Image generation system, image generation method, and image generation program

Abstract

This image generation system (10) comprises an acquisition unit (11), a conversion unit (12), a generation unit (13), and an output unit (15). The acquisition unit (11) acquires data pertaining to users' behaviors at a tourist facility. The conversion unit (12) converts the data pertaining to the users' behaviors into a text representing the users' behaviors or an environment at the time of the behaviors on the basis of set rules. The generation unit (13) generates an image on the basis of the text converted by the conversion unit by using a generation model by which an image pertaining to the tourist facility is generated on the basis of the text. The output unit (15) outputs the generated image.

Description

Image generation system, image generation method, and recording medium

[0001] The present disclosure relates to image generation systems and the like.

[0002] At a theme park, for example, users may repeatedly visit their favorite attractions. Furthermore, due to events such as rain or long wait times, users may not be able to enjoy the attractions they had planned to visit as they wished. To encourage such repeat visitors or users who did not enjoy their visit as they had hoped to return to the theme park, it may be necessary to ensure that they are satisfied with their experience at the theme park. To ensure that users are satisfied, it may be possible to provide content that each user finds enjoyable and surprising.

[0003] The image printing system of Patent Document 1 automatically photographs users at multiple locations in tourist spots by having a robot instruct the users to pose, and generates images to be printed in accordance with the user's selection, for example.

[0004] JP 2018-74281 A

[0005] With the technology described in Patent Document 1, it may be difficult to generate an image according to the user's actions.

[0006] In order to solve the above-mentioned problems, the present disclosure aims to provide an image generation system and the like that can generate an image according to the behavior of a user.

[0007] In order to solve the above problems, the image generation system of the present disclosure includes an acquisition means for acquiring data regarding user behavior at tourist facilities, a conversion means for converting the data regarding user behavior into text representing the user behavior or the environment at the time of the behavior based on set rules, a generation means for generating an image based on the text converted by the conversion means using a generation model that generates an image related to the tourist facility based on the text, and an output means for outputting the generated image.

[0008] The image generation method disclosed herein acquires data regarding user behavior at tourist facilities, converts the data regarding user behavior into text representing the user's behavior or the environment at the time of the behavior based on set rules, generates an image based on the converted text using a generation model that generates an image related to the tourist facility based on the text, and outputs the generated image.

[0009] The recording medium of the present disclosure non-temporarily records an image generation program that causes a computer to execute the following processes: acquiring data on user behavior at a tourist facility; converting the data on user behavior into text that represents the user's behavior or the environment at the time of the behavior based on set rules; generating an image based on the converted text using a generation model that generates an image related to the tourist facility based on the text; and outputting the generated image.

[0010] According to the present disclosure, an image can be generated according to the user's actions.

[0011] FIG. 1 is a diagram illustrating an example of a configuration in an embodiment of the present disclosure. FIG. 2 is a diagram illustrating an example of an image generated by an image generation system in an embodiment of the present disclosure. FIG. 3 is a diagram illustrating an example of an image generated by an image generation system in an embodiment of the present disclosure. FIG. 4 is a diagram illustrating an example of a configuration of an image generation system in an embodiment of the present disclosure. FIG. 5 is a diagram illustrating an example of an image of a user in an embodiment of the present disclosure. FIG. 6 is a diagram illustrating an example of an image generated by an image generation system in an embodiment of the present disclosure. FIG. 7 is a diagram illustrating an example of an image generated by an image generation system in an embodiment of the present disclosure. FIG. 8 is a diagram illustrating an example of an operation flow of an image generation system in an embodiment of the present disclosure. FIG. 9 is a diagram illustrating an example of a hardware configuration in an embodiment of the present disclosure.

[0012] An embodiment of the present disclosure will be described in detail with reference to the drawings. FIG. 1 is a diagram illustrating an example of the configuration of an image generation system. The image generation system includes an image generation system 10, an information management server 20, and a terminal device 30. The image generation system 10 is connected to the information management server 20 via a network. The image generation system 10 is connected to the terminal device 30 via the network. The terminal device 30 may also be connected to the information management server 20 via the network. There may be multiple information management servers 20 and multiple terminal devices 30. The number of information management servers 20 and the number of terminal devices 30 are set as appropriate.

[0013] The image generation system 10 is a system that generates images of tourist facilities based on, for example, data on the behavior of users of the tourist facilities. The image generation system 10 generates images of the tourist facilities according to the data on the behavior of users of the tourist facilities. In other words, the image generation system 10 generates different images according to the data on the behavior of users of the tourist facilities. The data on user behavior is, for example, behavior history data of users within the tourist facility and data on the environment surrounding the users during their stay at the tourist facility. The behavior history data may also include data on the purchase history of users within the tourist facility.

[0014] The behavioral history data is, for example, a history of the areas and attractions used by the user within a tourist facility, the parades viewed, the shows viewed, the length of stay, the waiting time, the products purchased by the user, and the services received by the user. An area refers to each region of a tourist facility divided according to a predetermined criterion. The predetermined criterion is, for example, a criterion related to at least one of the theme set for the area, the type of attraction, the characters present in the area, and the types of stores. The predetermined criterion is not limited to the above. Furthermore, using an area means, for example, a user staying in an area of ​​a tourist facility. Furthermore, using an area means, for example, taking a stroll within the area, viewing the scenery, watching a show, interacting with characters, shopping, eating, taking photos, and resting. The use of an area is not limited to the above.

[0015] Data relating to the environment surrounding the user includes, for example, weather information, temperature, wind speed, and the number of nearby customers. The environment surrounding the user is not limited to the above. Furthermore, data relating to the user's behavior may include behavioral history data of the user on at least one of the journey to and from the tourist facility. For example, if the user travels by airplane to the nearest airport to the tourist facility, the generated image may reflect that the user has boarded the airplane. Furthermore, data relating to the user's behavior is not limited to the above.

[0016] The image of a tourist facility is, for example, an image that reflects the characteristics of the tourist facility. The image of a tourist facility is, for example, an image that illustrates the characteristics of the tourist facility. The characteristics of a tourist facility are, for example, at least one of attractions, characters, objects, locations, scenery, buildings, rides, shows, products, and food and drink offered that are unique to each tourist facility. The characteristics of a tourist facility are not limited to the above. Furthermore, the image of a tourist facility may be an image based on a real-life image that shows the characteristics of the tourist facility.

[0017] The tourist facility is, for example, a theme park. When the tourist facility is a theme park, the image generation system 10 generates, for example, an image depicting characters and attractions of the theme park. The image generation system 10 generates an image in which the characters and attractions depicted in the image are changed, for example, in accordance with data related to the behavior of theme park users. The image generation system 10 changes the type of characters and the type of attractions depicted in the image, for example, in accordance with the data related to the behavior of theme park users. The image generation system 10 changes at least one of the number of characters depicted in the image, the character's posture, the character's facial expression, the character's possessions, and the character's clothing, for example, in accordance with the data related to the behavior of theme park users.

[0018] A tourist facility may be a commercial facility, an amusement park, a sports facility, a natural park, a career experience facility, a museum, or an art museum. A tourist facility may also include a tourist destination. For example, a tourist facility may be an area in a tourist destination where multiple tourist spots are scattered. Tourist facilities are not limited to the above.

[0019] The image generation system 10 generates an image from text corresponding to a user's behavior and the environment at the time of the behavior, using a generative model that generates images related to, for example, tourist facilities from text. The image generation system 10 converts data related to the user's behavior into text that represents the user's behavior or the environment at the time of the behavior based on rules. The image generation system 10 then generates an image using the generative model based on the text converted from the data related to the user's behavior. The generated image is an image related to a tourist facility that corresponds to the data related to the user's behavior. The generated image is output to, for example, a terminal device 30 owned by a user of the tourist facility.

[0020] FIG. 2 shows an example of an image of a tourist facility generated by the image generation system 10. The example image of FIG. 2 is an image of a theme park with an animation theme using animals as characters. In the example image of FIG. 2, for example, a user has visited a mountain area and a river area, so the image depicts illustrations of mountains and rivers. Also, in the example image of FIG. 2, an illustration of a raccoon dog, a character representing the forest area through which the user passed, is depicted. For example, the image generation system 10 converts behavioral data indicating that the user has visited the mountain area and the river area into text such as "mountain" and "river." Furthermore, the image generation system 10 converts behavioral data indicating that the user has passed through a forest area into text such as "raccoon dog," a character walking in the forest area. The image generation system 10 then generates an image such as the example of FIG. 2 based on the text converted from the behavioral data. For example, a user can recall their experiences in the theme park by referring to an image such as the example of FIG. 2. Also, for example, by depicting a raccoon dog, a character from the forest area, among illustrations of mountains, the user can feel a sense of enjoyment and surprise from the composition of the image.

[0021] Furthermore, the image generation system 10 changes at least one of the number of characters depicted in the image, the clothing worn by the characters, the possessions of the characters, and the background, depending on the environment around the user, for example. For example, if the area used by the user is crowded, the image generation system 10 increases at least one of the number of characters and the types of characters depicted in the image compared to normal. For example, if it is raining, the image generation system 10 generates an image in which rain is depicted in the background. For example, if it is raining, the image generation system 10 generates an image in which a character is wearing a raincoat or an image in which a character is holding an umbrella. How the environment around the user is reflected in the image is not limited to the above.

[0022] FIG. 3 shows an example of an image of a tourist facility generated by the image generation system 10 when the area visited by a user is crowded. Similar to the example of the image in FIG. 2 , the example of the image in FIG. 3 includes illustrations of mountains and rivers because the user visited the mountain area and the river area. The example of the image in FIG. 3 also includes an illustration of a raccoon dog, a character representing the forest area the user passed through. The example of the image in FIG. 3 also includes illustrations of multiple raccoon dogs to express that the forest area the user passed through was crowded. For example, the image generation system 10 converts behavior-related data indicating that the user used the mountain area and the river area into text such as "mountain" and "river." The image generation system 10 also converts behavior-related data indicating that the user passed through the forest area into text such as "raccoon dog," a character walking in the forest area. The image generation system 10 also converts behavior-related data indicating that many people were staying in the forest area into text such as "mixed." The image generation system 10 then generates an image like the example of the image in FIG. 3 based on the text converted from the behavior-related data. For example, by referring to an image with multiple illustrations of raccoon dogs, such as the example image in Figure 3, users can recall the crowded conditions and feel a sense of enjoyment and surprise from the composition of the image with many raccoon dogs.

[0023] By generating images of tourist facilities that users have visited in this way, users can obtain images that reflect their own actions within the tourist facility. That is, users can obtain images that reflect their memories within the tourist facility. Furthermore, by reflecting the user's actions, randomness corresponding to the user's actions is generated in the content of the generated images. Furthermore, generating images using a generative model can also generate randomness in the content of the generated images. Therefore, for example, even if a user behaves similarly within a tourist facility to when they visited in the past, the user can obtain an image that is different from the image obtained previously. Therefore, users who view the images can feel surprise and enjoyment from the images, which can increase the likelihood that users of the tourist facility will visit the facility again.

[0024] Here, a description will be given of an example of a specific configuration of the image generation system 10. FIG.

[0025] The image generation system 10 basically includes an acquisition unit 11, a conversion unit 12, a generation unit 13, and an output unit 15. The image generation system 10 also includes, for example, an insertion image generation unit 14 and a storage unit 16.

[0026] The acquisition unit 11 acquires data regarding the user's behavior in the tourist facility. For example, the acquisition unit 11 acquires, as the data regarding the user's behavior, behavior history data of the user in the tourist facility and data regarding the surrounding environment at the time of the behavior. The acquisition unit 11 acquires the data regarding the user's behavior in the tourist facility from, for example, the terminal device 30. The acquisition unit 11 may acquire the data regarding the user's behavior in the tourist facility from, for example, the terminal device 30 carried by a companion of the user. The acquisition unit 11 may acquire the data regarding the user's behavior in the tourist facility from, for example, an information management server 20 connected via a network. The information management server 20 is, for example, a server that manages data regarding the user's behavior in the tourist facility.

[0027] The acquisition unit 11 may acquire information regarding the user's preferences for the image to be generated. The acquisition unit 11 may acquire information indicating the timing to output the image. The acquisition unit 11 may also acquire an image showing the user to be used by the insertion image generation unit 14. The acquisition unit 11 may acquire information regarding the user's preferences, information indicating the timing to output the image, and the image showing the user from, for example, the terminal device 30. The acquisition unit 11 may acquire information regarding the user's preferences, information indicating the timing to output the image, and the image showing the user via, for example, the information management server 20.

[0028] The conversion unit 12 converts data related to a user's behavior into text that represents the user's behavior or the environment at the time of the behavior based on set rules. The rules are set, for example, based on the user's behavior in an area or attraction within a tourist facility, so that the data related to the user's behavior is converted into text related to the area or attraction that the user visited. The rules are set, for example, based on the environment surrounding the user while staying in an area within the tourist facility or while visiting an attraction, so that the data related to the user's behavior is converted into text related to the environment surrounding the user.

[0029] The rule indicates, for example, the data item related to the user's behavior that is the target of conversion. The data item related to the user's behavior is, for example, information indicating what the data relates to, among the user's behavior history data and data related to the surrounding environment. The rule may include at least one of the number of texts after conversion and the selection criteria for text to be used for image generation. The selection criteria for text to be used for image generation is, for example, a criterion related to at least one of weighting, priority, and the number of selections per data item when selecting text to be used for image generation. The selection criteria for text to be used for image generation are not limited to the above. Furthermore, the items included in the rule are not limited to the above.

[0030] The rules are set, for example, so that the text converted from data regarding the user's behavior includes at least one of the names of attractions, areas, and characters associated with the attractions within the tourist facility visited by the user.

[0031] The text representing the user's behavior is, for example, text indicating an area or attraction of a tourist facility that the user visited. The text representing the user's behavior may be text indicating both an area and an attraction of a tourist facility that the user visited. The text representing the user's behavior is, for example, text indicating a show that the user attended. The text representing the user's behavior may be text indicating the length of the user's waiting time. The text representing the user's behavior may be text indicating a character with whom the user interacted. The text representing the user's behavior may be text indicating at least one of the location where the user ate, the contents of the meal, the location where the user purchased a product, and the contents of the purchased product. The text representing the user's behavior may include text indicating the user's accompanying party. The text representing the user's behavior is not limited to the above. Furthermore, the text representing the environment at the time of the user's behavior is, for example, text indicating at least one of the weather, wind direction, wind speed, temperature, humidity, traffic mix, and attraction operation status when the user was staying at the tourist facility. The text representing the environment at the time of the user's behavior is not limited to the above.

[0032] The conversion unit 12 converts data related to a user's behavior into text corresponding to a manner in which the data is to be reflected in an image, for example, based on a set rule. The conversion unit 12 converts data related to a user's behavior into text corresponding to a classification of manners in which the data is to be reflected in an image, for example, based on a set rule. The manner in which the data is to be reflected in an image may be, for example, a manner in which the text is reflected in the background and foreground of the image. The manner in which the text is to be reflected in an image may be, for example, a manner in which the text is reflected in the number of illustrations depicted in the image and / or a manner in which the text is reflected in the content of the illustrations. The manner in which the data is to be reflected in an image is not limited to the above. Furthermore, the classification of manners in which the text is to be reflected in an image may refer to each group when the text is grouped according to the manner in which the text is to be reflected in the image. The conversion unit 12 converts data related to a user's behavior into text for the background of the image and text for the foreground of the image, for example, based on a set rule. The conversion unit 12 may convert data related to a user's behavior into text for the background of the image or text for the foreground of the image, for example, based on a set rule. Furthermore, there may be multiple texts for the background of the image and multiple texts for the foreground of the image. The conversion unit 12 may further convert the data related to the user's behavior into text for decorating the image based on, for example, pre-defined rules. The text for decorating the image may be reflected in, for example, a frame pattern added to the image. The classification according to how the text is reflected in the image is not limited to the above.

[0033] The conversion unit 12 converts the data related to the behavior into text so that, for example, at least one of the background text and the foreground text includes at least one of the names of the attractions, the names of the areas, and the characters. For example, the conversion unit 12 converts data indicating the attractions used by the user, which is included in the data related to the user's behavior, into background text.

[0034] The behavioral data and the converted text are set, for example, in a table that associates the behavioral data with the converted text. When the behavioral data is numerical data, the table associates the numerical value of the behavioral data with the converted text. The conversion unit 12 refers to the table and converts the user's behavioral data into text.

[0035] The conversion unit 12 may also use a conversion model to convert data related to user behavior into text. The conversion model is, for example, a learning model generated by learning the relationship between data related to behavior and the converted text. The conversion model is generated, for example, by deep learning using a neural network. The algorithm for generating the conversion model is not limited to the above. The conversion model may be generated, for example, in a system external to the image generation system 10.

[0036] The conversion unit 12 may convert the data regarding user behavior into text for each item of the data regarding user behavior. For example, if the tourist facility is a theme park, the conversion unit 12 converts the data regarding user behavior into text so that at least one piece of text from each of the area, character, and environment during the user's stay is used to generate an image. Furthermore, the number of pieces of text to be used to generate an image may be set for each classification of the data regarding user behavior. The classification of the data regarding user behavior, the predetermined priority, and the number of pieces of text to be used to generate an image for each classification are set, for example, by an administrator of the image generation system 10.

[0037] The conversion unit 12 may convert the data related to the user's behavior into text to be used for generating an image based on a predetermined priority. The predetermined priority is, for example, a ranking of which of multiple items of data related to the behavior should be preferentially converted into text. For example, if the tourist facility is a theme park, the predetermined priority is information indicating which of the items of data related to the area, characters, and environment during the user's stay should be preferentially converted into text.

[0038] The predetermined priority is set in advance, for example, based on a policy for reflecting which user actions should be reflected in the image. For example, when reflecting areas visited by a user in an image, the priority for converting history data of the area used, among data related to the user's actions, into text related to the user's area and the characters in that area is set higher than that of data of other items. The conversion unit 12 converts the action-related data into text based on the predetermined priority, for example, so that the amount of text converted from the action-related data becomes a predetermined number. The predetermined number is set, for example, to a value that makes the generated image more acceptable to users. The predetermined priority and the predetermined number are set, for example, by an administrator of the image generation system 10. Alternatively, the predetermined priority and the predetermined number may be set by the user. The predetermined number may be set randomly each time an image is generated.

[0039] The conversion unit 12 may select a layer from the layered text and convert the data related to the user's behavior into text included in the selected layer. The layering is configured, for example, so that the text included indicates more detailed objects from higher layers to lower layers. For example, in a nature-themed theme park, the layering is configured so that higher layers include text related to the area, middle layers include text related to the classification of creatures present in the area, and lower layers include text indicating the specific names of the creatures. For example, the conversion unit 12 converts the data related to the behavior into text at a lower layer the longer the user stays in the area. By converting the data into text in this manner, it is possible to generate an image that reflects the area in which the user is interested in in more detail.

[0040] The conversion unit 12 may convert data related to user behavior into text to be used for generating an image based on a predetermined weighting. The predetermined weighting is, for example, an index used when selecting data items to be converted into text from among multiple data items. The predetermined weighting refers, for example, to weighting each data item related to behavior. The conversion unit 12 converts data related to behavior that has a higher weight than other items based on the predetermined weighting into text to be used for generating an image. The conversion unit 12, for example, weights data related to behavior in areas where the user spends a long time, so that the weight is higher. By weighting in this way, for example, areas where the user spends a long time are more likely to be reflected in the image. The conversion unit 12 may also weight data related to items preferred by the user so that the weight is higher. For example, the conversion unit 12 weights data related to behavior in areas where the user spends a long time and at least one of attractions, so that the weight is higher. The criteria for the predetermined weighting are not limited to the above. For example, the conversion unit 12 converts data of items whose predetermined weighting is equal to or greater than a predetermined standard into text. The conversion unit 12 may also convert, for example, data of a predetermined number of items having the highest predetermined weighting values ​​into text. The predetermined weighting criteria and the predetermined number are set, for example, by the operator of the image generation system 10, the operator of the tourist facility, or the user.

[0041] The conversion unit 12 may convert behavioral data related to at least one of the timing of use of a tourist facility, a specific area used within the tourist facility, and a specific attraction used within the tourist facility into text. For example, if a special image of using a specific attraction is provided during a campaign period, the conversion unit 12 may convert the behavioral data into text capable of generating a special image indicating use of the specific area and the specific attraction. Also, for example, if a special image is provided during a specific custom period, the converted text may include text indicating the specific custom. For example, the converted text may include text indicating New Year's. In this way, for example, by converting an image according to a period into a generable text and generating an image, users can enjoy using tourist facilities for each period.

[0042] The conversion unit 12 may convert data related to user behavior into text corresponding to the attributes of the user. For example, the conversion unit 12 may convert data related to user behavior into text so that a different image is generated for a user who has used the facility a certain number of times per year than for other users. In this way, for example, converting an image according to the number of times of use into generatable text and generating the image may lead to an increase in the number of times a tourist facility is used. The conversion unit 12 may also convert data related to user behavior into text so that different images are generated for adults and children. For example, when generating an image for users under a certain age, the conversion unit 12 converts data related to user behavior into text so that the image contains more characters than images for users above a certain age. In this way, generating an image by converting age-appropriate images into generatable text may provide satisfaction to users of a wide range of ages, which may lead to group use of the tourist facility.

[0043] When an image generated by the generation unit 13 is output, the conversion unit 12 may convert data related to the user's behavior after the image was output into text representing the user's behavior or the environment at the time of the behavior. When an image for the same user is output, the conversion unit 12 converts data related to the behavior after the image was output into text representing the user's behavior or the environment at the time of the behavior. In other words, the conversion unit 12 resets the history of the behavioral data and converts the behavioral data acquired after the reset into text representing the user's behavior or the environment at the time of the behavior. In this way, by converting data related to the user's behavior after the image was output into text, when the generation unit 13 generates an image again, it becomes possible to generate an image that is not similar to an image that has already been output.

[0044] When the image generated by the generation unit 13 is output, the conversion unit 12 may convert data related to the user's behavior for a predetermined time period into text representing the user's behavior or the environment at the time of the behavior. For example, the conversion unit 12 converts data related to the user's behavior in the morning, afternoon, and evening into text representing the user's behavior or the environment at the time of the behavior, respectively. In this way, by converting the data related to the user's behavior for each time period into text representing the user's behavior or the environment at the time of the behavior, an image corresponding to the time period can be generated. The time period of the font is set, for example, by the operator of the image generation system 10, the operator of the tourist facility, or the user. In this way, by changing the period of the behavior-related data to be converted into text each time an image is generated, the user can obtain, for example, different images each time the image is acquired. This allows the user to, for example, feel enjoyment from each image.

[0045] The generation unit 13 uses a generative model that generates an image related to a tourist facility based on text, to generate an image based on the text converted by the conversion unit 12. For example, the generation unit 13 uses a generative model that generates an image related to a tourist facility from text, to generate an image from the text converted by the conversion unit 12. For example, the generation unit 13 uses the generative model to generate an image related to a tourist facility based on text converted by the conversion unit 12 from data related to user behavior. For example, the generative model generates an image related to a tourist facility using text related to a tourist facility as input. For example, the generative model generates an image related to a tourist facility that depicts features of the tourist facility as an illustration. For example, the generative model generates an image that reflects the features of the tourist facility and changes according to the data related to user behavior. For example, the generative model may generate an image based on a real-life image that depicts the features of the tourist facility.

[0046] A generative model is a machine learning model that generates images from text. The generative model is generated using, for example, a generative adversarial network (GAN). The generative model is generated using images of tourist facilities, information about the locations depicted in the images, and text associated with the images as training data. The images of tourist facilities are, for example, images that illustrate the features of the tourist facilities. The images of tourist facilities may also be photographs that show the features of the tourist facilities. The generative model may be generated by retraining a machine-learned learning model that generates images from text using training data for each tourist facility. Furthermore, the learning algorithm used to generate the generative model is not limited to GAN.

[0047] For example, if the tourist facility is a theme park, the image of the tourist facility used as training data may be, for example, an image depicting at least one of a theme park character and an attraction at the theme park. Text is associated with the image. The information about the location depicted in the image is the name of an attraction or area within the theme park. The information about the location depicted in the image may be the name of a character depicted in the image. Text associated with the image is, for example, text describing the characteristics of the image. The text describing the characteristics of the image is text that corresponds to the image when behavioral data is converted into text. For example, if the area or attraction visited by the user is crowded, the text describing the characteristics of the image is the text "crowded." In this case, the image associated with text may depict, for example, multiple characters. Multiple pieces of text may be associated with the image.

[0048] The generation unit 13 generates an image of a tourist facility using a generative model based on the text converted by the conversion unit 12, at a predetermined timing based on the user's behavior, for example. For example, the generation unit 13 generates an image of the tourist facility when the user leaves the tourist facility. The generation unit 13 may also generate an image of the tourist facility when the user's stay time or waiting time at the same location is equal to or exceeds a certain standard. The generation unit 13 may also generate an image of the tourist facility when the user is in a restaurant or rest area. The predetermined timing is set by the operator of the image generation system 10, the operator of the tourist facility, or the user.

[0049] The generation unit 13 may generate an image of a tourist facility at a predetermined time. Furthermore, the generation unit 13 may generate an image of a tourist facility at a predetermined time interval. The predetermined time and the predetermined time interval are set by the operator of the image generation system 10, the operator of the tourist facility, or a user. Furthermore, the timing at which the generation unit 13 generates an image of a tourist facility is not limited to the above.

[0050] The insertion image generation unit 14 generates an image by inserting an image based on a user into an image generated by the generative model from text, for example. The insertion image generation unit 14, for example, illustrates an image of the user and inserts it into the image generated by the generative model. The insertion image generation unit 14 generates, for example, an illustration image that reflects the facial features of the user appearing in the image. The insertion image generation unit 14 then inserts the generated illustration image into the image generated by the generative model. The insertion image generation unit 14 may also generate an illustration image that reflects the features of the posture or pose of the user appearing in the image and insert it into the image generated by the generative model.

[0051] The insertion image generation unit 14 generates an illustrated image that reflects the facial, posture, or pose characteristics of a user, for example, based on a character related to an attraction that the user has used in a tourist facility. The insertion image generation unit 14, for example, inserts an illustrated image of the user near a character depicted in an image generated by the generative model. The insertion image generation unit 14 generates an image in which the illustrated user appears to be interacting with a character depicted in an image generated by the generative model. The insertion image generation unit 14 may also insert an illustrated image of the user near an attraction depicted in an image generated by the generative model. The position at which the illustrated image of the user is inserted is not limited to the above.

[0052] The insertion image generation unit 14 uses, for example, an image insertion model to generate an image in which an image based on a user is inserted into an image generated by a generative model based on text. The insertion image generation unit 14 uses, for example, an image insertion model to generate an image in which an image based on a user is inserted into an image generated by a generative model from text. The image insertion model is a machine learning model that illustrates an image of a user and inserts the illustrated image into an image generated by the generative model. The image insertion model is generated using, for example, a GAN. The image insertion model is generated using an image in which an illustrated user is inserted and the user's image as learning data. Furthermore, the learning algorithm used to generate the image insertion model is not limited to GAN.

[0053] 5 is a diagram showing an example of an image showing the face of the user to be inserted into the image generated by the generation unit 13. The example of the image in FIG. 5 is, for example, an image of the upper body of the user captured by a photographing device included in the terminal device 30.

[0054] 6 shows an example of an image in which an illustration of the user in the example image of FIG. 5 is inserted into an image generated by the generation unit 13. In the example image of FIG. 6, the user is depicted as a raccoon dog by illustrating the facial features of the user in an image similar to the image shown in the example of FIG. 3. By generating an image like the example image of FIG. 6 based on an image in which the user appears, the image generation system 10 can generate an image that makes it easier for the user to recall their experience at a tourist facility, for example.

[0055] The output unit 15 outputs the generated image. The generated image is, for example, at least one of an image generated by a generative model and an image inserted into an image insertion model. The output unit 15 outputs the generated image to, for example, a terminal device 30. The output unit 15 may output the generated image to a management server that manages information about users of tourist facilities. The output unit 15 may also output the generated image to a display device (not shown) connected to the image generation system 10.

[0056] The output unit 15 outputs the generated image, for example, when the user is performing a predetermined action, or when the user leaves the exit of the tourist facility.

[0057] The output unit 15 outputs the generated image when a predetermined time has elapsed since the user left the exit of the tourist facility. The predetermined time is set, for example, based on the time when the user is expected to be on his / her way home from the tourist facility. The predetermined time may be set so that the image is output the day after the user visited the tourist facility or later. For example, by setting the predetermined time to output the image the next day, the user viewing the image can recall their actions from the previous day. Furthermore, by setting the predetermined time to output the image a long time after the user visited the tourist facility, it is possible to encourage the user to reuse the tourist facility. For example, the output unit 15 outputs the generated image three months after the user visited the tourist facility. Furthermore, the predetermined time is not limited to the above.

[0058] The output unit 15 may output the generated image when the user returns home from the tourist facility. The output unit 15 determines whether the user has returned home based on, for example, the location information of the terminal device 30 owned by the user and the user's registration information.

[0059] The output unit 15 may output the generated image, for example, when the user is in a restaurant in a tourist facility. The output unit 15 may also output the generated image when the time the user has been waiting to use an attraction exceeds a certain threshold. The output unit 15 determines the user's location or the waiting time for using an attraction, for example, based on the location information of the terminal device 30 owned by the user.

[0060] The output unit 15 may output the generated image in response to a user's request. The output unit 15 may also output the generated image at a predetermined time. The predetermined time is set, for example, by the operator of the image generation system 10, the operator of the tourist facility, or the user. The output unit 15 may also output the generated image at predetermined time intervals from the time the user enters the tourist facility to the time the user leaves. The predetermined time intervals are set, for example, by the operator of the image generation system 10, the operator of the tourist facility, or the user.

[0061] The output unit 15 may output the generated image to a manufacturing system for products related to tourist facilities. Products related to tourist facilities are, for example, products specific to the tourist facility that are sold at stores within the tourist facility. Products related to the tourist facility may also be products that are sent to users at a later date. For example, the output unit 15 outputs the generated image to a printing system that prints the generated image on T-shirts of the tourist facility. The output unit 15 may also output the generated image to a creation system that creates photo frames using the generated image. The output destination of the generated image is not limited to the above.

[0062] Fig. 7 shows an example of a diagram image of a tourist facility generated by the image generation system 10. The example image of Fig. 7 is an image of a theme park with an animation theme that uses animals as characters, similar to Fig. 2. The example image of Fig. 7 is an example of an image generated when, for example, a grassland area, a forest area, a mountain area, and a village area within the theme park are used.

[0063] The conversion unit 12 converts, for example, data on areas used, included in the data on the user's behavior, into text such as "grassland," "forest," "mountain," and "village." The conversion unit 12 also converts, for example, data on the number of areas used, included in the data on the user's behavior, into text such as "many areas." The generation unit 13 then generates, for example, an image like the example image in FIG. 7 using a generative model based on the text converted by the conversion unit 12.

[0064] In the example image of FIG. 7 , for example, a grassland at the foot of a mountain is depicted as the grassland area scenery based on the "grassland" converted from behavioral data due to the user's use of the grassland area. Also, in the example image of FIG. 7 , multiple characters are depicted based on the "grassland," "forest," "mountain," "village," and "many areas" converted from behavioral data due to the user's visit to multiple areas. In the example image of FIG. 7 , characters depicting a horse in the grassland area, a raccoon dog in the forest area, a hawk in the mountain area, and a dog and chicken in the village area are depicted. By generating an image like the example image of FIG. 7 , the image generation system 10 can, for example, generate an image that makes it easy for the user to recall having used multiple areas.

[0065] Fig. 8 is an example of an image in which weather information is further reflected in the example of the image in Fig. 2. The example of the image in Fig. 8 is an image in which, like the example of the image in Fig. 2, a user passes through a forest area and then visits a mountain area and a river area. The example of the image in Fig. 8 is an image in which a sudden thunderstorm occurs while the user is visiting a theme park.

[0066] For example, the conversion unit 12 converts data about the area used, included in the data about the user's behavior, into text such as "forest," "mountain," and "river." Furthermore, the conversion unit 12 converts data about thunderstorms, included in the data about the user's behavior, into text such as "sudden rain" and "thunder." The generation unit 13 then generates an image, such as the example image in FIG. 8 , using a generative model based on the text converted by the conversion unit 12.

[0067] In the example image of Fig. 8, illustrations of mountains and rivers, as well as an illustration of a raccoon dog, are drawn based on "forest," "mountain," and "river" converted from the data of the area used. Also, in the example image of Fig. 8, thunderclouds and rainclouds are drawn in part of the image based on, for example, "sudden rain" and "thunder" converted from meteorological data. By generating an image like the example image of Fig. 8, the image generation system 10 can generate an image that makes it easy for the user to recall a sudden event, such as being caught in a sudden rain shower.

[0068] The storage unit 16 stores, for example, data used to generate images related to tourist facilities. The storage unit 16 stores, for example, rules for converting data related to user behavior into text, and the storage unit 16 stores, for example, a table associating data related to user behavior with text. The storage unit 16 stores, for example, a generation model. The storage unit 16 also stores, for example, a conversion model. The storage unit 16 also stores, for example, an insertion image generation model. The generation model, the conversion model, and the insertion image generation model may be stored in a storage means other than the storage unit 16.

[0069] The information management server 20 manages, for example, information about the environment within a tourist facility. The information management server 20 manages, for example, information about the environment within a tourist facility for each date and time. The information about the environment within a tourist facility is, for example, information about one or more items of weather information, number of visitors, number of visitors per area, density of users staying in each area, average stay time per area, number of users of attractions, and average waiting time for attractions. The information about the environment within a tourist facility is not limited to the above. For example, the information about the environment within a tourist facility is used as data about the surrounding environment among data about user behavior in the conversion unit 12 of the image generation system 10. The information management server 20 outputs, for example, information about the environment within a tourist facility to the acquisition unit 11 of the image generation system 10 in response to a request from the image generation system 10.

[0070] The information management server 20 may manage behavior history data of users within a tourist facility. For example, the information management server 20 acquires the user behavior history data from the entrance and exit gates, the entrance and exit gates of each attraction, a monitoring system within the tourist facility, a terminal device 30 carried by the user, a POS (Point of Sales) system at a shop, and a POS system at a restaurant. The information management server 20 may also acquire the user behavior history data from systems other than those mentioned above. The user behavior history data within a tourist facility is used, for example, in the conversion unit 12 of the image generation system 10 as data related to the user's behavior.

[0071] The information management server 20 may manage images generated by the image generation system 10. The information management server 20 may acquire images generated by the image generation system 10, for example, from the output unit 15 of the image generation system 10. The information management server 20 may also output images to the terminal device 30 in response to a request from the terminal device 30.

[0072] The terminal device 30, for example, acquires an image generated by the image generation system 10. The terminal device 30 then outputs the acquired image to a display device (not shown). The terminal device 30 also records, for example, data related to the user's behavior. The terminal device 30 then outputs the recorded data related to the user's behavior to, for example, the image generation system 10. The terminal device 30 records the data related to the user's behavior, for example, using an application program for the tourist facility. The terminal device 30 records, for example, at least one of the following: the user's time of entry into the tourist facility, the areas in the tourist facility visited, the length of stay in each area, the attractions visited, the length of stay at each attraction, the wait time for the attraction, and the purchased products. When the location of the terminal device 30 is used as the user's location information, the terminal device 30 identifies the location of the terminal device 30, for example, using GNSS (Global Navigation Satellite System).

[0073] The following describes the operation of the image generation system 10 when generating an image of a tourist facility. Fig. 9 shows an example of the operation flow when the image generation system 10 generates an image of a tourist facility.

[0074] The acquisition unit 11 acquires data on the behavior of users at the tourist facility (Step S11). The acquisition unit 11 acquires data on the behavior of users at the tourist facility from the terminal device 30, for example.

[0075] When the data on the user's behavior is acquired, the conversion unit 12 converts the data on the user's behavior into text that represents the user's behavior or the environment at the time of the behavior, based on the set rules (step S12).

[0076] Once the data on user behavior has been converted into text, the generation unit 13 generates an image from the text converted by the conversion unit 12 using a generation model that generates an image related to a tourist facility from the text (step S13).

[0077] When an image is generated from text, if there is an image of the user to be inserted into the image (Yes in step S14), the insertion image generation unit 14 generates an image by inserting an image based on the user into the image generated by the generative model from the text (step S15).

[0078] When the image into which the user-based image is inserted is generated, the output unit 15 outputs the image generated by the insertion image generation unit 14 (step S16). The output unit 15 outputs the image generated by the insertion image generation unit 14 to, for example, the terminal device 30.

[0079] When an image is generated from text, if there is no image of the user to be inserted into the image (No in step S14), the output unit 15 outputs the image generated by the generation unit 13 (step S16). The output unit 15 outputs the image generated by the generation unit 13 to, for example, the terminal device 30.

[0080] The image generation system 10 converts data about user behavior in a tourist facility into text representing the user's behavior or the environment at the time of the behavior based on set rules. The image generation system 10 uses a generative model to generate images of the tourist facility from the text representing the user's behavior or the environment at the time of the behavior. By generating images that reflect the user's behavior in the tourist facility or the environment at the time of the behavior in this way, the image generation system 10 can generate images that reflect the user's experience in the tourist facility. Therefore, even if a user visits the same tourist facility multiple times, the image generation system 10 can generate different images each time the user visits the same facility. Furthermore, even if a user visits the same attraction in a tourist facility, the image generation system 10 can generate different images each time the user visits the attraction, depending on the environment at the time of the visit. Therefore, the image generation system 10 can generate images that correspond to the user's behavior. By generating images that correspond to the user's behavior, the image generation system 10 can generate images that evoke a sense of surprise and freshness in the user.

[0081] Furthermore, when an image based on an image showing a user is inserted into an image generated by a generative model, the image generation system 10 generates, for example, an image depicting the user in an image that reflects the environment in which the user was using the image. By generating such an image, the image generation system 10 can generate an image that evokes the user's experience. Therefore, the image generation system 10 can generate, for example, an image that gives the user a greater sense of satisfaction.

[0082] Each process in the image generation system 10 may be distributed and executed among a plurality of information processing devices connected via a network. For example, the process in the conversion unit 12 and the process in the generation unit 13 and the insertion image generation unit 14 may be executed in different information processing devices. Furthermore, for example, the process in the conversion unit 12 and the generation unit 13 and the process in the insertion image generation unit 14 may be executed in different information processing devices. It can be set as appropriate which of the plurality of information processing devices each process in the image generation system 10 is executed in.

[0083] Each process in the image generation system 10 can be realized by executing a computer program on a computer. Fig. 10 shows an example of the configuration of a computer 100 that executes a computer program that performs each process in the image generation system 10. The computer 100 includes a CPU (Central Processing Unit) 101, a memory 102, a storage device 103, an input / output I / F (Interface) 104, and a communication I / F 105.

[0084] The CPU 101 reads and executes computer programs for performing each process from the storage device 103. The CPU 101 may be configured with a combination of multiple CPUs. Furthermore, the CPU 101 may be configured with a combination of a CPU and another type of processor. For example, the CPU 101 may be configured with a combination of a CPU and a graphics processing unit (GPU). The memory 102 is configured with a dynamic random access memory (DRAM) or the like, and temporarily stores computer programs executed by the CPU 101 and data being processed. The storage device 103 stores computer programs executed by the CPU 101. The storage device 103 is configured with, for example, a non-volatile semiconductor storage device. Other storage devices such as a hard disk drive may also be used for the storage device 103. The input / output I / F 104 is an interface that accepts input from an operator and outputs display data, etc. The communication I / F 105 is an interface that transmits and receives data between the information management server 20, the terminal device 30, and other information processing devices. Furthermore, the terminal device 30 may have a configuration similar to that of the computer 100.

[0085] The computer program used to execute each process can also be stored and distributed on a computer-readable recording medium that non-temporarily stores data. Examples of recording media that can be used include magnetic tapes for recording data and magnetic disks such as hard disks. Optical disks such as CD-ROMs (Compact Disc Read Only Memory) can also be used as recording media. Non-volatile semiconductor storage devices can also be used as recording media.

[0086] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0087] [Supplementary Note 1] An image generation system comprising: an acquisition means for acquiring data on user behavior in a tourist facility; a conversion means for converting the data on user behavior into text that represents the user's behavior or the environment at the time of the behavior based on set rules; a generation means for generating an image based on the text converted by the conversion means using a generation model that generates an image related to a tourist facility based on the text; and an output means for outputting the generated image.

[0088] [Supplementary Note 2] The image generation system according to Supplementary Note 1, wherein the rule is a rule that converts data about user behavior into text about the area or attraction used by the user based on the user's behavior in the area or attraction within the tourist facility.

[0089] [Supplementary Note 3] The image generation system according to Supplementary Note 1 or 2, wherein the conversion means converts the data regarding the user's behavior into text according to a manner to be reflected in the image based on a set rule.

[0090] [Supplementary Note 4] The image generation system according to any one of Supplementary Notes 1 to 3, wherein the output means outputs the generated image at a timing when the user is performing a predetermined action.

[0091] [Supplementary Note 5] The image generation system according to any one of Supplementary Notes 1 to 4, wherein the conversion means converts the data on the user's behavior into text to be used in generating an image based on a weight indicating a priority to be reflected in the image.

[0092] [Supplementary Note 6] The image generation system according to any one of Supplementary Notes 1 to 5, further comprising an insertion image generation means for generating an image in which an image based on the face of the user is inserted into an image generated by the generative model based on text.

[0093] [Supplementary Note 7] The image generation system according to any one of Supplementary Notes 1 to 6, wherein the conversion means converts behavioral data relating to at least one of the timing of use of a tourist facility, a specified area used within the tourist facility, and a specified attraction used within the tourist facility into text.

[0094] [Supplementary Note 8] The image generation system according to any one of Supplementary Notes 1 to 7, wherein the tourist facility is a theme park, and the generative model generates an image based on at least one of an area, an attraction, and a character of the theme park.

[0095] [Supplementary Note 9] The image generation system according to any one of Supplementary Notes 1 to 8, wherein the conversion means, when the image is output, converts data relating to actions performed after the image is output into text representing the user's actions or the environment at the time of the actions.

[0096] [Supplementary Note 10] The image generation system according to any one of Supplementary Notes 1 to 8, wherein the output means outputs the generated image to a manufacturing system for a product related to the tourist facility.

[0097] [Supplementary Note 11] An image generation method comprising: acquiring data on user behavior at a tourist facility; converting the data on the user behavior into text that represents the user behavior or the environment at the time of the behavior based on set rules; generating an image based on the converted text using a generative model that generates an image related to the tourist facility based on the text; and outputting the generated image.

[0098] [Supplementary Note 12] A recording medium that non-temporarily records an image generation program that causes a computer to execute the following processes: a process of acquiring data on user behavior at a tourist facility; a process of converting the data on the user behavior into text that represents the user behavior or the environment at the time of the behavior based on set rules; a process of generating an image based on the converted text using a generative model that generates an image related to the tourist facility based on the text; and a process of outputting the generated image.

[0099] The present disclosure has been described above using the above-described embodiment as an example. However, the present disclosure is not limited to the above-described embodiment. That is, the present disclosure can be applied in various aspects that can be understood by a person skilled in the art within the scope of the present disclosure.

[0100] REFERENCE SIGNS LIST 10 Image generation system 11 Acquisition unit 12 Conversion unit 13 Generation unit 14 Insertion image generation unit 15 Output unit 16 Storage unit 20 Information management server 30 Terminal device 100 Computer 101 CPU 102 Memory 103 Storage device 104 Input / output I / F 105 Communication I / F

Claims

1. An acquisition means for acquiring data on user behavior at a tourist facility; a conversion means for converting the data relating to the user's behavior into text representing the user's behavior or the environment at the time of the behavior based on a set rule; a generation means for generating an image based on the text converted by the conversion means using a generation model that generates an image related to a tourist facility based on the text; an output means for outputting the generated image; An image generation system comprising:

2. The rule is a rule that converts data on user behavior into text about the area or attraction visited by the user based on the user's behavior in the area or attraction within the tourist facility. The image generation system of claim 1 .

3. the conversion means converts the data relating to the user's behavior into text according to a manner reflected in the image based on a set rule; 3. The image generation system according to claim 1 or 2.

4. the output means outputs the generated image at a timing when the user is performing a predetermined action.

3. The image generation system according to claim 1 or 2.

5. the conversion means converts the data on the user's behavior into text to be used for generating an image based on a weight indicating a priority to be reflected in the image; 3. The image generation system according to claim 1 or 2.

6. The system further includes an insertion image generation means for generating an image by inserting an image based on the face of the user into an image generated by the generative model based on text.

3. The image generation system according to claim 1 or 2.

7. the conversion means converts into text the behavioral data relating to at least one of the timing of visiting the tourist facility, the predetermined area visited within the tourist facility, and the predetermined attraction visited within the tourist facility; 3. The image generation system according to claim 1 or 2.

8. the tourist facility is a theme park, The generative model generates images based on at least one of a theme park area, an attraction, and a character.

3. The image generation system according to claim 1 or 2.

9. Obtaining data on user behavior at tourist facilities, converting data relating to the user's behavior into text representing the user's behavior or the environment at the time of the behavior based on established rules; generating an image based on the converted text using a generative model that generates an image related to a tourist facility based on the text; Output the generated image, Image generation method.

10. Acquiring data on user behavior at tourist facilities; A process of converting the data on the user's behavior into text that represents the user's behavior or the environment at the time of the behavior based on set rules; generating an image based on the converted text using a generative model that generates an image related to a tourist facility based on the text; The process of outputting the generated image An image generation program that causes a computer to execute the above.