block diagram showing internal functions of a model learning section. 3 is a flowchart of a routine executed in the display system of the embodiment. FIG. 7 is a diagram illustrating a modified example of hardware resources of a content server.

Embodiments will be described below with reference to the drawings. Note that common elements in each figure are denoted by the same reference numerals, and redundant explanations will be omitted.

Embodiment.
1. Outline of Display System in Embodiment FIG. 1 is a diagram illustrating a configuration example of a display system in an embodiment. The display system 100 displays content consisting of drawings, characters, or a combination thereof on the floor or wall surface of a facility for purposes such as advertising, guidance, or alerting users of the facility, and displays the content of the displayed content. It is a system that evaluates effectiveness for users. Here, displaying the content on the floor or wall may be done by displaying the content on a display installed on the floor or wall, or by projecting the content onto the floor or wall using a projection device. It may be displayed. Furthermore, the content may be still image content, or may be video content that has a video material or animation effect on part or all of it. Furthermore, examples of advertisements include advertisements for products, stores, and the like. Further, examples of the guidance or warning here include a display indicating a guide direction within the facility, a display indicating that passage is not allowed, and the like. Facilities include airport facilities, stations, commercial facilities, hospitals, etc. In the following description, an example will be described in which the display system 100 guides or calls attention to the inside of a commercial facility, and the display is based on a projection display.

The display system 100 includes a first content display device 10, a first imaging device 12, a second content display device 20, a second imaging device 22, and a content server 30.

The first content display device 10 is a device that projects and displays first content on a first position on a floor within a facility. There are no limitations on the projection method and structure of the first content display device 10. The first content is for inducing a predetermined action by the user. For example, if the predetermined action is "go straight and turn right," the content for inducing such a predetermined action within the facility may be the first content shown in Figure 1, such as "go straight and turn right." Display a curved arrow. Further, when the predetermined action is "going straight and turning left", an arrow (not shown) pointing to going straight and turning left is displayed as content for guiding such action within the facility.

The first imaging device 12 is a camera installed to capture an image of the first position P1 where the first content is displayed and its surroundings. The first imaging device 12 periodically captures and outputs images of people at the first position P1 and its surroundings. There are no limitations on the type, number, and installation location of the first imaging devices 12. The first imaging device 12 may be configured integrally with the first content display device 10. The image data captured by the first imaging device 12 is hereinafter referred to as "first image data." The first image data is not limited to still image data, but may be moving image data. The first image data is transmitted to the content server 30 via a communication network 8 such as the Internet.

The second content display device 20 is a device that projects and displays second content at a second position on a floor within the facility, which is different from the first position. There are no limitations on the number of second content display devices 20, installation locations, projection methods, and structures thereof. In the example shown in FIG. 1, two second content display devices 20a and 20b are installed as the second content display device 20. The second content display device 20a projects and displays the second content (OK) at a second position P2a in the middle of the guidance route guided by the first content. The second content is also for inducing a predetermined action by the user. "Second content (OK)" here is, for example, when a predetermined action is "go straight", the content for guiding such a predetermined action in the facility, for example, indicates the straight direction with an arrow. Show display.

The second content display device 20b projects and displays the second content (NG) at a second position P2b in the middle of a route that deviates from the guidance route guided by the second content. "Second content (NG)" here is, for example, when the predetermined action is "stop", content for guiding such a predetermined action in the facility, for example, if the direction of travel is the wrong direction. Displays an “x” to indicate that the item is present.

The second imaging device 22 is a camera installed to capture an image of a range including the second position P2 where the second content is displayed and its surroundings. The second imaging device 22 periodically captures and outputs images of people at the second position P2 and its surroundings. There are no limitations on the type, number, and installation location of the second imaging device 22. In the example shown in FIG. 1, two second imaging devices 22a and 22b are installed as the second imaging device 22. The second imaging device 22a is installed so as to image a range including the second position P2a where the second content (OK) of the second content display device 20a is displayed and its surroundings. The second imaging device 22b is installed so as to image a range including the second position P2b where the second content (NG) of the second content display device 20b is displayed and its surroundings. Note that the second imaging devices 22a and 22b may be configured integrally with the second content display devices 20a and 20b, respectively. The image data captured by the second imaging device 22 will be referred to as "second image data" hereinafter. Moreover, when distinguishing the second image data imaged by the second imaging devices 22a and 22b, these are hereinafter referred to as "second image data (OK)" and "second image data (NG)." The second image data is not limited to still image data, and may be moving image data. The second image data is transmitted to the content server 30 via a communication network 8 such as the Internet.

The content server 30 receives image data periodically captured by the first imaging device 12 and the second imaging device 22. This process is hereinafter referred to as "acquisition process." The content server 30 obtains attribute information and behavior information by analyzing the user's attributes and behavior based on the acquired image data. This process is hereinafter referred to as "analysis process." Examples of the attribute information here include the user's gender, age, and the like. In addition, the behavior information here includes, for example, the user's location, length of stay, and moving direction. In the analysis process, for example, a tracking process technique called Person Re-Identification is used. An example of the tracking process will be described later. Note that although the case where the content server 30 analyzes the user's attributes and behavior based on the acquired image data is exemplified here, the content server 30 has only the function of analyzing the user's behavior. There may be.

Further, the content server 30 determines whether the displayed content is valid based on the user's behavior analyzed by the analysis process. In the analysis process, if attributes are further analyzed in addition to the user's behavior, the content server 30 displays information for each user's attribute based on the analyzed user's attributes and behavior. It may also be a method for determining whether the contents of the content currently available are valid. Furthermore, if attribute information of the target user of the content is available, that information may be further taken into consideration when determining the effectiveness of the content. This process is hereinafter referred to as "judgment process." Some examples of the determination process will be described later.

The content server 30 outputs the judgment result of the judgment process to the external server 4 of the system installer of the display system 100. This processing is hereinafter referred to as "output processing." In the output process, the content server 30 may output the determination result of the determination process to the external server 6 of the system installer of the display system installed in a facility of the same industry. This allows the system installer of the display system to collect information regarding the effectiveness of content displayed within the facility and its factors.

Furthermore, the content server 30 generates alternative content based on the determination result of the determination process. This process is hereinafter referred to as "alternative content generation process." The alternative content here is content that is more effective than the first content. For example, in the case of content where a destination is indicated by an arrow, content with an arrow thicker than the first content may be used as the alternative content. In this case, the alternative content can be said to be more useful than the primary content in the sense that it has higher visibility. In another example, the alternative content may be one in which the contrast between the arrow part and the background part of the first content is increased. Furthermore, if the arrow as the first content is difficult to understand and is not useful, text guidance may be used as an alternative content. Japanese or English may be used as alternative content for the text guidance. In the alternative content generation process, a trained model for inferring alternative content is used. The trained model here is a model that receives input of the first content, first image data, and second image data and outputs alternative content. The trained model is generated in advance by model learning processing. In the model learning process, a learned model is generated by performing machine learning on the relationship between the first content, first image data, second image data, and alternative content whose effectiveness for the user is known. The model learning process will be explained later.

The content server 30 reflects the alternative content output from the trained model as new content on the first content display device 10 or the second content display device 20. This process is hereinafter referred to as "reflection process."

According to the display system 100 as described above, it is possible to accurately evaluate the effectiveness of content displayed in a facility for users according to the user's attributes and actions.

2. Configuration of Display System FIG. 2 is a block diagram showing an example of the configuration of the display system according to the embodiment. The display system 100 includes the above-described first content display device 10, a first imaging device 12, one or more second content display devices 20, one or more second imaging devices 22, and a content server 30. Equipped with.

The content server 30 has the function of an information processing device as a computer. The content server 30 is provided within a facility to be controlled. Alternatively, the content server 30 may be provided in a remote location different from the facility to be controlled. As another example, the content server 30 may be realized by a server on the cloud. When the content server 30 is provided in a remote location, the content server 30 connects the first content display device 10, the first imaging device 12, the second content display device 20, and the second imaging device via a communication network 8 such as the Internet. Data is sent to or received from the device 22.

Content server 30 includes at least one processor 40 and at least one memory 50. The memory 50 as a storage device stores at least one program 52 executable by the processor 40, a learned model storage section 54, and various related data 60. The program 52 may be recorded on a computer-readable recording medium. Information on content that can be displayed on the first content display device 10 and the second content display device 20 is stored in advance in the data 60. The content information here includes the use of the content and its meaning. Examples of the meaning of the content include, for example, "destination" for guiding/warning purposes, and "what type of users is the target audience for" for advertising purposes.

Various processes by the processor 40 are realized by the processor 40 executing the program 52. FIG. 3 is a block diagram illustrating functions realized by a processor of the content server executing a program. As shown in FIG. 3, the processor 40 includes an acquisition section 41, an analysis section 42, a judgment section 43, an alternative content generation section 44, an output section 45, a model learning section 46, and a reflection section 47. Be prepared. The functions of the processor 40 will be described below with reference to FIG. 1 as well. Note that although the case where the processor 40 includes the model learning section 46 is illustrated here, the model learning section 46 is not an essential component of the processor 40. That is, the processor 40 may be configured to acquire a learned model from an external system and subject the acquired learned model to processing by the alternative content generation unit 44.

The acquisition unit 41 is a functional block for performing acquisition processing. In the acquisition process, the acquisition unit 41 acquires first image data and second image data from the first imaging device 12 and the second imaging device 22, respectively.

The analysis unit 42 is a functional block for performing analysis processing. In the analysis process, the analysis unit 42 estimates attributes such as gender and age of the user by performing an image analysis process on one or both of the acquired first image data and second image data. At this time, unique ID information may be assigned to each user, and information on the estimated attributes may be linked to the ID information and stored in the data 60 at any time.

In addition, in the analysis process, behavior information representing the user's behavior is acquired at any time through a tracking process using the acquired first image data and second image data. The tracking process may employ a known tracking process for acquiring user behavior information using image data. For example, in the tracking process, the analysis unit 42 uses a technique called Person Re-Identification. In Person Re-Identification, first, a person area containing a person is detected from the input image data. The image information of the person included in the detected person area is hereinafter referred to as "person image data." The detected person image data is input as a search query to a neural network model for Person Re-Identification.

Further, template image data of candidate destinations is input to the neural network model. The template image data is data in which unique ID information for identification is linked to person image data identified in past image data. In the neural network model, template image data of a candidate with the highest degree of similarity to person image data input as a search query is output as an output result. Furthermore, if there is no candidate template image data similar to the person image data, data in which new ID information is linked to the person image data is stored as part of the new template image data. The analysis unit 42 performs tracking processing using Person Re-Identification on each of the inputted image data along the time series, and stores the behavior information of each user in the data 60.

The determination unit 43 is a functional block for performing determination processing. In the determination process, the determination unit 43 determines whether the content of the first content is valid based on the user's attribute information and behavior information analyzed by the analysis unit 42.

FIG. 4 is a diagram for explaining a specific example of the determination process. In the example shown in this figure, there are three users in the area around the first position P1 where the first content is displayed at time T=t1. The attribute information and behavior information of the three users have been analyzed through analysis processing. In the example shown in FIG. 4, the attributes of the three users are male/elderly, male/child, and female/adult. The first content depicts a destination display with an arrow indicating guidance to go straight and turn right.

FIG. 5 is a diagram for explaining the first embodiment of the determination process. In the first specific example shown in FIG. 5, at time T=t2 after the state of time T=t1 shown in FIG. It shows how the user moved. The attribute information and behavior information of the three users have been analyzed through analysis processing.

In this way, in the analysis process, if it is determined that all three users around the first position have moved to the range around the second position P2a, the user can move in the correct direction according to the guidance provided by the first content. It can be said that it has moved. In this case, in the determination process, it is determined that the first content is content that is easy to understand for users of any attribute.

FIG. 6 is a diagram for explaining a second embodiment of the determination process. In the second specific example shown in FIG. 6, at time T=t3 after the state of time T=t1 shown in FIG. It shows how the user moved. The attribute information and behavior information of the three users have been analyzed through analysis processing.

In this way, in the analysis process, if it is determined that all three users around the first position have moved to the vicinity of the second position P2b, it is possible that the user did not follow the guidance provided by the first content and made a mistake. It can be said that it has moved in the direction. In this case, in the determination process, it is determined that the first content is content that is difficult for users of any attribute to understand.

In addition, in the analysis process, if it is determined that the user who moved to the area surrounding the second position P2b did not return after that, or if the user who moved to the area surrounding the second position P2b is determined to have a predetermined standard stay. If it is analyzed that the user has stayed longer than the specified time, it can be said that the second content has failed to guide the user. In this case, in the determination process, it is determined that the second content (NG) is content that is difficult for users of any attribute to understand.

FIG. 7 is a diagram for explaining a third specific example of determination processing. In the third specific example shown in FIG. 7, at time T=t4 after the state of time T=t1 shown in FIG. The figure shows how a male/elderly user and a female/adult user move around the second position P2a where the second content (OK) is displayed. The attribute information and behavior information of these three users have been analyzed through analysis processing.

In this way, in the analysis process, if it is analyzed that among the three users around the first position, only the male/child user has moved to the area around the second position P2b, then the male/child user based on the first content /It can be said that the attempt to induce children to use the service failed. In this case, in the determination process, it is determined that the first content is content that is difficult for male/child users to understand.

In addition, in the analysis process, if it is determined that the male/child user who moved to the vicinity of the second position P2b did not return after that, or if the male/child user who moved to the vicinity of the second position P2b If it is analyzed that the user stayed longer than the specified standard stay time, it can be said that the second content failed to guide the male/child user. In the determination process, it is determined that the second content (NG) is content that is difficult for male/child users to understand.

The alternative content generation unit 44 is a functional block for performing alternative content generation processing. In the alternative content generation process, the alternative content generation unit 44 generates alternative content based on the determination result of the determination process. Specifically, the learned model is used in the alternative content generation process.

FIG. 8 is a functional block diagram showing the internal functions of the alternative content generation section 44. The alternative content generation section 44 includes a data acquisition section 442 and an inference section 444. The data acquisition unit 442 is a functional block for acquiring input information necessary for inferring alternative content. Examples of the input information include first content, first image data, and second image data. The inference unit 444 is a functional block for outputting alternative content using the trained model stored in the trained model storage unit 54.

FIG. 9 is a flowchart showing a routine of alternative content generation processing executed by the alternative content generation unit 44. As shown in FIG. In step S10 of the routine shown in FIG. 9, the data acquisition unit 442 acquires first image data and second image data. In the next step S12, the acquired first image data and second image data are input to the inference section 444. The inference unit 444 infers alternative content for the content determined to be difficult to understand, based on the input determination result. Then, in step S14, the alternative content inferred by the inference unit 444 is output to the first content display device 10 to be displayed.

The output unit 45 is a functional block for performing output processing. The output unit 45 outputs the determination result of the determination process to the external server 4 of the system installer of the display system 100 or the external server 6 of the system installer of the display system installed in a facility of the same industry.

The model learning unit 46 is a functional block for performing model learning processing in advance. FIG. 10 is an internal block diagram showing the internal functions of the model learning section. The model learning section 46 includes a data acquisition section 462 and a model generation section 464. The data acquisition unit 462 is a functional block for acquiring learning data. The learning data is data in which input 1 and input 2 as a correct answer to input 1 are associated with each other. For example, input 1 is first content, first image data, and second image data. Input 2 is an example of alternative content whose effectiveness for the user is known.

The model generation unit 464 learns outputs for inputs according to a learning algorithm. The learning algorithm here is not limited to the above-mentioned supervised learning, but may be any known learning algorithm such as unsupervised learning, semi-supervised learning, reinforcement learning, etc. Typically, learning algorithms include neural networks, deep learning, genetic programming, functional logic programming, SVM (Support Vector Machine), k-NN (k-nearest neighbor algorithm), and the like.

The reflection unit 47 is a functional block for performing reflection processing. In the reflection process, the reflection unit 47 reflects the alternative content generated by the alternative content generation unit 44 as new content on the first content display device 10 or the second content display device 20 to be displayed.

3. Specific Processing Executed in Display System FIG. 11 is a flowchart of a routine executed in the display system of the embodiment. Note that this routine also represents part of an evaluation method for evaluating the effectiveness of content displayed on the display system 100.

In step S100, content is displayed on each content device of display system 100. Here, specifically, the first content is displayed on the first content display device 10, and the second content is displayed on the second content display device 20.

In step S102, information on each content currently displayed is acquired by the content server 30. Here, the content server 30 reads content information corresponding to each currently displayed content from the data 60 of the memory 50.

In step S104, image data captured by the first imaging device 12 and the second imaging device 22 is transmitted to the content server 30. In step S106, the user's attribute information and behavior information in the image data are acquired through analysis processing. In step S108, it is determined by a determination process whether the first content and second content being displayed are valid. As a result, if it is determined that the first content and the second content are valid, this routine is ended, and if it is determined that either the first content or the second content is not valid, the process proceeds to step S110.

In step S110, the judgment result of the judgment process is presented to the external server 4 of the system installer of the display system 100. In step S112, alternative content is generated by an alternative content generation process for the content determined to be invalid in step S108. In step S114, it is determined whether the content is to be replaced with alternative content. Here, for example, it is determined whether a replacement instruction to substitute content has been received from the system installer. As a result, if the determination is not found to be true, this routine is ended, and if the determination is found to be true, the process proceeds to step S116.

In step S116, the content determined to be invalid in step S108 is changed to the alternative content generated in step S112.

According to the display system 100 described above, it is possible to accurately evaluate the effectiveness of content displayed within a facility for users. Furthermore, when the displayed content is not valid, it becomes possible to generate alternative content based on the learning data and replace it.

3. Modifications The display system 100 of this embodiment may adopt a modified form as follows.

3-1. Hardware resources of information processing equipment

FIG. 12 is a diagram showing a modified example of hardware resources of a content server as an information processing device. In the example shown in FIG. 12, the content server 30 as an information processing device includes a processing circuit 72 including, for example, a processor 40, a memory 50, and dedicated hardware 70. FIG. 12 shows an example in which some of the functions of the content server 30 are implemented by dedicated hardware 70. All of the functions of the content server 30 may be realized by dedicated hardware 70. The dedicated hardware 70 can be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

3-2. Functional Arrangement of Content Server 30 Some of the functions of the content server 30 are installed in other devices such as the first content display device 10, the second content display device 20, the first imaging device 12, and the second imaging device 22. You can leave it there.

3-3. Model learning processing The model learning unit 46 receives input of information such as the user's age, gender, behavior, and length of stay, and generates a trained model that can generate alternative content by taking that information into consideration. It may be. In this case, in addition to the first content, first image data, and second image data, the data acquisition unit 442 acquires information regarding the user's age, gender, behavior, length of stay, etc., such as user attribute information, behavior, etc. Obtain information, congestion level, etc. Then, the inference unit 444 uses the acquired information as input and infers alternative content using the learned model.

3-4. Determination Process The determination process performed by the determination unit 43 is not limited to determining the validity of the first content, but may also determine the validity of the second content. In this case, the determination unit 43 can determine the effectiveness of the second content based on, for example, the user's behavior information analyzed from the second image data, or the behavior information and attribute information.

Furthermore, at least one of the first content and the second content may be provided to induce behavior toward a specific attribute. Specifically, the information of the first content stored in the first content display device 10 includes attribute information of the target user, and the determination unit 43 determines the content based on the attribute information of the target user. The validity of the display of the first content may be determined based on the above information. Similarly, the information on the second content stored in the second content display device 20 includes attribute information of the target user, and the determination unit 43, based on the attribute information of the target user, The effectiveness of displaying the second content may be determined. In this case, it becomes possible to more accurately evaluate the effectiveness of content displayed within the facility for users having predetermined attributes.

4. Others Although the preferred embodiments have been described in detail above, the present disclosure is not limited to the embodiments described above, and the embodiments described above are not limited to the embodiments described above without departing from the scope of the claims. Various modifications and substitutions can be made to the above.

Hereinafter, various aspects of the present disclosure will be collectively described as supplementary notes.

(Additional note 1)
a first content display device that displays first content at a first position in the facility to induce a predetermined action by a user;
a first imaging device that outputs first image data capturing the user in the vicinity of the first position;
a second imaging device that outputs second image data capturing an image of the user around a second location different from the first location in the facility;
an analysis unit that analyzes the user's behavior based on the first image data and the second image data; and an analysis unit that analyzes the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis unit. a content server having a determination unit that makes a determination;
Display system with.
(Additional note 2)
The content server includes:
The display according to supplementary note 1, further comprising an alternative content generation unit that generates alternative content to be displayed at the first position in place of the first content when the judgment unit judges that the display of the first content is not effective. system.
(Additional note 3)
including a trained model generated in advance by learning a relationship between the first content, the first image data, the second image data, and the alternative content;
The alternative content generation unit includes:
a data acquisition unit that acquires the first content, the first image data, and the second image data;
an inference unit that outputs the alternative content based on the first image data, the second image data, and the first content acquired by the data acquisition unit using the learned model; Display system as described.
(Additional note 4)
The analysis section includes:
configured to further analyze attributes of the user based on at least one or both of the first image data and the second image data,
According to any one of Supplementary Notes 1 to 3, the judgment unit is configured to judge the effectiveness of displaying the first content based on the attributes and behavior of the user analyzed by the analysis unit. Display system as described.
(Appendix 5)
The information of the first content stored in the first content display device includes attribute information of a target user,
The display system according to appendix 4, wherein the determination unit determines the effectiveness of displaying the first content based on attribute information of the target user.
(Appendix 6)
a second content display device that displays second content at the second position for inducing a predetermined action by the user;
The analysis section includes:
configured to analyze user attributes based on at least one or both of the first image data and the second image data,
The display system according to any one of appendices 1 to 5, wherein the determination unit determines the effectiveness of displaying the second content based on the user's attributes and behavior analyzed by the analysis unit.
(Appendix 7)
The information of the second content stored in the second content display device includes attribute information of the target user,
The display system according to appendix 6, wherein the determination unit determines the effectiveness of displaying the second content based on attribute information of the target user.
(Appendix 8)
The content server includes:
The display system according to any one of Supplementary Notes 1 to 7, further comprising an output unit that outputs the validity judgment result determined by the judgment unit to an external server.
(Appendix 9)
An information processing device that is displayed to a user at a first position in a facility and that determines the effectiveness of first content for inducing a predetermined action by the user,
at least one processor;
a memory storing at least one program;
The at least one processor executes the at least one program, thereby
Acquisition processing for acquiring first image data of the user around the first position and second image data of the user around a second position in the facility that is different from the first position. and,
an analysis process for analyzing the user's behavior based on the first image data and the second image data;
a determination process that determines the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis process;
An information processing device configured to execute.
(Appendix 10)
An evaluation method for evaluating the effectiveness of first content displayed to a user at a first position in a facility to induce a predetermined action by the user, the method comprising:
an acquisition step of acquiring first image data that images the user around the first position and second image data that images the user around a second position in the facility that is different from the first position; and,
an analysis step of analyzing the user's behavior based on the first image data and the second image data;
a determination step of determining the effectiveness of displaying the first content based on the user's behavior analyzed in the analysis step;
An evaluation method comprising:
(Appendix 11)
A computer-readable recording medium that stores a program that causes a computer to execute a program that is displayed to a user at a first location in a facility and causes a computer to determine the effectiveness of the first content for guiding the user's action. There it is,
The program is
obtaining first image data that images the user around the first position and second image data that images the user around a second position in the facility that is different from the first position;
Analyzing the user's behavior based on the first image data and the second image data,
A computer-readable recording medium configured to cause a computer to: determine the effectiveness of displaying the first content based on the analyzed behavior of the user.

4, 6 external server, 8 communication network, 10 first content display device, 12 first imaging device, 20, 20a, 20b second content display device, 22, 22a, 22b second imaging device, 30 content server, 40 processor , 41 acquisition unit, 42 analysis unit, 43 determination unit, 44 alternative content generation unit, 45 output unit, 46 model learning unit, 47 reflection unit, 50 memory, 52 program, 54 learned model storage unit, 60 data, 70 dedicated hardware, 72 processing circuit, 100 display system, 442 data acquisition unit, 444 inference unit, 462 data acquisition unit, 464 model generation unit

Claims (14)

a first content display device that displays first content at a first position in the facility to induce a predetermined action by a user;
a first imaging device that outputs first image data capturing the user in the vicinity of the first position;
a second imaging device that outputs second image data capturing an image of the user around a second location different from the first location in the facility;
an analysis unit that analyzes the user's behavior based on the first image data and the second image data; and an analysis unit that analyzes the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis unit. a determining unit that makes a determination; and an alternative content generating unit that generates an alternative content to be displayed at the first position in place of the first content when the determining unit determines that display of the first content is not effective. a content server having;
Equipped with
including a trained model generated in advance by learning a relationship between the first content, the first image data, the second image data, and the alternative content;
The alternative content generation unit includes:
a data acquisition unit that acquires the first content, the first image data, and the second image data;
A display system comprising: an inference unit that uses the learned model to output the alternative content based on the first image data, the second image data, and the first content acquired by the data acquisition unit. The analysis section includes:
configured to further analyze attributes of the user based on at least one or both of the first image data and the second image data,
The display system according to claim 1 , wherein the determination unit determines the effectiveness of displaying the first content based on the attributes and behavior of the user analyzed by the analysis unit. The information of the first content stored in the first content display device includes attribute information of a target user,
The display system according to claim 2 , wherein the determination unit determines the effectiveness of displaying the first content based on attribute information of the target user. The content server includes:
The display system according to any one of claims 1 to 3, further comprising an output unit that outputs the validity determination result determined by the determination unit to an external server. a first content display device that displays first content at a first position in the facility to induce a predetermined action by a user;
a first imaging device that outputs first image data capturing the user in the vicinity of the first position;
a second imaging device that outputs second image data capturing an image of the user around a second location different from the first location in the facility;
an analysis unit that analyzes the user's behavior based on the first image data and the second image data, and an analysis unit that analyzes the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis unit. a content server having a determination unit that makes a determination;
a second content display device that displays second content at the second position for inducing a predetermined action by the user;
The analysis section includes:
configured to analyze user attributes based on at least one or both of the first image data and the second image data,
The display system is configured such that the determination unit determines the effectiveness of displaying the second content based on the attributes and behavior of the user analyzed by the analysis unit . The content server includes:
6. The content generating apparatus according to claim 5 , further comprising an alternative content generation part that generates alternative content to be displayed at the first position in place of the first content when the judgment part judges that displaying the first content is not effective. display system. The information of the second content stored in the second content display device includes attribute information of the target user,
The display system according to claim 5 , wherein the determination unit determines the effectiveness of displaying the second content based on attribute information of the target user. The content server includes:
The display system according to any one of claims 5 to 7 , further comprising an output unit that outputs the validity determination result determined by the determination unit to an external server. An information processing device that is displayed to a user at a first position in a facility and that determines the effectiveness of first content for inducing a predetermined action by the user,
at least one processor;
a memory storing at least one program;
The at least one processor executes the at least one program, thereby
Acquisition processing for acquiring first image data of the user around the first position and second image data of the user around a second position in the facility that is different from the first position. and,
an analysis process for analyzing the user's behavior based on the first image data and the second image data;
a determination process that determines the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis process;
an alternative content generation process for generating alternative content to be displayed at the first position in place of the first content if it is determined in the judgment process that displaying the first content is not effective;
is configured to run
The alternative content generation process includes:
a process of acquiring the first content, the first image data, and the second image data;
the first image data acquired using a trained model generated in advance by learning the relationship between the first content, the first image data, the second image data, and the alternative content; An information processing apparatus including: outputting the alternative content based on second image data and the first content . An information processing device that is displayed to a user at a first position in a facility and that determines the effectiveness of first content for inducing a predetermined action by the user,
at least one processor;
a memory storing at least one program;
The at least one processor executes the at least one program, thereby
first image data of the user in the vicinity of the first position where the first content is displayed and a position in the facility that is different from the first position, and induces a predetermined action by the user; an acquisition process of acquiring second image data of the user in the vicinity of a second position where second content is displayed ;
an analysis process for analyzing the user's behavior based on the first image data and the second image data;
a determination process that determines the effectiveness of displaying the first content based on the user's behavior analyzed by the analysis process;
is configured to run
The analysis process is
configured to analyze user attributes based on at least one or both of the first image data and the second image data,
The information processing apparatus is configured to perform the determination process to determine the effectiveness of displaying the second content based on the attributes and behavior of the user analyzed by the analysis process . An evaluation method that is executed by a computer, is displayed to a user at a first position in a facility, and evaluates the effectiveness of first content for inducing a predetermined action by the user, the method comprising:
an acquisition step of acquiring first image data that images the user around the first position and second image data that images the user around a second position in the facility that is different from the first position; and,
an analysis step of analyzing the user's behavior based on the first image data and the second image data;
a determination step of determining the effectiveness of displaying the first content based on the user's behavior analyzed in the analysis step;
an alternative content generation step of generating alternative content to be displayed at the first position in place of the first content if it is determined in the judgment step that displaying the first content is not effective;
The alternative content generation step includes:
a step of acquiring the first content, the first image data, and the second image data; and learning a relationship between the first content, the first image data, the second image data, and the alternative content. outputting the alternative content based on the acquired first image data, second image data, and first content using a trained model generated in advance by a trained model . An evaluation method that is executed by a computer, is displayed to a user at a first position in a facility, and evaluates the effectiveness of first content for inducing a predetermined action by the user, the method comprising:
an acquisition step of acquiring first image data that images the user around the first position and second image data that images the user around a second position in the facility that is different from the first position; and,
an analysis step of analyzing the user's behavior based on the first image data and the second image data;
a determination step of determining the effectiveness of displaying the first content based on the user's behavior analyzed in the analysis step;
displaying second content in the second position for inducing a predetermined action by the user;
The analysis step includes:
configured to analyze user attributes based on at least one or both of the first image data and the second image data,
The evaluation method is configured such that the judgment step judges the effectiveness of displaying the second content based on the attributes and behavior of the user analyzed in the analysis step . A computer-readable record containing a program that causes a computer to execute a program that is displayed to a user at a first location in a facility and causes a computer to determine the effectiveness of first content for inducing a predetermined action by the user. A medium,
The program is
obtaining first image data capturing the user in the vicinity of the first position and second image data capturing the user in the vicinity of a second position different from the first position within the facility;
Analyzing the user's behavior based on the first image data and the second image data,
determining the effectiveness of displaying the first content based on the analyzed behavior of the user ;
If it is determined that the display of the first content is not effective, the first content, the first image data, and the second image data are acquired, and the first content, the first image data, and the second image data are displayed. and the first image data and the second image obtained using a learned model generated in advance by learning the relationship between the first content and an alternative content to be displayed at the first position in place of the first content. generating the alternative content based on data and the first content;
A computer-readable storage medium configured to cause a computer to perform certain operations. A computer-readable record containing a program that causes a computer to execute a program that is displayed to a user at a first location in a facility and causes a computer to determine the effectiveness of first content for inducing a predetermined action by the user. A medium,
The program is
obtaining first image data capturing the user in the vicinity of the first position and second image data capturing the user in the vicinity of a second position different from the first position within the facility;
Analyzing the user's behavior based on the first image data and the second image data,
determining the effectiveness of displaying the first content based on the analyzed behavior of the user , and displaying second content in the second position for inducing a predetermined behavior by the user;
Analyzing attributes of the user based on at least one or both of the first image data and the second image data,
determining the effectiveness of displaying the second content based on the analyzed attributes and behavior of the user;
A computer-readable storage medium configured to cause a computer to perform certain operations.

Images