JP2018041334A - Generation device, generation method, and generation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To generate an appropriate image according to a user while suppressing a user's load.SOLUTION: A generation device includes an acquisition unit and generation unit. The acquisition unit obtains user information on a user using a terminal device. The generation unit generate a provision image to be provided for the terminal device, on the basis of both the user information obtained by the acquisition unit and a model for outputting an image according to input information. For example, the generation unit generates a provision image to be provided for the terminal device, on the basis of the user information including attribute information of the user.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a generation device, a generation method, and a generation program.

  Conventionally, techniques for generating images based on various information have been provided. For example, there is provided a technique for outputting (generating) a recommended image based on an image selected by a user as a target to be combined with an object included in the recommended image.

Japanese Patent Application Laid-Open No. 2015-097036

Alec Radford, Luke Metz, Soumith Chintala, "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks", arXiv preprint arXiv: 1511.06434 (2016) & ICLR (International Conference on Learning Representations) -2016 Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, "A Neural Algorithm of Artistic Style", arXiv preprint arXiv: 1508.06576

  However, with the above-described conventional technology, it may be difficult to generate an appropriate image according to the user while suppressing the load on the user. For example, it may be necessary for the user to select an image as a target to be combined with the target object included in the recommended image in spite of the recommended image to the user. It is difficult to generate an image.

  The present application has been made in view of the above, and an object thereof is to provide a generation device, a generation method, and a generation program that generate an appropriate image according to a user while suppressing a user's load.

  The generation device according to the present application is based on an acquisition unit that acquires user information related to a user who uses a terminal device, the user information acquired by the acquisition unit, and a model that outputs an image according to input information. And a generation unit that generates a provided image to be provided to the terminal device.

  According to one aspect of the embodiment, it is possible to generate an appropriate image according to the user while suppressing the load on the user.

FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the generation apparatus according to the embodiment. FIG. 3 is a diagram illustrating an example of a user attribute information storage unit according to the embodiment. FIG. 4 is a diagram illustrating an example of an action history information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of the action schedule information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the seed information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of a model information storage unit according to the embodiment. FIG. 8 is a flowchart illustrating an example of the generation process according to the embodiment. FIG. 9 is a diagram illustrating an example of the generation process according to the modification. FIG. 10 is a diagram illustrating a configuration example of a generation apparatus according to a modification. FIG. 11 is a diagram illustrating an example of a style information storage unit according to a modification. FIG. 12 is a flowchart illustrating an example of the generation process according to the modification. FIG. 13 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the generation apparatus.

  Hereinafter, a generation apparatus, a generation method, and a mode for executing a generation program (hereinafter referred to as “embodiment”) according to the present application will be described in detail with reference to the drawings. Note that the generation device, the generation method, and the generation program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. Generation process)
An example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 1 shows a case where the generation apparatus 100 generates a provided image to be provided to the terminal apparatus 10 used by the user based on the user information of the user. Further, FIG. 1 illustrates a case where the generation apparatus 100 generates a theme image of the mail application A as a provided image. In the example of FIG. 1, a case where the theme image of the mail application A is a provided image is shown as an example, but the provided image may be any image (content) as long as it is an image provided to the user.

  As illustrated in FIG. 1, the generation system 1 includes a terminal device 10 and a generation device 100. The terminal device 10 and the generation device 100 are connected to be communicable by wire or wireless via a predetermined communication network (not shown). The generation system 1 illustrated in FIG. 1 may include a plurality of terminal devices 10 and a plurality of generation devices 100.

  The generation apparatus 100 is an information processing apparatus that generates a provided image to be provided to the terminal device 10 based on user information and an image generation model (hereinafter also simply referred to as “model”) that outputs an image according to input information. It is. For example, as illustrated in the model information storage unit 125, the generation device 100 includes a model M1 that is used to generate a theme image of the mail application A. Note that the generation apparatus 100 may have a plurality of models according to the image to be generated.

  For example, in the example shown in FIG. 1, the model such as the model M1 used by the generation apparatus 100 may be a learning device that is appropriately generated using various conventional techniques such as a convolutional neural network. For example, the model such as the model M1 used by the generation apparatus 100 may be a model generated by DCGANs (Deep Convolutional Generative Adversarial Networks) as in Non-Patent Document 1. For example, the generation device 100 generates a model such as the model M1 by using input information extracted from various images (for example, an N-dimensional vector (N is an arbitrary number equal to or greater than 1)) as learning data. May be. For example, the generating apparatus 100 may generate the model M1 by using input information (for example, an N-dimensional vector) extracted from various images related to the theme image of the mail application A as learning data. Note that the above is an example, and the generation apparatus 100 may generate a model by any method as long as a desired model such as the model M1 can be generated.

  In the example of FIG. 1, the generation device 100 generates a model M1 as shown in the model information storage unit 125. Further, as shown in the model information storage unit 125, the model information related to the model M1 has a feature 1 weight of “0.5”, a feature 2 weight of “−0.4”, and a feature 3 weight of “0. 2 "etc. For example, the generation device 100 generates an image from input input information by inputting predetermined input information such as an N-dimensional vector to the model M1. Note that the generation apparatus 100 may acquire a desired model such as the model M1 from an external information processing apparatus.

  Further, the generation device 100 generates a provided image using a parameter based on a user context estimated based on user information. Note that the context here means the situation of the user or the terminal device 10 and the environment (background) of the user or the terminal device 10. For example, the context is information corresponding to a situation where the terminal device 10 is used by a user or a state where a user who owns the terminal device 10 is placed. The context includes the content of the content provided to the user, the content of the user's utterance, the user's attributes, the user's current location, the current time, the physical environment in which the user is placed, the social environment in which the user is placed, the user It may be estimated based on various information such as the exercise state of the user and the emotion of the user.

  In the example of FIG. 1, as shown in the user attribute information storage unit 121, the context is indicated by an abstract symbol such as the context CN11 or the context CN21, but each context is information indicating a specific situation of the user. It may be. For example, the context CN11 may be a context corresponding to a situation where “a user who likes anime is interested in the character A”. For example, the context CN21 may be a context corresponding to a situation “planned to watch a soccer game”.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. In the example shown in FIG. 1, the case where the terminal device 10 is a smartphone used by the user is shown. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10. Specifically, FIG. 1 illustrates a case where the terminal device 10 is a smartphone used by a user identified by the user ID “U1” (hereinafter, may be referred to as “user U1”).

  In the example illustrated in FIG. 1, the terminal device 10 will be described as the terminal devices 10-1 and 10-2 according to the display of the screen of the terminal device 10. The terminal devices 10-1 and 10-2 are the same terminal device 10. Hereinafter, the terminal devices 10-1 and 10-2 will be referred to as the terminal device 10 when they are not particularly distinguished.

  First, as illustrated in FIG. 1, the terminal device 10 starts the mail application A in response to the operation of the user U1 (step S11). And the terminal device 10 requests | requires the theme image of the mail application A from the production | generation apparatus 100 (step S12). In the example of FIG. 1, the terminal device 10 transmits user information of the user U1 when requesting the theme image of the mail application A to the generation device 100. Note that if the generation apparatus 100 has already acquired the user information of the user U1, the terminal apparatus 10 may not transmit the user information of the user U1 in step S12.

  For example, the terminal device 10-1 transmits information indicating that the user U1 who uses the terminal device 10 is a 20's female to the generation device 100. When the generation apparatus 100 stores user information related to the user U1, the terminal apparatus 10-1 transmits information indicating that the user U1 who uses the terminal apparatus 10 is a 20's female to the generation apparatus 100. It does not have to be. In the example of FIG. 1, the terminal device 10 requests the generation device 100 for a theme image of the mail application A when the mail application A is activated. A theme image of A may be acquired, and the theme image may be displayed when the mail application A is activated.

  The generation device 100 that has acquired the request for the theme image of the mail application A from the terminal device 10 used by the user U1 estimates a context related to the user U1 (step S13). The generation device 100 estimates the context related to the user U1 using the user information of the user U1. For example, the generating apparatus 100 estimates a context related to the user U1 using various information related to the user U1 stored in the user attribute information storage unit 121, the action history information storage unit 122, the action schedule information storage unit 123, and the like. For example, the generation apparatus 100 may include a user action history, a user action schedule, a user attribute, a user current position, a current time, a physical environment in which the user is placed, a social environment in which the user is placed, a user exercise state, And a user's context is estimated based on various information, such as a user's emotion.

  In the example of FIG. 1, the generation apparatus 100 uses the user information including the fact that the user U1 has searched for the character A appearing in the anime A, and plans to watch a movie of the anime A, and the context of the user U1. Is estimated. For example, as illustrated in the user attribute information storage unit 121-1, the generation device 100 estimates that the context of the user U1 is the context CN11. Note that the user attribute information storage unit 121-1 is the same as the user attribute information storage unit 121 except that the information related to the context of the user U 1 has been updated to the context “CN 11”. As described above, in the example of FIG. 1, the generating apparatus 100 estimates that the context of the user U1 is the context CN11 corresponding to the situation where “the user who likes anime is interested in the character A”.

  Thereafter, the generation apparatus 100 extracts seeds (Step S14). Here, the seed is a seed vector that is a basis of a vector input to the model. In the example of FIG. 1, a case where the generation apparatus 100 stores a plurality of seeds in the seed information storage unit 124 is illustrated. For example, a seed identified by a seed ID “SD1” (hereinafter, also referred to as “seed SD1”) is a vector for generating a flower pattern theme image when input to the model M1. For example, the seed identified by the seed ID “SD2” (hereinafter, also referred to as “seed SD2”) is a vector that generates a soccer-style theme image when input to the model M1. For example, the seed identified by the seed ID “SD3” (hereinafter, also referred to as “seed SD3”) is assumed to be a vector for generating an animated theme image when input to the model M1.

  In the example of FIG. 1, the generation apparatus 100 extracts (selects) the seed SD3 based on the context CN11 indicating that the context of the user U1 is “a user who likes anime is interested in the character A”. To do. For example, the generation apparatus 100 extracts a seed SD3 from which an animated theme image is generated based on a situation in which the user U1 is interested in animation. In the example of FIG. 1, the generation apparatus 100 extracts the seed SD3 from the plurality of seeds SD1 to SD3 based on the context CN11 of the user U1, but the generation apparatus 100 appropriately stores other information. It may be used to extract seeds or generate seeds.

  Thereafter, the generation device 100 generates input information based on the seed SD3 (step S15). Hereinafter, a case where the input information is a 100-dimensional vector will be described as an example. For example, the generating device 100 generates input information in which the numerical value of each dimension of the seed SD3 is changed based on the context of the user U1. For example, the generating apparatus 100 generates input information in which numerical values of each dimension of the seed SD3 are changed using parameters based on the user context.

  Here, it is assumed that the generation apparatus 100 has information regarding how the dimensional vector of 100 dimensional vectors has an influence on an image generated. For example, it is assumed that the generation apparatus 100 has information indicating that the greater the fifth-dimensional numerical value among 100-dimensional vectors, the stronger the floral element in the generated image. That is, the generating apparatus 100 has information indicating that the dimension affects the floral elements in the image in which the fifth dimension is generated among the 100-dimensional vectors.

  Further, for example, the generation apparatus 100 has information indicating that a vector having a larger third-dimensional numerical value among 100-dimensional vectors has stronger cat elements in the generated image. That is, the generation apparatus 100 has information indicating that the dimension affects the cat element in the image in which the third dimension is generated among the 100-dimensional vectors. Information indicating the correspondence relationship of which dimension affects which element may be input and set by the administrator of the generation apparatus 100 to the generation apparatus 100 or automatically generated by the generation apparatus 100. You may learn at.

  Here, a case where the character A described above is a cat character will be described as an example. The generation device 100 generates input information in which numerical values of each dimension of the seed SD3 are changed using parameters based on the context CN11 of the user U1. In the example of FIG. 1, the generation apparatus 100 is the target of the character A in the input information because the user U1 is in the context CN11, that is, “the user who likes anime is interested in the character A”. The input information is generated by changing the numerical value of each dimension of the seed SD3 using the parameter that makes the element of the cat strong. In this case, the parameter may be information such as increasing the numerical value of the dimension related to the cat element. The parameter may be any information as long as the value of a desired dimension in the seed can be changed.

  For example, the generating apparatus 100 uses the parameter indicating that the dimension value related to the element of the cat is increased, and changes the numerical value of each dimension of the seed SD3 so that the third dimension value of the 100-dimensional vector increases. Generate the input information. In the example of FIG. 1, as illustrated in the input information list IL1, the generation apparatus 100 generates input information in which the numerical value of the third dimension, which is a dimension related to a cat element, is increased from the seed SD3. Specifically, the generation device 100 generates the input information SD3-1 in which the numerical value of the third dimension is changed from “0.1” to “1.0” in the seed SD3. In this way, the generation apparatus 100 uses the input information SD3-1 in which the seed SD3 related to the anime-style theme image is changed so that the cat element is strong, thereby enabling the animation style suitable for the context CN11 of the user U1. Make it easier to generate theme images for cats.

  Thereafter, the generation device 100 inputs the input information SD3-1 to the model M1 (Step S16). The model M1 to which the input information SD3-1 is input by the generation device 100 outputs a theme image (step S17). In the example of FIG. 1, the model M1 to which the input information SD3-1 is input by the generation device 100 outputs the theme image IM1. As illustrated in FIG. 1, the model M1 to which the input information SD3-1 is input outputs a theme image IM1 related to an anime-like cat that is suitable for the context CN11 of the user U1.

  Thereafter, the generation device 100 provides the theme image generated in step S17 to the terminal device 10 (step S18). In the example of FIG. 1, the generation device 100 provides the terminal device 10 with a theme image IM1 related to an anime-like cat.

  The terminal device 10 provided with the theme image IM1 from the generation device 100 performs display related to the mail application A (step S19). In the example of FIG. 1, the display is transitioned from the terminal device 10-1 to the terminal device 10-2.

  The application screen AP1 of the mail application A is displayed on the screen of the terminal device 10-2. In the example of FIG. 1, the application screen AP1 of the mail application A using the theme image IM1 is displayed on the screen of the terminal device 10-2.

  As described above, the generation apparatus 100 can provide the user with a theme image suitable for the user by generating the theme image using the input information that varies according to the user's context. Therefore, the generation device 100 can generate an appropriate image according to the user while suppressing the load on the user.

  Note that the generation apparatus 100 may generate an image using not only the model M1 but also various models as appropriate. For example, the generating apparatus 100 may generate a provided image from input information using a model selected according to user information from among a plurality of models. For example, the generation apparatus 100 may generate a provided image from input information using a model selected according to user information among a plurality of models generated for each category. For example, the generation device 100 may generate a provided image from input information using a model selected according to user information among a plurality of models generated for various categories such as sports and flowers. . In addition, for example, the generation apparatus 100 uses the model generated using the image group that is likely to be interested in men and the model generated using the image group that is likely to be interested in women. An image may be generated from the image. For example, the generation apparatus 100 generates a model generated using an image group in which the male click rate is relatively higher than the female click rate, or an image in which the female click rate is relatively higher than the male click rate. You may produce | generate an image from input information using the model produced | generated using the group. In this case, for example, when the requesting user is a male, the generating apparatus 100 may generate a theme image using a model generated using an image group that is likely to be of interest to a male. In addition, for example, when the requesting user is a woman, the generating apparatus 100 may generate a theme image using a model generated using an image group that is likely to be interested by a woman.

  Moreover, although the example which the production | generation apparatus 100 produced | generated the theme image IM1 was shown in the example mentioned above, the production | generation apparatus 100 may produce | generate not only the theme image IM1 but a various image. For example, the generation apparatus 100 may generate various objects such as characters using a model (hereinafter, also referred to as “object generation model”) that generates various objects according to input information. In this case, the generation apparatus 100 may generate an object according to the user context by inputting input information that varies based on the user context into the object generation model. Further, the generation apparatus 100 may apply an object generated according to the user's context to a predetermined theme image, and generate a theme image to which the object is applied to the user. In the example of FIG. 1, the generation device 100 uses an object generation model that generates various objects such as a cat character (hereinafter referred to as “cat character”) in the theme image IM1 according to the user's context. An object may be generated. In this case, the generation apparatus 100 may generate a cat character by inputting input information generated according to the context CN11 of the user U1 to the object generation model. Further, the generation device 100 applies a cat character generated according to the context CN11 of the user U1 to a predetermined theme image, and generates a theme image (for example, the theme image IM1) to which the cat character is applied. Also good.

  Further, the generation apparatus 100 may collect information regarding whether the user who provided the generated theme image continues to use the theme image. For example, the generation apparatus 100 may collect information regarding whether or not the user who provided the generated theme image has set the theme image as the theme image to be used. Further, for example, when the setting rate of the theme image IM50 generated according to a certain context (context CN100) is higher than the setting rate of other theme images, the generation device 100 has a correlation between the context CN100 and the theme image IM50. Input information that determines that the theme image IM50 is generated when the user context is the context CN100 may be used.

[2. Configuration of the generator
Next, the configuration of the generation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the generation apparatus 100 according to the embodiment. As illustrated in FIG. 2, the generation apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The generation device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the generation device 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network by wire or wireless, and transmits / receives information to / from the terminal device 10.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2, the storage unit 120 according to the embodiment includes a user attribute information storage unit 121, an action history information storage unit 122, an action schedule information storage unit 123, a seed information storage unit 124, and a model information storage. Part 125.

(User attribute information storage unit 121)
The user attribute information storage unit 121 according to the embodiment stores various types of information regarding the user. For example, the user attribute information storage unit 121 stores various information related to user attributes. FIG. 3 is a diagram illustrating an example of a user attribute information storage unit according to the embodiment. The user attribute information storage unit 121 illustrated in FIG. 3 includes items such as “user ID”, “age”, “sex”, “residence”, “interest”, and “context”.

  “User ID” indicates identification information for identifying a user. For example, the user identified by the user ID “U1” corresponds to the user U1 illustrated in the example of FIG. “Age” indicates the age of the user identified by the user ID. The “age” may be a specific age of the user identified by the user ID, such as 35 years old. “Gender” indicates the gender of the user identified by the user ID.

  “Residence” indicates a region where the user is identified by the user ID. “Residence” may be a specific address of the user identified by the user ID. Further, “interest” indicates an object in which the user identified by the user ID is interested. A plurality of “interests” may be registered. “Context” indicates the context of the user identified by the user ID.

  For example, in the example illustrated in FIG. 3, the age of the user (user U1) identified by the user ID “U1” is “20s”, and the gender is “female”. In addition, for example, in the example illustrated in FIG. 3, the user U1 indicates that the residence is “A region” and the object of interest is “animation”. Further, the user U1 indicates that the context is “−”, that is, unestimated.

  For example, in the example illustrated in FIG. 3, the age of the user (user U2) identified by the user ID “U2” is “30s”, and the gender is “male”. Further, for example, in the example illustrated in FIG. 3, the user U <b> 2 indicates that the residence is “B area” and the object of interest is “sports”. Further, the user U2 indicates that the latest context estimated based on the user information is “CN21”.

  The user attribute information storage unit 121 is not limited to the above, and may store various types of information according to the purpose. For example, the user attribute information storage unit 121 may store other demographic attribute information and psychographic attribute information in addition to age and sex. For example, the user attribute information storage unit 121 may store information such as name, work place, family structure, income, lifestyle, and the like.

(Behavior history information storage unit 122)
The action history information storage unit 122 according to the embodiment stores various types of information related to the action history. FIG. 4 is a diagram illustrating an example of an action history information storage unit according to the embodiment. For example, the action history information storage unit 122 stores information related to actions that the user has performed in the past. The action history information storage unit 122 illustrated in FIG. 4 includes items such as “user ID” and “behavior information”.

  “User ID” indicates identification information for identifying a user. For example, the user identified by the user ID “U1” corresponds to the user U1 illustrated in the example of FIG. In addition, “behavior information” indicates information related to the action of the corresponding user, and includes items such as “behavior ID”, “date and time”, and “content”.

  “Action ID” indicates identification information for identifying each action. “Date and time” indicates the date and time when the corresponding action was performed. In the example of FIG. 4, the information stored in the “date and time” is illustrated by a code such as “DA1-1”, but the “date and time” includes “20:16:43 on August 31, 2016”. It is assumed that a specific date and time is stored. “Content” indicates the type of action of the corresponding user, the contents targeted in the action, and the like.

  For example, in the example illustrated in FIG. 4, the user (user U1) identified by the user ID “U1” is the behavior identified by the behavior ID “AC1-1” or the behavior identified by the behavior ID “AC1-2”. Indicates that Further, for example, in the example illustrated in FIG. 4, the action identified by the action ID “AC1-1” is performed on the date “DA1-1”, and the content indicates that the content A is viewed. Further, for example, in the example illustrated in FIG. 4, the action identified by the action ID “AC1-2” is performed on the date “DA1-2”, and the content is a search using the query “Character A”. Indicates.

  The action history information storage unit 122 is not limited to the above, and may store various information according to the purpose. For example, the behavior history information storage unit 122 may store information regarding a period if the behavior is performed continuously for a predetermined period.

(Behavior schedule information storage unit 123)
The action schedule information storage unit 123 according to the embodiment stores various types of information related to the action schedule. FIG. 5 is a diagram illustrating an example of the action schedule information storage unit according to the embodiment. For example, the action schedule information storage unit 123 stores information related to a schedule of actions that the user will perform in the future. For example, the action schedule information storage unit 123 may store information related to the user's schedule. The action schedule information storage unit 123 illustrated in FIG. 5 includes items such as “user ID” and “schedule information”.

  “User ID” indicates identification information for identifying a user. For example, the user identified by the user ID “U1” corresponds to the user U1 illustrated in the example of FIG. Further, “schedule information” indicates information related to the action of the corresponding user and includes items such as “schedule ID”, “start date / time”, and “content”.

  “Schedule ID” indicates identification information for identifying each schedule. “Start date and time” indicates the date and time when the corresponding scheduled action is performed (started). In the example of FIG. 5, the information stored in the “start date / time” is illustrated by a symbol such as “FD1-1”, but the “start date / time” includes “18:45 on September 15, 2016”. It is assumed that a specific date and time is stored. “Content” indicates the type of action of the corresponding user, the content that is the target of the action, and the like.

  For example, in the example illustrated in FIG. 5, the user (user U1) identified by the user ID “U1” indicates that there is a plan to perform an action related to the schedule identified by the schedule ID “PD1-1” in the future. Further, for example, in the example shown in FIG. 5, the date and time when the action identified by the schedule ID “PD1-1” is scheduled to be performed is date and time “FD1-1”, and the content is a movie appreciation of animation A. It shows that.

  For example, in the example illustrated in FIG. 5, the user (user U2) identified by the user ID “U2” indicates that there is a plan to perform an action related to the schedule identified by the schedule ID “PD2-1” in the future. Further, for example, in the example shown in FIG. 5, the date and time when the action identified by the schedule ID “PD2-1” is scheduled to be performed is the date and time “FD2-1”, the content of which is the game watching of the soccer team A ( Show sports).

  In addition, the action schedule information storage part 123 may memorize | store not only the above but various information according to the objective. For example, the action schedule information storage unit 123 may store information related to the end date and time when the action ends. For example, if the action is performed continuously for a predetermined period, the action schedule information storage unit 123 may store information regarding the period.

(Seed information storage unit 124)
The seed information storage unit 124 according to the embodiment stores various types of information related to seeds. FIG. 6 shows an example of the seed information storage unit 124 according to the embodiment. The seed information storage unit 124 illustrated in FIG. 6 includes items such as “seed (vector)”, “dimension 1”, “dimension 2”, and “dimension 3”. It should be noted that the item “dimension” is provided as many as the number of dimensions of each seed. Specifically, when the seed is a 100-dimensional vector, items “dimension 1”, “dimension 2”, “dimension 3”... “Dimension 100” are provided.

  “Seed (vector)” indicates identification information for identifying each seed. “Dimension 1”, “Dimension 2”, and “Dimension 3” indicate numerical values of the corresponding dimensions.

  For example, in the example shown in FIG. 6, the vector information corresponding to the seed (seed SD1) identified by the seed ID “SD1” has a numerical value of dimension 1 of “0.5” and a numerical value of dimension 2 of “0.2”. ", Indicating that the numerical value of dimension 3 is" -0.7 "or the like.

  Note that the seed information storage unit 124 is not limited to the above, and may store various information according to the purpose. For example, the seed information storage unit 124 may store information regarding what image is generated when each seed is input to the model. For example, when the seed SD1 is input to the model M1, the seed SD1 may store information indicating that a flower pattern theme image is a generated vector. For example, the seed SD2 may store information indicating that it is a vector for generating a soccer-style theme image when input to the model M1. For example, the seed SD3 may store information indicating that it is a vector for generating an animated theme image when input to the model M1.

(Model information storage unit 125)
The model information storage unit 125 according to the embodiment stores information related to the model. For example, the model information storage unit 125 stores model information generated by the generation process. FIG. 7 is a diagram illustrating an example of a model information storage unit according to the embodiment. The model information storage unit 125 illustrated in FIG. 7 includes items such as “feature 1” to “feature 3” corresponding to each model M1 and the like as model information. In FIG. 7, only the model M1 is illustrated, but a plurality of model information such as models M2 and M3 may be stored.

  For example, in the example illustrated in FIG. 7, the model information regarding the model M1 includes feature 1 weight “0.5”, feature 2 weight “−0.4”, feature 3 weight “0.2”, and the like. Indicates that For example, when the feature (feature value) of the model is expressed by an m-dimensional vector, the number of features is m, and the weights of the features 1 to m are stored.

  The model information storage unit 125 is not limited to the above, and may store various model information according to the purpose.

(Control unit 130)
Returning to the description of FIG. 2, the control unit 130 is a controller and is stored in a storage device inside the generation apparatus 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of a generation program) are implemented by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 2, the control unit 130 includes an acquisition unit 131, an extraction unit 132, a generation unit 133, and a provision unit 134, and realizes or executes information processing functions and operations described below. . The internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 2, and may be another configuration as long as the information processing described later is performed.

(Acquisition part 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various types of information from the user attribute information storage unit 121, the action history information storage unit 122, the action schedule information storage unit 123, the seed information storage unit 124, the model information storage unit 125, and the like. The acquisition unit 131 may acquire various types of information from an external information processing apparatus.

  For example, the acquisition unit 131 acquires user information regarding a user who uses the terminal device 10. The acquisition unit 131 may acquire user information related to a user who uses the terminal device 10 from an external device other than the terminal device 10 used by the user. The acquisition unit 131 may acquire user information from an information processing apparatus that collects user information regarding a user who uses the terminal device 10.

  In the example of FIG. 1, the acquisition unit 131 acquires user information of the user U1 from the terminal device 10 used by the user U1. For example, the acquisition unit 131 acquires information indicating that the user U1 who uses the terminal device 10 is a 20's female from the terminal device 10. For example, the acquisition unit 131 acquires various information such as an action history and an action schedule of the user U1 who uses the terminal device 10 from the terminal device 10. The acquisition unit 131 stores the acquired user information in the user attribute information storage unit 121, the action history information storage unit 122, and the action schedule information storage unit 123.

  For example, the acquisition unit 131 may acquire information about seeds stored in the seed information storage unit 124 (see FIG. 6) or information about models stored in the model information storage unit 125 (see FIG. 7). . For example, the acquisition unit 131 acquires information about seeds stored in the seed information storage unit 124 (see FIG. 6) and information about models stored in the model information storage unit 125 (see FIG. 7) from an external information processing apparatus. May be.

(Extractor 132)
The extraction unit 132 extracts various information. For example, the extraction unit 132 extracts seeds. For example, the extraction unit 132 extracts a seed corresponding to the user's context from the plurality of seeds stored in the seed information storage unit 124.

  In the example of FIG. 1, the extraction unit 132 extracts (selects) the seed SD3 based on the context CN11 indicating that the context of the user U1 is “a user who likes anime is interested in the character A”. To do. For example, the extraction unit 132 extracts a seed SD3 from which an animated theme image is generated based on a situation in which the user U1 is interested in animation.

  The extraction unit 132 may extract (estimate) the user's context. For example, the extraction unit 132 estimates a context related to the user U1 based on the user information of the user U1. In the example of FIG. 1, the extracting unit 132 uses the various types of information related to the user U1 stored in the user attribute information storage unit 121, the action history information storage unit 122, the action schedule information storage unit 123, and the like to obtain a context related to the user U1. presume. For example, the extraction unit 132 may include a user action history, a user action schedule, a user attribute, a user current position, a current time, a physical environment in which the user is placed, a social environment in which the user is placed, a user exercise state, And a user's context is estimated based on various information, such as a user's emotion.

  In the example of FIG. 1, the extracting unit 132 determines the context of the user U1 from user information including that the user U1 has performed a search for the character A appearing in the anime A, and that the user U1 is planning to watch a movie of the anime A. Is estimated. For example, in the example of FIG. 1, the extraction unit 132 estimates that the context of the user U1 is the context CN11 corresponding to the situation “a user who likes anime is interested in the character A”.

(Generator 133)
The generation unit 133 generates various information. For example, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on the user information acquired by the acquisition unit 131 and a model that outputs an image according to the input information.

  For example, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on user information including user attribute information. Further, for example, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on user information including information related to a target that the user is interested in. Further, for example, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on user information including a user's action history. For example, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on user information including information related to the user's action schedule.

  For example, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on the user context estimated based on the user information. Further, for example, the generation unit 133 generates a provided image using a parameter based on a user context estimated based on user information. Further, for example, the generation unit 133 generates a provided image by inputting input information that varies depending on a parameter to the model.

  For example, the generation unit 133 may generate a model. For example, the generation unit 133 generates a model M1 as shown in the model information storage unit 125 (see FIG. 7). For example, the generation apparatus 100 generates a model M1 in which the weight of the feature 1 is “0.5”, the weight of the feature 2 is “−0.4”, the weight of the feature 3 is “0.2”, and the like. For example, the generation device 100 generates an image from input input information by inputting predetermined input information such as an N-dimensional vector to the model M1.

  For example, the generation unit 133 may generate a provided image from input information using a model selected according to user information from among a plurality of models. For example, the generation unit 133 generates a provided image using a parameter based on a user context estimated based on user information.

  In the example of FIG. 1, the generation unit 133 generates input information based on the seed SD3. For example, the generation unit 133 generates input information in which the numerical value of each dimension of the seed SD3 is changed based on the context of the user U1. For example, the generating apparatus 100 generates input information in which numerical values of each dimension of the seed SD3 are changed using parameters based on the user context.

  In the example of FIG. 1, the generation unit 133 generates input information in which the numerical value of each dimension of the seed SD3 is changed using a parameter based on the context CN11 of the user U1. For example, since the generation unit 133 has a context CN11, that is, “a user who likes anime is interested in character A”, for example, in the input information, the element of the cat that is the target of character A is The input information is generated by changing the numerical value of each dimension of the seed SD3 using a parameter that becomes stronger.

  For example, the generation unit 133 changes the numerical value of each dimension of the seed SD3 so that the numerical value of the third dimension of the 100-dimensional vector is increased using a parameter indicating that the numerical value of the dimension related to the cat element is increased. Generate the input information. In the example of FIG. 1, as shown in the input information list IL1, the generation unit 133 generates input information in which the numerical value of the third dimension, which is a dimension related to the cat element, is increased from the seed SD3. Specifically, the generation unit 133 generates input information SD3-1 in which the numerical value of the third dimension is changed from “0.1” to “1.0” in the seed SD3.

  Further, for example, the generation unit 133 generates a theme image by inputting input information to the model. In the example of FIG. 1, the generation unit 133 generates the theme image IM1 by inputting the input information SD3-1 to the model M1. For example, the generation unit 133 generates a theme image IM1 related to an anime-style cat suitable for the context CN11 of the user U1.

(Providing unit 134)
The providing unit 134 provides various information. For example, the providing unit 134 provides various information to the terminal device 10. For example, the providing unit 134 provides a service based on the theme image generated by the generating unit 133. For example, the providing unit 134 provides the theme image generated by the generating unit 133 to the terminal device 10. In the example of FIG. 1, the providing unit 134 provides the terminal device 10 with the theme image IM <b> 1 related to the anime-like cat generated by the generating unit 133.

[3. Generation process flow)
Next, a generation process procedure performed by the generation system 1 according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of the generation process according to the embodiment.

  As illustrated in FIG. 8, the generation device 100 acquires user information (step S101). For example, the generation device 100 acquires user information regarding a user who uses the terminal device 10 from the terminal device 10 used by the user.

  Thereafter, the generation apparatus 100 extracts seeds (vectors) based on the estimated user context (step S102). In the example of FIG. 1, the generation apparatus 100 extracts (selects) the seed SD3 based on the context CN11 indicating that the context of the user U1 is “a user who likes anime is interested in the character A”. To do.

  Thereafter, the generation device 100 generates input information based on the extracted seed (step S103). In the example of FIG. 1, the generation device 100 generates input information SD3-1 in which numerical values of each dimension of the seed SD3 are changed using parameters based on the context CN11 of the user U1.

  Thereafter, the generation apparatus 100 generates a theme image based on the input information and the image generation model (model) (step S104). In the example of FIG. 1, the generation apparatus 100 generates the theme image IM1 by inputting the input information SD3-1 to the model M1.

[4. (Modification)
Not limited to the above embodiment, the generation apparatus 100 may generate an image based on various information. The generation apparatus 100A according to the modification may generate an image in which a predetermined style (style) is applied to the image. This point will be described with reference to FIGS. In addition, about the structure similar to embodiment, the same code | symbol is attached | subjected and description is abbreviate | omitted.

[4-1. Generation process)
First, the generation process according to the modification will be described. FIG. 9 is a diagram illustrating an example of the generation process according to the modification. In FIG. 9, the generation device 100 </ b> A illustrates a case where a provided image to be provided to the terminal device 10 used by the user is generated based on the user information of the user. Further, FIG. 9 illustrates a case where the generation apparatus 100A generates a provided image in which an image style determined according to the user's context is applied to an image acquired from the user.

  As illustrated in FIG. 9, the generation system 1A includes a terminal device 10 and a generation device 100A. The terminal device 10 and the generation device 100A are connected to be communicable by wire or wireless via a predetermined communication network (not shown). In addition, the generation system 1A illustrated in FIG. 9 may include a plurality of terminal devices 10 and a plurality of generation devices 100A. As described above, the generation system 1A is different from the generation system 1 in that the generation system 100A includes the generation device 100A instead of the generation device 100.

  The generation device 100A is an information processing device that generates a provided image to be provided to the terminal device 10 based on a style determined according to a user context estimated from user information and an image. For example, as illustrated in the style information storage unit 126, the generation apparatus 100A determines (extracts) a style corresponding to the user's context among a plurality of styles (hereinafter also referred to as “styles”), and uses the extracted style. Performs processing applied to other images.

  First, as illustrated in FIG. 9, the generation device 100A acquires user information of the user U1 from the terminal device 10 used by the user U1 (Step S21). For example, the generation device 100A acquires schedule information indicating that the user U1 who uses the terminal device 10 has a plan to appreciate art in the near future. Note that if the generation apparatus 100A has already acquired user information regarding the user U1, the process of step S21 may not be performed.

  Then, the generation device 100A acquires a seed image from the terminal device 10 (step S22). Here, the seed image refers to an image to which a style is applied according to the user's context. Note that the seed image may not be acquired from the user. For example, the seed image may be the theme image in the example of FIG. In the example of FIG. 9, the generation device 100A acquires a seed image IM21 including a dog as a target from the terminal device 10.

  100 A of production | generation apparatuses which acquired seed image IM21 from the terminal device 10 which the user U1 uses estimate the context regarding the user U1 (step S23). The generation device 100A estimates the context related to the user U1 using the user information of the user U1 as in step S13 illustrated in FIG. For example, 100 A of production | generation apparatuses estimate the context regarding the user U1 using action schedule information for the user U1 memorize | stored in the action schedule information storage part 123-1. The action schedule information storage unit 123-1 is the same as the action schedule information storage unit 123 in FIG. 1 except that the action schedule includes art appreciation of painting instead of the animation A movie appreciation.

  In the example of FIG. 9, the generation device 100A estimates the context of the user U1 from user information including the schedule for the user U1 to appreciate paintings in the near future. For example, as illustrated in the user attribute information storage unit 121-2, the generation device 100A estimates that the context of the user U1 is the context CN12. The user attribute information storage unit 121-2 is the same as the user attribute information storage unit 121, except that the information related to the context of the user U1 is updated to the context “CN12”. As described above, in the example of FIG. 9, the generation apparatus 100A estimates that the context of the user U1 is the context CN12 corresponding to the situation “scheduled to appreciate a painting in the near future”.

  Thereafter, the generation device 100A extracts a style (step S24). For example, the style here refers to the style that appears in the image, that is, the style, and means the tendency and characteristics of the image group created by the creator who created the image. The example of FIG. 9 shows a case where the generation apparatus 100A stores a plurality of styles in the style information storage unit 126.

  For example, in the example shown in FIG. 9, the style identified by the style ID “ST1” (hereinafter sometimes referred to as “style ST1”) is expressed in the corresponding image “STM1”, and its style is Indicates "Anime X style". Further, for example, in the example shown in FIG. 9, the style identified by the style ID “ST2” (hereinafter sometimes referred to as “style ST2”) is expressed in the corresponding image “STM2”. This indicates that the style is “painter Y style”. As described above, in the example of FIG. 9, the generation device 100 </ b> A stores a plurality of styles in the style information storage unit 126.

  Therefore, in the example of FIG. 9, the generating apparatus 100A sets the style ST2 to the seed image IM21 based on the context CN12 indicating that the context of the user U1 is “scheduled to appreciate a painting in the near future”. Extracted (decided) as a style to apply style.

  Thereafter, the generating apparatus 100A generates an image by applying the extracted style ST2 style to the seed image IM21 (step S25). In the example of FIG. 9, the generating apparatus 100A generates the post-application image IM22 to which the style ST2 is applied by applying the style of the painter Y style ST2 to the seed image IM21. For example, the generation apparatus 100A generates an image by applying the extracted style ST2 style to the seed image IM21 using various conventional techniques such as an algorithm for transforming the style described in Non-Patent Document 2 as appropriate. To do.

  Thereafter, the generation device 100A provides the image generated in step S25 to the terminal device 10 (step S26). In the example of FIG. 9, the generation device 100 </ b> A provides the terminal device 10 with the applied image IM <b> 22 to which the painter Y style is applied.

  As described above, the generation apparatus 100A can provide an image suitable for the user by generating an image using a style determined according to the user's context. In the above-described example, the user U1 can generate an image to which a style according to his / her context is applied only by transmitting the image to which the style is to be applied (changed) to the generation apparatus 100A. Therefore, the generation apparatus 100A can generate an appropriate image according to the user while suppressing the load on the user. The generating apparatus 100A may apply the above-described style to the theme image. For example, the generation apparatus 100A may apply a style extracted according to the user's context to a predetermined theme image, and provide the user with the theme image after applying the style. For example, the generation apparatus 100A may provide a theme image to which the style extracted based on the context of the user U1 is applied to the user U1 who uses the mail application A as in the example illustrated in FIG.

[4-2. Configuration of decision device]
Next, the configuration of the generation apparatus 100A according to the modification will be described with reference to FIG. FIG. 10 is a diagram illustrating a configuration example of a determination device 100A according to a modification. As illustrated in FIG. 10, the generation device 100A includes a communication unit 110, a storage unit 120A, and a control unit 130A. The generation device 100A includes an input unit (for example, a keyboard and a mouse) that acquires various operations from an administrator of the generation device 100A and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Storage unit 120A)
The storage unit 120A is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 10, the storage unit 120 </ b> A according to the modification includes a user attribute information storage unit 121, an action history information storage unit 122, an action schedule information storage unit 123, and a style information storage unit 126. The storage unit 120A is different from the storage unit 120 according to the embodiment in that it includes a style information storage unit 126.

(Style information storage unit 126)
The style information storage unit 126 according to the modification stores various pieces of information related to the style. FIG. 11 is a diagram illustrating an example of a style information storage unit according to a modification. The style information storage unit 126 illustrated in FIG. 11 includes items such as “style ID”, “image”, and “content”.

  “Style ID” indicates identification information for identifying a style. “Image” indicates an image (image information) indicating the feature of the corresponding style. Specifically, the “image” indicates an image in which the feature of the style is remarkably expressed. In FIG. 11, an image identified by an image ID is illustrated for explanation, but a file path name indicating the storage location of the image may be stored as “image”. “Content” is information attached in association with an image, and indicates a target included in the style (image style) of the image.

  For example, in the example shown in FIG. 11, the style identified by the style ID “ST1” is expressed in the corresponding image “STM1”, and indicates that the style is “animation X style”. Further, for example, in the example shown in FIG. 11, the style identified by the style ID “ST2” is expressed in the corresponding image “STM2”, and indicates that the style is “painter Y style”.

  The style information storage unit 126 is not limited to the above, and may store various information according to the purpose. For example, the style information storage unit 126 is not limited to an “image”, and may store any information as long as it is information indicating style characteristics.

(Control unit 130A)
Returning to the description of FIG. 10, the control unit 130A is a controller. For example, various programs (corresponding to an example of the generation program) stored in the storage device inside the generation device 100A are stored in the RAM by the CPU, the MPU, or the like. This is realized by being executed as a work area. The control unit 130A is a controller, and is realized by an integrated circuit such as an ASIC or FPGA, for example.

  As illustrated in FIG. 10, the control unit 130A includes an acquisition unit 131, an extraction unit 132A, a generation unit 133A, and a provision unit 134, and implements or executes information processing functions and operations described below. .

(Extractor 132A)
The extraction unit 132A extracts various information. For example, the extraction unit 132A performs the same processing as the extraction unit 132 according to the embodiment. For example, the extraction unit 132A extracts a style. For example, the extraction unit 132A extracts a style from the style information storage unit 126. In the example of FIG. 9, the extraction unit 132A displays the style ST2 on the seed image IM21 based on the context CN12 indicating that the context of the user U1 is “scheduled to appreciate a painting in the near future”. Extract (decide) as the style to apply.

(Generator 133A)
The generation unit 133A generates various information. For example, the generation unit 133A performs the same processing as the generation unit 133 according to the embodiment. For example, the generation unit 133A generates a provided image to be provided to the terminal device 10 based on the style and the image determined according to the user context estimated from the user information acquired by the acquisition unit 131.

  In the example of FIG. 9, the generation unit 133A generates an image by applying the style ST2 style extracted by the extraction unit 132A to the seed image IM21. For example, the generation unit 133A generates the post-application image IM22 to which the style ST2 is applied by applying the style of the painter Y style ST2 to the seed image IM21. For example, the generation unit 133A generates an image by applying the extracted style ST2 style to the seed image IM21 using various conventional techniques such as an algorithm for transforming the style described in Non-Patent Document 2 as appropriate. To do.

[4-3. Generation process flow)
Next, a generation process procedure performed by the generation system 1A according to the modification will be described with reference to FIG. FIG. 12 is a flowchart illustrating an example of the generation process according to the modification.

  As illustrated in FIG. 12, the generation device 100A acquires user information (step S201). In the example of FIG. 9, the generation device 100A acquires user information of the user U1 from the terminal device 10 used by the user U1.

  Thereafter, the generation device 100A acquires a seed image (step S202). In the example of FIG. 9, the generation device 100A acquires a seed image IM21 including a dog as a target from the terminal device 10.

  Thereafter, the generation device 100A extracts a style based on the estimated user context (step S203). In the example of FIG. 9, the generating apparatus 100A displays the style ST2 and the style on the seed image IM21 based on the context CN12 indicating that the context of the user U1 is “scheduled to appreciate a painting soon”. Extract (decide) as the style to apply.

  Thereafter, the generation device 100A generates an applied image based on the seed image and the style (step S204). In the example of FIG. 9, the generating apparatus 100A generates the post-application image IM22 to which the style ST2 is applied by applying the style of the painter Y style ST2 to the seed image IM21.

[5. effect〕
As described above, the generation device 100 according to the embodiment includes the acquisition unit 131 and the generation unit 133. The acquisition unit 131 acquires user information related to a user who uses the terminal device 10. Further, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on the user information acquired by the acquisition unit 131 and a model that outputs an image according to the input information.

  Accordingly, the generation device 100 according to the embodiment generates a provided image to be provided to the terminal device 10 based on the acquired user information and a model that outputs an image according to the input information, thereby reducing the load on the user. It is possible to generate an appropriate image according to the user while suppressing the above.

  In the generation device 100 according to the embodiment, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on user information including user attribute information.

  Thereby, the production | generation apparatus 100 which concerns on embodiment produces | generates the provision image provided to the terminal device 10 based on the user information containing a user's attribute information, and according to a user, suppressing a user's load. Appropriate images can be generated.

  Moreover, in the generation device 100 according to the embodiment, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on user information including information related to a target that the user is interested in.

  Thereby, the generation device 100 according to the embodiment generates a provided image to be provided to the terminal device 10 based on user information including information related to a target that the user is interested in, thereby suppressing the load on the user. An appropriate image can be generated according to the user.

  Further, in the generation device 100 according to the embodiment, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on user information including a user's behavior history.

  Thereby, the production | generation apparatus 100 which concerns on embodiment produces | generates the provision image provided to the terminal device 10 based on the user information containing a user's action log | history, and according to a user, suppressing a user's load. Appropriate images can be generated.

  In the generation device 100 according to the embodiment, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on user information including information related to the user's action schedule.

  Thereby, the production | generation apparatus 100 which concerns on embodiment produces | generates the provision image provided to the terminal device 10 based on the user information containing the information regarding a user's action plan, and suppresses a user's load to a user. An appropriate image can be generated accordingly.

  In the generation device 100 according to the embodiment, the generation unit 133 generates a provided image to be provided to the terminal device 10 based on a user context estimated based on user information.

  Thereby, the generation device 100 according to the embodiment generates the provided image to be provided to the terminal device 10 based on the user context estimated based on the user information, thereby suppressing the load on the user. An appropriate image can be generated according to the above.

  Further, in the generation device 100 according to the embodiment, the generation unit 133 generates a provided image using a parameter based on information related to a user context estimated based on user information.

  Thereby, the generation apparatus 100 according to the embodiment generates a provided image using a parameter based on information related to the user context estimated based on the user information, thereby suppressing the load on the user and responding to the user. And an appropriate image can be generated.

  Further, in the generation device 100 according to the embodiment, the generation unit 133 generates a provided image by inputting input information that varies depending on a parameter to the model.

  Accordingly, the generation apparatus 100 according to the embodiment generates an appropriate image according to a user while suppressing a user's load by generating a provided image by inputting input information that varies depending on a parameter to the model. can do.

  In the generation device 100 according to the embodiment, the generation unit 133 generates a provided image from input information using a model selected according to user information from among a plurality of models.

  Thereby, the generation device 100 according to the embodiment generates a provided image from input information using a model selected according to user information among a plurality of models, while suppressing the load on the user. An appropriate image can be generated according to the user.

  Further, the generation device 100A according to the modification includes an acquisition unit 131 and a generation unit 133A. The acquisition unit 131 acquires user information regarding a user who uses the terminal device 10 and an image. The generation unit 133A generates a provided image to be provided to the terminal device 10 based on the image style (style) determined based on the user context estimated from the user information acquired by the acquisition unit 131 and the image. Generate.

  Thereby, 100 A of production | generation apparatuses which concern on a modification produce | generate the provision image provided to the terminal device 10 based on the style of the image determined according to the user's context estimated from user information, and an image. Thus, an appropriate image can be generated according to the user while suppressing the load on the user.

[6. Hardware configuration)
The generation apparatus 100 according to the above-described embodiment is realized by a computer 1000 having a configuration as illustrated in FIG. FIG. 13 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the generation apparatus. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the generation apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them. However, as another example, these programs may be acquired from other devices via the network N.

  As described above, some of the embodiments and modifications of the present application have been described in detail with reference to the drawings. However, these are merely examples, and various aspects can be made based on the knowledge of those skilled in the art including the aspects described in the disclosure line of the invention. It is possible to carry out the present invention in other forms that have been modified and improved.

[7. Others]
In addition, among the processes described in the above-described embodiments and modifications, all or a part of the processes described as being automatically performed can be manually performed, or are described as being performed manually. All or part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  Further, the processes described in the above-described embodiments and modifications can be appropriately combined within a range in which the processing contents are not contradictory.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Generation system 100 Generation apparatus 121 User attribute information storage part 122 Action history information storage part 123 Action plan information storage part 124 Seed information storage part 125 Model information storage part 130 Control part 131 Acquisition part 132 Extraction part 133 Generation part 134 Providing part 10 Terminal device N network

Claims (12)

An acquisition unit for acquiring user information regarding a user who uses the terminal device;
A generating unit that generates a provided image to be provided to the terminal device based on user information acquired by the acquiring unit and a model that outputs an image according to input information;
A generating apparatus comprising: The generator is
The generation apparatus according to claim 1, wherein a provision image to be provided to the terminal device is generated based on the user information including user attribute information. The generator is
The generation apparatus according to claim 1, wherein a provision image to be provided to the terminal device is generated based on the user information including information regarding an object that the user is interested in. The generator is
The generation device according to claim 1, wherein a provision image to be provided to the terminal device is generated based on the user information including a user's action history. The generator is
The generation device according to claim 1, wherein a provision image to be provided to the terminal device is generated based on the user information including information related to a user's action schedule. The generator is
The generation device according to claim 1, wherein a provision image to be provided to the terminal device is generated based on a user context estimated based on the user information. The generator is
The generating apparatus according to claim 6, wherein the provided image is generated using a parameter based on a user context estimated based on the user information. The generator is
The generation apparatus according to claim 7, wherein the provided image is generated by inputting the input information that varies according to the parameter to the model. The generator is
The generating apparatus according to claim 1, wherein the provided image is generated from the input information using a model selected from the plurality of models according to the user information. . A generation method executed by a computer,
An acquisition step of acquiring user information relating to a user who uses the terminal device;
Based on the user information acquired by the acquisition step and a model that outputs an image according to input information, a generation step of generating a provided image to be provided to the terminal device,
A generation method comprising: An acquisition procedure for acquiring user information relating to a user who uses the terminal device;
A generation procedure for generating a provided image to be provided to the terminal device based on user information acquired by the acquisition procedure and a model for outputting an image according to input information;
A program for causing a computer to execute. An acquisition unit for acquiring user information and an image regarding a user who uses the terminal device;
A generating unit that generates a provided image to be provided to the terminal device based on the image style determined according to the user context estimated from the user information acquired by the acquiring unit and the image;
A generating apparatus comprising: