Device and method

Abstract

In the present invention, a recommendation device (10) includes: a reception unit (11) that receives information pertaining to an interaction for an imaginary character that interacts with a user in a virtual space; a control unit (12) that updates information pertaining to the character on the basis of the information pertaining to the interaction, and determines, on the basis of the updated information pertaining to the character, information pertaining to a product or the like to be recommended; and an output unit (13) that outputs the determined information pertaining to the product or the like.

Description

Apparatus and method

[0001] One aspect of the present invention relates to an apparatus and a method.

[0002] Patent Document 1 discloses a technique for creating a character in a virtual space and moving the character.

[0003] Japanese Patent Application Laid-Open No. 2020-205057

[0004] In recent years, the so-called "oshikatsu" (supporting a fictional character in a virtual space) trend of supporting the character and purchasing merchandise related to the character has become popular, creating a need for effective sales of merchandise related to the fictional character. Generally, there are multiple users who watch a fictional character, but it is difficult to propose products or services that will likely interest these multiple users without destroying the character's image (worldview).

[0005] One aspect of the present invention has been made in consideration of the above-described circumstances, and aims to use fictional characters to suggest products or services that are likely to interest users.

[0006] An apparatus according to one aspect of the present invention includes a reception unit that receives information relating to interactions between a fictional character and a user in a virtual space, a control unit that updates information relating to the character based on the information relating to the interactions and determines information relating to a product or service to be proposed based on the updated information relating to the character, and an output unit that outputs the determined information relating to the product or service.

[0007] In a device according to one aspect of the present invention, information about the character is updated based on information about interactions between the user and the fictional character, information about suggested products, etc. is determined based on the updated information about the character, and the determined information about the products, etc. is proposed (output). It is assumed that the user creates valuable memories through interactions with the character. By updating the information about the character based on information about such interactions and determining suggested products, etc. based on the updated information about the character, it is possible to propose products, etc. that are likely to interest the user without causing the user to feel uncomfortable (without destroying the image of the character). As described above, a device according to one aspect of the present invention can use a fictional character to propose products or services that are likely to interest the user.

[0008] According to one aspect of the present invention, it is possible to propose products or services that are likely to interest the user.

[0009] Fig. 1 is a functional block diagram showing the functional configuration of a recommendation device according to this embodiment. Fig. 2 is a diagram illustrating an overview of recommendations using fictional characters. Fig. 3 is a flowchart showing the processing from character creation to recommendation. Fig. 4 is a diagram showing the hardware configuration of the recommendation device.

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or equivalent elements are designated by the same reference numerals, and redundant description will be omitted.

[0011] FIG. 1 is a functional block diagram showing the functional configuration of a recommendation device 10 according to this embodiment. The recommendation device 10 according to this embodiment is a device that recommends information related to products or services (hereinafter, sometimes referred to as products, etc.) to a user. The recommendation device 10 may, for example, recommend information related to products, etc. to a user for the purpose of selling the products, etc. In the following, the recommendation device 10 is described as recommending information related to products, etc. to a user for the purpose of selling the products, etc., but this is not limited thereto, and the recommendation device 10 may also recommend information related to products, etc. to a user for purposes other than selling the products, etc. (for example, for the purpose of simply introducing the products, etc.).

[0012] The recommendation device 10 recommends information related to products and the like to users by using fictional characters that interact with users in the Metaverse, a virtual space on the Internet. More specifically, the recommendation device 10 recommends information related to products and the like to users using information related to interactions between the users and the characters. In this way, by making recommendations taking into account the experiences and memories the users have gained through interactions with the characters, it is possible to recommend to users products and the like that are likely to interest the users. This makes it possible to sell products and the like more effectively.

[0013] Fig. 2 is a diagram illustrating an overview of recommendations using fictional characters. As shown in Fig. 2, recommendations using characters can be broadly divided into a stage of creating a character (creation stage), a stage of interacting between a user and the character (interaction stage), a stage of updating information related to the character (e.g., the character's personality) to identify products, etc. that the character prefers (character update stage), and a stage of determining and recommending products, etc. to be recommended (recommendation stage).

[0014] In the creation stage, as shown in the upper left of Fig. 2, a character C is created by inputting a creation prompt related to character creation into, for example, a large language model (LLM). In the example creation prompt shown in Fig. 2, the condition is specified: "You will play a character named ◎◎ and communicate with the user," and input information indicating the characteristics of the character is specified: "Hobbies: singing, listening to music, Catchphrase: Yeah!"

[0015] In the interaction stage, the user interacts with character C, which was created based on the creation prompt described above, as shown in the upper right of Fig. 2. In the example shown in Fig. 2, character C makes suggestions to the user, such as "Let's go for a drive," "I like rock music," and "Change into blue clothes," which allows interaction between the user and character C in the virtual space (interaction in response to suggestions from the character).

[0016] In the character update stage, as shown in the lower left of Figure 2, for example, an update prompt based on information related to the interaction between the user and character C is input into the large-scale language model, thereby updating information related to character C (here, character C's personality is added). In the example of the update prompt shown in Figure 2, input information indicating the content of the interaction is specified, such as "Recent events: I went for a drive recently and had fun. I've also become interested in rock music. I was happy when someone complimented me on my blue clothes." The condition is also specified, such as "Add a character personality based on the input information, and tell us what "(product genre, earphones, etc.)" the character with the added personality likes." Based on this update prompt, character C's personality is added, and information such as products that character C with the added personality likes is identified.

[0017] In the recommendation stage, as shown in the lower right of FIG. 2 , a product to be recommended is determined based on information about a product preferred by the character C, and the product is recommended (output). The recommended product may be, for example, a product similar to the product preferred by the character C and available for sale. The recommended product may also be, for example, a product similar to the product preferred by the character C selected from a list of products to be recommended to a pre-specified user (for example, a list of products preferred by the user). In the example shown in FIG. 2 , the character C recommends the thus determined recommended product by saying, "I like the blue headphones from company XXX. They look good with blue clothes, and they're great to listen to rock music when you go for a drive!"

[0018] Returning to FIG. 1 , the functions of the recommendation device 10 will be described. As shown in FIG. 1 , the recommendation device 10 includes a reception unit 11, a control unit 12, and an output unit 13. The recommendation device 10 executes a character creation process and a character update and recommendation process. The character update and recommendation process is executed after the character creation process. Each process will be described in order.

[0019] (Character Creation Process) The reception unit 11 receives information related to character creation. The reception unit 11 receives, for example, information related to character creation from a user of an operator that operates the recommendation device 10. The information related to character creation is information for creating a creation prompt, which will be described later, and is information that enables character creation. The information related to character creation may include, for example, information indicating the characteristics of the character and information indicating an action that the character is desired to perform. The information indicating the characteristics of the character may be, for example, information such as the character's name, the character's appearance, the character's age, the character's hobbies, and the character's catchphrases. The information indicating an action that the character is desired to perform may be, for example, information related to specific actions when interacting with a user (such as the content of the interaction, the frequency of the interaction, and the duration of the interaction). Note that the reception unit 11 receives the information related to character creation before receiving the information related to the interaction, which will be described later. The reception unit 11 outputs the received information to the control unit 12.

[0020] The control unit 12 creates a character based on the information related to character creation received by the reception unit 11. The control unit 12 creates a creation prompt 30 based on the information related to character creation, and creates a character by inputting the creation prompt 30 into a language model 50. The language model 50 is described here as being stored in a server or the like external to the recommendation device 10, but may also be stored inside the recommendation device 10.

[0021] The language model 50 is modeled using the occurrence probability of sentences and words, receives input text data indicating a prompt, and produces a predetermined output according to the content of the prompt. The language model 50 may be, for example, a large language model (LLM). The LLM is a language model constructed using large amounts of text data and deep learning technology, and is a language model in which the amount of input data, the amount of calculation, and the amount of coefficients in probability calculations are significantly increased compared to conventional language models. For example, "LLMA2" may be used as the LLM.

[0022] The language model 50 receives input of the creation prompt 30, which is text data. The language model 50 creates a character in accordance with the content of the creation prompt 30, and transmits information related to the character to the output unit 13.

[0023] The creation prompt 30 is a prompt created by the control unit 12 based on information related to character creation, and specifies information such as a task, conditions, input information, and output examples. The task is information indicating an overview of the content to be output by the language model 50, such as "Please create a character." The conditions are information indicating detailed conditions for the task, such as "Please create a character that will communicate with the user." The input information is information to be considered when executing the task, such as information related to character characteristics, such as the character's name, appearance, age, hobbies, and catchphrases. The output examples are information indicating specific examples of characters that can be output (created). The control unit 12 may create a creation prompt 30 that specifies at least the character characteristics as input information and the task of creating a character. By specifying the creation prompt 30 in this manner, the control unit 12 creates a character, and information related to the character is transmitted to the output unit 13. The information related to the character includes, for example, character setting information (characteristics, etc.), character movement information, character images, and character voice information.

[0024] The output unit 13 outputs the information related to the character transmitted from the language model 50 to a user (a user who interacts with the created character) to whom a product or the like is to be recommended. That is, the output unit 13 outputs an image of the created character and a sound related to the character to the terminal (smartphone, etc.) of the user.

[0025] (Character Update and Recommendation Processing) The reception unit 11 receives information related to interactions with fictional characters (characters created in the character creation process) that interact with users in a virtual space. The reception unit 11 receives, for example, information related to the interactions from the terminal of a user who interacts with the character. The information related to the interactions is information for creating an update prompt (described later) and is information that enables updating of information related to the character. The information related to the interactions may be, for example, information indicating the specific content of the interaction between the user and the character, the user's state at the time of the interaction (mood, information about the clothes worn, etc.), the frequency of the interaction, the duration of the interaction, etc. The reception unit 11 outputs the received information to the control unit 12.

[0026] The control unit 12 updates the information related to the character based on the information related to the interaction received by the reception unit 11, and determines information related to products, etc. to be recommended (suggested) based on the updated information related to the character. The control unit 12 creates an update prompt 40 based on the information related to the interaction, and inputs the update prompt 40 into the language model 50, thereby updating the information related to the character and determining information related to products, etc. to be recommended (suggested).

[0027] The language model 50 receives input of the update prompt 40, which is text data. The language model 50 updates the information related to the character in accordance with the content of the update prompt 40, and further identifies products, etc. that the character likes in accordance with the updated information related to the character as products, etc. to be recommended, and transmits information related to the products, etc. to the output unit 13.

[0028] The update prompt 40 is a prompt created by the control unit 12 based on information related to the interaction, and specifies information such as a task, conditions, input information, and output examples. The task is information that outlines the content to be output by the language model 50, such as "Update the information related to the character, and output products, etc. that the updated character likes as recommended products, etc." The conditions are information that indicate detailed conditions for the task, such as "Update the information related to the character to add character personality, identify products, etc. that the character likes based on the updated information related to the character, and output recommended products, etc. from among the products, etc. that the character likes." The input information is information that is taken into consideration when executing the task, such as information indicating the specific content of the interaction between the user and the character, the user's state at the time of the interaction (e.g., mood, information about the clothes worn), the frequency of the interaction, and the duration of the interaction. The output examples are information that indicate specific examples of recommended products, etc. that can be output (created), such as product genres.

[0029] The control unit 12 may create an update prompt 40 in which at least the content of the interaction is specified as input information and the task is to update information related to the character and recommend products, etc., that the updated character prefers. The control unit 12 may create an update prompt 40 in which the task is to recommend products, etc., that the user prefers among the products, etc., that the character prefers. In this case, the products, etc., that the user prefers may be provided in the prompt or may be learned in advance in a language model. The control unit 12 may also create an update prompt 40 in which the task is to recommend products, etc., other than the products, etc., that the user prefers among the products, etc., that the character prefers.

[0030] The output unit 13 outputs information related to the determined recommended product, etc. to the terminal of the user to whom the product, etc. is to be recommended. Here, the information related to the recommended product, etc. is, for example, information including the name of the recommended product, etc. As shown in FIG. 2 , the output unit 13 may output the name of the recommended product, etc. as the character's statement, including the character's catchphrase, etc.

[0031] 3 is a flowchart showing the process from character creation to recommendation. As shown in Fig. 3, first, the reception unit 11 of the recommendation device 10 receives information related to character creation (step S1).

[0032] Next, the control unit 12 creates a creation prompt 30 based on the information related to the creation of the character, and the creation prompt 30 is input to the language model 50 (step S2).

[0033] Next, information related to the character (i.e., the created character) output from the language model 50 is output by the output unit 13 to a user (a user who will interact with the created character) to whom a product or the like is to be recommended (step S3). The processing up to this point is the character creation processing.

[0034] Next, the reception unit 11 receives information regarding interactions between the user and the character (step S4).

[0035] Next, the control unit 12 creates an update prompt 40 based on the information related to the interaction, and inputs the update prompt 40 to the language model 50 (step S5). As a result, information related to a product or the like corresponding to the information related to the updated character is output from the language model 50 as information related to a product or the like to be recommended.

[0036] Next, the information on the recommended product or the like output from the language model 50 is output (displayed) by the output unit 13 as the character's utterance, including the character's catchphrases or the like (step S6). This completes the character update and recommendation process.

[0037] Next, the effects of this embodiment will be described.

[0038] The recommendation device 10 of this embodiment includes a reception unit 11 that receives information related to interactions between a fictional character and a user in a virtual space, a control unit 12 that updates information related to the character based on the information related to the interaction and determines information related to products, etc. to be recommended based on the updated information related to the character, and an output unit 13 that outputs the determined information related to the products, etc.

[0039] In the recommendation device 10 according to this embodiment, information about the character is updated based on information about interactions between the user and the fictional character, information about products, etc. to be suggested is determined based on the updated information about the character, and the determined information about the products, etc. is recommended (output). It is assumed that the user creates valuable memories through interactions with the character. By updating the information about the character based on information about such interactions and determining recommended products, etc. based on the updated information about the character, it is possible to suggest products, etc. that are likely to interest the user without causing the user to feel uncomfortable (without destroying the image of the character). As described above, the recommendation device 10 according to this embodiment can suggest products or services that are likely to interest the user using fictional characters.

[0040] The control unit 12 may create an update prompt 40 based on the information related to the interaction, and input the update prompt 40 into a language model 50 that outputs according to the content of the prompt, thereby updating the information related to the character and determining information related to products to be recommended, etc. With this configuration, it is possible to use the language model to easily and appropriately suggest products or services that are likely to interest the user.

[0041] The control unit 12 may create an update prompt 40 in which the content of the interaction is specified as input information and the tasks are to update information related to the character and recommend products, etc. that the updated character will like. By creating such a prompt, it is possible to appropriately suggest products or services that are likely to interest the user while taking into account the content of the interaction.

[0042] The control unit 12 may create an update prompt 40 that specifies a task of suggesting products that the user likes from among the products that the character likes. In this way, by suggesting products that are liked by both the updated character and the user, it is possible to suggest products that the user is likely to be interested in with a high probability.

[0043] The control unit 12 may create an update prompt 40 that specifies, as a task, the suggestion of products, etc., other than the products, etc., preferred by the character, among the products, etc., preferred by the user. In this way, products, etc., which were not originally in line with the user's preferences but are linked to interactions with the character, can be said to be products, etc., that the user may become newly interested in through the interaction. Such products, etc., would never be recommended simply based on the user's preferences, and are recommended products, etc., unique to the configuration of this embodiment, in which products, etc., are recommended taking into account information related to interactions with the character. By recommending such products, etc., it is possible to effectively recommend products, etc., that were previously difficult to effectively recommend, based on the user's new interests.

[0044] The reception unit 11 may receive information related to character creation before receiving information related to interactions, the control unit 12 may create a character based on the information related to character creation, and the output unit 13 may output information related to the created character. With this configuration, a desired character can be appropriately created based on arbitrarily set information related to character creation.

[0045] The control unit 12 may create a character by creating a creation prompt 30 based on information related to character creation and inputting the creation prompt 30 into the language model 50. With this configuration, a desired character can be created easily and appropriately using the language model.

[0046] The control unit 12 may create a creation prompt 30 that specifies the input information of a character and the task of creating a character. By creating such a prompt, a desired character can be created appropriately while taking into account the specified character characteristics.

[0047] Next, the hardware configuration of the recommendation device 10 described above will be described with reference to Fig. 4. The recommendation device 10 may be physically 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.

[0048] In the following description, the term "device" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the recommendation device 10 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

[0049] Each function of the recommendation device 10 is realized by loading specific software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations and control communication via the communication device 1004 and the reading and / or writing of data in the memory 1002 and storage 1003.

[0050] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control unit, an arithmetic unit, a register, etc. For example, the control functions of the reception unit 11 and the like may be realized by the processor 1001.

[0051] The processor 1001 also reads programs (program codes), software modules, and data from the storage 1003 and / or the communication device 1004 into the memory 1002, and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above embodiments.

[0052] For example, the control functions of the reception unit 11 and the like may be realized by a control program stored in the memory 1002 and running on the processor 1001, and similar functions may be realized for other functional blocks. Although the above-described various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented on one or more chips. The program may be transmitted from a network via a telecommunications line.

[0053] The memory 1002 is a computer-readable recording medium and may be composed of at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to one embodiment of the present invention.

[0054] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk 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 versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including memory 1002 and / or storage 1003.

[0055] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired and / or wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0056] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0057] Furthermore, each device such as the processor 1001 and the memory 1002 is connected to a bus 1007 for communicating information. The bus 1007 may be configured as a single bus, or may be configured as different buses between the devices.

[0058] The recommendation device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these pieces of hardware.

[0059] Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented in modified and altered forms without departing from the spirit and scope of the present invention as defined by the claims. Therefore, the description in this specification is intended to be illustrative and does not have any limiting meaning on the present embodiment.

[0060] Each aspect / embodiment described herein may be applied to systems utilizing LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA, GSM, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth, or other suitable systems and / or next generation systems enhanced thereon.

[0061] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described herein may be rearranged unless it is consistent. For example, the methods described herein present elements of various steps in an example order and are not limited to the particular order presented.

[0062] Input and output information may be stored in a specific location (for example, memory) or managed in a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0063] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0064] The aspects / embodiments described herein may be used alone or in combination, or may be switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0065] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0066] Software, instructions, etc. may also be transmitted or received over a transmission medium. For example, if the 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 Line (DSL), and / or wireless technologies such as infrared, radio, and microwave, these wired and / or wireless technologies are included within the definition of transmission media.

[0067] The information, signals, etc. described herein may be represented using any one of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0068] It should be noted that terms explained in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

[0069] Furthermore, the information, parameters, etc. described in this specification may be expressed as absolute values, as relative values ​​from a predetermined value, or as corresponding other information.

[0070] A communications terminal may also be referred to by those skilled in the art as a mobile communications terminal, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communications device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0071] As used herein, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0072] When designations such as "first," "second," etc. are used herein, any reference to such elements does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed therein or that the first element must precede the second element in some way.

[0073] To the extent that the terms "include," "including," and variations thereof are used herein or in the claims, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used herein or in the claims, is not intended to be an exclusive or.

[0074] In this specification, a plurality of devices is also included unless the context or the technology clearly indicates that only one device exists.

[0075] Throughout this disclosure, the plural is intended to be included unless the singular is clearly indicated by the context.

[0076] Finally, various exemplary embodiments included in the present disclosure are described below in [E1] to [E9].

[0077] [E1] A device comprising: a reception unit that receives information regarding interactions between a fictional character and a user in a virtual space; a control unit that updates information regarding the character based on the information regarding the interactions and determines information regarding a product or service to be proposed based on the updated information regarding the character; and an output unit that outputs the determined information regarding the product or service.

[0078] [E2] The device described in [E1], wherein the control unit creates an update prompt based on information related to the interaction, and inputs the update prompt into a language model that outputs according to the content of the prompt, thereby updating information related to the character and determining information related to the proposed product or service.

[0079] [E3] The device described in [E2], wherein the control unit creates the update prompt, in which the content of the interaction is specified as input information and the task is to update information related to the character and suggest products or services that the character will prefer after the update.

[0080] [E4] The device according to [E3], wherein the control unit creates the update prompt, the task of which is to suggest a product or service that the user prefers from among products or services that the character prefers.

[0081] [E5] The device described in [E3], wherein the control unit creates the update prompt, which specifies that the task is to suggest products or services preferred by the character other than products or services preferred by the user.

[0082] [E6] The device described in any one of [E1] to [E5], wherein the reception unit receives information related to the creation of the character before receiving information related to the interaction, the control unit creates the character based on the information related to the character creation, and the output unit outputs information related to the created character.

[0083] [E7] The device according to claim [E6], wherein the control unit creates a creation prompt based on information related to the creation of the character, and inputs the creation prompt into the language model to create the character.

[0084] [E8] The device according to claim [E7], wherein the control unit creates the creation prompt in which input information specifies characteristics of the character and a task specifies creating the character.

[0085] [E9] A method executed by a device, comprising: receiving information relating to an interaction between a fictional character and a user in a virtual space; updating information relating to the character based on the information relating to the interaction; determining information relating to a product or service to be proposed based on the updated information relating to the character; and outputting the determined information relating to the product or service.

[0086] 10... Recommendation device, 11... Reception unit, 12... Control unit, 13... Output unit, 30... Creation prompt, 40... Update prompt, 50... Language model.

Claims

1. A device comprising: a reception unit that receives information regarding interactions between a fictional character and a user in a virtual space; a control unit that updates information regarding the character based on the information regarding the interactions and determines information regarding a product or service to be proposed based on the updated information regarding the character; and an output unit that outputs the determined information regarding the product or service.

2. The device of claim 1, wherein the control unit creates an update prompt based on the information related to the interaction, and inputs the update prompt into a language model that outputs according to the content of the prompt, thereby updating the information related to the character and determining the information related to the suggested product or service.

3. The device of claim 2, wherein the control unit creates the update prompt, in which the content of the interaction is specified as input information and the task is to update information related to the character and to suggest products or services that the character will prefer after the update.

4. The device according to claim 3, wherein the control unit creates the update prompt in which the task is to suggest a product or service that the user prefers from among products or services that the character prefers.

5. The device of claim 3, wherein the control unit creates the update prompt in which the task is to suggest a product or service that is preferred by the character but is not preferred by the user.

6. The device described in claim 2, wherein the reception unit receives information related to the creation of the character before receiving information related to the interaction, the control unit creates the character based on the information related to the character creation, and the output unit outputs information related to the created character.

7. The device according to claim 6, wherein the control unit creates a creation prompt based on information related to the creation of the character, and inputs the creation prompt into the language model to create the character.

8. The device according to claim 7, wherein the control unit creates the creation prompt in which characteristics of the character are defined as input information and creation of the character is defined as a task.

9. A method executed by a device, comprising: receiving information relating to an interaction between a fictional character and a user in a virtual space; updating information relating to the character based on the information relating to the interaction; determining information relating to a product or service to be suggested based on the updated information relating to the character; and outputting the determined information relating to the product or service.