system

Abstract

The system according to this embodiment aims to effectively communicate the appeal of stores and products by linking them with external information. [Solution] The system according to the embodiment comprises a reception unit, an external information acquisition unit, a topic generation unit, and a playback unit. The reception unit receives input such as store names and product / service names. The external information acquisition unit acquires external information based on the information received by the reception unit. The topic generation unit incorporates the appeal of the store and products into the topic based on the external information acquired by the external information acquisition unit. The playback unit plays the radio talk generated by the topic generation unit in the store.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that means for effectively conveying the charm of stores and products are limited, and it is difficult to perform an effective promotion in conjunction with external information.

[0005] The system according to the embodiment aims to effectively convey the charm of stores and products in conjunction with external information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an external information acquisition unit, a topic generation unit, and a playback unit. The reception unit receives input such as store names and product / service names. The external information acquisition unit acquires external information based on the information received by the reception unit. The topic generation unit incorporates the appeal of the store and products into topics based on the external information acquired by the external information acquisition unit. The playback unit plays the radio talk generated by the topic generation unit within the store. [Effects of the Invention]

[0007] The system according to this embodiment can effectively communicate the appeal of stores and products by linking them with external information. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The radio agent system according to an embodiment of the present invention is a radio-like agent that automatically interacts with external information while incorporating information about stores and the products and services they handle. This radio agent system takes the store name and product / service names as input, and a generating AI incorporates external information to create a realistic radio talk show that highlights the store's and products' appeal, generating an unlimited number of tracks for playback within the store. This mechanism allows stores to effectively promote their products and services. For example, the store name and product / service names are input. For instance, information such as "SB Takeshiba Store" or "Tobidel Protective Film" is input. This information is input to the generating AI. Next, the generating AI analyzes the input information and incorporates external information to highlight the store's and products' appeal. For example, it incorporates external information such as weather data, day of the week data, and discussions about Friday night movies to introduce the store's and products' appeal. Based on this information, the generating AI generates a radio talk show. The generated radio talk show is played indefinitely within the store. For example, the generating AI could create a conversation like, "Today the temperature in Tokyo is around 18 degrees Celsius, so it might feel a little chilly, but the sun is shining, and it looks like it will be a pleasant day. It's the perfect temperature to go outside," and play it in the store. This system allows stores to effectively promote their products and services. For example, the generating AI could create a conversation like, "Recently, I learned about a screen protector called 'Tobidel' at the SB Takeshiba mobile phone shop. You just stick it on your smartphone, and images and videos will appear in 3D. If you watch a baseball game with this, you might be able to experience the thrill of Ohtani's slider just like you would at the stadium. It's a product I'm quite interested in, so I'd like everyone to try it out," and play it in the store. Furthermore, the generating AI can provide conversations tailored to the store's intentions. For example, if a store wants to emphasize a particular product, it can generate conversations related to that product and play them in the store. The generating AI can also provide conversations that match the store's intentions while avoiding topic duplication. In this way, by using generative AI, stores can effectively promote their products and services and create an appealing in-store environment.This allows the radio agent system to effectively promote the store's products and services.

[0029] The radio agent system according to this embodiment comprises a reception unit, an external information acquisition unit, a topic generation unit, and a playback unit. The reception unit accepts input of store names and product / service names. Store names and product / service names include, but are not limited to, restaurants, apparel shops, and online services. The reception unit stores the store names and product / service names entered by the user in a database, for example. The reception unit can also provide multiple input methods, such as voice input and text input. For example, the reception unit can use speech recognition technology to convert the store names and product / service names spoken by the user into text data. The reception unit can also analyze the information entered by the user in real time and present appropriate input candidates. The external information acquisition unit acquires external information based on the information received by the reception unit. External information includes, but is not limited to, data from the internet, information via APIs, news articles, and social media posts. The external information acquisition unit collects data from the internet using, for example, web scraping technology. The external information acquisition unit can also acquire external information using APIs from specific data providers. For example, the external information acquisition unit uses news article APIs to obtain the latest news information. The external information acquisition unit can also use social media APIs to obtain user posts. The topic generation unit incorporates the appeal of stores and products into topics based on the external information acquired by the external information acquisition unit. For example, the topic generation unit uses a generation AI to generate topics based on external information such as weather data, day of the week data, and event information. The generation AI uses a text generation AI (e.g., LLM) to incorporate the appeal of stores and products into the topics. The topic generation unit can also record past conversation content to avoid topic duplication. For example, the topic generation unit saves previously generated conversation content in a database and uses a duplication detection algorithm to avoid topic overlap. Furthermore, the topic generation unit can generate conversations tailored to the store's intentions. For example, the topic generation unit generates conversations related to specific products or services based on the store's promotional policies and marketing strategies.The playback unit plays the radio talk generated by the topic generation unit within the store. The playback unit can, for example, play the generated radio talk indefinitely. The playback unit can also, for example, play it repeatedly during a specific time period. Furthermore, since there is no limit to the playback time, the playback unit can play long talks. The playback unit plays the generated radio talk through, for example, the store's speaker system. The playback unit can also display the talk content on the store's display. As a result, the radio agent system according to this embodiment can effectively promote the store's products and services.

[0030] The reception desk accepts input of store names and product / service names. These include, but are not limited to, restaurants, apparel shops, and online services. The reception desk can, for example, store the store names and product / service names entered by the user in a database. Furthermore, the reception desk can offer multiple input methods, such as voice input and text input. For example, the reception desk can use speech recognition technology to convert the store names and product / service names spoken by the user into text data. The speech recognition technology uses a deep learning-based speech recognition model, enabling high-precision text conversion of user speech. In addition, the reception desk can analyze the information entered by the user in real time and suggest appropriate input candidates. For example, if a user enters "cafe," related store names and product names will be displayed as candidates, making it easier for the user to select. This allows users to input information quickly and accurately. The reception desk can also learn the user's input history and suggest more appropriate candidates for subsequent inputs. For example, a user who has previously entered "cafe" will have café-related candidates displayed preferentially in subsequent entries. This is expected to improve user convenience and increase the frequency of system use. Furthermore, the reception desk can analyze user input and extract specific keywords and phrases. This allows for an understanding of user needs and interests, enabling the provision of more appropriate information. For example, if a user enters keywords such as "new product" or "sale," providing relevant information preferentially can increase user satisfaction.

[0031] The external information acquisition unit acquires external information based on the information received by the reception unit. External information includes, but is not limited to, data from the internet, information via APIs, news articles, and social media posts. The external information acquisition unit can, for example, collect data from the internet using web scraping technology. Web scraping technology is a technique that automatically extracts necessary information from specific websites and is often implemented using programming languages ​​such as Python. The external information acquisition unit can also acquire external information using APIs from specific data providers. For example, it can use a news article API to obtain the latest news information. The external information acquisition unit can also use social media APIs to obtain user posts. By using social media APIs, it is possible to collect trend information and user opinions in real time. This allows the external information acquisition unit to quickly acquire the latest information and update information throughout the entire system. Furthermore, the external information acquisition unit can filter the acquired information and extract only the necessary information. For example, it can filter information based on specific keywords or hashtags and obtain only highly relevant information. This improves the accuracy and relevance of the information and increases the reliability of the system. Furthermore, the external information acquisition unit stores the acquired information in a database so that it can be referenced later. This enables analysis and trend identification based on past data, resulting in more effective information provision.

[0032] The topic generation unit incorporates the appeal of stores and products into topics based on external information acquired by the external information acquisition unit. For example, the topic generation unit uses a generation AI to generate topics based on external information such as weather data, day of the week data, and event information. The generation AI uses a text generation AI (e.g., LLM) to incorporate the appeal of stores and products into topics. Specifically, the generation AI utilizes natural language processing technology to generate conversation content that is interesting to the user. For example, based on weather data, it can generate conversation such as, "It's sunny today, so we recommend having lunch on the terrace." The topic generation unit can also record past conversation content to avoid topic duplication. For example, the topic generation unit saves previously generated conversation content in a database and uses a duplication detection algorithm to avoid topic duplication. This ensures that users are always provided with fresh information. The topic generation unit can also generate conversations tailored to the store's intentions. For example, the topic generation unit generates conversations related to specific products or services based on the store's promotion policy and marketing strategy. This can contribute to increasing store sales and improving brand image. Furthermore, the topic generation unit can collect user feedback and continuously improve the accuracy and appeal of the generated talk content. For example, if a user rates a talk as "interesting," that feedback can be used to inform future talk generation. This allows the topic generation unit to continue providing engaging talk that meets user needs.

[0033] The playback unit plays the radio talk generated by the topic generation unit within the store. The playback unit can, for example, play the generated radio talk indefinitely. The playback unit can also, for example, play it repeatedly during specific time periods. For example, the content of the talk can be changed to suit specific time periods such as lunchtime or dinnertime, enabling effective promotion. Furthermore, since there is no limit to the playback time, the playback unit can play long talks. The playback unit plays the generated radio talk through, for example, the store's speaker system. The speaker system is installed in each area of ​​the store, allowing the talk to be played at a uniform volume. The playback unit can also display the talk content on the store's displays. The displays can show the text of the talk content, related images, videos, etc., to visually appeal to users. As a result, the radio agent system according to this embodiment can effectively promote the store's products and services. In addition, the playback unit can monitor user reactions in real time and evaluate the effectiveness of the talk content. For example, it can analyze user dwell time and purchasing behavior to help improve the talk content. As a result, the playback unit can always provide optimal talk content and maximize the promotional effect of the store.

[0034] The external information acquisition unit can acquire external information by collecting data from the internet or by using APIs. For example, the external information acquisition unit can use web scraping technology as a specific method for collecting data from the internet. For instance, the external information acquisition unit can automatically collect necessary data from specific websites. The external information acquisition unit can also acquire the latest information using RSS feeds. For example, the external information acquisition unit can subscribe to RSS feeds of news sites and acquire the latest news articles. Furthermore, the external information acquisition unit can acquire external information using APIs. For example, the external information acquisition unit can use APIs from specific data providers to acquire weather data and day-of-the-week data. This allows for efficient acquisition of external information using the internet and APIs. Some or all of the above-described processes in the external information acquisition unit may be performed using AI, or not. For example, the external information acquisition unit can input data collected from the internet into a generating AI, which can then analyze the data.

[0035] The topic generation unit can incorporate the appeal of stores and products into topics based on external information such as weather data, day of the week data, and event information. For example, the topic generation unit uses a generation AI to generate topics based on weather data. For instance, the topic generation unit inputs weather data into the generation AI, which then generates a conversation like, "Today the temperature in Tokyo is around 18 degrees Celsius, so it might feel a little chilly, but there are also sunny spells, making it a pleasant day. It's the perfect temperature to go outside." The topic generation unit can also generate topics based on day of the week data. For example, the topic generation unit inputs day of the week data into the generation AI, which then generates a conversation like, "Today is Friday, so it's the perfect day to make plans for the weekend." The topic generation unit can also generate topics based on event information. For example, the topic generation unit inputs event information into the generation AI, which then generates a conversation like, "There's a local event happening this weekend, so be sure to check it out." In this way, by generating topics based on external information, the appeal of stores and products can be effectively conveyed. Some or all of the processing described above in the topic generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the topic generation unit can input weather data and day-of-the-week data into a generation AI, and the generation AI can generate topics.

[0036] The playback unit can play the generated radio talk indefinitely within the store. The playback unit can, for example, repeatedly play the generated radio talk during specific time periods. For example, the playback unit can repeatedly play the generated radio talk between 10 a.m. and 6 p.m. every day. Furthermore, since there is no limit to the playback time, the playback unit can also play long talks. For example, the playback unit can play radio talks longer than one hour indefinitely. This allows for increased in-store promotional effectiveness by playing the generated radio talk indefinitely. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input the generated radio talk into a generation AI, which can then control the playback.

[0037] The topic generation unit can record past conversation content and avoid topic duplication. For example, the topic generation unit can save previously generated conversation content to a database. For example, the topic generation unit can record generated conversation content by date and time and save it to a database. The topic generation unit can also avoid topic duplication using a duplication detection algorithm. For example, the topic generation unit can analyze the generated conversation content and compare it with previously generated conversation content to detect duplicate parts. By recording past conversation content, topic duplication can be avoided, and fresh content can always be provided. Some or all of the above processing in the topic generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the topic generation unit can input the generated conversation content into a generation AI, and the generation AI can perform duplication detection.

[0038] The topic generation unit can generate conversations tailored to the store's intentions. For example, it can generate conversations related to specific products or services based on the store's promotional policies and marketing strategies. For instance, the topic generation unit inputs the store's promotional policies into the generation AI, which then generates conversations such as, "Recently, I learned about a screen protector called 'Tobidel' at the SB Takeshiba mobile phone shop. You just stick it on your smartphone, and images and videos will appear in 3D. If you watch a baseball game with this, you might be able to experience the thrill of Ohtani's slider just as if you were there in person. It's a product I'm quite interested in, so I'd like everyone to try it out." The topic generation unit can also generate conversations that emphasize the features of specific products, tailored to the store's intentions. For example, the topic generation unit inputs specific product information into the generation AI, which then generates conversations such as, "This screen protector lets you view images and videos in 3D just by sticking it on your smartphone. If you watch a movie with this, you'll feel like you're in a movie theater." By generating conversations tailored to the store's intentions, the promotional effect can be enhanced. Some or all of the above-described processing in the topic generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the topic generation unit can input the store's promotion policy into a generation AI, and the generation AI can generate the talk.

[0039] The reception desk can analyze past input history and suggest the optimal input method. For example, the reception desk can automatically display store names or product / service names that the user has frequently entered in the past as suggestions. For example, the reception desk can store the user's past input history in a database and prioritize displaying store names or product / service names that have been entered frequently. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. For example, if the reception desk has frequently used voice input in the past, it will prioritize displaying the voice input option. The reception desk can also predict and suggest store names or product / service names that the user will use at specific times of day based on their past input history. For example, if the reception desk tends to enter specific store names or product / service names at specific times of day, it will display input suggestions appropriate for that time of day. In this way, by analyzing past input history, the reception desk can suggest the optimal input method for the user. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input past input history data into a generating AI, and the generating AI can suggest the optimal input method.

[0040] The input unit can present input suggestions based on the user's current areas of interest during input. For example, the input unit can present relevant store names and product / service names as suggestions based on products and services the user has recently searched for. For example, the input unit can analyze the user's search history and display relevant store names and product / service names. The input unit can also suggest relevant store names and product / service names based on topics the user has shown interest in on social media. For example, the input unit can analyze the user's social media activity and display relevant store names and product / service names. The input unit can also present relevant store names and product / service names based on products and services the user has previously purchased. For example, the input unit can analyze the user's purchase history and display relevant store names and product / service names. This improves input efficiency by presenting input suggestions based on the user's areas of interest. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's search history data into a generating AI, which can then present input suggestions.

[0041] The input system can present highly relevant input suggestions by considering the user's geographical location during input. For example, the input system can prioritize displaying store names, product names, and service names close to the user's current location. For instance, it can acquire the user's current location information and display nearby store names, product names, and service names. Furthermore, if the user is in a specific region, the input system can suggest store names, product names, and service names related to that region. For example, if the input system determines that the user is in a specific region, it will display store names, product names, and service names related to that region. Additionally, if the user is traveling, the input system can suggest store names, product names, and service names in the user's travel destination. For example, it can acquire the user's travel destination information and display store names, product names, and service names in the travel destination. This allows the system to present highly relevant input suggestions by considering the user's geographical location. Some or all of the above processing in the input system may be performed using AI, or without AI. For example, the input system can input the user's geographical location information into a generating AI, which can then use to present input suggestions.

[0042] The reception desk can analyze the user's social media activity during input and suggest relevant input options. For example, the reception desk can suggest relevant store names or product / service names based on the stores or brands the user follows on social media. For example, the reception desk can analyze the user's social media following information and display relevant store names or product / service names. The reception desk can also suggest relevant store names or product / service names based on the products or services the user has "liked" or commented on on social media. For example, the reception desk can analyze the user's "like" and comment history and display relevant store names or product / service names. The reception desk can also suggest relevant store names or product / service names based on articles or posts the user has shared on social media. For example, the reception desk can analyze the user's sharing history and display relevant store names or product / service names. In this way, relevant input options can be suggested by analyzing the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input user social media activity data into a generating AI, which can then suggest input candidates.

[0043] The external information acquisition unit can analyze past external information acquisition history and select the optimal acquisition method. For example, the external information acquisition unit can prioritize acquiring external information that the user has frequently acquired in the past. For example, the external information acquisition unit can store the user's past external information acquisition history in a database and prioritize acquiring frequently acquired external information. The external information acquisition unit can also predict and acquire external information needed at specific time periods based on the user's past acquisition history. For example, if the external information acquisition unit has a tendency for the user to acquire specific external information at specific time periods, it will acquire external information suitable for those time periods. The external information acquisition unit can also select the optimal acquisition method based on the types of external information the user has acquired in the past. For example, the external information acquisition unit can analyze the types of external information the user has acquired in the past and select the optimal acquisition method. This allows the optimal acquisition method to be selected by analyzing past external information acquisition history. Some or all of the above processing in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input past external information acquisition history data into a generating AI, and the generating AI can select the optimal acquisition method.

[0044] The external information acquisition unit can filter external information based on the user's current areas of interest when acquiring it. For example, the external information acquisition unit can prioritize acquiring relevant external information based on topics the user has recently searched for. For example, the external information acquisition unit can analyze the user's search history and acquire relevant external information. The external information acquisition unit can also acquire relevant external information based on topics the user has shown interest in on social media. For example, the external information acquisition unit can analyze the user's social media activity and acquire relevant external information. The external information acquisition unit can also filter relevant external information based on articles and news the user has previously viewed. For example, the external information acquisition unit can analyze the user's browsing history and acquire relevant external information. This allows the system to provide highly relevant information by filtering external information based on the user's areas of interest. Some or all of the above processing in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input the user's search history data into a generating AI, and the generating AI can filter the external information.

[0045] The external information acquisition unit can prioritize the acquisition of highly relevant information by considering the user's geographical location when acquiring external information. For example, the external information acquisition unit can prioritize the acquisition of information close to the user's current location. For example, the external information acquisition unit can acquire the user's current location information and prioritize the acquisition of nearby information. The external information acquisition unit can also acquire information related to a specific region if the user is in that region. For example, if the external information acquisition unit determines that the user is in a specific region, it acquires information related to that region. The external information acquisition unit can also prioritize the acquisition of information about the user's travel destination if the user is traveling. For example, the external information acquisition unit can acquire the user's travel destination information and prioritize the acquisition of information about the travel destination. This allows the system to provide highly relevant information by considering the user's geographical location. Some or all of the above processing in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input the user's geographical location information into a generating AI, and the generating AI can acquire the information.

[0046] The external information acquisition unit can analyze the user's social media activity and acquire relevant information when acquiring external information. For example, the external information acquisition unit can acquire relevant information based on the accounts the user follows on social media. For example, the external information acquisition unit can analyze the user's social media following information and acquire relevant information. The external information acquisition unit can also acquire relevant information based on posts that the user has "liked" or commented on on social media. For example, the external information acquisition unit can analyze the user's "like" and comment history and acquire relevant information. The external information acquisition unit can also acquire relevant information based on articles and posts that the user has shared on social media. For example, the external information acquisition unit can analyze the user's sharing history and acquire relevant information. In this way, relevant information can be provided by analyzing the user's social media activity. Some or all of the above processing in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input the user's social media activity data into a generating AI, and the generating AI can acquire the information.

[0047] The topic generation unit can adjust the level of detail in topics based on the importance of the store or product during topic generation. For example, for important products or services, the topic generation unit generates topics that include detailed descriptions. For instance, the topic generation unit inputs important product information into the generation AI, which then generates a statement such as, "This screen protector lets you view images and videos in 3D simply by applying it to your smartphone. Watching movies with this will give you an immersive experience, just like being in a movie theater." The topic generation unit can also generate topics with concise descriptions for general products and services. For example, the topic generation unit inputs general product information into the generation AI, which then generates a statement such as, "This screen protector is easy to use; simply apply it to your smartphone." Furthermore, the topic generation unit can generate topics with detailed information for specific campaigns or promotions. For example, the topic generation unit inputs campaign information into the generation AI, which then generates a statement such as, "A special campaign will be held this weekend, so please come visit us." By adjusting the level of detail in topics based on the importance of the store or product, effective promotions become possible. Some or all of the above-described processing in the topic generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the topic generation unit can input important product information into the generation AI, and the generation AI can adjust the level of detail of the topic.

[0048] The topic generation unit can apply different topic generation algorithms depending on the store or product category when generating topics. For example, in the case of a restaurant, the topic generation unit can apply a topic generation algorithm related to menus and recommended dishes. For example, the topic generation unit inputs menu information from the restaurant into the generation AI, and the generation AI generates a message such as, "Today's recommended dish is the chef's special pasta." The topic generation unit can also apply a topic generation algorithm related to new products and sale information in the case of a retail store. For example, the topic generation unit inputs new product information from the retail store into the generation AI, and the generation AI generates a message such as, "We have new products in stock, so please take a look." The topic generation unit can also apply a topic generation algorithm related to the services offered and customer feedback in the case of a service industry. For example, the topic generation unit inputs information about the services offered by the service industry into the generation AI, and the generation AI generates a message such as, "We offer relaxation massages." By applying a topic generation algorithm according to the store or product category, more appropriate topics can be generated. Some or all of the above processing in the topic generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the topic generation unit can input store and product category information into the generation AI, which then applies a topic generation algorithm.

[0049] The topic generation unit can determine topic priority based on the timing of acquisition of external information during topic generation. For example, the topic generation unit can determine topic priority based on the latest external information. For example, the topic generation unit inputs the latest external information into the generation AI, and the generation AI generates a statement such as, "According to the latest news, a special event will be held this weekend." The topic generation unit can also determine topic priority based on past external information. For example, the topic generation unit inputs past external information into the generation AI, and the generation AI generates a statement such as, "Last week's event was a great success." The topic generation unit can also determine topic priority based on external information related to a specific event or campaign. For example, the topic generation unit inputs event information into the generation AI, and the generation AI generates a statement such as, "A special campaign will be held this weekend, so please come." By determining topic priority based on the timing of acquisition of external information, the latest information can be effectively provided. Some or all of the above processing in the topic generation unit may be performed using, for example, the generation AI, or without using the generation AI. For example, the topic generation unit can input data on the timing of acquisition of external information into the generation AI, which can then determine the priority of topics.

[0050] The topic generation unit can adjust the order of topics based on the relevance of external information during topic generation. For example, the topic generation unit can adjust the order of topics based on highly relevant external information. For example, the topic generation unit inputs highly relevant external information into the generation AI, and the generation AI generates a statement such as, "According to the latest news, a special event will be held this weekend." The topic generation unit can also adjust the order of topics based on less relevant external information. For example, the topic generation unit inputs less relevant external information into the generation AI, and the generation AI generates a statement such as, "Last week's event was a great success." The topic generation unit can also adjust the order of topics based on external information related to a specific theme. For example, the topic generation unit inputs theme information into the generation AI, and the generation AI generates a statement such as, "A special campaign will be held this weekend, so please come." By adjusting the order of topics based on the relevance of external information, effective information provision becomes possible. Some or all of the above processing in the topic generation unit may be performed using the generation AI, for example, or without using the generation AI. For example, the topic generation unit can input relational data from external information into the generation AI, which can then adjust the order of the topics.

[0051] The playback unit can analyze past playback history and select the optimal playback method during playback. For example, the playback unit can select the optimal playback method based on content that the user has previously preferred to play. For example, the playback unit can store the user's past playback history in a database and prioritize playing content that has been played frequently. The playback unit can also select a playback method suitable for a specific time period based on the user's past playback history. For example, if the playback unit has a tendency to play specific content at a specific time period, it will select a playback method suitable for that time period. The playback unit can also select the optimal playback method based on the types of content that the user has previously played. For example, the playback unit can analyze the types of content that the user has previously played and select the optimal playback method. In this way, the optimal playback method can be selected by analyzing past playback history. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input past playback history data into a generating AI, and the generating AI can select the optimal playback method.

[0052] The playback unit can customize the playback content based on the current store situation during playback. For example, if the store is crowded, the playback unit can provide short, concise playback content. For example, the playback unit can analyze the store's congestion status in real time and generate a short talk. The playback unit can also provide playback content with detailed explanations if the store is not crowded. For example, the playback unit can analyze the store's congestion status in real time and generate a detailed talk. The playback unit can also provide playback content related to specific events or campaigns if they are taking place. For example, the playback unit can acquire event information from the store and generate relevant talk. This allows for effective information provision by customizing the playback content based on the store's current situation. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input store congestion data into a generating AI, which can then customize the playback content.

[0053] The playback unit can select the optimal playback content by considering the store's geographical location information during playback. For example, if the store is located in a tourist area, the playback unit can provide playback content for tourists. For example, the playback unit can acquire the store's geographical location information and generate talk for tourists. The playback unit can also provide playback content for business people if the store is located in a business district. For example, the playback unit can acquire the store's geographical location information and generate talk for business people. The playback unit can also provide playback content for families if the store is located in a residential area. For example, the playback unit can acquire the store's geographical location information and generate talk for families. In this way, the playback unit can provide the optimal playback content by considering the store's geographical location information. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input the store's geographical location information into a generating AI, and the generating AI can select the playback content.

[0054] The playback unit can analyze the store's social media activity and suggest playback content during playback. For example, the playback unit can provide relevant playback content based on information the store has posted on social media. For example, the playback unit can analyze the store's social media posts and generate relevant talk. The playback unit can also suggest relevant playback content based on the accounts the store follows on social media. For example, the playback unit can analyze the store's following information and generate relevant talk. The playback unit can also provide relevant playback content based on posts the store has "liked" or commented on on social media. For example, the playback unit can analyze the store's "likes" and comment history and generate relevant talk. In this way, by analyzing the store's social media activity, relevant playback content can be provided. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input the store's social media activity data into a generating AI, and the generating AI can suggest playback content.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The radio agent system can analyze a user's past input history and suggest the most relevant topics. For example, it can generate topics based on store names or product / service names that the user has frequently entered in the past. The generating AI analyzes the user's past input history and generates talk such as, "A new version of the 'Tobidel Protective Film' we introduced previously is now available." It can also suggest the most suitable topic generation method based on the input method the user has used in the past (voice, text, etc.). The generating AI analyzes the user's past input method and prioritizes suggesting voice input. Furthermore, it can suggest topics suitable for specific time periods based on the user's past input history. The generating AI analyzes the user's tendency to enter specific store names or product / service names at specific time periods and generates topics suitable for those times. In this way, by analyzing the user's past input history, it can suggest the most relevant topics.

[0057] The radio agent system can generate topics considering the user's geographical location. For example, if the user is in a tourist area, it can generate topics for tourists. The generating AI analyzes the user's geographical location and generates a conversation such as, "There are many beautiful tourist spots in this area, so please come and visit." If the user is in a business district, it can generate topics for business people. The generating AI generates a conversation such as, "There are many business opportunities in this area, so please take advantage of them." Furthermore, if the user is in a residential area, it can generate topics for families. The generating AI generates a conversation such as, "There are many facilities in this area that families can enjoy, so please come and visit." In this way, by considering the user's geographical location, it can provide the most appropriate topics.

[0058] The radio agent system can analyze a user's social media activity and generate relevant topics. For example, it can generate relevant topics based on the stores and brands a user follows on social media. The generating AI analyzes the user's social media following information and generates a message such as, "A new product has been released from a brand you recently follow." It can also generate relevant topics based on products and services a user has liked or commented on on social media. The generating AI analyzes the user's history of likes and comments and generates a message such as, "We'll bring you the latest information on the products you recently liked." Furthermore, it can generate relevant topics based on articles and posts a user has shared on social media. The generating AI analyzes the user's sharing history and generates a message such as, "We'll bring you information related to the articles you recently shared." In this way, by analyzing a user's social media activity, it can provide relevant topics.

[0059] The radio agent system can prioritize topics based on when external information is acquired. For example, it can prioritize topics based on the latest external information. The generating AI analyzes the latest external information and generates talk such as, "According to the latest news, a special event will be held this weekend." It can also prioritize topics based on past external information. The generating AI generates talk such as, "Last week's event was a great success." Furthermore, it can prioritize topics based on external information related to a specific event or campaign. The generating AI generates talk such as, "A special campaign will be held this weekend, so please come and join us." In this way, by prioritizing topics based on when external information is acquired, the system can effectively provide the latest information.

[0060] The radio agent system can analyze past playback history to select the optimal playback method during playback. For example, it can select the optimal playback method based on content that the user has previously enjoyed listening to. The generating AI analyzes the user's past playback history and prioritizes playing content that has been played frequently. It can also select a playback method suitable for a specific time of day based on the user's past playback history. The generating AI analyzes the user's tendency to listen to specific content at specific time periods and selects a playback method suitable for that time period. Furthermore, it can select the optimal playback method based on the types of content the user has previously listened to. The generating AI analyzes the types of content the user has previously listened to and selects the optimal playback method. In this way, the system can select the optimal playback method by analyzing past playback history.

[0061] The radio agent system can customize playback content based on the current situation of the store. For example, if the store is crowded, it can provide short, concise content. The generating AI analyzes the store's congestion level in real time and generates short talks. If the store is not crowded, it can also provide playback content with detailed explanations. The generating AI analyzes the store's congestion level in real time and generates detailed talks. Furthermore, if a specific event or campaign is taking place, it can provide playback content related to that. The generating AI retrieves the store's event information and generates relevant talks. This allows for effective information delivery by customizing playback content based on the store's current situation.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The reception desk accepts input of store names and product / service names. These include restaurants, apparel shops, online services, etc. The reception desk stores the store names and product / service names entered by the user in a database. It also provides multiple input methods, such as voice input and text input, and uses voice recognition technology to convert the store names and product / service names spoken by the user into text data. Furthermore, it can analyze the information entered by the user in real time and suggest appropriate input candidates. Step 2: The external information acquisition unit acquires external information based on the information received by the reception unit. External information includes data from the internet, information via APIs, news articles, and social media posts. The external information acquisition unit acquires external information using web scraping technology or APIs from specific data providers. For example, it can use a news article API to obtain the latest news information or use a social media API to obtain user posts. Step 3: The topic generation unit incorporates the appeal of the store and its products into the topics based on external information acquired by the external information acquisition unit. The topic generation unit uses a generation AI to generate topics based on external information such as weather data, day of the week data, and event information. The generation AI uses a text generation AI (e.g., LLM) to incorporate the appeal of the store and its products into the topics. The topic generation unit also records past conversation content and uses a duplicate detection algorithm to avoid topic duplication. Furthermore, it can generate conversations related to specific products or services based on the store's promotional policies and marketing strategies. Step 4: The playback unit plays the radio talk generated by the topic generation unit within the store. The playback unit can play the generated radio talk indefinitely and can also play it repeatedly at specific times. Furthermore, there is no limit to the playback time, so long talks can be played. The playback unit can play the generated radio talk through the store's speaker system and can also display the talk content on the store's display.

[0064] (Example of form 2)The radio agent system according to an embodiment of the present invention is a radio-like agent that automatically interacts with external information while incorporating information about stores and the products and services they handle. This radio agent system takes the store name and product / service names as input, and a generating AI incorporates external information to create a realistic radio talk show that highlights the store's and products' appeal, generating an unlimited number of tracks for playback within the store. This mechanism allows stores to effectively promote their products and services. For example, the store name and product / service names are input. For instance, information such as "SB Takeshiba Store" or "Tobidel Protective Film" is input. This information is input to the generating AI. Next, the generating AI analyzes the input information and incorporates external information to highlight the store's and products' appeal. For example, it incorporates external information such as weather data, day of the week data, and discussions about Friday night movies to introduce the store's and products' appeal. Based on this information, the generating AI generates a radio talk show. The generated radio talk show is played indefinitely within the store. For example, the generating AI could create a conversation like, "Today the temperature in Tokyo is around 18 degrees Celsius, so it might feel a little chilly, but the sun is shining, and it looks like it will be a pleasant day. It's the perfect temperature to go outside," and play it in the store. This system allows stores to effectively promote their products and services. For example, the generating AI could create a conversation like, "Recently, I learned about a screen protector called 'Tobidel' at the SB Takeshiba mobile phone shop. You just stick it on your smartphone, and images and videos will appear in 3D. If you watch a baseball game with this, you might be able to experience the thrill of Ohtani's slider just like you would at the stadium. It's a product I'm quite interested in, so I'd like everyone to try it out," and play it in the store. Furthermore, the generating AI can provide conversations tailored to the store's intentions. For example, if a store wants to emphasize a particular product, it can generate conversations related to that product and play them in the store. The generating AI can also provide conversations that match the store's intentions while avoiding topic duplication. In this way, by using generative AI, stores can effectively promote their products and services and create an appealing in-store environment.This allows the radio agent system to effectively promote the store's products and services.

[0065] The radio agent system according to this embodiment comprises a reception unit, an external information acquisition unit, a topic generation unit, and a playback unit. The reception unit accepts input of store names and product / service names. Store names and product / service names include, but are not limited to, restaurants, apparel shops, and online services. The reception unit stores the store names and product / service names entered by the user in a database, for example. The reception unit can also provide multiple input methods, such as voice input and text input. For example, the reception unit can use speech recognition technology to convert the store names and product / service names spoken by the user into text data. The reception unit can also analyze the information entered by the user in real time and present appropriate input candidates. The external information acquisition unit acquires external information based on the information received by the reception unit. External information includes, but is not limited to, data from the internet, information via APIs, news articles, and social media posts. The external information acquisition unit collects data from the internet using, for example, web scraping technology. The external information acquisition unit can also acquire external information using APIs from specific data providers. For example, the external information acquisition unit uses news article APIs to obtain the latest news information. The external information acquisition unit can also use social media APIs to obtain user posts. The topic generation unit incorporates the appeal of stores and products into topics based on the external information acquired by the external information acquisition unit. For example, the topic generation unit uses a generation AI to generate topics based on external information such as weather data, day of the week data, and event information. The generation AI uses a text generation AI (e.g., LLM) to incorporate the appeal of stores and products into the topics. The topic generation unit can also record past conversation content to avoid topic duplication. For example, the topic generation unit saves previously generated conversation content in a database and uses a duplication detection algorithm to avoid topic overlap. Furthermore, the topic generation unit can generate conversations tailored to the store's intentions. For example, the topic generation unit generates conversations related to specific products or services based on the store's promotional policies and marketing strategies.The playback unit plays the radio talk generated by the topic generation unit within the store. The playback unit can, for example, play the generated radio talk indefinitely. The playback unit can also, for example, play it repeatedly during a specific time period. Furthermore, since there is no limit to the playback time, the playback unit can play long talks. The playback unit plays the generated radio talk through, for example, the store's speaker system. The playback unit can also display the talk content on the store's display. As a result, the radio agent system according to this embodiment can effectively promote the store's products and services.

[0066] The reception desk accepts input of store names and product / service names. These include, but are not limited to, restaurants, apparel shops, and online services. The reception desk can, for example, store the store names and product / service names entered by the user in a database. Furthermore, the reception desk can offer multiple input methods, such as voice input and text input. For example, the reception desk can use speech recognition technology to convert the store names and product / service names spoken by the user into text data. The speech recognition technology uses a deep learning-based speech recognition model, enabling high-precision text conversion of user speech. In addition, the reception desk can analyze the information entered by the user in real time and suggest appropriate input candidates. For example, if a user enters "cafe," related store names and product names will be displayed as candidates, making it easier for the user to select. This allows users to input information quickly and accurately. The reception desk can also learn the user's input history and suggest more appropriate candidates for subsequent inputs. For example, a user who has previously entered "cafe" will have café-related candidates displayed preferentially in subsequent entries. This is expected to improve user convenience and increase the frequency of system use. Furthermore, the reception desk can analyze user input and extract specific keywords and phrases. This allows for an understanding of user needs and interests, enabling the provision of more appropriate information. For example, if a user enters keywords such as "new product" or "sale," providing relevant information preferentially can increase user satisfaction.

[0067] The external information acquisition unit acquires external information based on the information received by the reception unit. External information includes, but is not limited to, data from the internet, information via APIs, news articles, and social media posts. The external information acquisition unit can, for example, collect data from the internet using web scraping technology. Web scraping technology is a technique that automatically extracts necessary information from specific websites and is often implemented using programming languages ​​such as Python. The external information acquisition unit can also acquire external information using APIs from specific data providers. For example, it can use a news article API to obtain the latest news information. The external information acquisition unit can also use social media APIs to obtain user posts. By using social media APIs, it is possible to collect trend information and user opinions in real time. This allows the external information acquisition unit to quickly acquire the latest information and update information throughout the entire system. Furthermore, the external information acquisition unit can filter the acquired information and extract only the necessary information. For example, it can filter information based on specific keywords or hashtags and obtain only highly relevant information. This improves the accuracy and relevance of the information and increases the reliability of the system. Furthermore, the external information acquisition unit stores the acquired information in a database so that it can be referenced later. This enables analysis and trend identification based on past data, resulting in more effective information provision.

[0068] The topic generation unit incorporates the appeal of stores and products into topics based on external information acquired by the external information acquisition unit. For example, the topic generation unit uses a generation AI to generate topics based on external information such as weather data, day of the week data, and event information. The generation AI uses a text generation AI (e.g., LLM) to incorporate the appeal of stores and products into topics. Specifically, the generation AI utilizes natural language processing technology to generate conversation content that is interesting to the user. For example, based on weather data, it can generate conversation such as, "It's sunny today, so we recommend having lunch on the terrace." The topic generation unit can also record past conversation content to avoid topic duplication. For example, the topic generation unit saves previously generated conversation content in a database and uses a duplication detection algorithm to avoid topic duplication. This ensures that users are always provided with fresh information. The topic generation unit can also generate conversations tailored to the store's intentions. For example, the topic generation unit generates conversations related to specific products or services based on the store's promotion policy and marketing strategy. This can contribute to increasing store sales and improving brand image. Furthermore, the topic generation unit can collect user feedback and continuously improve the accuracy and appeal of the generated talk content. For example, if a user rates a talk as "interesting," that feedback can be used to inform future talk generation. This allows the topic generation unit to continue providing engaging talk that meets user needs.

[0069] The playback unit plays the radio talk generated by the topic generation unit within the store. The playback unit can, for example, play the generated radio talk indefinitely. The playback unit can also, for example, play it repeatedly during specific time periods. For example, the content of the talk can be changed to suit specific time periods such as lunchtime or dinnertime, enabling effective promotion. Furthermore, since there is no limit to the playback time, the playback unit can play long talks. The playback unit plays the generated radio talk through, for example, the store's speaker system. The speaker system is installed in each area of ​​the store, allowing the talk to be played at a uniform volume. The playback unit can also display the talk content on the store's displays. The displays can show the text of the talk content, related images, videos, etc., to visually appeal to users. As a result, the radio agent system according to this embodiment can effectively promote the store's products and services. In addition, the playback unit can monitor user reactions in real time and evaluate the effectiveness of the talk content. For example, it can analyze user dwell time and purchasing behavior to help improve the talk content. As a result, the playback unit can always provide optimal talk content and maximize the promotional effect of the store.

[0070] The external information acquisition unit can acquire external information by collecting data from the internet or by using APIs. For example, the external information acquisition unit can use web scraping technology as a specific method for collecting data from the internet. For instance, the external information acquisition unit can automatically collect necessary data from specific websites. The external information acquisition unit can also acquire the latest information using RSS feeds. For example, the external information acquisition unit can subscribe to RSS feeds of news sites and acquire the latest news articles. Furthermore, the external information acquisition unit can acquire external information using APIs. For example, the external information acquisition unit can use APIs from specific data providers to acquire weather data and day-of-the-week data. This allows for efficient acquisition of external information using the internet and APIs. Some or all of the above-described processes in the external information acquisition unit may be performed using AI, or not. For example, the external information acquisition unit can input data collected from the internet into a generating AI, which can then analyze the data.

[0071] The topic generation unit can incorporate the appeal of stores and products into topics based on external information such as weather data, day of the week data, and event information. For example, the topic generation unit uses a generation AI to generate topics based on weather data. For instance, the topic generation unit inputs weather data into the generation AI, which then generates a conversation like, "Today the temperature in Tokyo is around 18 degrees Celsius, so it might feel a little chilly, but there are also sunny spells, making it a pleasant day. It's the perfect temperature to go outside." The topic generation unit can also generate topics based on day of the week data. For example, the topic generation unit inputs day of the week data into the generation AI, which then generates a conversation like, "Today is Friday, so it's the perfect day to make plans for the weekend." The topic generation unit can also generate topics based on event information. For example, the topic generation unit inputs event information into the generation AI, which then generates a conversation like, "There's a local event happening this weekend, so be sure to check it out." In this way, by generating topics based on external information, the appeal of stores and products can be effectively conveyed. Some or all of the processing described above in the topic generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the topic generation unit can input weather data and day-of-the-week data into a generation AI, and the generation AI can generate topics.

[0072] The playback unit can play the generated radio talk indefinitely within the store. The playback unit can, for example, repeatedly play the generated radio talk during specific time periods. For example, the playback unit can repeatedly play the generated radio talk between 10 a.m. and 6 p.m. every day. Furthermore, since there is no limit to the playback time, the playback unit can also play long talks. For example, the playback unit can play radio talks longer than one hour indefinitely. This allows for increased in-store promotional effectiveness by playing the generated radio talk indefinitely. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input the generated radio talk into a generation AI, which can then control the playback.

[0073] The topic generation unit can record past conversation content and avoid topic duplication. For example, the topic generation unit can save previously generated conversation content to a database. For example, the topic generation unit can record generated conversation content by date and time and save it to a database. The topic generation unit can also avoid topic duplication using a duplication detection algorithm. For example, the topic generation unit can analyze the generated conversation content and compare it with previously generated conversation content to detect duplicate parts. By recording past conversation content, topic duplication can be avoided, and fresh content can always be provided. Some or all of the above processing in the topic generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the topic generation unit can input the generated conversation content into a generation AI, and the generation AI can perform duplication detection.

[0074] The topic generation unit can generate conversations tailored to the store's intentions. For example, it can generate conversations related to specific products or services based on the store's promotional policies and marketing strategies. For instance, the topic generation unit inputs the store's promotional policies into the generation AI, which then generates conversations such as, "Recently, I learned about a screen protector called 'Tobidel' at the SB Takeshiba mobile phone shop. You just stick it on your smartphone, and images and videos will appear in 3D. If you watch a baseball game with this, you might be able to experience the thrill of Ohtani's slider just as if you were there in person. It's a product I'm quite interested in, so I'd like everyone to try it out." The topic generation unit can also generate conversations that emphasize the features of specific products, tailored to the store's intentions. For example, the topic generation unit inputs specific product information into the generation AI, which then generates conversations such as, "This screen protector lets you view images and videos in 3D just by sticking it on your smartphone. If you watch a movie with this, you'll feel like you're in a movie theater." By generating conversations tailored to the store's intentions, the promotional effect can be enhanced. Some or all of the above-described processing in the topic generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the topic generation unit can input the store's promotion policy into a generation AI, and the generation AI can generate the talk.

[0075] The reception system can estimate the user's emotions and adjust the timing of inputting store names and product / service names based on the estimated emotions. For example, if the user is relaxed, the reception system can provide detailed input options and suggest customizable input methods. For instance, if the reception system estimates the user is relaxed, it can display multiple input options for the user to choose from. Furthermore, if the user is in a hurry, the reception system can prioritize voice input to allow for quick input of store names and product / service names. For example, if the reception system estimates the user is in a hurry, it can highlight the voice input option, allowing the user to start voice input immediately. Additionally, if the user is stressed, the reception system can provide a simple interface and minimize the input steps. For example, if the reception system estimates the user is stressed, it can display minimal input fields, allowing the user to easily complete the input. This improves user convenience by adjusting input timing according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes at the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input user facial expression data into a generating AI, which can then estimate the user's emotions.

[0076] The reception desk can analyze past input history and suggest the optimal input method. For example, the reception desk can automatically display store names or product / service names that the user has frequently entered in the past as suggestions. For example, the reception desk can store the user's past input history in a database and prioritize displaying store names or product / service names that have been entered frequently. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. For example, if the reception desk has frequently used voice input in the past, it will prioritize displaying the voice input option. The reception desk can also predict and suggest store names or product / service names that the user will use at specific times of day based on their past input history. For example, if the reception desk tends to enter specific store names or product / service names at specific times of day, it will display input suggestions appropriate for that time of day. In this way, by analyzing past input history, the reception desk can suggest the optimal input method for the user. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input past input history data into a generating AI, and the generating AI can suggest the optimal input method.

[0077] The input unit can present input suggestions based on the user's current areas of interest during input. For example, the input unit can present relevant store names and product / service names as suggestions based on products and services the user has recently searched for. For example, the input unit can analyze the user's search history and display relevant store names and product / service names. The input unit can also suggest relevant store names and product / service names based on topics the user has shown interest in on social media. For example, the input unit can analyze the user's social media activity and display relevant store names and product / service names. The input unit can also present relevant store names and product / service names based on products and services the user has previously purchased. For example, the input unit can analyze the user's purchase history and display relevant store names and product / service names. This improves input efficiency by presenting input suggestions based on the user's areas of interest. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input the user's search history data into a generating AI, which can then present input suggestions.

[0078] The reception system can estimate the user's emotions and prioritize input based on those emotions. For example, if the user is in a hurry, the reception system can prioritize important store names or product / service names. For example, if the reception system estimates the user is in a hurry, it can highlight important input fields to allow the user to enter information quickly. The reception system can also allow the user to enter detailed information if they are relaxed. For example, if the reception system estimates the user is relaxed, it can display detailed input options to allow the user to enter information freely. The reception system can also prioritize simple information if the user is stressed. For example, if the reception system estimates the user is stressed, it can display minimal input fields to allow the user to complete the input easily. This improves user convenience by prioritizing input content according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes at the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input user facial expression data into a generating AI, which can then estimate the user's emotions.

[0079] The input system can present highly relevant input suggestions by considering the user's geographical location during input. For example, the input system can prioritize displaying store names, product names, and service names close to the user's current location. For instance, it can acquire the user's current location information and display nearby store names, product names, and service names. Furthermore, if the user is in a specific region, the input system can suggest store names, product names, and service names related to that region. For example, if the input system determines that the user is in a specific region, it will display store names, product names, and service names related to that region. Additionally, if the user is traveling, the input system can suggest store names, product names, and service names in the user's travel destination. For example, it can acquire the user's travel destination information and display store names, product names, and service names in the travel destination. This allows the system to present highly relevant input suggestions by considering the user's geographical location. Some or all of the above processing in the input system may be performed using AI, or without AI. For example, the input system can input the user's geographical location information into a generating AI, which can then use to present input suggestions.

[0080] The reception desk can analyze the user's social media activity during input and suggest relevant input options. For example, the reception desk can suggest relevant store names or product / service names based on the stores or brands the user follows on social media. For example, the reception desk can analyze the user's social media following information and display relevant store names or product / service names. The reception desk can also suggest relevant store names or product / service names based on the products or services the user has "liked" or commented on on social media. For example, the reception desk can analyze the user's "like" and comment history and display relevant store names or product / service names. The reception desk can also suggest relevant store names or product / service names based on articles or posts the user has shared on social media. For example, the reception desk can analyze the user's sharing history and display relevant store names or product / service names. In this way, relevant input options can be suggested by analyzing the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input user social media activity data into a generating AI, which can then suggest input candidates.

[0081] The external information acquisition unit can estimate the user's emotions and adjust the timing of external information acquisition based on the estimated emotions. For example, if the user is relaxed, the external information acquisition unit can periodically acquire external information and provide the latest information. For example, if the external information acquisition unit estimates that the user is relaxed, it can acquire external information at regular intervals and provide it to the user. The external information acquisition unit can also quickly acquire only the minimum necessary external information if the user is in a hurry. For example, if the external information acquisition unit estimates that the user is in a hurry, it can quickly acquire only the important external information and provide it to the user. Furthermore, if the external information acquisition unit is feeling stressed, it can acquire only the important external information to avoid information overload. For example, if the external information acquisition unit estimates that the user is stressed, it can acquire only the important external information and provide it to the user. In this way, by adjusting the timing of external information acquisition according to the user's emotions, user convenience can be improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input user facial expression data into a generating AI, and the generating AI can estimate emotions.

[0082] The external information acquisition unit can analyze past external information acquisition history and select the optimal acquisition method. For example, the external information acquisition unit can prioritize acquiring external information that the user has frequently acquired in the past. For example, the external information acquisition unit can store the user's past external information acquisition history in a database and prioritize acquiring frequently acquired external information. The external information acquisition unit can also predict and acquire external information needed at specific time periods based on the user's past acquisition history. For example, if the external information acquisition unit has a tendency for the user to acquire specific external information at specific time periods, it will acquire external information suitable for those time periods. The external information acquisition unit can also select the optimal acquisition method based on the types of external information the user has acquired in the past. For example, the external information acquisition unit can analyze the types of external information the user has acquired in the past and select the optimal acquisition method. This allows the optimal acquisition method to be selected by analyzing past external information acquisition history. Some or all of the above processing in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input past external information acquisition history data into a generating AI, and the generating AI can select the optimal acquisition method.

[0083] The external information acquisition unit can filter external information based on the user's current areas of interest when acquiring it. For example, the external information acquisition unit can prioritize acquiring relevant external information based on topics the user has recently searched for. For example, the external information acquisition unit can analyze the user's search history and acquire relevant external information. The external information acquisition unit can also acquire relevant external information based on topics the user has shown interest in on social media. For example, the external information acquisition unit can analyze the user's social media activity and acquire relevant external information. The external information acquisition unit can also filter relevant external information based on articles and news the user has previously viewed. For example, the external information acquisition unit can analyze the user's browsing history and acquire relevant external information. This allows the system to provide highly relevant information by filtering external information based on the user's areas of interest. Some or all of the above processing in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input the user's search history data into a generating AI, and the generating AI can filter the external information.

[0084] The external information acquisition unit can estimate the user's emotions and determine the priority of external information to acquire based on the estimated emotions. For example, if the user is in a hurry, the external information acquisition unit will prioritize acquiring important external information. For example, if the external information acquisition unit estimates that the user is in a hurry, it will prioritize acquiring important external information and provide it to the user. The external information acquisition unit can also acquire detailed external information if the user is relaxed. For example, if the external information acquisition unit estimates that the user is relaxed, it will acquire detailed external information and provide it to the user. The external information acquisition unit can also prioritize acquiring concise external information if the user is stressed. For example, if the external information acquisition unit estimates that the user is stressed, it will acquire concise external information and provide it to the user. In this way, user convenience can be improved by determining the priority of external information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input user facial expression data into a generating AI, and the generating AI can estimate emotions.

[0085] The external information acquisition unit can prioritize the acquisition of highly relevant information by considering the user's geographical location when acquiring external information. For example, the external information acquisition unit can prioritize the acquisition of information close to the user's current location. For example, the external information acquisition unit can acquire the user's current location information and prioritize the acquisition of nearby information. The external information acquisition unit can also acquire information related to a specific region if the user is in that region. For example, if the external information acquisition unit determines that the user is in a specific region, it acquires information related to that region. The external information acquisition unit can also prioritize the acquisition of information about the user's travel destination if the user is traveling. For example, the external information acquisition unit can acquire the user's travel destination information and prioritize the acquisition of information about the travel destination. This allows the system to provide highly relevant information by considering the user's geographical location. Some or all of the above processing in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input the user's geographical location information into a generating AI, and the generating AI can acquire the information.

[0086] The external information acquisition unit can analyze the user's social media activity and acquire relevant information when acquiring external information. For example, the external information acquisition unit can acquire relevant information based on the accounts the user follows on social media. For example, the external information acquisition unit can analyze the user's social media following information and acquire relevant information. The external information acquisition unit can also acquire relevant information based on posts that the user has "liked" or commented on on social media. For example, the external information acquisition unit can analyze the user's "like" and comment history and acquire relevant information. The external information acquisition unit can also acquire relevant information based on articles and posts that the user has shared on social media. For example, the external information acquisition unit can analyze the user's sharing history and acquire relevant information. In this way, relevant information can be provided by analyzing the user's social media activity. Some or all of the above processing in the external information acquisition unit may be performed using AI, for example, or without AI. For example, the external information acquisition unit can input the user's social media activity data into a generating AI, and the generating AI can acquire the information.

[0087] The topic generation unit can estimate the user's emotions and adjust the way topics are presented based on those emotions. For example, if the user is relaxed, the topic generation unit will present the topic in a relaxed tone. For instance, the topic generation unit inputs the user's emotion data into the generating AI, which then generates a statement such as, "Today is the perfect day to relax." The topic generation unit can also use a concise and to-the-point expression if the user is in a hurry. For example, the topic generation unit inputs the user's emotion data into the generating AI, which then generates a statement such as, "Today looks like it's going to be a busy day. Here's some concise information." The topic generation unit can also present the topic in an energetic tone if the user is excited. For example, the topic generation unit inputs the user's emotion data into the generating AI, which then generates a statement such as, "Today is going to be an exciting day!" By adjusting the way topics are presented according to the user's emotions, user convenience can be improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the topic generation unit may be performed using AI, or not using AI. For example, the topic generation unit can input user sentiment data into the generating AI, and the generating AI can adjust the way the topic is expressed.

[0088] The topic generation unit can adjust the level of detail in topics based on the importance of the store or product during topic generation. For example, for important products or services, the topic generation unit generates topics that include detailed descriptions. For instance, the topic generation unit inputs important product information into the generation AI, which then generates a statement such as, "This screen protector lets you view images and videos in 3D simply by applying it to your smartphone. Watching movies with this will give you an immersive experience, just like being in a movie theater." The topic generation unit can also generate topics with concise descriptions for general products and services. For example, the topic generation unit inputs general product information into the generation AI, which then generates a statement such as, "This screen protector is easy to use; simply apply it to your smartphone." Furthermore, the topic generation unit can generate topics with detailed information for specific campaigns or promotions. For example, the topic generation unit inputs campaign information into the generation AI, which then generates a statement such as, "A special campaign will be held this weekend, so please come visit us." By adjusting the level of detail in topics based on the importance of the store or product, effective promotions become possible. Some or all of the above-described processing in the topic generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the topic generation unit can input important product information into the generation AI, and the generation AI can adjust the level of detail of the topic.

[0089] The topic generation unit can apply different topic generation algorithms depending on the store or product category when generating topics. For example, in the case of a restaurant, the topic generation unit can apply a topic generation algorithm related to menus and recommended dishes. For example, the topic generation unit inputs menu information from the restaurant into the generation AI, and the generation AI generates a message such as, "Today's recommended dish is the chef's special pasta." The topic generation unit can also apply a topic generation algorithm related to new products and sale information in the case of a retail store. For example, the topic generation unit inputs new product information from the retail store into the generation AI, and the generation AI generates a message such as, "We have new products in stock, so please take a look." The topic generation unit can also apply a topic generation algorithm related to the services offered and customer feedback in the case of a service industry. For example, the topic generation unit inputs information about the services offered by the service industry into the generation AI, and the generation AI generates a message such as, "We offer relaxation massages." By applying a topic generation algorithm according to the store or product category, more appropriate topics can be generated. Some or all of the above processing in the topic generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the topic generation unit can input store and product category information into the generation AI, which then applies a topic generation algorithm.

[0090] The topic generation unit can estimate the user's emotions and adjust the length of the topic based on the estimated emotions. For example, if the user is in a hurry, the topic generation unit will generate a short, concise topic. For instance, the topic generation unit inputs the user's emotion data into the generating AI, which then generates a short conversation such as, "It looks like you're going to have a busy day today. Here's some concise information." The topic generation unit can also generate longer topics with more detailed explanations if the user is relaxed. For example, the topic generation unit inputs the user's emotion data into the generating AI, which then generates a longer conversation such as, "Today is the perfect day to relax. Here's some detailed information." The topic generation unit can also generate topics with visually stimulating effects if the user is excited. For example, the topic generation unit inputs the user's emotion data into the generating AI, which then generates a conversation such as, "It looks like you're going to have an exciting day today!" By adjusting the length of the topic according to the user's emotions, the user experience can be improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the topic generation unit may be performed using AI, or not using AI. For example, the topic generation unit can input user sentiment data into the generating AI, which can then adjust the length of the topic.

[0091] The topic generation unit can determine topic priority based on the timing of acquisition of external information during topic generation. For example, the topic generation unit can determine topic priority based on the latest external information. For example, the topic generation unit inputs the latest external information into the generation AI, and the generation AI generates a statement such as, "According to the latest news, a special event will be held this weekend." The topic generation unit can also determine topic priority based on past external information. For example, the topic generation unit inputs past external information into the generation AI, and the generation AI generates a statement such as, "Last week's event was a great success." The topic generation unit can also determine topic priority based on external information related to a specific event or campaign. For example, the topic generation unit inputs event information into the generation AI, and the generation AI generates a statement such as, "A special campaign will be held this weekend, so please come." By determining topic priority based on the timing of acquisition of external information, the latest information can be effectively provided. Some or all of the above processing in the topic generation unit may be performed using, for example, the generation AI, or without using the generation AI. For example, the topic generation unit can input data on the timing of acquisition of external information into the generation AI, which can then determine the priority of topics.

[0092] The topic generation unit can adjust the order of topics based on the relevance of external information during topic generation. For example, the topic generation unit can adjust the order of topics based on highly relevant external information. For example, the topic generation unit inputs highly relevant external information into the generation AI, and the generation AI generates a statement such as, "According to the latest news, a special event will be held this weekend." The topic generation unit can also adjust the order of topics based on less relevant external information. For example, the topic generation unit inputs less relevant external information into the generation AI, and the generation AI generates a statement such as, "Last week's event was a great success." The topic generation unit can also adjust the order of topics based on external information related to a specific theme. For example, the topic generation unit inputs theme information into the generation AI, and the generation AI generates a statement such as, "A special campaign will be held this weekend, so please come." By adjusting the order of topics based on the relevance of external information, effective information provision becomes possible. Some or all of the above processing in the topic generation unit may be performed using the generation AI, for example, or without using the generation AI. For example, the topic generation unit can input relational data from external information into the generation AI, which can then adjust the order of the topics.

[0093] The playback unit can estimate the user's emotions and adjust the way the playback content is presented based on the estimated emotions. For example, if the user is relaxed, the playback unit will present the content in a calm tone. For instance, the playback unit inputs the user's emotion data into a generating AI, which then generates a calm message such as, "Today is the perfect day for a relaxing day." The playback unit can also use a concise and to-the-point approach if the user is in a hurry. For example, the playback unit inputs the user's emotion data into a generating AI, which then generates a message such as, "It looks like today will be a busy day. Here's some essential information." The playback unit can also present the content in an energetic tone if the user is excited. For example, the playback unit inputs the user's emotion data into a generating AI, which then generates a message such as, "Today is going to be an exciting day!" By adjusting the way the playback content is presented according to the user's emotions, user convenience can be improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the playback unit may be performed using AI, or not using AI. For example, the playback unit can input user emotion data into the generation AI, and the generation AI can adjust the way the playback content is expressed.

[0094] The playback unit can analyze past playback history and select the optimal playback method during playback. For example, the playback unit can select the optimal playback method based on content that the user has previously preferred to play. For example, the playback unit can store the user's past playback history in a database and prioritize playing content that has been played frequently. The playback unit can also select a playback method suitable for a specific time period based on the user's past playback history. For example, if the playback unit has a tendency to play specific content at a specific time period, it will select a playback method suitable for that time period. The playback unit can also select the optimal playback method based on the types of content that the user has previously played. For example, the playback unit can analyze the types of content that the user has previously played and select the optimal playback method. In this way, the optimal playback method can be selected by analyzing past playback history. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input past playback history data into a generating AI, and the generating AI can select the optimal playback method.

[0095] The playback unit can customize the playback content based on the current store situation during playback. For example, if the store is crowded, the playback unit can provide short, concise playback content. For example, the playback unit can analyze the store's congestion status in real time and generate a short talk. The playback unit can also provide playback content with detailed explanations if the store is not crowded. For example, the playback unit can analyze the store's congestion status in real time and generate a detailed talk. The playback unit can also provide playback content related to specific events or campaigns if they are taking place. For example, the playback unit can acquire event information from the store and generate relevant talk. This allows for effective information provision by customizing the playback content based on the store's current situation. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input store congestion data into a generating AI, which can then customize the playback content.

[0096] The playback unit can estimate the user's emotions and prioritize the content to be played based on those emotions. For example, if the user is in a hurry, the playback unit will prioritize playing important content. For instance, the playback unit inputs the user's emotion data into a generating AI, which then generates a message such as, "It looks like you're going to have a busy day today. We'll prioritize delivering important information to you." The playback unit can also provide detailed content if the user is relaxed. For example, the playback unit inputs the user's emotion data into a generating AI, which then generates a message such as, "Today seems like a perfect day for a relaxing day. We'll deliver detailed information to you." Furthermore, if the user is stressed, the playback unit can prioritize playing concise content. For example, the playback unit inputs the user's emotion data into a generating AI, which then generates a message such as, "You seem stressed today. We'll deliver concise information to you." By prioritizing content according to the user's emotions, user convenience can be improved. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the playback unit may be performed using AI, or not using AI. For example, the playback unit can input user emotion data into the generation AI, which can then determine the priority of the playback content.

[0097] The playback unit can select the optimal playback content by considering the store's geographical location information during playback. For example, if the store is located in a tourist area, the playback unit can provide playback content for tourists. For example, the playback unit can acquire the store's geographical location information and generate talk for tourists. The playback unit can also provide playback content for business people if the store is located in a business district. For example, the playback unit can acquire the store's geographical location information and generate talk for business people. The playback unit can also provide playback content for families if the store is located in a residential area. For example, the playback unit can acquire the store's geographical location information and generate talk for families. In this way, the playback unit can provide the optimal playback content by considering the store's geographical location information. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input the store's geographical location information into a generating AI, and the generating AI can select the playback content.

[0098] The playback unit can analyze the store's social media activity and suggest playback content during playback. For example, the playback unit can provide relevant playback content based on information the store has posted on social media. For example, the playback unit can analyze the store's social media posts and generate relevant talk. The playback unit can also suggest relevant playback content based on the accounts the store follows on social media. For example, the playback unit can analyze the store's following information and generate relevant talk. The playback unit can also provide relevant playback content based on posts the store has "liked" or commented on on social media. For example, the playback unit can analyze the store's "likes" and comment history and generate relevant talk. In this way, by analyzing the store's social media activity, relevant playback content can be provided. Some or all of the above processing in the playback unit may be performed using AI, for example, or without AI. For example, the playback unit can input the store's social media activity data into a generating AI, and the generating AI can suggest playback content.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The radio agent system can estimate the user's emotions and adjust the tone of the topic based on those emotions. For example, if the user is relaxed, it can generate topics in a calm tone. The generating AI analyzes the user's emotional data and generates a conversation such as, "Today is the perfect day for a relaxing day." If the user is in a hurry, it can generate concise and to-the-point conversation. The generating AI generates a conversation such as, "It looks like it's going to be a busy day today. Here's some essential information." Furthermore, if the user is excited, it can generate topics in an energetic tone. The generating AI generates a conversation such as, "Today is going to be an exciting day!" By adjusting the tone of the topic according to the user's emotions, the system can improve user experience.

[0101] The radio agent system can analyze a user's past input history and suggest the most relevant topics. For example, it can generate topics based on store names or product / service names that the user has frequently entered in the past. The generating AI analyzes the user's past input history and generates talk such as, "A new version of the 'Tobidel Protective Film' we introduced previously is now available." It can also suggest the most suitable topic generation method based on the input method the user has used in the past (voice, text, etc.). The generating AI analyzes the user's past input method and prioritizes suggesting voice input. Furthermore, it can suggest topics suitable for specific time periods based on the user's past input history. The generating AI analyzes the user's tendency to enter specific store names or product / service names at specific time periods and generates topics suitable for those times. In this way, by analyzing the user's past input history, it can suggest the most relevant topics.

[0102] The radio agent system can generate topics considering the user's geographical location. For example, if the user is in a tourist area, it can generate topics for tourists. The generating AI analyzes the user's geographical location and generates a conversation such as, "There are many beautiful tourist spots in this area, so please come and visit." If the user is in a business district, it can generate topics for business people. The generating AI generates a conversation such as, "There are many business opportunities in this area, so please take advantage of them." Furthermore, if the user is in a residential area, it can generate topics for families. The generating AI generates a conversation such as, "There are many facilities in this area that families can enjoy, so please come and visit." In this way, by considering the user's geographical location, it can provide the most appropriate topics.

[0103] The radio agent system can analyze a user's social media activity and generate relevant topics. For example, it can generate relevant topics based on the stores and brands a user follows on social media. The generating AI analyzes the user's social media following information and generates a message such as, "A new product has been released from a brand you recently follow." It can also generate relevant topics based on products and services a user has liked or commented on on social media. The generating AI analyzes the user's history of likes and comments and generates a message such as, "We'll bring you the latest information on the products you recently liked." Furthermore, it can generate relevant topics based on articles and posts a user has shared on social media. The generating AI analyzes the user's sharing history and generates a message such as, "We'll bring you information related to the articles you recently shared." In this way, by analyzing a user's social media activity, it can provide relevant topics.

[0104] The radio agent system can estimate the user's emotions and adjust the length of the topic based on that estimation. For example, if the user is in a hurry, it can generate a short, to-the-point topic. The generating AI analyzes the user's emotion data and generates a short talk such as, "It looks like you're going to have a busy day today. Here's some concise information." If the user is relaxed, it can also generate a longer topic with more detailed explanations. The generating AI generates a longer talk such as, "Today is the perfect day to relax. Here's some detailed information." Furthermore, if the user is excited, it can generate a topic with visually stimulating effects. The generating AI generates a talk such as, "It looks like you're going to have an exciting day today!" By adjusting the length of the topic according to the user's emotions, the system can improve user convenience.

[0105] The radio agent system can prioritize topics based on when external information is acquired. For example, it can prioritize topics based on the latest external information. The generating AI analyzes the latest external information and generates talk such as, "According to the latest news, a special event will be held this weekend." It can also prioritize topics based on past external information. The generating AI generates talk such as, "Last week's event was a great success." Furthermore, it can prioritize topics based on external information related to a specific event or campaign. The generating AI generates talk such as, "A special campaign will be held this weekend, so please come and join us." In this way, by prioritizing topics based on when external information is acquired, the system can effectively provide the latest information.

[0106] The radio agent system can estimate the user's emotions and adjust the way the content is presented based on those emotions. For example, if the user is relaxed, the content can be presented in a calm tone. The generating AI analyzes the user's emotional data and generates a gentle message such as, "Today is the perfect day to relax." If the user is in a hurry, the system can use a concise and to-the-point approach. The generating AI generates a message such as, "It looks like it's going to be a busy day. Here's some essential information." Furthermore, if the user is excited, the content can be presented in an energetic tone. The generating AI generates a message such as, "It looks like it's going to be an exciting day!" By adjusting the presentation of the content according to the user's emotions, the system can improve user experience.

[0107] The radio agent system can analyze past playback history to select the optimal playback method during playback. For example, it can select the optimal playback method based on content that the user has previously enjoyed listening to. The generating AI analyzes the user's past playback history and prioritizes playing content that has been played frequently. It can also select a playback method suitable for a specific time of day based on the user's past playback history. The generating AI analyzes the user's tendency to listen to specific content at specific time periods and selects a playback method suitable for that time period. Furthermore, it can select the optimal playback method based on the types of content the user has previously listened to. The generating AI analyzes the types of content the user has previously listened to and selects the optimal playback method. In this way, the system can select the optimal playback method by analyzing past playback history.

[0108] The radio agent system can customize playback content based on the current situation of the store. For example, if the store is crowded, it can provide short, concise content. The generating AI analyzes the store's congestion level in real time and generates short talks. If the store is not crowded, it can also provide playback content with detailed explanations. The generating AI analyzes the store's congestion level in real time and generates detailed talks. Furthermore, if a specific event or campaign is taking place, it can provide playback content related to that. The generating AI retrieves the store's event information and generates relevant talks. This allows for effective information delivery by customizing playback content based on the store's current situation.

[0109] The radio agent system can estimate a user's emotions and prioritize content based on those emotions. For example, if a user is in a hurry, important content can be prioritized. The generating AI analyzes the user's emotion data and generates a message such as, "It looks like you're going to have a busy day today. We'll prioritize delivering important information to you." If the user is relaxed, it can also provide more detailed content. The generating AI generates a message such as, "Today is the perfect day to relax. We'll deliver detailed information to you." Furthermore, if the user is stressed, it can prioritize delivering concise content. The generating AI generates a message such as, "You seem stressed today. We'll deliver concise information to you." In this way, by prioritizing content according to the user's emotions, the system can improve user convenience.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The reception desk accepts input of store names and product / service names. These include restaurants, apparel shops, online services, etc. The reception desk stores the store names and product / service names entered by the user in a database. It also provides multiple input methods, such as voice input and text input, and uses voice recognition technology to convert the store names and product / service names spoken by the user into text data. Furthermore, it can analyze the information entered by the user in real time and suggest appropriate input candidates. Step 2: The external information acquisition unit acquires external information based on the information received by the reception unit. External information includes data from the internet, information via APIs, news articles, and social media posts. The external information acquisition unit acquires external information using web scraping technology or APIs from specific data providers. For example, it can use a news article API to obtain the latest news information or use a social media API to obtain user posts. Step 3: The topic generation unit incorporates the appeal of the store and its products into the topics based on external information acquired by the external information acquisition unit. The topic generation unit uses a generation AI to generate topics based on external information such as weather data, day of the week data, and event information. The generation AI uses a text generation AI (e.g., LLM) to incorporate the appeal of the store and its products into the topics. The topic generation unit also records past conversation content and uses a duplicate detection algorithm to avoid topic duplication. Furthermore, it can generate conversations related to specific products or services based on the store's promotional policies and marketing strategies. Step 4: The playback unit plays the radio talk generated by the topic generation unit within the store. The playback unit can play the generated radio talk indefinitely and can also play it repeatedly at specific times. Furthermore, there is no limit to the playback time, so long talks can be played. The playback unit can play the generated radio talk through the store's speaker system and can also display the talk content on the store's display.

[0112] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0114] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0115] Each of the multiple elements described above, including the reception unit, external information acquisition unit, topic generation unit, and playback unit, is implemented by at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the reception device 38 of the smart device 14 and stores the store name and product / service name entered by the user in the database 24. The external information acquisition unit is implemented by the specific processing unit 290 of the data processing unit 12 and acquires data from the internet and information via APIs. The topic generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and incorporates the appeal of the store and products into topics using generation AI. The playback unit is implemented by the output device 40 of the smart device 14 and plays the generated radio talk in the store. The correspondence between each unit and the devices and control units is not limited to the example described above and can be changed in various ways.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0122] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0123] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0124] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0125] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0126] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0130] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements described above, including the reception unit, external information acquisition unit, topic generation unit, and playback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the smart glasses 214 and converts the store name or product / service name spoken by the user into text data. The external information acquisition unit is implemented by the specific processing unit 290 of the data processing unit 12 and acquires news articles and social media posts. The topic generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates topics using a generation AI. The playback unit is implemented by the speaker 240 of the smart glasses 214 and plays the generated radio talk in the store. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0134] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0135] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0136] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0138] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0139] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0140] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0141] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements described above, including the reception unit, external information acquisition unit, topic generation unit, and playback unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the headset terminal 314 and converts the store name or product / service name spoken by the user into text data. The external information acquisition unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and acquires data from the internet or information via APIs. The topic generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and incorporates the appeal of the store or product into the topic using generation AI. The playback unit is implemented by, for example, the speaker 240 of the headset terminal 314 and plays the generated radio talk in the store. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0152] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0154] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0155] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0156] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements described above, including the reception unit, external information acquisition unit, topic generation unit, and playback unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the robot 414 and converts the store name or product / service name spoken by the user into text data. The external information acquisition unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and acquires news articles and social media posts. The topic generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates topics using a generation AI. The playback unit is implemented by, for example, the speaker 240 of the robot 414 and plays the generated radio talk in the store. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0165] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0166] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0167] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0168] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0169] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0170] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0171] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0172] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0173] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0174] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0175] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0176] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0177] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0178] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0179] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0180] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0181] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0182] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0183] (Note 1) A reception desk that accepts input of store names and product / service names, An external information acquisition unit that acquires external information based on the information received by the aforementioned reception unit, A topic generation unit incorporates the appeal of stores and products into topics based on external information acquired by the aforementioned external information acquisition unit, The system includes a playback unit that plays the radio talk generated by the topic generation unit within the store. A system characterized by the following features. (Note 2) The aforementioned external information acquisition unit, Data is collected from the internet and external information is obtained using APIs. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned topic generation unit, Incorporate the appeal of stores and products into conversations based on external information such as weather data, day of the week data, and event information. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned regeneration unit is Unlimited playback of generated radio talk within the store. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned topic generation unit, Record past conversation topics to avoid repetition. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned topic generation unit, Generates dialogue tailored to the store's intentions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of inputting store names, product names, and service names based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is We analyze past input history and suggest the optimal input method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When inputting text, the system suggests input options based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates the user's emotions and prioritizes input content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When inputting data, the system considers the user's geographical location to suggest highly relevant input options. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is During input, the system analyzes the user's social media activity and suggests relevant input options. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned external information acquisition unit, It estimates the user's emotions and adjusts the timing of acquiring external information based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned external information acquisition unit, Analyze past external information acquisition history and select the optimal acquisition method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned external information acquisition unit, When acquiring external information, filtering is performed based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned external information acquisition unit, It estimates the user's emotions and determines the priority of external information to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned external information acquisition unit, When acquiring external information, the system prioritizes the acquisition of highly relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned external information acquisition unit, When acquiring external information, the system analyzes the user's social media activity and retrieves relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned topic generation unit, It estimates the user's emotions and adjusts the way topics are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned topic generation unit, When generating topics, adjust the level of detail based on the importance of the store or product. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned topic generation unit, When generating topics, different topic generation algorithms are applied depending on the store or product category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned topic generation unit, It estimates the user's emotions and adjusts the length of the topic based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned topic generation unit, When generating a topic, the priority of topics is determined based on when external information was acquired. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned topic generation unit, When generating topics, the order of topics is adjusted based on the relevance of external information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned regeneration unit is It estimates the user's emotions and adjusts the way the content is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned regeneration unit is During playback, the system analyzes past playback history to select the optimal playback method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned regeneration unit is During playback, the content will be customized based on the current status of the store. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned regeneration unit is It estimates the user's emotions and prioritizes the content to be played based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned regeneration unit is During playback, the optimal playback content is selected by considering the store's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned regeneration unit is During the revitalization process, we analyze the store's social media activity and suggest revitalization strategies. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0184] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that accepts input of store names and product / service names, An external information acquisition unit that acquires external information based on the information received by the aforementioned reception unit, A topic generation unit incorporates the appeal of stores and products into topics based on external information acquired by the aforementioned external information acquisition unit, The system includes a playback unit that plays the radio talk generated by the topic generation unit within the store. A system characterized by the following features.

2. The aforementioned external information acquisition unit, Data is collected from the internet and external information is obtained using APIs. The system according to feature 1.

3. The aforementioned topic generation unit, Incorporate the appeal of stores and products into conversations based on external information such as weather data, day of the week data, and event information. The system according to feature 1.

4. The aforementioned regeneration unit is Unlimited playback of generated radio talk within the store. The system according to feature 1.

5. The aforementioned topic generation unit, Record past conversation topics to avoid repetition. The system according to feature 1.

6. The aforementioned topic generation unit, Generates dialogue tailored to the store's intentions. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of inputting store names, product names, and service names based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is We analyze past input history and suggest the optimal input method. The system according to feature 1.

Images