Space evaluation support device and program

Abstract

To provide a space evaluation support device and program capable of acquiring information related to a persona that exactly represents a space to be an object.SOLUTION: A space evaluation support device 10 includes an acquisition part 11C for acquiring specific information that can specify a space to be an object, and first information being a portion of information among a plurality of types of element information included in persona information representing a typical user image in the space, an estimation part 11D for estimating second information by inputting the specific information and the first information acquired by the acquisition part 11C to a persona estimation model 13E obtained by regarding the specific information and the first information as input information and regarding the second information being information of an another part in the element information as output information, and a presentation part 11E for presenting persona related information about the second information estimated by the estimation part 11D.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a space evaluation support device and a program. [Background technology]

[0002] When planning a marketing strategy or redeveloping a space such as an urban area, commercial district, or tourist spot, it is extremely important to understand the persona of that space in advance. Note that "persona" here refers to the typical user image of the target space.

[0003] Traditionally, the mainstream method for creating personas has been through brainstorming using existing information, information obtained through questionnaire surveys, etc., following the KJ method, etc. However, this method has a strong tendency to reflect people's personal feelings in the creation of personas, and as a result, the personas created often end up being arbitrary.

[0004] Other conventional techniques for creating personas include the following:

[0005] Patent Document 1 discloses a persona creation support device that aims to enable simple and easy creation of personas.

[0006] This persona creation support device includes a component input means for inputting the components of a persona, a classification means for classifying the components into a hierarchical structure, and a persona generation means for generating a portrait, profile, and story from the components classified into the hierarchical structure. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-100380 Summary of the Invention [Problem to be solved by the invention]

[0008] However, while the technology disclosed in Patent Document 1 makes it possible to easily generate personas, it does not take into account information about the target space, and therefore has the problem that it is not possible to obtain information about a persona that accurately represents the space.

[0009] The present invention has been made in consideration of the above circumstances, and aims to provide a space evaluation support device and program that can obtain information about a persona that accurately represents a target space. [Means for solving the problem]

[0010] The space evaluation support device according to the present invention as set forth in claim 1 includes an acquisition unit that acquires specific information capable of identifying a target space and first information that is part of multiple types of element information included in persona information that represents a typical user image of the space; an estimation unit that estimates the second information by inputting the specific information and the first information acquired by the acquisition unit into a persona estimation model in which the specific information and the first information are used as input information and second information that is the other part of the element information is used as output information; and a presentation unit that presents persona-related information related to the second information estimated by the estimation unit. The persona estimation models are two types of models in which input information and output information are interchanged, and the two types of models are selectively used. .

[0011] According to the spatial evaluation support device of the present invention described in claim 1, specific information that can identify the target space and first information that is part of multiple types of element information contained in persona information that represents a typical user image of the space are obtained, and the specific information and the first information are used as input information and second information, which is the other part of the element information, is used as output information.The acquired specific information and first information are input into a persona estimation model in which the specific information and the first information are used as input information and second information, which is the other part of the element information, is used as output information, thereby estimating second information and presenting persona-related information related to the estimated second information.As a result, it is possible to take into account the specific information and first information related to the target space, and obtain information related to a persona that accurately represents the target space.

[0012] The spatial evaluation support device of the present invention described in claim 2 is the spatial evaluation support device described in claim 1, further comprising a learning information acquisition unit that acquires learning specific information, which is the specific information for learning, learning first information, which is the first information for learning, and learning second information, which is the second information for learning, and a learning unit that performs machine learning of the persona estimation model using the learning specific information and learning first information acquired by the learning information acquisition unit as input information and the learning second information acquired by the learning information acquisition unit as output information.

[0013] According to the spatial evaluation support device of the present invention described in claim 2, a persona estimation model can be constructed more easily by acquiring specific learning information, first learning information, and second learning information, and performing machine learning of a persona estimation model using the acquired specific learning information and first learning information as input information and the acquired second learning information as output information.

[0014] The spatial evaluation support device of the present invention as described in claim 3 is a spatial evaluation support device as described in claim 1 or claim 2, wherein the element information includes at least one of attribute information which is information indicating a person's attributes, behavioral information which is information indicating a person's behavioral patterns, purchasing information which is information indicating a person's purchasing status, and interest information which is information indicating objects of interest to a person.

[0015] According to the spatial evaluation support device of the present invention as set forth in claim 3, by including in the element information at least one of attribute information, which is information indicating a person's attributes, behavioral information, which is information indicating a person's behavioral patterns, purchasing information, which is information indicating a person's purchasing status, and interest information, which is information indicating objects of interest to a person, it is possible to obtain information about a persona that accurately represents the target space from the included information.

[0016] The spatial evaluation support device according to the present invention as set forth in claim 4 is the spatial evaluation support device as set forth in claim 3, wherein the attribute information includes at least one of a person's age group, gender, and residential area.

[0017] According to the spatial evaluation support device of the present invention as set forth in claim 4, by including at least one of a person's age group, gender, and residential area in the attribute information, it is possible to obtain information about a persona that accurately represents the target space from the included information.

[0018] The spatial evaluation support device of the present invention described in claim 5 is a spatial evaluation support device described in any one of claims 1 to 4, wherein the presentation unit synthesizes the persona-related information with a map image and presents it.

[0019] According to the spatial evaluation support device of the present invention as set forth in claim 5, persona-related information can be more effectively utilized by synthesizing the persona-related information with a map image and presenting the information.

[0020] A space evaluation support device according to the present invention as set forth in claim 6 is the space evaluation support device as set forth in claim 5, in which the map image is a social heat map image.

[0021] According to the spatial evaluation support device of the present invention as set forth in claim 6, the map image is made into a social heat map image, thereby making it possible to more effectively utilize persona-related information.

[0022] The program according to the present invention as set forth in claim 7 acquires specific information capable of identifying a target space and first information which is a portion of multiple types of element information included in persona information which represents a typical user image of the space, estimates the second information by inputting the acquired specific information and first information into a persona estimation model in which the specific information and the first information are used as input information and second information which is the other portion of the element information is used as output information, and presents persona-related information related to the estimated second information. a process in which the persona estimation model is two types of models in which input information and output information are interchanged, and the two types of models are selectively used; The processing is executed by a computer.

[0023] According to the program of the present invention described in claim 7, specific information that can identify the target space and first information that is part of multiple types of element information included in persona information that represents a typical user image of the space are obtained, and the specific information and the first information are used as input information and second information, which is the other part of the element information, is used as output information.The acquired specific information and first information are input into a persona estimation model in which the specific information and the first information are used as input information and second information, which is the other part of the element information, is used as output information, thereby estimating second information and presenting persona-related information related to the estimated second information.As a result, it is possible to take into account the specific information and first information related to the target space, and obtain information related to a persona that accurately represents the target space. [Effects of the Invention]

[0024] As described above, according to the present invention, information on a persona that accurately represents a target space can be obtained. [Brief explanation of the drawings]

[0025] [Figure 1] 1 is a block diagram showing an example of a hardware configuration of a space evaluation support system according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing an example of the functional configuration of the space evaluation support device according to the embodiment when learning a persona estimation model. [Figure 3]FIG. 1 is a block diagram showing an example of the functional configuration of a space evaluation support device according to an embodiment when a persona estimation model is in operation. [Figure 4] FIG. 2 is a schematic diagram illustrating an example of a configuration of a target region information database according to the embodiment. [Figure 5] FIG. 2 is a schematic diagram showing an example of the configuration of a learning information database according to the embodiment. [Figure 6] 10 is a flowchart illustrating an example of a learning process according to the embodiment. [Figure 7] 10 is a flowchart illustrating an example of an evaluation information presentation process according to the embodiment. [Figure 8] 10 is a flowchart illustrating an example of an evaluation information display process according to the embodiment. [Figure 9] FIG. 2 is a front view showing an example of the configuration of an initial screen according to the embodiment. [Figure 10] FIG. 10 is a front view showing an example of the configuration of an evaluation result screen according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0026] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. In this embodiment, the present invention will be described as being applied to a space evaluation support system including a space evaluation support device configured by a server computer or the like and a plurality of user terminals, each of which is a terminal used individually by a user.

[0027] First, the configuration of a space evaluation support system 90 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of the hardware configuration of the space evaluation support system 90 according to this embodiment.

[0028] 1, a space evaluation support system 90 according to this embodiment includes a space evaluation support device 10 and multiple user terminals 30, each of which is capable of accessing a network 80. Examples of the space evaluation support device 10 include information processing devices such as a personal computer and a server computer. Examples of the user terminal 30 include portable terminals such as smartphones, tablet terminals, and PDAs (Personal Digital Assistants, mobile information terminals).

[0029] The user terminal 30 according to this embodiment is a terminal carried by each of multiple users (hereinafter simply referred to as "users") who are intended to use the space evaluation support system 90. The user terminal 30 includes a CPU (Central Processing Unit) 31, a memory 32 serving as a temporary storage area, a nonvolatile memory unit 33, an input unit 34 such as a touch panel, a display unit 35 such as a liquid crystal display, and a media read / write device (R / W) 36. The user terminal 30 also includes a camera 38, a microphone 39, a GPS (Global Positioning Systems) 40, and a wireless communication unit 42. The CPU 31, memory 32, memory unit 33, input unit 34, display unit 35, media read / write device 36, camera 38, microphone 39, GPS 40, and wireless communication unit 42 are interconnected via a bus B1. The media read / write device 36 reads information from and writes information to a recording medium 37.

[0030] The storage unit 33 is realized by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. A rating information display program 33A is stored in the storage unit 33 as a storage medium. The rating information display program 33A is stored in the storage unit 33 when a recording medium 37 on which the rating information display program 33A is written is set in the medium reading and writing device 36 and the medium reading and writing device 36 reads the rating information display program 33A from the recording medium 37. The CPU 31 reads the rating information display program 33A from the storage unit 33, expands it in the memory 32, and sequentially executes the processes of the rating information display program 33A.

[0031] On the other hand, the space evaluation support device 10 is a device that plays a central role in the space evaluation support system 90, and is a device that comprehensively stores and uses various information handled by the space evaluation support system 90. The space evaluation support device 10 includes a CPU 11, a memory 12 as a temporary storage area, a non-volatile memory unit 13, an input unit 14 such as a keyboard and mouse, a display unit 15 such as a liquid crystal display, a medium read / write device 16, and a communication interface (I / F) unit 18. The CPU 11, memory 12, memory unit 13, input unit 14, display unit 15, medium read / write device 16, and communication I / F unit 18 are connected to one another via a bus B2. The medium read / write device 16 reads information written in a recording medium 17 and writes information to the recording medium 17.

[0032] The storage unit 13 is realized by an HDD, an SSD, a flash memory, etc. The storage unit 13 as a storage medium stores a learning program 13A and an evaluation information presentation program 13B.

[0033] The learning program 13A is stored in the storage unit 13 by setting the recording medium 17 on which the learning program 13A is written in the medium reading and writing device 16 and having the medium reading and writing device 16 read out the learning program 13A from the recording medium 17. The evaluation information presentation program 13B is stored in the storage unit 13 by setting the recording medium 17 on which the evaluation information presentation program 13B is written in the medium reading and writing device 16 and having the medium reading and writing device 16 read out the evaluation information presentation program 13B from the recording medium 17.

[0034] The CPU 11 reads out the learning program 13A from the storage unit 13, loads it in the memory 12, and sequentially executes the processes included in the learning program 13A. The CPU 11 also reads out the evaluation information presentation program 13B from the storage unit 13, loads it in the memory 12, and sequentially executes the processes included in the evaluation information presentation program 13B.

[0035] Furthermore, a target area information database 13C and a learning information database 13D are stored in the storage unit 13. The target area information database 13C and the learning information database 13D will be described in detail later.

[0036] Furthermore, a persona estimation model 13E is stored in the storage unit 13. In the persona estimation model 13E according to this embodiment, input information is first information that is specific information that can identify a target space (hereinafter referred to as "target space") and information that is part of multiple types of element information included in persona information that represents a typical user image of the target space. In addition, in the persona estimation model 13E according to this embodiment, output information is second information that is information that is the other part of the element information.

[0037] In the space evaluation support system 90 according to this embodiment, four types of information are applied as the element information: attribute information indicating a person's attributes, behavior information indicating a person's behavior pattern, purchase information indicating a person's purchasing situation, and interest information indicating a person's interests, but the invention is not limited to these. For example, of these four types of information, any one type, a combination of any two types, or a combination of any three types may be applied as the element information, or other types of element information may be included in addition to these four types and applied as the element information.

[0038] Furthermore, in the space evaluation support system 90 according to this embodiment, three types of information, namely, a person's age group, sex, and residential area, are applied as the attribute information, but the present invention is not limited to this. For example, any one or a combination of any two of these three types of information may be applied as the attribute information, or other types of attribute information may be included in addition to these three types and applied as the attribute information.

[0039] The persona estimation model 13E according to this embodiment is an AI (Artificial Intelligence) model using an MLP (Multilayer Perceptron), but is not limited to this. A machine learning model such as an AI other than an MLP, such as an AI model using an RNN (Recurrent Neural Network), may also be applied as the persona estimation model 13E. Furthermore, the persona estimation model 13E is not limited to an AI model, and may instead be a model based on a statistical method such as regression analysis.

[0040] Here, in the spatial evaluation support system 90 according to this embodiment, as shown in Figures 2 and 3 described below, two models, a first estimation model 13E1 and a second estimation model 13E2, are prepared as the persona estimation model 13E.

[0041] In the first estimation model 13E1 according to this embodiment, of the above-mentioned element information, attribute information (in this embodiment, three types of information: a person's age group, gender, and residential area) is considered to be the first information, and other information (in this embodiment, three types of information: behavioral information, purchase information, and interest information) is considered to be the second information. Also, in the second estimation model 13E2 according to this embodiment, information of the element information excluding attribute information is considered to be the first information, and attribute information is considered to be the second information.

[0042] That is, in the spatial evaluation support system 90 according to this embodiment, two types of models are prepared as persona estimation models 13E in which the input information and output information are swapped, and one of these two types of models is selectively used to estimate the second information in the persona information.

[0043] Next, the functional configuration of the space evaluation support device 10 according to this embodiment when learning the persona estimation model 13E will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the functional configuration of the space evaluation support device 10 according to this embodiment when learning the persona estimation model 13E.

[0044] 2, during learning of the persona estimation model 13E, the space evaluation support device 10 includes a learning information acquisition unit 11A and a learning unit 11B. The CPU 11 of the space evaluation support device 10 executes the learning program 13A, thereby functioning as the learning information acquisition unit 11A and the learning unit 11B.

[0045] The learning information acquisition unit 11A according to this embodiment acquires the learning specific information, which is the above-mentioned specific information for learning, the learning first information, which is the first information for learning, and the learning second information, which is the second information for learning. In this embodiment, the learning specific information, the learning first information, and the learning second information are acquired by reading them from the learning information database 13D (see also FIG. 5), which will be described later. However, this is not limited to this form. For example, the learning specific information, the learning first information, and the learning second information may be acquired by downloading them from an external server device connected to the network 80.

[0046] Then, the learning unit 11B in this embodiment performs machine learning of the persona estimation model 13E using the learning specific information and learning first information acquired by the learning information acquisition unit 11A as input information and the learning second information acquired by the learning information acquisition unit 11A as output information.

[0047] Next, the functional configuration of the space evaluation support device 10 according to this embodiment when the persona estimation model 13E is in operation will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example of the functional configuration of the space evaluation support device 10 according to this embodiment when the persona estimation model 13E is in operation.

[0048] 3, the space evaluation support device 10 when the persona estimation model 13E is in operation includes an acquisition unit 11C, an estimation unit 11D, and a presentation unit 11E. The CPU 11 of the space evaluation support device 10 executes the evaluation information presentation program 13B, thereby functioning as the acquisition unit 11C, the estimation unit 11D, and the presentation unit 11E.

[0049] The acquisition unit 11C according to this embodiment acquires specific information and first information corresponding to the target space. Note that in this embodiment, the specific information and first information are acquired by having the user of the user terminal 30 input them via the input unit 34 of the user terminal 30, but this is not the only possible form. For example, the specific information and the first information may be acquired by having the user of the user terminal 30 speak via the microphone 39 of the user terminal 30.

[0050] Furthermore, the estimation unit 11D according to this embodiment estimates the second information by inputting the specific information and the first information acquired by the acquisition unit 11C to the persona estimation model 13E. Then, the presentation unit 11E according to this embodiment presents persona-related information related to the second information estimated by the estimation unit 11D.

[0051] In this embodiment, the second information estimated by the estimation unit 11D itself is applied as the persona-related information, but this is not limited thereto. For example, an image representing a human figure indicated by the second information estimated by the estimation unit 11D may be applied as the persona-related information. Furthermore, in this embodiment, presentation by the presentation unit 11E is applied by display on the display unit, but this is not limited thereto. For example, presentation by the presentation unit 11E may be applied by audio using an audio playback device such as a speaker or by printing using an image forming device such as a printer.

[0052] In addition, in this embodiment, the presentation unit 11E is configured to present persona-related information by combining it with a map image, but this is not limited to this. For example, it may be configured to present only the persona-related information without combining it with a map image, or to present the persona-related information by combining it with an image other than a map image.

[0053] Furthermore, in this embodiment, the presentation unit 11E presents persona-related information by transmitting information about the persona-related information to the requested user terminal 30 and displaying it on the display unit 35 of the user terminal 30, but this is not limited to this. For example, the persona-related information may be presented by displaying it on the display unit 15 of the space evaluation support device 10.

[0054] In this embodiment, a social heat map image is used as the map image. The social heat map image is an image showing a map that highlights locations with a large amount of information that matches the user's attributes by displaying areas with different densities or colors overlaid on the normally displayed map image of the corresponding area. That is, in this embodiment, each user is asked to answer multiple questions in advance, and the attributes of each user are determined in advance by analyzing and classifying the answers. The social heat map image according to this embodiment is then displayed overlaid on the map image so that the density increases with the amount of information that matches the user's attributes (in this embodiment, information posted on a social networking service (SNS)). However, this is not limited to changing the density, and the color may also be changed in order from high density to low density, such as red → yellow → green.

[0055] In this embodiment, the space evaluation support device 10 is connected via a network 80 or the like to a server that provides the latest social heat map images of each area (hereinafter referred to as the "target area") that the space evaluation support system 90 handles. The space evaluation support device 10 then acquires the latest social heat map images from this server and sequentially updates the social heat map images stored in the target area information database 13C (see also FIG. 4), which will be described later. However, this is not limiting, and the space evaluation support device 10 itself may sequentially update the social heat map images corresponding to each user.

[0056] Here, the behavioral information, purchase information, and interest information according to this embodiment will be described.

[0057] The behavioral information in this embodiment is information that defines a person's behavioral pattern using information that indicates the trajectory of the person's movement when the person walks or moves using public transportation or a car, etc., as measured by GPS, beacons, etc., with stations, facilities, etc. as nodes.

[0058] Furthermore, the purchasing information according to this embodiment is information about a person's purchasing behavior, obtained from the usage history information of a point card, a credit card, etc. In this embodiment, the purchasing information is information obtained by stratifying the amount paid by the corresponding person, but is not limited to this. For example, in addition to the amount, the purchasing information may include information indicating the store where the corresponding person purchased the product or service, the date and time of purchase, etc.

[0059] Furthermore, the interest information in this embodiment is information that is identified from natural language-based posted information on SNS, using techniques such as machine learning AI and text mining to identify the subjects of interest of the corresponding person.

[0060] Next, the target area information database 13C according to this embodiment will be described with reference to Fig. 4. Fig. 4 is a schematic diagram showing an example of the configuration of the target area information database 13C according to this embodiment.

[0061] The target area information database 13C according to this embodiment is a database in which information about the target area described above is registered. As shown in Fig. 4, the target area information database 13C according to this embodiment stores information such as the target area name, the social heatmap image, the target district name, and the target district position.

[0062] The target area name is information indicating the name of each of the target areas, the social heat map image is information indicating the above-mentioned social heat map image for each user in the target area indicated by the corresponding target area name, the target district name is information indicating the name of a district located within the corresponding target area, and the target district location is information indicating the location of the corresponding target district.

[0063] In this embodiment, the target district is defined as an area divided by blocks in each town in the corresponding target area. Furthermore, in this embodiment, the target district position is defined as a pair of diagonal coordinate positions in a two-dimensional coordinate system of a circumscribing rectangular frame of the corresponding target district. However, the present invention is not limited to these forms. For example, the target district may be defined as an area divided by an address in each town in the corresponding target area, or the target district position may be defined as the coordinate position in the two-dimensional coordinate system of the center point of the circumscribing rectangular frame. Furthermore, latitude and longitude may be used instead of the coordinate position in the two-dimensional coordinate system.

[0064] Next, the learning information database 13D according to this embodiment will be described with reference to Fig. 5. Fig. 5 is a schematic diagram showing an example of the configuration of the learning information database 13D according to this embodiment.

[0065] The learning information database 13D according to this embodiment stores various pieces of learning information described above. As shown in Fig. 5, the learning information database 13D according to this embodiment stores the target district name, user ID (Identification), and learning information.

[0066] The target area name is the same information as the target area name in the target area information database 13C, and the user ID is information that is assigned in advance to each user as a unique ID to identify each user individually. The learning information is learning information about the corresponding user for the corresponding target area, and is information that indicates each of the above-mentioned attribute information, interest information, behavior information, and purchase information.

[0067] In the example shown in Figure 5, the user assigned the user ID "U001" is a man in his 40s living in Kawasaki, and his attribute information is registered as such. His interest information includes events, sports, etc., his behavioral information includes travel between Kawasaki Station and Tokyo Station, and his purchasing information includes the amount of money spent on the items purchased during the corresponding behavior.

[0068] Next, the operation of the space evaluation support system 90 according to this embodiment will be described with reference to FIGS.

[0069] First, the operation of the space evaluation support device 10 when executing the learning process according to this embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the learning process according to this embodiment.

[0070] The CPU 11 of the space evaluation support device 10 executes the learning program 13A, thereby executing the learning process shown in Fig. 6. The learning process shown in Fig. 6 is executed when an instruction to start execution of the learning program 13A is input by the operator of the space evaluation support device 10 via the input unit 14. Note that, in order to avoid confusion, a case will be described here in which the number of pieces of learning information required to train the persona estimation model 13E is registered in the learning information database 13D.

[0071] 6, CPU 11 reads out the name of any target district (hereinafter referred to as "processing target district name") from learning information database 13D, and in step 102, CPU 11 reads out the attribute information of any user (hereinafter referred to as "processing target person") corresponding to the processing target district name from learning information database 13D. In step 104, CPU 11 reads out one set of interest information, behavior information, and purchase information corresponding to the processing target district name and the processing target person from learning information database 13D.

[0072] In step 106, the CPU 11 uses the read processing target district name and attribute information as input information and the read interest information, behavior information, and purchase information as output information (correct answer information) to machine-learn the first estimation model 13E1.

[0073] In addition, in step 106, the CPU 11 uses the read processing target district name, interest information, behavior information, and purchase information as input information and the read attribute information as output information (correct answer information) to machine-train the second estimation model 13E2.

[0074] In step 108, CPU 11 determines whether or not machine learning in step 106 has been completed for all interest information, behavioral information, and purchase information that correspond to the processing target district name and the processing target person, which are stored in learning information database 13D, and if the determination is negative, CPU 11 returns to step 104, whereas if the determination is positive, CPU 11 proceeds to step 110. When repeatedly executing the processes of steps 104 to 106, CPU 11 processes interest information, behavioral information, and purchase information that have not been the target up to that point.

[0075] In step 110, CPU 11 determines whether or not machine learning in step 106 has been completed for all users stored in learning information database 13D, and if the determination is negative, CPU 11 returns to step 102, whereas if the determination is positive, CPU 11 proceeds to step 112. When repeatedly executing the processes of steps 102 to 108, CPU 11 makes users who have not been targeted up to that point into the processing targets.

[0076] In step 112, CPU 11 determines whether or not machine learning in step 106 has been completed for all target districts stored in learning information database 13D, and if the determination is negative, the process returns to step 100, whereas if the determination is positive, the learning process ends. Note that when repeatedly executing the processes of steps 100 to 110, CPU 11 processes target districts that have not been considered as targets up to that point.

[0077] Through the above learning process, the persona estimation model 13E (the first estimation model 13E1 and the second estimation model 13E2) is learned.

[0078] In this manner, in this embodiment, a single persona estimation model 13E is constructed as a model corresponding to all target districts, but this is not limitative. For example, a different persona estimation model 13E may be constructed for each target district.

[0079] Next, the operation of the space evaluation support device 10 according to this embodiment when executing the evaluation information presentation process will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of the evaluation information presentation process according to this embodiment.

[0080] In the spatial evaluation support system 90 according to this embodiment, when a user wishes to view evaluation information, including persona-related information for a target area, the user executes an evaluation information display process (described later) using the user's user terminal 30. In this evaluation information display process, reference request information including information indicating the target area for which the user wishes to view the evaluation information (corresponding to the specific information described above, hereinafter referred to as "designated target area information") is transmitted to the spatial evaluation support device 10. In this evaluation information display process, the user is expected to input information corresponding to the first information described above, and the reference request information including the first information entered by the user is transmitted to the spatial evaluation support device 10. When this reference request information is received, the CPU 11 of the spatial evaluation support device 10 executes the evaluation information presentation program 13B, thereby executing the evaluation information presentation process shown in FIG. 7. Here, to avoid confusion, a case will be described in which a target area information database 13C has already been established.

[0081] 7, the CPU 11 extracts the designated area information from the received reference request information. In step 202, the CPU 11 determines whether the received reference request information includes attribute information as the first information. If the determination is affirmative, the CPU 11 proceeds to step 204.

[0082] In step 204, the CPU 11 inputs the designated target district information included in the reference request information as specific information and the attribute information included in the reference request information as first information into the first estimation model 13E1, and then proceeds to step 208.

[0083] On the other hand, if the determination in step 202 is negative, the process proceeds to step 206, assuming that the first information included in the reference request information is interest information, behavior information, and purchase information.

[0084] In step 206, the CPU 11 inputs the designated target area information included in the reference request information as specific information, and the interest information, behavioral information, and purchasing information included in the reference request information as first information into the second estimation model 13E2, and then proceeds to step 208.

[0085] When the specific information and the first information are input, the first estimation model 13E1 and the second estimation model 13E2 output second information corresponding to the input information, and therefore, in step 208, the CPU 11 acquires the second information output from the first estimation model 13E1 or the second estimation model 13E2.

[0086] In step 210, the CPU 11 reads from the target area information database 13C the target area location corresponding to the target area indicated by the specified target area information (hereinafter referred to as the "processing target area") and a social heat map image corresponding to the target area that includes the processing target area and that corresponds to the user who is the access source.

[0087] In step 212, the CPU 11 uses the read social heat map image, the target district location, and the acquired second information to create information showing a predetermined evaluation result screen (hereinafter referred to as "evaluation result screen information"). In step 214, the CPU 11 transmits the created evaluation result screen information to the accessing user terminal 30, and then ends this evaluation information presentation process.

[0088] Next, the operation of the user terminal 30 according to this embodiment when executing the above-mentioned evaluation information display process will be described with reference to Fig. 8. The evaluation information display process shown in Fig. 8 is executed when the CPU 31 of any of the user terminals 30 executes the evaluation information display program 33A. The evaluation information display process shown in Fig. 8 is executed, for example, when an instruction to execute the evaluation information display process is input from any of the users (hereinafter referred to as "active users") via the input unit 34 of their own user terminal 30.

[0089] 8, the CPU 31 controls the display unit 35 to display an initial screen having a predetermined configuration, and waits until predetermined information is input in step 302. An example of the configuration of the initial screen according to this embodiment is shown in FIG.

[0090] 9, the initial screen according to this embodiment displays a message prompting the user to input the name of the target district, and also displays an input area 35A for inputting the name of the target district for which the user wishes to refer to evaluation information. The initial screen according to this embodiment also displays a message prompting the user to input attribute information or other information (interest information, behavioral information, purchase information), and also displays an input area 35B for inputting this information.

[0091] When the initial screen shown in FIG. 9 is displayed on the display unit 35, the actual user uses the input unit 34 to input the name of the target area for which the user wishes to refer to evaluation information in the input field 35A, input attribute information or other information in the input field 35B, and then selects the end button 35C. In response to this, a positive determination is made in step 302, and the process proceeds to step 304. Note that FIG. 9 illustrates an example of the display state when attribute information is input. In this embodiment, the name of the target area on the initial screen is input by directly entering the name of the target area, but this is not limited thereto. It is also possible to display the names of all target areas for which persona-related information can be referenced in a pull-down format, and then select the name of the desired target area from the displayed names of the target areas.

[0092] In step 304, the CPU 31 creates the above-mentioned reference request information using the information input on the initial screen, and transmits the reference request information to the space evaluation support device 10. In response to this, the space evaluation support device 10 executes the evaluation information presentation process as described above, and transmits evaluation result screen information to the user terminal 30 that is the access source.

[0093] Therefore, in step 306, the CPU 31 waits until evaluation result screen information is received from the space evaluation support device 10. In step 308, the CPU 31 controls the display unit 35 to display the evaluation result screen indicated by the received evaluation result screen information, and in step 310, the CPU 31 waits until predetermined information is input, and then terminates this evaluation information display process. Figure 10 shows an example of the configuration of the evaluation result screen according to this embodiment.

[0094] As an example, as shown in Figure 10, the evaluation result screen of this embodiment displays a social heat map image of a target area that includes the target district, with a speech bubble 35D containing first information 35D1, which is information entered by the actual user, and second information 35D2 estimated by any of the persona estimation models 13E corresponding to the first information 35D1, with the source of the speech bubble being the location of the target district.

[0095] Therefore, by referring to the evaluation result screen, the actual user can understand persona-related information (in this embodiment, second information) regarding the element information indicated by the first information entered by the user for the desired target area, along with the social heat map image.

[0096] Note that the example shown in Figure 10 illustrates a case where the first information is attribute information, but it goes without saying that if the first information is interest information, behavioral information, or purchasing information, the attribute information will be displayed as persona-related information as the second information.

[0097] As described above, according to this embodiment, specific information capable of identifying a target space and first information, which is a portion of multiple types of element information included in persona information representing a typical user image of the space, are acquired, and the acquired specific information and first information are input into a persona estimation model in which the specific information and the first information are used as input information and second information, which is the other portion of the element information, is used as output information, thereby estimating second information and presenting persona-related information related to the estimated second information. Therefore, as a result of being able to take into account the specific information and first information related to the target space, it is possible to obtain information related to a persona that accurately represents the target space.

[0098] Furthermore, according to this embodiment, specific information for training, first information for training, and second information for training are acquired, and machine learning of a persona estimation model is performed using the acquired specific information for training and the first information for training as input information and the acquired second information for training as output information. Therefore, a persona estimation model can be constructed more easily.

[0099] Furthermore, according to this embodiment, the element information includes attribute information that indicates a person's attributes, behavioral information that indicates a person's behavioral patterns, purchase information that indicates a person's purchasing status, and interest information that indicates objects that a person is interested in. Therefore, from this information, information about a persona that accurately represents the target space can be obtained.

[0100] Furthermore, according to this embodiment, the attribute information includes information on a person's age group, gender, and residential area. Therefore, from this information, information on a persona that accurately represents a target space can be obtained.

[0101] Furthermore, according to this embodiment, persona-related information is synthesized with a map image and presented, allowing the persona-related information to be utilized more effectively.

[0102] Furthermore, according to this embodiment, the map image is a social heat map image, which allows for more effective use of persona-related information.

[0103] In the above embodiment, the case where the user himself specifies the target area to be referenced has been described, but the present invention is not limited to this. For example, a configuration may be adopted in which the GPS 40 built into the user terminal 30 carried by the user is used to automatically apply the area including the location of the user terminal 30 as the target area to be referenced. Also, a configuration may be adopted in which information indicating the user's preference trends is acquired in advance by the space evaluation support device 10, and information on target areas according to the user's preferences is provided to the user as needed.

[0104] Furthermore, in the above embodiment, the information included in the persona information is classified into two categories, attribute information and other information, and two models in which one type of information is used as input information and the other type of information is used as output information are applied as persona estimation models. However, this is not limited to this. Any combination of input information and output information of the persona estimation model can be used as a combination of element information included in the persona information. For example, a model in which only gender in the attribute information is used as input information and age group, behavior information, and interest information in the attribute information are used as output information may be applied as the persona estimation model.

[0105] In the above embodiment, the second information is directly estimated from the specific information and the first information using a single persona estimation model, but the present invention is not limited to this. For example, the second information may be estimated using multiple persona estimation models, such as estimating behavioral information from the specific information and the first information using a first persona estimation model, and then estimating the second information using a second persona estimation model that uses the behavioral information as input information.

[0106] In the above embodiment, the learning process and the evaluation information presentation process are executed in the space evaluation support device 10, but the present invention is not limited to this. For example, the learning process and the evaluation information presentation process may be executed by each user terminal 30. In this case, the space evaluation support device of the present invention is included in the user terminal 30.

[0107] In the above embodiment, the target area to be referred to is input on the initial screen using the input unit 34, but the present invention is not limited to this. For example, the target area to be referred to may be input as voice information using the microphone 39.

[0108] In the above embodiment, the case where persona-related information is derived for each target area has been described, but this is not limiting. For example, persona-related information may be derived for each time period or for each day of the week.

[0109] Furthermore, in the above embodiment, for example, the following various processors can be used as the hardware structure of the processing units that execute the processes of the learning information acquisition unit 11A, the learning unit 11B, the acquisition unit 11C, the estimation unit 11D, and the presentation unit 11E. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as a processing unit, as well as dedicated electrical circuits that are processors having a circuit configuration specifically designed to execute specific processes, such as a programmable logic device (PLD) that is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field-Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

[0110] The processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA).The processing unit may also be configured with a single processor.

[0111] Examples of configuring a processing unit with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as the processing unit, as typified by computers such as client and server. Second, a form in which a processor is used to realize the functions of the entire system, including the processing unit, on a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs). In this way, the processing unit is configured using one or more of the above-mentioned various processors as a hardware structure.

[0112] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. [Explanation of symbols]

[0113] 10. Spatial evaluation support device 11 CPU 11A Learning information acquisition unit 11B Learning Department 11C Acquisition Department 11D Estimation Section 11E Presentation section 12 Memory 13 Storage section 13A Study Program 13B Evaluation Information Presentation Program 13C Subject Area Information Database 13D Learning Information Database 13E Persona Estimation Model 13E1 First estimation model 13E2 Second estimation model 14 Input section 15 Display section 16 Media reading and writing device 17 Recording Media 18 Communication I / F section 30 User terminal 31 CPU 32 memory 33 Storage section 33A Evaluation Information Display Program 34 Input section 35 Display section 36 Media reading and writing device 37 Recording Media 38 Camera 39. Mike 40 GPS 42 Radio Communication Department 80 Network 90 Space Evaluation Support System

Claims

1. an acquisition unit that acquires first information that is part of information among multiple types of element information included in specific information that can identify a target space and persona information that represents a typical user image of the space; an estimation unit that estimates the second information by inputting the specific information and the first information acquired by the acquisition unit into a persona estimation model in which the specific information and the first information are input information and second information, which is information of another part of the element information, is output information; and a presentation unit that presents persona-related information related to the second information estimated by the estimation unit; Equipped with The persona estimation models are two types of models in which input information and output information are interchanged, and the two types of models are selectively used. Spatial evaluation support device.

2. a learning information acquisition unit that acquires learning specific information, which is the specific information for learning, learning first information, which is the first information for learning, and learning second information, which is the second information for learning; a learning unit that performs machine learning of the persona estimation model using the specific learning information and first learning information acquired by the learning information acquisition unit as input information and the second learning information acquired by the learning information acquisition unit as output information; The space evaluation support device according to claim 1, further comprising:

3. The element information includes at least one of attribute information which is information indicating the attributes of a person, behavior information which is information indicating the behavior pattern of a person, purchase information which is information indicating the purchasing situation of a person, and interest information which is information indicating objects of interest to a person.

3. The space evaluation support device according to claim 1 or 2.

4. The attribute information includes at least one of the person's age group, gender, and residential area. The space evaluation support device according to claim 3.

5. the presentation unit presents the persona-related information by combining it with a map image. The space evaluation support device according to any one of claims 1 to 4.

6. The map image is a social heatmap image. The space evaluation support device according to claim 5.

7. acquiring first information that is part of a plurality of types of element information included in specific information that can identify a target space and persona information that represents a typical user image of the space; the acquired specific information and the first information are input to a persona estimation model in which the specific information and the first information are input information and second information, which is information of another part of the element information, is output information, thereby estimating the second information; presenting persona-related information related to the estimated second information; The persona estimation models are two types of models in which input information and output information are interchanged, and the two types of models are selectively used. A program that causes a computer to execute a process.

Images