Acquisition device and acquisition method

Abstract

A RAG system 20 according to the present disclosure comprises: an attribute reception unit 101 that receives attribute information indicating an attribute of a user; a persona determination unit 102 that determines persona information corresponding to the user on the basis of the attribute information; a route determination unit 103 that determines a plurality of pieces of movement route information on the basis of the persona information; an information generation unit 104 that, on the basis of the plurality of pieces of movement route information, generates input information for requesting generation of content indicating a movement route suitable for the user; and a content acquisition unit 105 that acquires the content by inputting the input information to a generative AI model.

Description

Acquisition Device and Acquisition Method 【0001】 One aspect of the present disclosure relates to an acquisition device and an acquisition method. 【0002】 In recent years, a route planning system has been used in which each of a plurality of agents plans a route to move to a destination. This route planning system searches for the route of each agent from a start state to a goal state on a roadmap constructed for each of the plurality of agents. Then, when searching for a route, the route planning system constructs a roadmap for each agent based on the attributes of each agent (for example, size, shape, maximum speed, weight, etc.). 【0003】 Japanese Patent Application Laid-Open No. 2023-59382 【0004】 Recently, the diversification of user attributes has been progressing, and the types of user attributes are also various. Therefore, it has become difficult to provide content related to a moving route suitable for each user. 【0005】 Therefore, an object of the present disclosure is to provide an acquisition device and an acquisition method that can efficiently provide content related to a moving route suitable for each user. 【0006】 The acquisition device of the present disclosure includes an attribute reception unit that receives attribute information indicating user attributes, a persona determination unit that determines persona information corresponding to the user based on the attribute information, a route determination unit that determines a plurality of moving route information based on the persona information, an information generation unit that generates input information for requesting generation of content indicating a moving route suitable for the user based on the plurality of moving route information, and a content acquisition unit that acquires the content by inputting the input information into a generation AI model. 【0007】Alternatively, the acquisition method of this disclosure is an acquisition method performed by an acquisition device, comprising: an attribute reception step of receiving attribute information indicating the attributes of a user; a persona determination step of determining persona information corresponding to the user based on the attribute information; a route determination step of determining multiple travel route information based on the persona information; an information generation step of generating input information that requests the generation of content indicating a travel route suitable for the user based on the multiple travel route information; and a content acquisition step of acquiring content by inputting the input information into a generation AI model. 【0008】 According to one aspect of this disclosure, it is possible to efficiently provide each user with content related to suitable travel routes. 【0009】 Figure 1 is a block diagram showing the configuration of the acquisition system of this disclosure. Figure 2 is a diagram showing an example of the data structure of attribute information received by the attribute receiving unit 101 in Figure 1. Figure 3 is a diagram showing an example of the data structure of persona attribute information stored in the attribute storage unit 106 in Figure 1. Figure 4 is a diagram showing an example of the data structure of route selection information stored in the route selection information storage unit 107 in Figure 1. Figure 5 is a flowchart showing the procedure for content acquisition processing by the RAG system 20. Figure 6 is a diagram showing an example of the hardware configuration of the RAG system 20 according to one embodiment of this disclosure. Figure 7 is a diagram showing an example of the data structure of route selection information stored in the route selection information storage unit 107 in a modified example. 【0010】 Embodiments of this disclosure will be described with reference to the attached drawings. Where possible, the same parts will be denoted by the same reference numerals, and redundant descriptions will be omitted. 【0011】 Figure 1 is a diagram showing the device configuration of the acquisition system according to this embodiment. The acquisition system 1 shown in Figure 1 includes terminals 10, a RAG (Retrieval-Augmented Generation) system 20, and a server device 30, all configured to communicate with each other via a network including a wireless communication network and a fixed communication network. The RAG system 20 constitutes an acquisition device that acquires content related to travel routes based on attribute information received from terminal 10. 【0012】 Terminal 10 is a device used by a user who attempts to acquire content using an interactive AI model. Terminal 10 can be, for example, a personal computer, smartphone, tablet, feature phone, server, or game console. Although only one terminal 10 is shown in Figure 1, the acquisition system 1 may include two or more terminals 10. 【0013】 The server device 30 is a device that enables the provision of content using a generative AI model. A generative AI model is a model that, in response to input from a prompt containing input information, generates content according to one or a combination of the instructions, context, questions, and output format indicated by the prompt, and returns that content as response information. The prompt can also include input information, in which case the generative AI model generates response information targeting the input information. The generative AI model may be, for example, an interactive AI model that includes a Large Language Model (LLM) and a user interface (UI) for interaction with the user, enabling text chat or voice chat with the user. 【0014】 The generative AI model used in this embodiment returns text-based response information in response to text-based prompt input. Examples of such generative AI models include ChatGPT, GPT®-3.5, GPT-3.5 Turbo, GPT-4.0, GPT-4.0 Turbo, Azure OpenAI Service, tsuzumi, GPT-4V, PaLM2, and the like. 【0015】In this embodiment, the server device 30 enables the provision of content using an interactive AI model 31. This interactive AI model 31 may be stored within the server device 30, or it may be stored in another device connected to the server device 30 via a network, and configured to exchange information with the user via the server device 30. Alternatively, the interactive AI model 31 may be stored within the terminal 10. Although only one server device 30 is shown in Figure 1, the acquisition system may include multiple server devices 30. Furthermore, while the above description uses a large-scale language model as an example, other AI models may be used. In addition, the acquisition system may use an AI model selected from among multiple types of AI models. 【0016】 The RAG system 20 is composed of functional components including an attribute receiving unit 101, a persona determination unit 102, a route determination unit 103, an information generation unit 104, a content acquisition unit 105, an attribute storage unit 106, and a route selection information storage unit 107. The RAG system 20 relays prompts (input information) generated based on information acquired from the terminal 10 to the server device 30 and acquires response information from the server device 30 to those prompts. The functions of each functional unit of the RAG system 20 will be described in detail below. 【0017】The attribute receiving unit 101 receives attribute information from the terminal 10 that indicates the attributes of the user of terminal 10. Figure 2 shows an example of the data structure of attribute information received by the attribute receiving unit 101. The attribute information includes, for example, a user ID "FFF" which is an identifier that identifies the user, age "25", gender "male", place of residence "Tokyo", income class "A rank", occupation "IT engineer", information indicating the user's preferences such as purchasing behavior "anime goods", visited facilities "concert hall", and application usage "video application", etc. Here, the attribute receiving unit 101 may store some or all of the attribute information inside the RAG system 20 and retrieve some or all of the attribute information from inside the RAG system 20 based on the user ID received from terminal 10. Alternatively, the attribute receiving unit 101 may similarly retrieve some or all of the attribute information from an external device. 【0018】The persona determination unit 102 determines persona information corresponding to the user by referring to the attribute storage unit 106 based on the attribute information received by the attribute reception unit 101. Persona information is information that represents the attributes of a persona, which is a pre-defined profile of a person. The attribute storage unit 106 stores persona attribute information, which is a text description of multiple attributes related to a pre-defined persona. Figure 3 shows an example of the data structure of persona attribute information stored in the attribute storage unit 106. The attribute storage unit 106 stores persona attribute information for multiple personas in advance. For example, the persona attribute information "a man in his 20s working in an IT-related profession who enjoys a modern lifestyle, likes music and anime" is stored in association with the name "AAA BBB" that represents one persona. The persona determination unit 102 calculates the similarity between the user's attribute information and the persona attribute information for multiple personas stored in the attribute storage unit 106. The persona determination unit 102 then extracts the persona attribute information of the persona with the highest similarity from among the persona attribute information of multiple personas, and determines that the extracted persona attribute information corresponds to the user. At this time, the persona determination unit 102 calculates the similarity between each element of the user's attribute information (age, gender, etc.) and the persona attribute information using a known calculation method, and then comprehensively calculates the similarity between the entire user's attribute information and the persona attribute information. For example, the persona determination unit 102 extracts the persona attribute information "A man in his 20s working in an IT-related field who enjoys a modern lifestyle, loves music and anime" from among the persona attribute information shown in Figure 3, which is comprehensively similar to the attribute information shown in Figure 2, which includes elements such as age "25", gender "male", occupation "IT engineer", and purchasing behavior "anime goods". 【0019】The route determination unit 103 determines multiple travel route information that indicates a travel route suitable for the persona corresponding to the user by referring to the route selection information storage unit 107 based on the persona attribute information determined by the persona determination unit 102. Figure 4 shows an example of the data structure of the route selection information stored in the route selection information storage unit 107. The route selection information storage unit 107 stores multiple route selection information that indicates candidate travel route information, associated with the user's departure point. Each route selection information includes information such as “Persona Attribute 1” and “Persona Attribute 2” indicating the persona’s attributes, “Origin” and “Destination” which are route information indicating the travel route, “Probability” which is probability information indicating the probability that a persona having the attributes shown in “Persona Attribute 1” and “Persona Attribute 2” will select a route, “Travel Time” which is travel time information indicating the average travel time when a persona travels along the route, “Average Stay Time” which is stay time information indicating the average stay time at the destination of the route, and “Visitable Time Slot” which is time slot information indicating the time slots during which the destination of the route can be visited (business hours, opening hours, etc.). For example, one route selection piece of information might include: departure point "Shibuya Station", persona attribute 1 "Male", persona attribute 2 "Anime lover", origin "Shibuya Station", destination "Store A", probability "2%", travel time "6 minutes", average stay time "1 hour", and available visit time "10:00-19:00". 【0020】The route determination unit 103 extracts multiple route selection pieces of route selection information stored in the route selection information storage unit 107 from among multiple route selection pieces of route selection information that match the departure location information and whose content described in the persona attribute information is similar to persona attribute 1 and persona attribute 2, based on the departure location information set in advance by user input from terminal 10 or location information related to terminal 10, and persona attribute information. The route determination unit 103 then determines the multiple extracted route selection pieces of route selection information as multiple travel route pieces of route information that indicate a travel route suitable for the persona corresponding to the user. For example, if the departure location is "Shibuya Station" and the persona attribute information is "a man in his 20s working in an IT-related occupation who enjoys a modern lifestyle and likes music and anime", the route determination unit 103 extracts four route selection pieces of route selection information from among the multiple route selection pieces of route selection information shown in Figure 4, including "Shibuya Station" as the departure location, persona attribute 1 "male", and persona attribute 2 "anime lover". The route selection information determined includes, for each of the multiple travel route options, probability information (e.g., probability "2%"), travel time information (e.g., travel time "6 minutes"), dwell time information (e.g., average dwell time "1 hour"), and time of day information (e.g., available time of day "10:00 to 19:00"). 【0021】The information generation unit 104 generates a prompt (input information) that requests the generation of content indicating a suitable travel route for the user of terminal 10, based on the persona attribute information determined by the persona determination unit 102 and the multiple travel route information determined by the route determination unit 103. A prompt is information that indicates an instruction or question to be entered by a user in an interactive system such as a dialogue with an AI model or a command line interface (CLI). In the prompt generated by the information generation unit 104, the text expresses, for example, the command to be executed by the interactive AI model, the task to be executed by the interactive AI model, the background / context to be considered by the interactive AI model (e.g., role, conditions), the question to be answered by the interactive AI model, and the output format of the response information from the interactive AI model. The prompt may also have input information that is the target of the command / task to be executed by the interactive AI model. Examples of such input information include data files such as text data, image data, audio data, video data, and still image data. 【0022】For example, the information generation unit 104 generates a prompt based on persona attribute information and multiple route selection information. In this case, the information generation unit 104 includes probability information, travel time information, and dwell time information contained in each of the multiple route selection information as input information. The information generation unit 104 may also estimate the arrival time at the destination from the target time (e.g., current time), which is the time when the user starts moving, and the travel time, and determine the dwell time information from the arrival time and the time zone information of the destination, and include the determined dwell time information in the input information. For example, if the estimated arrival time at the destination is "18:30" and the visitable time zone of the destination is "10:00 to 19:00", the information generation unit 104 will determine the average dwell time to be "30 minutes". Below is an example of a prompt generated by the information generation unit 104. <Example of a prompt generated by the information generation unit 104> Role You are a man in your 20s working in an IT-related field and you like music and anime. Task You are currently at Shibuya Station. Create multiple travel routes within a 3-hour time limit. The routes should be chosen considering probability. The routes must fit within the time limit and allow visits to multiple destinations within their respective available time slots. Consider the combinations of origin and destinations with the highest probability of being visited, and their probabilities. After explaining the possible routes, please tell us which destination has the highest probability of being visited. Please refer to the following information: Origin, Destination, Probability, Travel Time, Average Time at Destination Shibuya Station, Store A, 2%, 6 minutes, 30 minutes Shibuya Station, Square B, 1.5%, 1 minute, 1 hour Shibuya Station, Department Store C, 1.2%, 3 minutes, 30 minutes Store A, Department Store C, 1.4%, 4 minutes, 30 minutes <Example prompt, end> 【0023】The content acquisition unit 105 inputs a prompt generated by the information generation unit 104 to the interactive AI model 31 and acquires content indicating a travel route from the interactive AI model 31. Specifically, the content acquisition unit 105 acquires content that includes text representing a travel route suitable for the user. In addition to text, the content acquisition unit 105 may also acquire image data, audio data, or video data that can convey the travel route to the user. The content acquisition unit 105 then outputs the acquired content as output data. The output of the output data by the content acquisition unit 105 may be performed by transmitting it to an external device such as a terminal 10, or by storing it in a data storage unit within the RAG system 20 so that it can be accessed from the outside. The following is an example of content acquired by the content acquisition unit 105. <Example of content acquired by the content acquisition unit 105> The travel route that you are most likely to take is: Shibuya Station → Department Store C → Store A Shibuya Station → Square B → Store D ... Regardless of which route you choose, there's a high probability you'll end up going from Department Store C to Store A. <End of content example> 【0024】 The procedure for content acquisition processing by the RAG system 20 configured as described above, that is, the flow of the acquisition method according to this embodiment, will now be explained. Figure 5 is a flowchart showing the procedure for content acquisition processing by the RAG system 20. 【0025】 The content acquisition process is executed in response to instructions from the user of terminal 10. When the content acquisition process starts, the attribute reception unit 101 of the RAG system 20 first acquires the user's attribute information from terminal 10 (step S01). Then, the persona determination unit 102 determines persona attribute information corresponding to the user based on the attribute information (step S02). Subsequently, the route determination unit 103 determines multiple travel route information based on the persona attribute information (step S03). 【0026】Next, the information generation unit 104 generates a prompt based on the persona attribute information and multiple travel route information (step S04). Then, the content acquisition unit 105 inputs the prompt into the interactive AI model and acquires content that indicates a travel route suitable for the user (step S05). Finally, the content acquisition unit 105 outputs the acquired content to the terminal 10 (step S06). 【0027】 Next, the operation and effects of the acquisition device of this disclosure will be explained. According to the RAG system 20 of this disclosure, attribute information regarding the user's attributes is acquired from the terminal 10, and based on that attribute information, a persona corresponding to the user is selected from among multiple personas, and multiple travel routes corresponding to the selected persona are determined. Then, the RAG system 20 generates a prompt requesting the generation of content that shows a travel route suitable for the user based on the multiple travel routes determined. Furthermore, the RAG system 20 inputs the generated prompt into the interactive AI model 31, thereby acquiring the content. As a result, the user is categorized into a single persona, and travel route information is acquired by referring to multiple travel routes that match the categorized persona, enabling efficient provision of content regarding travel routes suitable for each user. 【0028】 In the RAG system 20 of this disclosure, an attribute storage unit 106 is further provided for storing multiple persona attribute information indicating the attributes of multiple personas. The persona determination unit 102 determines persona information by extracting persona attribute information similar to the attribute information from among the multiple persona attribute information stored in the attribute storage unit 106. In this case, a persona that matches the attributes of each user can be easily selected from a predetermined number of personas, and content related to suitable travel routes can be easily obtained for each user. 【0029】Furthermore, in the RAG system 20 of this disclosure, the route determination unit 103 further determines probability information for each of the multiple travel route information, which persona indicated by the persona information will select the route indicated by the travel route information, and the information generation unit 104 includes probability information for each of the multiple routes in the input information. In this case, since content can be generated based on the probability of selecting one of the multiple travel routes by the interactive AI model 31, content related to travel routes that is more suitable for each user can be obtained. 【0030】 Furthermore, in the RAG system 20 of this disclosure, the route determination unit 103 further determines travel time information indicating the time it takes to travel along the route indicated by the multiple travel route information for each of the multiple travel route information, and the information generation unit 104 includes the travel time information for each of the multiple routes in the input information. In this case, since the interactive AI model 31 can generate content based on the travel times for multiple travel routes, it is possible to obtain content related to travel routes that are more suitable for each user who has travel time constraints. 【0031】 Furthermore, in the RAG system 20 of this disclosure, the route determination unit 103 further determines the time period information for which the destinations of the routes indicated by the multiple travel route information can be visited for each of the multiple travel route information, and the information generation unit 104 determines the dwell time for each of the multiple routes based on the target time and time period information, and includes the dwell time information determined for each of the multiple routes in the input information. With this configuration, the interactive AI model 31 can generate content based on the time period information for which the destinations of the multiple travel routes can be visited, so that each user can obtain content related to the travel route that is useful for the target time. 【0032】 The acquisition apparatus and acquisition method of this disclosure have the following configuration. 【0033】[1] An acquisition device comprising: an attribute receiving unit that receives attribute information indicating the attributes of a user; a persona determination unit that determines persona information corresponding to the user based on the attribute information; a route determination unit that determines a plurality of travel route information based on the persona information; an information generation unit that generates input information requesting the generation of content indicating a travel route suitable for the user based on the plurality of travel route information; and a content acquisition unit that acquires the content by inputting the input information into a generation AI model. 【0034】 [2] The acquisition device according to [1] above, further comprising an attribute storage unit for storing multiple persona attribute information indicating the attributes of multiple personas, wherein the persona determination unit determines the persona information by extracting persona attribute information similar to the attribute information from among the multiple persona attribute information stored in the attribute storage unit. 【0035】 [3] The acquisition device according to [1] or [2] above, wherein the route determination unit further determines probability information for each of the plurality of travel route information that the persona indicated by the persona information will select the route indicated by the travel route information, and the information generation unit includes the probability information for each of the plurality of routes in the input information. 【0036】 [4] The acquisition device according to any one of [1] to [3] above, wherein the route determination unit further determines travel time information indicating the time to travel along the route indicated by the plurality of travel route information for each of the plurality of travel route information, and the information generation unit includes the travel time information for each of the plurality of routes in the input information. 【0037】 [5] The acquisition device according to any one of [1] to [4] above, wherein the route determination unit further determines visitable time period information for the destination of the route indicated by the plurality of travel route information for each of the plurality of travel route information, and the information generation unit determines the dwell time for each of the plurality of routes based on the target time and the time period information, and includes the information of the dwell time determined for each of the plurality of routes in the input information. 【0038】[6] The acquisition device according to any one of [1] to [5] above, wherein the route determination unit determines the plurality of travel route information using a learning model that outputs travel route information for each attribute of the persona indicated by the persona information. 【0039】 [7] An acquisition method performed by an acquisition device, comprising: an attribute reception step of receiving attribute information indicating the attributes of a user; a persona determination step of determining persona information corresponding to the user based on the attribute information; a route determination step of determining a plurality of travel route information based on the persona information; an information generation step of generating input information that requests the generation of content indicating a travel route suitable for the user based on the plurality of travel route information; and a content acquisition step of acquiring the content by inputting the input information into a generation AI model. 【0040】 The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may be realized by combining the one or more devices with software. 【0041】Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited. 【0042】 For example, the RAG system 20, which constitutes the acquisition device in one embodiment of the present disclosure, may function as a computer that processes the acquisition method of the present disclosure. Figure 6 is a diagram showing an example of the hardware configuration of the RAG system 20 according to one embodiment of the present disclosure. The RAG system 20 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc. The RAG system 20 may be configured as a computer device including at least one processor such as a CPU or GPU, may be configured as a computer device including multiple processors, or may be configured as including multiple computer devices. The terminal 10 and server device 30 may also adopt a similar hardware configuration. 【0043】 In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the RAG system 20 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices. 【0044】Each function in the RAG system 20 is realized by causing a processor 1001 to load a predetermined software (program) onto hardware such as a memory 1002, etc., so that the processor 1001 performs operations, controls communication by a communication device 1004, or controls at least one of reading and writing data in the memory 1002 and a storage 1003. 【0045】 The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be constituted by a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic device, a register, etc. For example, the above-described attribute reception unit 101, persona determination unit 102, route determination unit 103, information generation unit 104, content acquisition unit 105, etc. may be realized by the processor 1001. 【0046】 Further, the processor 1001 reads a program (program code), software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program for causing a computer to execute at least a part of the operations described in the above embodiments is used. For example, the attribute reception unit 101, persona determination unit 102, route determination unit 103, information generation unit 104, content acquisition unit 105 may be stored in the memory 1002 and realized by a control program operating in the processor 1001, and the same may be true for other functional blocks. Although it has been described that the above various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be mounted by one or more chips. Note that the program may be transmitted from a network via a telecommunication line. 【0047】Memory 1002 is a computer-readable recording medium and may be constituted by at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 1002 may be referred to as a register, cache, main memory (main storage device), etc. Memory 1002 can store a program (program code), software module, etc. executable for implementing the acquisition method according to an embodiment of the present disclosure. 【0048】 Storage 1003 is a computer-readable recording medium and may be constituted by at least one of, for example, optical disks such as CD-ROM (Compact Disc ROM), hard disk drives, flexible disks, magneto-optical disks (e.g., compact disks, digital versatile disks, Blu-ray (registered trademark) disks), smart cards, flash memories (e.g., cards, sticks, key drives), floppy (registered trademark) disks, magnetic strips, etc. Storage 1003 may be referred to as an auxiliary storage device. The above-described recording medium may be, for example, a database, server, or other appropriate medium including at least one of Memory 1002 and Storage 1003. 【0049】The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include high-frequency switches, duplexers, filters, frequency synthesizers, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the attribute receiving unit 101 and content acquisition unit 105 described above may be implemented by the communication device 1004. 【0050】 The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel). 【0051】 Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device. 【0052】 Furthermore, the RAG system 20 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components. 【0053】 Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc. 【0054】 The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented. 【0055】 Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices. 【0056】 The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value). 【0057】Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification). 【0058】 Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way. 【0059】 The acquisition system is not limited to the configuration shown in Figure 1, and may also be configured with the server device 30 implemented on the terminal 10. This configuration can be realized by installing an application on the terminal 10 that performs the functions of the server device 30. Alternatively, the RAG system 20 may be implemented on the terminal 10. This configuration can be realized by installing an application on the terminal 10 that performs the functions of the RAG system 20. Furthermore, although Figure 1 shows an example where the attribute storage unit 106 and the route selection information storage unit 107 are implemented outside the terminal 10 (for example, on the network), the attribute storage unit 106 and the route selection information storage unit 107 may also be implemented on the terminal 10. 【0060】 Furthermore, in the RAG system 20 disclosed herein, the route determination unit 103 determines multiple travel route information using a learning model that outputs travel route information for each persona attribute indicated by the persona information (for example, preference information such as "anime lover"). With this configuration, multiple travel routes corresponding to the selected persona are efficiently determined, and content related to travel routes suitable for each user can be efficiently acquired. 【0061】Furthermore, in the RAG system 20 of this disclosure, the route determination unit 103 may determine information indicating a travel route that passes through three or more points as travel route information. Figure 7 shows an example of the data structure of route selection information stored in the route selection information storage unit 107, which the route determination unit 103 refers to when determining travel route information. As shown above, the route selection information includes information on a route that passes through multiple points, such as "Shibuya Station → Store D → Department Store C → Store A" as route selection information indicating a travel route. By using route selection information with such a data structure, the route determination unit 103 can determine information indicating a travel route that passes through three or more points as travel route information. 【0062】 Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name. 【0063】 Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium. 【0064】 The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. 【0065】 In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc. 【0066】 Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information. For example, wireless resources may be indicated by an index. 【0067】 The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way. 【0068】 In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably. 【0069】 A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other appropriate term. 【0070】As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering." 【0071】The terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain. 【0072】 In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on." 【0073】 Any reference to elements using designations such as “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way. 【0074】 Where the terms “include,” “including,” and their variations are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to be exclusive OR. 【0075】In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural. 【0076】 In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different." 【0077】 10...Terminal, 20...RAG system, 30...Server device, 31...Interactive AI model, 101...Attribute reception unit, 102...Persona determination unit, 103...Route determination unit, 104...Information generation unit, 105...Content acquisition unit, 106...Attribute storage unit.

Claims

1. An acquisition device comprising: an attribute receiving unit that receives attribute information indicating the attributes of a user; a persona determination unit that determines persona information corresponding to the user based on the attribute information; a route determination unit that determines multiple travel route information based on the persona information; an information generation unit that generates input information requesting the generation of content indicating a travel route suitable for the user based on the multiple travel route information; and a content acquisition unit that acquires the content by inputting the input information into a generation AI model.

2. The acquisition device according to claim 1, further comprising an attribute storage unit for storing a plurality of persona attribute information indicating the attributes of a plurality of personas, wherein the persona determination unit determines the persona information by extracting persona attribute information similar to the attribute information from the plurality of persona attribute information stored in the attribute storage unit.

3. The acquisition device according to claim 1, wherein the route determination unit further determines, for each of the plurality of travel route information, probability information that the persona indicated by the persona information will select the route indicated by the travel route information, and the information generation unit includes the probability information for each of the plurality of routes in the input information.

4. The acquisition device according to claim 1, wherein the route determination unit further determines travel time information indicating the time required to travel along the route indicated by the plurality of travel route information for each of the plurality of travel route information, and the information generation unit includes the plurality of travel time information for each of the route in the input information.

5. The acquisition device according to claim 1, wherein the route determination unit further determines visitable time period information for the destination of the route indicated by the plurality of travel route information for each of the plurality of travel route information, and the information generation unit determines the dwell time for each of the plurality of routes based on the target time and the time period information, and includes the information of the dwell time determined for each of the plurality of routes in the input information.

6. The acquisition device according to claim 1, wherein the route determination unit determines the plurality of travel route information using a learning model that outputs travel route information for each attribute of the persona indicated by the persona information.

7. An acquisition method performed by an acquisition device, comprising: an attribute reception step of receiving attribute information indicating the attributes of a user; a persona determination step of determining persona information corresponding to the user based on the attribute information; a route determination step of determining a plurality of travel route information based on the persona information; an information generation step of generating input information that requests the generation of content indicating a travel route suitable for the user based on the plurality of travel route information; and a content acquisition step of acquiring the content by inputting the input information into a generation AI model.

Images