Device and method

Abstract

This device comprises: a collection unit for collecting the action history of a user; a profile generation unit for generating the sense-of-value profile of the user on the basis of the action history of the user; a selection unit for selecting a filter corresponding to the sense-of-value profile from a database that stores multiple types of filters relating to the appearance of an NPC; and a display unit for displaying the NPC to which the filter selected by the selection unit is applied.

Description

Device and Method

[0001] One aspect of the present disclosure relates to a device and a method.

[0002] Patent Document 1 describes changing the display color of an NPC according to the friendly relationship between a player and the NPC. Patent Document 2 also describes changing the display related to the NPC according to the actions of the player.

[0003] Japanese Unexamined Patent Application Publication No. 2010-213824, Japanese Unexamined Patent Application Publication No. 9-140932

[0004] In the technology of changing the appearance of an NPC according to the actions of a user as described above, a more personalized display of the NPC for each individual user is required.

[0005] One aspect of the present disclosure has been made in view of the above situation, and provides a device and a method for realizing a display of an NPC personalized for each individual user.

[0006] The device according to one aspect of the present disclosure includes a collection unit that collects the action history of a user, a profile generation unit that generates a value profile of the user based on the action history of the user, a selection unit that selects a filter corresponding to the value profile from a database storing a plurality of types of filters related to the appearance of the NPC, and a display unit that displays the NPC to which the filter selected by the selection unit is applied.

[0007] In one aspect of the present disclosure, a user's value profile is generated based on the user's behavioral history, a filter (a filter related to the appearance of the NPC) corresponding to the value profile is selected, and the NPC to which the selected filter is applied is displayed. In this way, by estimating the user's value profile from the user's behavioral history and displaying the NPC to which the filter corresponding to the value profile is applied, it is possible to realize personalized NPC display that is tailored to each user's values ​​and preferences. By providing personalized NPC display to individual users in the same space, even if each user is viewing the same NPC, it is possible to provide them with different experiences (experiences related to the appearance of the NPC for each individual user). As described above, in one aspect of the present disclosure, it is possible to realize personalized NPC display for individual users and provide an experience that is suitable for each user.

[0008] According to one aspect of this disclosure, an apparatus and method can be provided for realizing the display of personalized NPCs for individual users.

[0009] Figure 1 is a functional block diagram of the NPC customization system. Figure 2 is a diagram illustrating the generation of a values ​​profile. Figure 3 is a diagram illustrating the learning process. Figure 4 is a diagram illustrating filter generation and filter application. Figure 5 is a flowchart illustrating the process related to the NPC customization method. Figure 6 is a diagram illustrating an example of the hardware configuration of the server and client terminals.

[0010] The embodiments will be described in detail below with reference to the drawings. In the description, the same elements or elements having the same function will be denoted by the same reference numeral, and redundant descriptions will be omitted.

[0011] In recent years, the metaverse, a virtual space on the internet, has been gaining popularity. In the metaverse, for example, users can move freely through their avatars, which are representations of themselves, in a three-dimensional virtual space, interact with other users, and experience things like buying and selling goods or services. Metaverse platforms are equipped with functions that allow users to build and publish virtual spaces, so anyone can build a metaverse. Among these, the use of NPCs (Non-Player Characters), which are game-specific content, is attracting attention. NPCs are characters in a game that are not controlled by the player.

[0012] The NPC customization system according to this embodiment customizes the appearance of NPCs according to the user's values ​​and preferences. Specifically, the NPC customization system according to this embodiment applies different filters (details described later) to a common basic model of NPCs for each user, providing personalized NPC appearances to individual users existing in the same metaverse space. This makes it possible to provide different experiences related to the appearance of NPCs for each user, even when viewing the same NPC in the same metaverse space.

[0013] Figure 1 is a functional block diagram of the NPC customization system 1. The NPC customization system 1 (device) consists of a server 10 and multiple client terminals 20. Although only one client terminal 20 is shown in Figure 1, in reality, multiple client terminals 20 capable of communicating with the server 10 are provided. The server 10 may consist of one unit or multiple units. The multiple client terminals 20 are, for example, the terminals of each user who uses services (games, etc.) provided on the metaverse platform. Each user has at least one client terminal 20. The client terminals 20 are, for example, personal computers, smartphones, tablet terminals, feature phones, server devices, game machines, etc.

[0014] Server 10 comprises a data collection unit 11 (collection unit), a values ​​profile generation unit 12 (profile generation unit), a filter database 13, a filter selection unit 14 (selection unit), and an NPC database 15. Client terminal 20 comprises a filter generation unit 21 and a filter application unit 22 (display unit). Each function will be described below.

[0015] The data collection unit 11 collects each user's behavior history in the metaverse space from each user's client terminal 20. The user's behavior history in the metaverse space includes the behavior history of the user's avatar, which is a representation of the user. The user's behavior history may also include, for example, the user's dialogue history and the user's item selection history.

[0016] A user's dialogue history may include, for example, the content of conversations between the user's avatar and an NPC or another user's avatar. A user's dialogue history may also include, for example, information about the role of the user's avatar in the conversation. This role information may include information such as whether the user was more of a listener or a speaker, as indicated by the balance of speaking time in the conversation. A user's dialogue history may also include, for example, information indicating the length of the conversation (conversation duration) or the level of excitement. This level of excitement may be information identified by the number of words spoken in the conversation or the duration of the conversation. A user's dialogue history may also include, for example, information indicating the number of times each NPC, etc., was spoken to.

[0017] The user item selection history may include information about items that the user has equipped to their avatar. Items equipped to an avatar refer to information related to the appearance of the avatar that the user has set (selected), such as the avatar's clothing, avatar accessories, colors related to the avatar's appearance, avatar's facial expressions, or information indicating effects related to the avatar's appearance.

[0018] The values ​​profile generation unit 12 generates a values ​​profile for each user based on the user's behavioral history collected by the data collection unit 11. A values ​​profile is information that indicates (explains) a user's values.

[0019] Figure 2 illustrates the generation of value profiles. In the example shown in Figure 2, value profiles are generated for three users, A to C, based on their behavioral history (specifically, their conversation history and item selection history). From the user's conversation history, the value profile is classified into five categories, such as "extroversion," "agreeableness," "conscientiousness," "emotional instability," and "experiential liberation." Similarly, from the user's item selection history, the value profile is classified into five categories, such as "casual," "conservative," "fashionable," "natural," and "formal." Based on these classifications, a value profile is then generated. In the example shown in Figure 2, a value profile of "extroverted and casual" is generated for user A, a value profile of "agreeable and fashionable" is generated for user B, and a value profile of "conscientious and formal" is generated for user C. In the example in Figure 2, one classification is selected from the user's conversation history and one from the user's item selection history, but multiple classifications may be selected to generate value profiles.

[0020] The values ​​profile generation unit 12 may generate a values ​​profile by analyzing and scoring the behavioral history of each user (specifically, the user's dialogue history and item selection history) collected by the data collection unit 11. The values ​​profile generation unit 12 may also store the generated values ​​profile for each user in a predetermined database (not shown) for each user ID that identifies the user.

[0021] Returning to Figure 1, the filter database 13 is a database that stores multiple types of filters related to the appearance of NPCs. A filter is information that determines a part of the appearance of an NPC. Here, we assume that the filter database 13 stores multiple types of filters for each of five items. The five items are, for example, α: clothing filter, β: accessory filter, γ: color filter, δ: facial expression filter, and ε: effect filter. α: Clothing filter is a filter related to the NPC's clothing. β: Accessory filter is a filter related to the NPC's accessories. γ: Color filter is a filter related to the color of the NPC's appearance. δ: Facial expression filter is a filter related to the NPC's facial expression. ε: Effect filter is a filter related to the effects of the NPC's appearance. As described above, multiple types of filters are stored for each item. Note that the filter database 13 may store filters for at least one of the five items described above, or it may store filters for items other than the five items.

[0022] The filter selection unit 14 selects a filter according to the value profile for each user from a filter database 13 that stores multiple types of filters related to the appearance of NPCs, and transmits the selection result to the client terminal 20. The filter selection unit 14 selects a filter according to the value profile based on learning data that has been built by learning the relationship between the value profile and the filters. For this reason, the filter selection unit 14 has performed a learning process in advance to build the learning data. The learning process will be explained below with reference to Figure 3.

[0023] Figure 3 illustrates the learning process performed by the filter selection unit 14. In the learning process, the filter selection unit 14 accumulates each user's evaluation of NPCs displayed with random filters applied, and constructs learning data by associating each user's value profile, the applied filter, and the above evaluation. In the learning process, the filter selection unit 14 derives the above evaluation based on the user's actions toward NPCs displayed with random filters applied.

[0024] In the example shown in Figure 3, a values ​​profile of "extroverted and casual" is generated for a user A. In this case, the filter selection unit 14 randomly selects filters (α´´, β´, γ´, δ´´, ε´´) for each of the five items mentioned above (α: clothing filter, β: accessory filter, γ: color filter, δ: facial expression filter, ε: effect filter). Then, based on the user's actions towards the NPC displayed with the selected filters applied, the user's evaluation of each filter (α´´, β´, γ´, δ´´, ε´´) is derived. This evaluation may be based, for example, on the length of the conversation with the NPC to which the randomly applied filter was applied, the level of engagement in the conversation with the NPC, the number of times the NPC was spoken to, etc., in the user's behavior history collected by the data collection unit 11. For example, if a filter has a low evaluation, it may be changed and the NPC may be displayed again, and the evaluation after the change may be derived. This process is repeated until the filter with the highest evaluation for each of the five items is identified. The evaluation may also be performed on combinations of filters for the five items. Then, the above evaluations are accumulated for each value profile, and for each user, the value profile, the above evaluation (highest evaluation), and the filter with the highest evaluation are associated and learned (reinforcement learning) to build learning data that shows which value users prefer which filters.

[0025] The NPC database 15 is a database that stores a common basic model of NPCs (NPC basic model). By applying various filters to the NPC basic model, it is possible to display NPCs with different appearances for each user. The NPC database 15 may store only one NPC basic model or may store multiple types.

[0026] The filter generation unit 21, based on the filters output from the filter selection unit 14 (for example, filter combination data of five items), prepares for drawing the color and shape of the filters, for example, using a shader program, and generates a 3D model combining each filter (see Figure 4).

[0027] The filter application unit 22 reads the NPC basic model from the NPC database 15 and applies the filter generated by the filter generation unit 21 (the filter selected by the filter selection unit 14) to the NPC basic model. The filter application unit 22 displays the filtered NPC in a manner that is visible to the user. As shown in the right-hand diagram of Figure 4, different filters are applied to each user, so even when viewing the same NPC, different appearances of the NPC can be displayed for each user.

[0028] Figure 5 is a flowchart showing the process related to the NPC customization method executed by the NPC customization system 1.

[0029] First, the user's behavioral history is collected (Step S1).

[0030] Next, a user values ​​profile is generated based on the user's behavioral history (Step S2).

[0031] Next, a filter corresponding to the value profile is selected from the filter database 13, which stores multiple types of filters related to the appearance of NPCs (step S3).

[0032] Then, the NPC to which the selected filter has been applied is displayed (step S4). This concludes the process related to the NPC customization method.

[0033] Next, the effects and benefits of the NPC customization system 1 according to this embodiment will be described.

[0034] The NPC customization system 1 according to this embodiment includes a data collection unit 11 that collects the user's behavior history, a values ​​profile generation unit 12 that generates a values ​​profile of the user based on the user's behavior history, a filter selection unit 14 that selects a filter according to the values ​​profile from a filter database 13 that stores a plurality of types of filters related to the appearance of NPCs, and a filter application unit 22 that displays an NPC to which the filter selected by the filter selection unit 14 has been applied.

[0035] In the NPC customization system 1 according to this embodiment, a user's value profile is generated based on the user's behavior history, a filter (a filter related to the appearance of the NPC) corresponding to the value profile is selected, and the NPC with the selected filter applied is displayed. In this way, by estimating the user's value profile from the user's behavior history and displaying an NPC with a filter corresponding to the value profile applied, it is possible to realize personalized NPC display that is tailored to each user's values ​​and preferences. By providing personalized NPC display to individual users in the same space, even if each user is viewing the same NPC, it is possible to provide them with different experiences (experiences related to the appearance of the NPC for each individual user). As described above, the device according to one aspect of this disclosure can realize personalized NPC display for individual users and provide an experience suitable for each user.

[0036] The user's behavioral history may include at least one of the user's dialogue history and the user's item selection history. With such a configuration, it is possible to appropriately collect user behavioral history that is highly relevant to the user's values.

[0037] A user's dialogue history may include information about the content of the dialogue and their role in the dialogue, or at least one of the two. Such a configuration allows for the appropriate collection of information that can appropriately identify the user's values.

[0038] A user's item selection history may include information about items the user has equipped to their avatar. Such a configuration allows for the appropriate collection of information that can appropriately identify the user's values.

[0039] The filter database 13 may store filters of multiple types, including filters related to at least one of the following: NPC's clothing, accessories, colors, facial expressions, and effects. With such a configuration, it becomes possible to use filters that can appropriately customize the appearance of NPCs.

[0040] The value profile generation unit 12 may generate a value profile by scoring the user's behavior history. By scoring, a value profile that appropriately reflects a plurality of behavior histories can be generated.

[0041] The filter selection unit 14 may select a filter corresponding to the value profile based on the learning data in which the relationship between the value profile and the filter has been learned. As a result, a filter more in line with the value profile can be selected.

[0042] The filter selection unit 14 may execute a learning process for constructing learning data, and in the learning process, accumulate the evaluation of each user for the NPC to which a random filter is applied and displayed, and for each user, associate the value profile, the applied filter, and the evaluation and learn, thereby constructing learning data. Thereby, learning data that reflects the user's evaluation and enables selection of a filter along the value profile can be constructed.

[0043] The filter selection unit 14 may derive an evaluation based on the user's behavior for the NPC to which a random filter is applied and displayed in the learning process. Thereby, an appropriate evaluation can be derived based on the user's behavior, and learning data that enables selection of a filter along the value profile can be constructed.

[0044] Next, the hardware configurations of the server 10 and the client terminal 20 included in the NPC customization system 1 described above will be described with reference to FIG. 6. The server 10 and the client terminal 20 may physically be configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0045] In the following description, the term "device" can be read as a circuit, a device, a unit, etc. The hardware configuration of the server 10 and the client terminal 20 may be configured to include one or more of each device shown in the figure, or may be configured without including some devices.

[0046] Each function in the server 10 and the client terminal 20 is realized by causing a processor 1001 to load a predetermined software (program) onto hardware such as a memory 1002, so that the processor 1001 performs calculations and controls communication by a communication device 1004 and reading and / or writing of data in the memory 1002 and a storage 1003.

[0047] The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be composed of a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic unit, a register, and the like. For example, control functions such as the data collection unit 11 may be realized by the processor 1001.

[0048] Further, the processor 1001 reads a program (program code), a software module, and data from the storage 1003 and / or the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program for causing a computer to execute at least a part of the operations described in the above embodiments is used.

[0049] For example, control functions such as the data collection unit 11 may be stored in the memory 1002 and realized by a control program operating on the processor 1001, and other functional blocks may be realized in the same manner. Although it has been described that the above various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be mounted on one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

[0050] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out a wireless communication method according to one embodiment of the present invention.

[0051] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital multipurpose disk, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including memory 1002 and / or storage 1003.

[0052] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via a wired and / or wireless network, and is also referred to as a network device, network controller, network card, communication module, etc.

[0053] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0054] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may consist of a single bus, or different buses may be used for communication between devices.

[0055] Furthermore, the server 10 and client terminal 20 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0056] Although this embodiment has been described in detail above, it will be clear to those skilled in the art that this embodiment is not limited to the embodiments described herein. This embodiment can be implemented as a modified and altered form without departing from the spirit and scope of the invention as defined by the claims. Therefore, the description herein is for illustrative purposes only and is not intended to be restrictive in any way to this embodiment.

[0057] Each aspect / embodiment described herein may be applied to systems utilizing LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA®, GSM®, CDMA2000, UMB (Ultra Mobile Broad-band), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth®, and other appropriate systems, and / or next-generation systems extended based thereon.

[0058] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described herein may be reordered, provided they are consistent with each other. For example, the methods described herein present the elements of various steps in an exemplary order and are not limited to that specific order.

[0059] Input and output information may be stored in a specific location (e.g., memory) or managed in a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0060] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0061] Each aspect / embodiment described herein may be used individually, in combination, or switched between during implementation. Furthermore, notification of predetermined information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0062] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0063] Furthermore, software, instructions, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies such as coaxial cable, fiber optic cable, twisted pair, and digital subscriber lines (DSL) and / or wireless technologies such as infrared, radio, and microwave, these wired and / or wireless technologies are included in the definition of a transmission medium.

[0064] The information, signals, etc. described herein may be represented using any one of various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0065] In addition, terms used herein and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

[0066] Furthermore, the information, parameters, etc., described herein may be expressed as absolute values, relative values ​​from a given value, or as corresponding other information.

[0067] Communication terminals may also be referred to by those skilled in the art as mobile communication terminals, subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, mobile terminals, wireless terminals, remote terminals, handsets, user agents, mobile clients, clients, or several other appropriate terms.

[0068] As used herein, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0069] Where the terms “first,” “second,” etc., are used herein, no reference to those elements shall generally limit the quantity or order of those elements. These terms may be used herein as a convenient way to distinguish between two or more elements. Accordingly, references to the first and second elements shall not imply that only two elements may be employed therein, or that the first element must precede the second element in any way.

[0070] To the extent that “include,” “including,” and their variations are used herein or in the claims, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used herein or in the claims is not intended to be exclusive OR.

[0071] In this specification, unless it is clear from the context or technically that only one device exists, the term also includes multiple devices.

[0072] Throughout this disclosure, unless the context clearly indicates a singular number, the terms shall include plural ones.

[0073] Finally, various exemplary embodiments included in this disclosure are described below in [E1] to [E10].

[0074] [E1] A device comprising: a collection unit for collecting user behavior history; a profile generation unit for generating a value profile of the user based on the user behavior history; a selection unit for selecting a filter corresponding to the value profile from a database storing multiple types of filters relating to the appearance of an NPC; and a display unit for displaying the NPC to which the filter selected by the selection unit has been applied.

[0075] [E2] The apparatus according to [E1], wherein the user's behavior history includes at least one of the user's dialogue history and the user's item selection history.

[0076] [E3] The device according to [E2], wherein the user's dialogue history includes at least one of the content of the dialogue and information relating to the role in the dialogue.

[0077] [E4] The device according to [E2] or [E3], wherein the user's item selection history includes information about items that the user has equipped to their avatar.

[0078] [E5] The apparatus according to any one of [E1] to [E4], wherein the database stores a filter relating to at least one of the following as the multiple types of filters: the clothing, accessories, colors, facial expressions, and effects of an NPC.

[0079] [E6] The apparatus according to any one of [E1] to [E5], wherein the profile generation unit generates the value profile by scoring the user's behavior history.

[0080] [E7] The apparatus according to any one of [E1] to [E6], wherein the selection unit selects a filter according to the value profile based on learning data in which the relationship between the value profile and the filter has been learned.

[0081] [E8] The apparatus according to [E7], wherein the selection unit executes a learning process to construct the learning data, and in the learning process, accumulates each user's evaluation of the NPC displayed with a random filter applied, and constructs the learning data by learning the relationship between the value profile, the applied filter, and the evaluation for each user.

[0082] [E9] The apparatus according to [E8], wherein the selection unit derives the evaluation based on the user's actions toward the NPC displayed by applying the random filter in the learning process.

[0083] [E10] A method performed by the device, comprising: collecting a user's behavior history; generating a value profile of the user based on the user's behavior history; selecting a filter from a database storing a plurality of types of filters relating to the appearance of an NPC, according to the value profile; and displaying the NPC to which the selected filter has been applied.

[0084] 1...NPC customization system (device), 11...Data collection unit (collection unit), 12...Value profile generation unit (profile generation unit), 14...Filter selection unit (selection unit), 22...Filter application unit (display unit).

Claims

1. A device comprising: a collection unit for collecting user behavior history; a profile generation unit for generating a value profile of the user based on the user behavior history; a selection unit for selecting a filter corresponding to the value profile from a database storing multiple types of filters relating to the appearance of an NPC; and a display unit for displaying the NPC to which the filter selected by the selection unit has been applied.

2. The apparatus according to claim 1, wherein the user's behavior history includes at least one of the user's dialogue history and the user's item selection history.

3. The apparatus according to claim 2, wherein the user's dialogue history includes at least one of the content of the dialogue and information relating to the role in the dialogue.

4. The device according to claim 2, wherein the user's item selection history includes information about items that the user has equipped to their avatar.

5. The apparatus according to claim 1, wherein the database stores filters relating to at least one of the following as the plurality of types of filters: the clothing, accessories, colors, facial expressions, and effects of an NPC.

6. The apparatus according to claim 1, wherein the profile generation unit generates the values ​​profile by scoring the user's behavioral history.

7. The apparatus according to claim 1, wherein the selection unit selects a filter according to the value profile based on learning data in which the relationship between the value profile and the filter has been learned.

8. The apparatus according to claim 7, wherein the selection unit executes a learning process to construct the learning data, and in the learning process, accumulates each user's evaluation of the NPC displayed with a random filter applied, and constructs the learning data by learning to associate the value profile, the applied filter, and the evaluation for each user.

9. The apparatus according to claim 8, wherein the selection unit derives the evaluation based on the user's actions toward the NPC displayed by applying the random filter in the learning process.

10. A method performed by the device, comprising: collecting a user's behavior history; generating a value profile of the user based on the user's behavior history; selecting a filter from a database storing multiple types of filters relating to the appearance of an NPC, according to the value profile; and displaying the NPC to which the selected filter has been applied.

Images