Information processing device, information processing method, and recording medium

Abstract

An information processing device (10) has an acquisition unit (110), a content information generation unit (120), an instruction information generation unit (130), an input processing unit (140), and an output information generation unit (150). The acquisition unit (110) acquires item identification information for identifying an item to be included in a profile of a subject. The content information generation unit (120) generates content information concerning the content of the item by using related information related to the subject. The instruction information generation unit (130) sets the content information as the content of the item and generates instruction information including the content of the item and input information input by the subject. The input processing unit (140) performs processing for inputting the instruction information into a model that outputs response information corresponding to the instruction information. The output information generation unit (150) acquires the response information generated by the model and uses the response information to generate output information to outputted by a communication device operated by the subject.

Description

Information processing device, information processing method, and recording medium

[0001] The present invention relates to an information processing device, an information processing method, and a recording medium.

[0002] In recent years, the use of generative AI (Artificial Intelligence), typified by large-scale language models, has been considered. One example of an application of generative AI is a device that converses with people, such as a chatbot. For example, Patent Literature 1 describes that prompts for a chatbot include instructions to role-play as a persona, as well as the persona's characteristics, guidelines for action, input / output examples, and constraints.

[0003] JP 2024-75549 A

[0004] In order to increase the value of a device that converses with a subject, the device needs to respond accurately in accordance with the subject's preferences.

[0005] An information processing device according to one aspect of the present disclosure comprises: an acquisition means for acquiring item-specific information that identifies items to be included in a subject's profile; a content information generation means for generating content information regarding the content of the item using related information related to the subject; an instruction information generation means for setting the content information to the content of the item and generating instruction information including the content of the item and input information input by the subject; an input processing means for performing processing to input the instruction information to a model that outputs response information in response to the instruction information; and an output information generation means for acquiring the response information generated by the model and using the response information to generate output information to be output by a communication device operated by the subject.

[0006] An information processing method in one aspect of the present disclosure includes a computer: acquiring item-specific information that identifies items to be included in a subject's profile; generating content information regarding the content of the item using related information related to the subject; setting the content information to the content of the item; generating instruction information including the content of the item and input information entered by the subject; performing processing to input the instruction information to a model that outputs response information in response to the instruction information; acquiring the response information generated by the model; and using the response information to generate output information to be output by a communication device operated by the subject.

[0007] A program according to one aspect of the present disclosure has a computer equipped with: an acquisition means for acquiring item-specific information that identifies items to be included in a subject's profile; a content information generation means for generating content information regarding the content of the item using related information related to the subject; an instruction information generation means for setting the content information to the content of the item and generating instruction information including the content of the item and input information entered by the subject; an input processing means for performing processing to input the instruction information to a model that outputs response information in response to the instruction information; and an output information generation means for acquiring the response information generated by the model and using the response information to generate output information to be output by a communication device operated by the subject.

[0008] According to an example of the present disclosure, a device that converses with a subject can accurately respond in a way that the subject desires.

[0009] FIG. 1 is a diagram illustrating an example of a usage environment and configuration of an information processing device according to the present disclosure. FIG. 2 is a diagram for explaining an example of items that may be included in instruction information. FIG. 3 is a diagram illustrating an example of a usage environment and configuration of an information processing device. FIG. 4 is a diagram illustrating an example of a usage environment and configuration of an information processing device. FIG. 5 is a diagram illustrating an example of a hardware configuration of an information processing device. FIG. 6 is a flowchart illustrating an example of a process performed by an information processing device. FIG. 7 is a flowchart illustrating an example of a process performed by an information processing device. FIG. 8 is a diagram illustrating an example of a usage environment and configuration of an information processing device. FIG. 9 is a diagram illustrating an example of a screen displayed by a communication device.

[0010] Hereinafter, in this disclosure, the drawings relate to one or more embodiments. In addition, in all drawings, similar components are given similar reference numerals and descriptions thereof will be omitted as appropriate.

[0011] 1, the information processing device 10 is used together with a communication device 20, an external device 30, and a storage unit 40. The information processing device 10 communicates with other devices via, for example, the Internet, but may communicate using other methods.

[0012] The communication device 20 is a device operated by the subject and is capable of input and output. Input to the communication device 20 may be performed by voice or via an operating device such as a touch panel. Output from the communication device 20 may be performed by voice or by display on a display. An example of the communication device 20 is a portable communication device such as a smartphone or tablet, but it may also be a fixed communication device.

[0013] When instruction information is input, the external device 30 generates response information corresponding to the instruction information. For example, the external device 30 generates the response information using a machine learning model, but may also generate the response information using a rule-based model. The machine learning model used by the external device 30 is, for example, a conversational artificial intelligence (AI) such as a large-scale language model, but is not limited to this.

[0014] The storage unit 40 stores various types of information used by the information processing device 10. Specific examples of the information stored in the storage unit 40 will be described later.

[0015] When using the information processing device 10, the subject provides a predetermined input to the communication device 20 as part of a conversation. The communication device 20 uses this input to generate input information and transmits the generated input information to the information processing device 10. This input information includes, for example, text as part of a conversation between the subject and the information processing device 10 (or the external device 30). The information processing device 10 uses this input information to generate instruction information to be input to the model and transmits this instruction information to the external device 30. For example, if the model is a conversational AI, the instruction information is a prompt.

[0016] When the external device 30 acquires instruction information from the information processing device 10, it inputs the instruction information into a model and generates response information using the model. The response information includes text. If the model is conversational AI (Artificial Intelligence), the text is part of a conversation between the subject and the information processing device 10 (or the external device 30). The external device 30 then transmits the response information to the information processing device 10. The information processing device 10 uses the response information to generate output information to be output by the communication device 20, and transmits the output information to the communication device 20.

[0017] The communication device 20 outputs the output information. After the subject recognizes the output information, the subject makes the next input to the communication device 20 as necessary. By repeating this process, the subject can converse with the information processing device 10.

[0018] In order for the output information to match the preferences of the subject, it is necessary to include appropriate information in the instruction information input to the model. As will be described in detail below, the items to be included in the instruction information are predetermined in the information processing device 10. The information processing device 10 then uses related information related to the subject to generate content information regarding the contents of the items and includes this content information in the instruction information. Therefore, the output information output by the external device 30 is likely to match the preferences of the subject.

[0019] An example of the related information is input information generated by the communication device 20. In other words, the related information and the input information may be the same information. For example, if the model is a conversational AI such as a large-scale language model, examples of the related information and the input information include text indicating what the subject has spoken to the large-scale language model. Here, "utterance" includes not only voice input, but also input of text using an input device such as a touch panel or keyboard. However, the related information may include at least one of information posted by the subject using a social networking service (SNS) or the like and information registered when using a service such as an SNS.

[0020] The information processing device 10 includes, for example, an acquisition unit 110 , a content information generation unit 120 , a command information generation unit 130 , an input processing unit 140 , and an output information generation unit 150 .

[0021] The acquisition unit 110 acquires information that identifies items to be included in the subject's profile. Hereinafter, this information will be referred to as item-specific information. The item-specific information is stored, for example, in the storage unit 40. In this case, the information processing device 10 reads the item-specific information from the storage unit 40.

[0022] The item specifying information is set by, for example, an administrator of the information processing device 10 and stored in the storage unit 40. However, the item specifying information may also be set by the subject and stored in the storage unit 40.

[0023] The items indicated by the item-specific information are related to the attributes of the subject. More specifically, these items include the demographic attributes and psychographic attributes of the subject, as shown in Fig. 2, for example. The items indicated by the item-specific information further preferably include at least one of the subject's current interests and the subject's current problems, and preferably both.

[0024] The demographic attribute is a demographic attribute, and examples of the attribute include at least one of gender, age, occupation, income, place of residence or area of ​​residence, family structure, and educational background.

[0025] The psychographic attributes are psychological attributes of the subject, and items related to these attributes relate to at least one of values, personality, lifestyle, behavioral style, and consumption preferences, for example.

[0026] More specifically, the psychographic attributes include at least one of the following:

[0027] (1) Basic Values ​​Examples of items related to this include: - Self-centered, i.e., putting one's own interests first. - Socially responsible, i.e., emphasizing the interests of society as a whole. - Liberal, i.e., respecting individual freedom and rights. - Conservative, i.e., emphasizing tradition and order. - Religious, i.e., emphasizing values ​​based on religious beliefs. - Humanitarian, i.e., cherishing equality and empathy. - Creative, i.e., emphasizing creativity and ingenuity. - Self-actualizing, i.e., pursuing personal growth and self-realization. - Spiritual, i.e., respecting spiritual growth and inner peace. - Environmentally responsible, i.e., focusing on environmental protection and sustainability.

[0028] (2) Personality traits (Enneagram) - Idealistic, i.e., seeking perfection and striving for improvement. - Helpful, i.e., finding joy in supporting and helping others. - Ambitious, i.e., focusing on goals and success. - Ambitious, i.e., placing importance on achieving goals and success. - Inventive, i.e., valuing originality and expression. - Obsessive, i.e., striving for perfection down to the smallest detail and tending to explore deeply until satisfied. - Security-oriented, i.e., seeking stability and security and being loyal. - Optimistic, i.e., cheerful and enjoying new experiences. - Challenger, i.e., willing to face problems and overcome difficulties. - Pacifist, i.e., avoiding conflict and valuing harmony.

[0029] (3) Life-oriented / social contribution-oriented, i.e., they place importance on contributing to society through work or volunteering. Family-oriented, i.e., they value maintaining family ties and traditions. Self-actualization-oriented, i.e., they place importance on personal learning and growth, and investing in hobbies and leisure activities. Faith-oriented, i.e., they place importance on involvement in religious activities and faith. Nature-lovers, i.e., they actively participate in activities to coexist with nature and protect the environment.

[0030] (4) Communication style The following items relate to the subject's communication method preferences. - Face-to-face preference, i.e., preferring to meet and talk in person. - Telephone preference, i.e., preferring to talk over the phone. - Email preference, i.e., preferring to communicate via email. - SNS preference, i.e., preferring to communicate via SNS. - Anonymous preference, i.e., preferring to communicate anonymously.

[0031] (5) Styles of receiving and providing information - Information receivers, i.e., they primarily prefer to receive information. - Information senders, i.e., they prefer to actively send information themselves. - Emotional empathy, i.e., they place importance on emotional empathy in information exchange. - Logical debaters, i.e., they prefer logical arguments based on information.

[0032] (6) Consumption behavior and preferences The following items indicate factors that influence purchasing behavior. - Brand lover, i.e., preferring to purchase products from famous brands. - Trend-conscious, i.e., tending to prefer popular products. - Functionality-conscious, i.e., placing the most importance on product functions and performance. - Early adopter, i.e., wanting to be the first to try new technologies and products. - Price fanatic, i.e., thinking that expensive products are of good quality. - Foreign product lover, i.e., preferring foreign-made products over domestically produced products. - Cost-performance-conscious, i.e., placing the most importance on the balance between price and quality. - Value-conscious, i.e., choosing only products that I truly value. - Brand loyalist, i.e., tending to purchase only products from specific brands. - Counterfeit hater, i.e., absolutely avoiding counterfeits and fakes. - Individuality-conscious, i.e., seeking unique products that are different from others.

[0033] (7) Purchasing method preferences: Convenience is important, i.e., when purchasing, people prefer easy methods such as online shopping or vending machines. Authenticity is important, i.e., people prefer to purchase in stores where they can actually touch and check the product.

[0034] (8) Methods of gathering information before purchasing: - Influence of advertising, i.e., becoming interested in a product after seeing an advertisement. - Influence of social media, i.e., referring to reviews and posts on social media. - Information overload, i.e., finding it difficult to choose because there is too much information. - Love of new products, i.e., being interested in trying new products. - Emphasis on traceability, i.e., the origin and manufacturing process of a product are important.

[0035] (9) Hobbies and Preferences - Music lover, i.e., enjoys going to concerts, playing musical instruments, listening to music, etc. - Movie and TV lover, i.e., enjoys watching movies at the cinema, watching TV series, writing movie reviews, etc. - Book lover, i.e., enjoys reading novels and business books, and going to the library, etc. - Cook lover, i.e., enjoys trying new recipes and attending cooking classes, etc. - Creative, i.e., enjoys drawing, crafting and DIY (Do It Yourself), making music, etc. - Game lover, i.e., enjoys video games and board games, etc. - Outdoor lover, i.e., enjoys hiking and camping, and participating in nature conservation activities, etc. - Health conscious, i.e., enjoys dieting, healthy eating, and excessive exercise (walking), etc. - Sports lover, i.e., enjoys playing sports and watching sports, etc. - Travel lover, i.e., enjoys visiting new places and planning trips, etc.

[0036] (10) How do you spend your leisure time? Outdoorsy: I enjoy activities in nature, such as camping and hiking, and sports. Indoorsy: I enjoy relaxing indoor activities, such as watching videos and movies and reading. Creative: I enjoy spending time on creative activities, such as art, music, and crafts. Social: I enjoy social activities, such as attending events, getting together with friends, and parties. Relaxation: I value relaxation, such as spa yoga and meditation. Sports: I enjoy watching sports and playing sports myself. Gamer: I enjoy playing games, such as video games and board games. Cook: I enjoy cooking and trying new recipes. Traveler: I enjoy visiting new places and planning trips (domestic and international travel). Volunteer: I enjoy participating in community activities and social contribution activities. Shopper: I enjoy shopping at shopping malls and brick-and-mortar stores, and / or online shopping.

[0037] Then, the administrator or subject of the information processing device 10 selects, for example, multiple items to actually use from these items. For example, the information processing device 10 generates information that can identify the selected items as item specification information and stores this item specification information in the storage unit 40. Note that when item specification information is generated according to items selected by the administrator, one piece of item specification information may be applied to multiple subjects. On the other hand, when item specification information is generated according to items selected by the subjects, the item specification information is stored in the storage unit 40 for each subject.

[0038] The acquisition unit 110 also acquires various types of information used by the content information generation unit 120 and the instruction information generation unit 130. For example, the acquisition unit 110 acquires, from the communication device 20, input information generated by an input made by the subject to the communication device 20.

[0039] The content information generating unit 120 generates content information about the content of the above-mentioned items using related information related to the subject. For example, the content information generating unit 120 generates content information using a machine learning model.

[0040] When generating content information for items related to demographic attributes, the content information generation unit 120 uses, as related information, input information generated by the communication device 20, for example, text indicating what the subject has said to the large-scale language model. However, the content information generation unit 120 may also use, as related information, at least one of information posted by the subject using SNS or the like and information registered when using a service such as SNS.

[0041] Furthermore, when generating content information for items related to psychographic attributes, the content information generation unit 120 uses, as related information, input information generated by the communication device 20, for example, text indicating what the subject has said to the large-scale language model. However, the content information generation unit 120 may also use, as related information, information posted by the subject using SNS or the like.

[0042] The content information generation unit 120 stores the generated content information in the storage unit 40 as necessary. When there are multiple subjects, the content information generation unit 120 may store the content information of each subject in association with the subject's identification information. In this way, the instruction information generation unit 130, the details of which will be described later, can use the content information stored in the storage unit 40, thereby reducing the frequency with which the content information generation unit 120 generates content information.

[0043] The content information generating unit 120 may store the related information in the storage unit 40 as necessary. When there are multiple subjects, the content information generating unit 120 stores the related information of each subject in association with the identification information of the subject. The content information generating unit 120 may then generate content information using the related information stored in the storage unit 40.

[0044] When related information is repeatedly acquired, the content information generating unit 120 may store the related information in the storage unit 40. In this way, the content information generating unit 120 can generate content information using the history of the related information.

[0045] The instruction information generation unit 130 sets the content information generated by the content information generation unit 120 as the content of the item, and generates instruction information including the content of the item and input information input by the subject. The input information used here includes, for example, text indicating the content spoken by the subject to the large-scale language model. An example of instruction information is a prompt.

[0046] The input processing unit 140 performs processing for inputting instruction information to a model that outputs response information in response to the instruction information. For example, the input processing unit 140 transmits the instruction information to the external device 30.

[0047] The output information generation unit 150 acquires the response information generated by the model. For example, the output information generation unit 150 acquires the response information from the external device 30. Here, the response information changes depending on the content information included in the instruction information. For example, the information indicated by the response information may change, or the information indicated by the response information may remain the same but the wording or tone may change.

[0048] Then, the output information generation unit 150 generates output information using this response information and transmits this output information to the communication device 20. The output information generation unit 150 includes, for example, text as conversation information included in the response information in the output information.

[0049] 3, the information processing device 10 may also function as the communication device 20. In this case, the information processing device 10 is a portable communication device such as a smartphone or tablet.

[0050] 4, the information processing device 10 may also have a model unit 160. The model unit 160 performs the processing that was performed by the external device 30 in FIG. 1. In this case, the information processing device 10 has a model. In the example shown in this figure, the information processing device 10 does not use the external device 30. The input processing unit 140 inputs instruction information to the model unit 160. The output information generation unit 150 then acquires response information from the model unit 160.

[0051] The information processing apparatus 10 has, as a hardware configuration, for example, as shown in FIG. 5, a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

[0052] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0053] The processor 1020 is implemented by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

[0054] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0055] The storage device 1040 is an auxiliary storage device realized by removable media such as a hard disk drive (HDD), a solid state drive (SSD), a memory card, or a read-only memory (ROM), and has a recording medium. The recording medium of the storage device 1040 stores program modules that realize each function of the information processing device 10 (e.g., the acquisition unit 110, the content information generation unit 120, the instruction information generation unit 130, the input processing unit 140, the output information generation unit 150, the model unit 160, and the statistical processing unit 170 described below). The processor 1020 loads each of these program modules into the memory 1030 and executes them, thereby realizing each function corresponding to the program module. The storage device 1040 may also function as the memory unit 40.

[0056] The input / output interface 1050 is an interface for connecting the information processing device 10 to various input / output devices. For example, the information processing device 10 may communicate with the storage unit 40 via the input / output interface 1050.

[0057] The network interface 1060 is an interface for connecting the information processing device 10 to a network. This network is, for example, a local area network (LAN) or a wide area network (WAN). The network interface 1060 may connect to the network wirelessly or by wire. The information processing device 10 may communicate with at least one of the communication device 20, the external device 30, and the storage unit 40 via the network interface 1060.

[0058] The information processing device 10 operates, for example, as shown in Fig. 6. First, the acquisition unit 110 acquires item-specific information, for example, from the storage unit 40. If the storage unit 40 stores item-specific information for multiple subjects, the acquisition unit 110 acquires information identifying the subjects, for example, from the communication device 20, and acquires item-specific information corresponding to this information from the storage unit 40 (step S10).

[0059] The content information generating unit 120 also acquires related information from, for example, the communication device 20 (step S20). The content information generating unit 120 then generates content information for the item indicated by the item identification information. If there are multiple items, the content information generating unit 120 generates information indicating the content of each of the multiple items, and converts this information into content information (step S30). The content information generating unit 120 stores the content information in the storage unit 40 as necessary.

[0060] The instruction information generation unit 130 acquires input information (step S40). Note that the related information may also serve as input information. In this case, step S40 is omitted. The instruction information generation unit 130 then generates instruction information using the input information and the content information generated in step S30, and performs processing to input this instruction information into the model. One example of this processing is transmitting the instruction information to the external device 30 (step S50).

[0061] It should be noted that steps S20 and S30 are omitted if the content information is stored in the storage unit 40. The instruction information generating unit 130 then reads out the content information from the storage unit 40 and uses it.

[0062] After step S50, the instruction information is input to the model. Then, the output information generation unit 150 acquires the response information generated by the model. For example, the external device 30 inputs the instruction information acquired from the input processing unit 140 to the model and transmits the response information generated by the model to the information processing device 10 (step S60). Then, the output information generation unit 150 generates output information using the acquired response information and transmits this output information to, for example, the communication device 20 (step S70).

[0063] When the communication device 20 acquires the output information, it outputs the output information to make the target person aware of it.

[0064] Here, when the information processing device 10 is used when a subject interacts with a model, the input information and the related information may be the same information, and this information may be information indicating the content of the subject's utterance, for example, text information indicating the content of the utterance. In this case, the information processing device 10 may operate, for example, as shown in FIG. 7.

[0065] First, the acquisition unit 110 acquires the item-specific information (step S10). This process is similar to the example shown in FIG.

[0066] Next, the subject inputs information indicating the content of the utterance to the communication device 20. As a result, the communication device 20 generates information indicating the content of the utterance. Hereinafter, this information will be referred to as utterance information. The communication device 20 transmits the utterance information to the information processing device 10. Then, the content information generation unit 120 of the information processing device 10 acquires this utterance information (step S22).

[0067] Next, the content information generating unit 120 generates content information for the item indicated by the item specifying information using the utterance information, and stores the generated content information in the storage unit 40 (step S32). At this time, the content information generating unit 120 stores the utterance information in the storage unit 40.

[0068] Thereafter, the information processing device 10 performs steps S50 to S70. These steps are the same as those in the example shown in Fig. 6. Note that in step S50, speech information is used as input information.

[0069] When the communication device 20 acquires the output information, it outputs the output information to the subject to recognize it. The subject then inputs information indicating the utterance content to the communication device 20 as necessary. The information processing device 10 then repeats the processes of steps S22 to S70. Note that in step S32, the content information generation unit 120 updates the content information using the newly acquired utterance information. For example, the content information generation unit 120 may update the content information using a history of utterance information including the newly acquired utterance information, or may update the content information using the content information generated in the previous process and the newly acquired utterance information. When the content information is updated, the user is more likely to be satisfied with the response information from the model.

[0070] As described above, in the information processing device 10, the items to be included in the instruction information are determined by the item specification information acquired by the acquisition unit 110. The content information generation unit 120 then generates content information related to the content of the items using related information related to the subject. The instruction information generation unit 130 then includes this content information in the instruction information. Therefore, the response information output by the model is likely to match the preferences of the subject. This allows the output information generation unit 150 to accurately generate output information that the subject desires.

[0071] In particular, if the items include something that the subject is currently interested in or currently struggling with, the response information is likely to include suggestions based on these. In this case, the output information generating unit 150 can accurately generate output information that the subject particularly desires.

[0072] Furthermore, when the amount of related information is less than the amount of content information, the amount of information in the instruction information is smaller than when the related information is included in the instruction information. In this case, the load on the model is smaller. In particular, when the related information is an example of conversation information and the content information is updated with new conversation information, the content information includes content reflecting the history of the conversation information. In this case, the amount of information in the instruction information is less likely to increase compared to when the history of the conversation information is included in the instruction information, and the output information generation unit 150 can obtain response information with similar accuracy. Furthermore, according to one aspect of the embodiment, the information processing device 10 can estimate the preferences of a subject based on the subject's item-specific information. Conventionally, in order to respond in accordance with the subject's preferences, the information processing device 10 was required to repeatedly engage in dialogue with the subject. In addition, even if dialogue was repeated, there was a risk of misinterpreting the subject's preferences, requiring corrections each time. As a result, the amount of information handled by the information processing device 10 increased, and computer resources capable of executing such a process were required. Furthermore, there was also the problem that the longer the response took, the greater the power consumption of the information processing device 10. In contrast, according to the information processing device 10 of the embodiment, the item-specific information necessary for estimating the preferences of the subject is provided, so the information processing device 10 does not need to perform excessive trials to estimate the preferences of the subject. Such an improvement leads to a reduction in the resources required for the information processing device 10.

[0073] 8, after updating the content information in step S32, the content information generating unit 120 may store the updated content information in the storage unit 40, thereby storing a history of the content information in the storage unit 40 (step S34). In this way, by using the information stored in the storage unit 40, it is possible to check how the content information of the subject, for example, preferences, has changed.

[0074] Furthermore, even when the related information is information other than utterance information, the content information generating unit 120 may update the content information by repeatedly acquiring the related information. In this case, the content information generating unit 120 may store a history of the content information in the input processing unit 140.

[0075] When the storage unit 40 stores content information for each of a plurality of subjects, the information processing device 10 may include a statistical processing unit 170, as shown in FIG. 9 . The statistical processing unit 170 statistically processes the content information for the plurality of subjects stored in the storage unit 40, and stores statistical information indicating the results in the storage unit 40. For example, the statistical processing unit 170 identifies the most common content information for a certain item. The items processed by the statistical processing unit 170 may be, for example, things that the subject is currently interested in or things that the subject is currently struggling with. In this case, trends can be identified using the processing results of the statistical processing unit 170.

[0076] Furthermore, when the statistical processing unit 170 operates periodically to generate new statistical information periodically, the history of the statistical information can be stored in the storage unit 40. In this case, by using the history of the statistical information, it is possible to grasp, for example, changes in trends.

[0077] The output information generation unit 150 may use the content information stored in the storage unit 40 to identify products or services that suit the preferences of the target person, and transmit information about the identified products and services to the communication device 20. In this case, the output information generation unit 150 may also use current trends to identify the products or services.

[0078] 10 , the communication device 20 may output information transmitted from the information processing device 10 via an avatar 200. This output may be performed by displaying text on a screen or by audio output. In this case, the output information generation unit 150 of the information processing device 10 may use content information stored in the storage unit 40 to determine the appearance of the avatar 200 and / or control the avatar 200.

[0079] For example, the appearance of the avatar 200 may reflect the demographic attributes of the subject, such as gender and age. In this case, the avatar 200 will be of the same gender and age as the subject. Alternatively, the avatar 200 may be of the opposite gender to the subject. Furthermore, if the psychographic attributes of the subject include information that can identify the subject's preferences in appearance, the output information generation unit 150 will match the appearance of the avatar 200 to these preferences.

[0080] Furthermore, the output information generation unit 150 may use at least one of the demographic attributes and psychographic attributes of the subject to determine at least one of the movements and facial expressions of the avatar 200. For example, if the psychographic attributes of the subject indicate that they are logical, the movements and facial expressions of the avatar 200 may be those that a logical person would make.

[0081] This makes it easier for the target person to feel a sense of affinity with avatar 200.

[0082] 10 is an example of a screen displayed by communication device 20 when the target person inputs predetermined information while conversing with avatar 200. This screen is a screen for inputting information for identifying a product or service to be introduced to the target person, for example.

[0083] The predetermined information to be input, in other words, the information that avatar 200 prompts the user to input, may be, for example, at least one of the items exemplified as demographic attributes or at least one of the items exemplified as psychographic attributes. In this case, output information generation unit 150 displays this screen, and when the specific content of the item to be input is identified from the content spoken by the subject, output information generation unit 150 may treat the content as input information and reflect it as having been input on the screen displayed by communication device 20.

[0084] The output information generation unit 150 may also change the screen itself displayed on the communication device 20 or the transition of the screen using at least one of the items exemplified as demographic attributes or at least one of the items exemplified as psychographic attributes. For example, for a subject presumed to be accustomed to entering information, the number of explanatory sentences displayed on the screen of the communication device 20 may be reduced, or more or fewer input fields may be included on one screen. On the other hand, for a subject presumed to be inexperienced in entering information, the number of explanatory sentences displayed on the screen of the communication device 20 may be increased, or fewer or more input fields may be included on one screen. Furthermore, the output information generation unit 150 may frequently display confirmation screens for subjects presumed to be inexperienced in entering information.

[0085] When the generation and control of the avatar is performed by the communication device 20, the above-described processing is performed by the communication device 20.

[0086] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0087] In addition, although the flowcharts used in the above description show a sequence of steps (processes), the order of steps executed in each embodiment is not limited to the sequence shown in the flowcharts. In each embodiment, the order of steps shown in the diagrams can be changed as long as it does not cause any problems in terms of the content.

[0088] Some or all of the above embodiments may be described as, but are not limited to, the following notes. 1. An information processing device comprising: an acquisition means for acquiring item-specific information that identifies items to be included in a profile of a subject; a content information generation means for generating content information related to the content of the item using related information related to the subject; an instruction information generation means for setting the content information to the content of the item and generating instruction information including the content of the item and input information input by the subject; an input processing means for processing to input the instruction information to a model that outputs response information in response to the instruction information; and an output information generation means for acquiring the response information generated by the model and using the response information to generate output information to be output by a communication device operated by the subject. 2. The information processing device described in above 1, wherein the model is a large-scale language model. 3. The information processing device described in above 2, wherein the related information and the input information include content spoken by the subject to the large-scale language model. 4. The information processing device described in any one of above 1 to 3, wherein the content information generation means updates the content information by repeatedly acquiring the related information. 5. The information processing device according to claim 4, wherein the content information generating means stores a history of the content information in a storage means. 6. The information processing device according to any one of claims 1 to 5, wherein the items are related to attributes of the subject. 7. The information processing device according to claim 6, wherein the items are related to psychographic attributes of the subject. 8. The information processing device according to claim 7, wherein the items are related to at least one of values, personality, lifestyle orientation, behavioral style, and consumption preferences. 9. The information processing device according to claim 6, wherein the items include at least one of things that the subject is currently interested in and things that the subject is currently struggling with. 10. The information processing device according to claim 9, comprising statistical processing means for statistically processing things that a plurality of the subjects are currently interested in or things that the subjects are currently struggling with.11. An information processing device according to any one of claims 1 to 10 above, wherein the output information includes an avatar, and wherein the output information generation means uses the content information to determine the appearance of the avatar and / or control the avatar. 12. An information processing method, wherein a computer: acquires item-specific information that identifies items to be included in a subject's profile; generates content information relating to the content of the items using related information related to the subject; sets the content information to the content of the items; generates instruction information including the content of the items and input information input by the subject; performs processing to input the instruction information to a model that outputs response information in response to the instruction information; acquires the response information generated by the model, and uses the response information to generate output information to be output by a communication device operated by the subject. 13. 13. A program for causing a computer to have: an acquisition means for acquiring item specification information that specifies items to be included in a subject's profile; a content information generation means for generating content information regarding the content of the item using related information related to the subject; an instruction information generation means for setting the content information to the content of the item and generating instruction information including the content of the item and input information input by the subject; an input processing means for performing processing to input the instruction information to a model that outputs response information in response to the instruction information; and an output information generation means for acquiring the response information generated by the model and using the response information to generate output information to be output by a communication device operated by the subject. 14. A recording medium having the program described in 13 recorded thereon.

[0089] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 11, which are dependent on Supplementary Note 1, may also be dependent on Supplementary Notes 12, 13, and 14 in the same dependent relationship as Supplementary Notes 2 to 11. Furthermore, not limited to Supplementary Notes 1, 12, 13, and 14, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0090] This application claims priority based on Japanese Patent Application No. 2024-143993, filed on August 26, 2024, the disclosure of which is incorporated herein by reference in its entirety.

[0091] REFERENCE SIGNS LIST 10 Information processing device 20 Communication device 30 External device 40 Storage unit 110 Acquisition unit 120 Content information generation unit 130 Instruction information generation unit 140 Input processing unit 150 Output information generation unit 160 Model unit 170 Statistical processing unit

Claims

an acquisition means for acquiring item-specific information that identifies items to be included in the subject's profile; content information generating means for generating content information relating to the content of the item using related information relating to the subject; an instruction information generating means for setting the content information to the content of the item and generating instruction information including the content of the item and input information input by the subject; an input processing means for performing processing to input the instruction information to a model that outputs response information according to the instruction information; an output information generating means for acquiring the response information generated by the model and generating output information to be output by a communication device operated by the subject person using the response information; An information processing device comprising:

2. The information processing device according to claim 1, The information processing device, wherein the model is a large-scale language model.

3. The information processing device according to claim 2, The information processing device, wherein the related information and the input information include content spoken by the subject to the large-scale language model. 　 In the information processing device according to any one of claims 1 to 3, The content information generating means updates the content information by repeatedly acquiring the related information. 　 In the information processing device according to any one of claims 1 to 3, An information processing device, wherein the items are related to attributes of the subject. 　 In the information processing device according to any one of claims 1 to 3, The information processing device, wherein the items include at least one of things that the subject is currently interested in and things that the subject is currently struggling with.

7. The information processing device according to claim 6, An information processing device comprising a statistical processing means for statistically processing the things that the plurality of subjects are currently interested in or the things that the subjects are currently struggling with. 　 In the information processing device according to any one of claims 1 to 3, the output information includes an avatar; The information processing device, wherein the output information generating means uses the content information to determine at least one of the appearance of the avatar and the control of the avatar.

5. The information processing device according to claim 4, The content information generating means stores the history of the content information in a storage means.

6. The information processing device according to claim 5, An information processing device, wherein the items are related to psychographic attributes of the subject.

11. The information processing device according to claim 10, The information processing device, wherein the items relate to at least one of values, personality, lifestyle orientation, behavioral style, and consumption preferences. 　 The computer obtaining item-specific information that identifies items to be included in the subject's profile; generating content information about the content of the item using relevant information related to the subject; setting the content information to the content of the item, and generating instruction information including the content of the item and the input information input by the subject; performing a process for inputting the instruction information into a model that outputs response information in response to the instruction information; An information processing method that acquires the response information generated by the model and uses the response information to generate output information to be output by a communication device operated by the subject. 　 On the computer, an acquisition means for acquiring item-specific information that identifies items to be included in the subject's profile; content information generating means for generating content information relating to the content of the item using related information relating to the subject; an instruction information generating means for setting the content information to the content of the item and generating instruction information including the content of the item and input information input by the subject; an input processing means for performing processing to input the instruction information to a model that outputs response information according to the instruction information; an output information generating means for acquiring the response information generated by the model and generating output information to be output by a communication device operated by the subject person using the response information; A recording medium that stores a program that allows the user to

Images