A multi-role assistant system and device based on a large language model for cultural tourism scenarios

Abstract

This invention discloses a multi-role assistant system and device based on a large language model for cultural tourism scenarios. The tourist assistant can understand natural language questions posed by users and provide information on attractions, planned travel routes, transportation information, and surrounding services. The merchant assistant has intelligent customer service, business analysis and strategy suggestions, and user review analysis functions. The government back-end management assistant can generate tourism revenue reports and assist in market supervision and emergency command. Through large language model training and optimization, and auxiliary data processing, the system improves the tourist experience and merchant benefits, assists in scientific government decision-making and supervision, and promotes the development of the cultural tourism industry.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and in particular to a multi-role assistant system and device based on a large language model for cultural and tourism scenarios. Background Technology

[0002] In the current cultural and tourism landscape, tourists, merchants, and government back-office management all face a series of significant challenges.

[0003] For tourists, planning a trip often presents a challenge due to the overwhelming amount of information and its inaccuracy. They need to gather information about attractions, food, accommodation, transportation, and other aspects of their destination from numerous channels, but this information is often scattered, incomplete, and sometimes contradictory. During the trip, obtaining real-time and accurate local information may also be difficult. Furthermore, personalized needs are often unmet, making it impossible to tailor the most suitable travel itinerary based on individual interests and time constraints.

[0004] Merchants face challenges such as intense competition, rising operating costs, and diversified customer needs. In customer service, human customer service struggles to handle peak inquiry volumes, leading to low service efficiency and decreased customer satisfaction. Regarding business decision-making, the lack of accurate data analysis and market trend forecasting makes it difficult to grasp market dynamics and make reasonable adjustments to business strategies. Furthermore, merchants struggle to accurately analyze numerous user reviews to identify areas for improvement, hindering their ability to effectively enhance operational quality.

[0005] For government back-office management, there are challenges in effectively regulating and scientifically planning the cultural and tourism market. Regarding data collection, there are issues with fragmented data sources and inconsistent data quality, making it difficult to comprehensively and accurately grasp the actual situation of the cultural and tourism market. Furthermore, the ability to monitor and respond to emergencies and market anomalies needs improvement. Summary of the Invention

[0006] The purpose of this invention is to address the shortcomings of existing technologies by proposing a multi-role assistant system and device based on a large language model for cultural and tourism scenarios, which can meet the different needs of different entities such as tourists, merchants and government back-end management in cultural and tourism scenarios.

[0007] The objective of this invention is achieved through the following technical solution: a multi-role assistant system based on a large language model in a cultural tourism scenario, the system comprising:

[0008] The Tourist Assistant module constructs a tourism database containing information on tourist attractions. Based on tourists' travel needs, it generates travel route suggestions using a large language model based on information in the tourism database, and generates transportation suggestions by combining information from the transportation data platform. It also filters the business information of the merchants in need based on the merchant database.

[0009] The Merchant Assistant module constructs a merchant database containing merchant operating information. Based on tourist inquiries, it uses a large language model to filter eligible merchants from the database and provides their operating information back to the tourists. It also extracts key booking information from user questions based on tourist booking needs and sends it to the online booking platform, processing bookings according to rules and priorities. Furthermore, it uses a large language model to deeply mine and analyze merchant sales information, calculate operating indicators, and perform sentiment analysis and keyword extraction on tourist review text data, classifying and summarizing tourist satisfaction, opinions, and suggestions.

[0010] The government back-end management assistant module collects transaction and revenue data from scenic area merchants, as well as user review data. It analyzes tourism revenue trends through a large language model and extracts key information by combining text and structured data to evaluate the business behavior of merchants.

[0011] Furthermore, the tourist assistant module's tourism database periodically collects and updates detailed information about tourist destinations from public databases and online resources, including attraction information, opening hours, distances between attractions, and modes of transportation.

[0012] Furthermore, the large language model in the tourist assistant module connects and interacts with the real-time traffic data platform to obtain traffic information for scenic spots, including the operating hours, routes, fares, and real-time road conditions of transportation vehicles, as well as the operating hours and fares of sightseeing buses and cable cars within the scenic area. The large language model generates route planning, traffic information, and merchant information through text descriptions, charts, and map annotations, and conducts multiple rounds of dialogue based on user needs to modify the information.

[0013] Furthermore, the merchant operating information includes the merchant's operating hours, business scope, product information, and preferential policies.

[0014] Furthermore, the Merchant Assistant module builds and maintains a question bank for tourists, categorizes and statistically analyzes common tourist questions and answers from a large language model, and adds them to the list of common questions.

[0015] Furthermore, through the API interface of the online booking platform service, the merchant assistant module can interact with the booking platform to complete the booking process based on the extracted booking information; and use the payment system of the payment platform service to generate a payment link or QR code based on the booking or purchase information and provide feedback to the tourist. After the payment operation is completed, the tourist is given instant feedback on whether the booking is successful or unsuccessful.

[0016] Furthermore, the merchant assistant module constructs a database of merchants' sales, inventory, and financial information. When the large language model completes a user-initiated reservation or purchase request, it can automatically record the transaction data into the database. The inventory and financial change information of the merchants themselves is also stored in the database through manual entry or large language model-assisted entry. When merchants need to conduct business performance analysis, the large language model reads this information, calculates key indicators such as sales volume, profit margin, and inventory turnover rate, analyzes business trends and potential problems by comparing with historical and industry data, and generates a business performance analysis report, which is then fed back to the merchants through the large language model.

[0017] Furthermore, the large language model in the government back-end management assistant module generates detailed monthly, quarterly, and annual reports, which are presented in a combination of charts and text.

[0018] Furthermore, the government back-end management assistant module interacts with meteorological, traffic, and public safety monitoring systems in real time, uses large language models to analyze meteorological and traffic information in real time, quickly identifies key issues and needs, and generates emergency command strategies and action plans by combining manually set emergency plan rules.

[0019] On the other hand, the present invention also provides a multi-role assistant device based on a large language model in a cultural and tourism scenario, including a memory and one or more processors. The memory stores executable code, and when the processor executes the executable code, it implements the multi-role assistant system based on a large language model in a cultural and tourism scenario.

[0020] The beneficial effects of this invention are:

[0021] This invention effectively solves the following problems existing in the background technology through a multi-role assistant system based on a large language model in the cultural and tourism scenario:

[0022] For tourists, the problem of large amounts of inaccurate information has been solved. Through the personalized services of the tourist assistant module, tourists can easily plan their travel routes, obtain real-time traffic information and restaurant and accommodation recommendations, greatly enhancing their travel experience.

[0023] For merchants, the Merchant Assistant module addresses the challenges of rising operating costs and diversified customer needs. It improves service efficiency through intelligent customer service and automated booking services, and helps merchants make reasonable adjustments to their business strategies through business performance analysis and user feedback analysis, effectively improving the quality of their operations.

[0024] For government back-office management, it solves the problems of effective supervision and scientific planning of the cultural and tourism market. The government back-office management assistant module improves the monitoring and response capabilities of the cultural and tourism market through functions such as tourism revenue reports, industry supervision, and emergency command, and achieves a comprehensive and accurate grasp of the market.

[0025] In summary, this invention, through large language model technology, provides comprehensive intelligent services and support for different entities in cultural and tourism scenarios, effectively solving problems such as information asymmetry, low service efficiency, and difficulties in market supervision that exist in the background technology, and has significant practical value and social benefits. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a schematic diagram of a multi-role assistant structure based on a large language model in a cultural tourism scenario provided by the present invention;

[0028] Figure 2 This is a structural diagram of a multi-role assistant device based on a large language model in a cultural tourism scenario according to the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described below with reference to the accompanying drawings and examples. It should be understood that the specific examples described herein are merely illustrative and not intended to limit the invention.

[0030] like Figure 1 As shown, the present invention provides a multi-role assistant system based on a large language model in a cultural tourism scenario, including a tourist assistant module, a merchant assistant module, and a government back-end management assistant module.

[0031] Tourist Assistant Module: Utilizing large language model technology, the Tourist Assistant provides tourists with comprehensive and personalized services. Through interaction with the Tourist Assistant, tourists can easily plan their travel routes, obtain scenic area transportation information, and access key service information such as dining, hotels, and accommodations from the merchant database, greatly enhancing their travel experience. The Tourist Assistant module implements the following functions:

[0032] 1. Construct a tourism database to serve as a travel assistant. This database collects detailed information about tourist destinations from public databases, online resources, and other channels, including attractions, opening hours, distances between attractions, and transportation methods. The database is updated periodically to ensure the accuracy and timeliness of the information.

[0033] 2. Train a large language model to enable direct interaction between the visitor assistant and tourists. This large language model is trained using detailed attraction information from official tourist website websites and tourism information from tourism databases as additional training data. This allows it to better understand the characteristics of different attractions and the relationships between them, and to analyze tourism-related information. The trained model is then integrated into the visitor assistant module to ensure that it can receive user input and provide intelligent responses.

[0034] 3. Design a user interface that allows tourists to input their travel needs, such as travel time, preferred attraction types (e.g., natural scenery, historical and cultural sites, entertainment and leisure), and budget range. Input this tourist information into a large language model (MLM). Utilize the MLM model for data analysis, comprehensively considering factors such as attraction popularity, tourist interests, travel time constraints, and transportation convenience, to generate one or more personalized travel route suggestions. Display detailed itineraries to tourists, including specific attractions to visit, estimated time spent at each attraction, and optimal transportation methods and routes between attractions. Build a plugin based on the MLM model. This plugin connects to a real-time traffic data platform to obtain the latest traffic information. The plugin's technical implementation first involves creating an interface that can communicate with the real-time traffic data platform's API. This interface is responsible for sending requests and receiving traffic data. Then, the plugin parses this data and converts it into a format suitable for algorithm processing. Next, the plugin inputs the user's itinerary information and real-time traffic data into the algorithm model, waiting for the algorithm to calculate recommended transportation options. After calculation, the plugin is responsible for converting the algorithm's output into a user-friendly format, such as map markers, text descriptions, or charts, and displaying it to the user through the user interface. In addition, the plugin needs to have an error handling mechanism to deal with abnormal situations such as API call failure or data parsing errors, so as to ensure the stability and reliability of the plugin.

[0035] 4. Based on the previously listed itinerary and real-time traffic information, provide suggestions for the fastest and most economical transportation options. This process involves cleaning and formatting raw data obtained from a real-time traffic data platform, then analyzing and extracting key traffic information using a predefined algorithm model. This information includes the operating hours, routes, fares, and real-time road conditions of various modes of transportation (bus, subway, taxi, ride-hailing). When tourists inquire about transportation options within a scenic area, such as whether taking the subway or a taxi is faster or more convenient from the hotel, the large language model calculates the optimal route using a shortest path algorithm based on the user's specific itinerary. It considers multiple factors, such as the speed and cost of different modes of transportation and the user's time preferences, and uses a weighted scoring system to integrate these factors, providing accurate and timely transportation suggestions. The model ultimately outputs one or more recommended transportation options and provides information on transportation within the scenic area, such as the availability of sightseeing buses and cable cars, their operating hours, and fares. To cope with real-time changes in traffic conditions, the recommended solutions are dynamically adjusted based on specific traffic conditions to ensure that the suggestions provided are always the fastest and most economical.

[0036] 5. A plugin based on a large language model is built to connect with a merchant database and obtain detailed information on restaurants and hotels. When tourists need to book restaurants or accommodations, the plugin uses the large language model to search and match merchant information according to the tourist's needs, and displays the merchant information that meets the tourist's needs in a structured format, including key information such as name, address, contact information, user reviews, and price range, to help tourists make more suitable choices. The plugin first establishes a communication interface connecting the large language model and the merchant database. This interface is implemented using a specific database connection library and the language model's API. The interface receives query requests from the large language model and transforms them into query statements that the merchant database can understand. When the query statement is sent to the merchant database, the database returns the corresponding result set. The plugin then processes this result set, extracting merchant information that meets the tourist's needs, including key content such as name, address, and contact information. The plugin uses data structures such as dictionaries or objects to store the information of each merchant, and then passes this structured data to the large language model. The large language model can generate natural language descriptions based on this structured data and display them to the tourist. The plugin also considers error handling, such as database connection failures, query errors, or no matching merchants being found. Appropriate error messages are provided to ensure the plugin's stability and reliability. During the query process, the plugin uses methods such as indexing and caching query results to reduce query time and resource consumption.

[0037] 6. Multimodal Data and Multi-Turn Dialogue Functionality: To ensure tourists can clearly understand and effectively utilize the information provided by the large language model, it also presents complex route planning, traffic information, and merchant service information in a concise and intuitive way. The large language model can generate various output formats such as text descriptions, charts, and map annotations to help tourists understand various information more intuitively. Furthermore, the tourist assistant supports multi-turn dialogue, allowing tourists to provide further details or modification requests based on initial information. The large language model will continuously optimize and improve the services provided to meet the ever-changing and refined needs of tourists.

[0038] Merchant Assistant Module: The Merchant Assistant provides comprehensive support for merchants' business management through features such as intelligent customer service, automated booking service, business performance analysis, and user review analysis; specifically, it includes the following functions:

[0039] 1. Construct a merchant information database to serve as a merchant assistant. This database will create a series of data tables for each merchant, including information such as operating hours, business scope, product information, and preferential policies. Design a merchant review process to regularly check the information in all merchant data tables to ensure the accuracy and timeliness of the database information. Build a plugin based on a large language model, enabling the large language model to access the relevant information stored in the database. Implement an intelligent customer service system. When a tourist inquires with the merchant assistant, the intelligent customer service system can filter merchants that meet the user's criteria from the database and integrate the relevant information stored in the database of these merchants to provide feedback to the tourist. Simultaneously, the intelligent customer service system will provide a function to browse frequently asked questions. This function will categorize and statistically analyze common questions that tourists may ask and the answers from the large language model, adding them to the FAQ list. To ensure the accuracy and professionalism of the answers, merchants will regularly review and update the database, supplementing it with the latest product information and relevant policies.

[0040] 2. Establish and maintain a frequently asked questions (FAQ) database. This database collects conversations between tourists and merchant assistants, and uses a large language model to select the most frequent question types or examples, adding them to the database. The database is regularly updated to include new frequently asked questions and answers.

[0041] 3. When a user initiates a reservation or purchase request to the merchant assistant, the system uses a large language model to extract key reservation or purchase information from the user's request. If necessary, the system confirms the accuracy of the extracted information with the user, such as the specified dining time, number of people, special dining requirements, or specific accommodation dates and room preferences. This information is then sent to the online booking platform for searching and matching, and the reservation is processed according to booking rules and priorities. An API interface is implemented to allow the merchant assistant module to interact with the online booking platform, obtain real-time reservation information, including the number of available dining seats, room types and quantities, and reservation prices. The reservation process is completed based on the extracted information. A payment system using mainstream payment platforms is implemented. After the user completes the reservation, a payment link or QR code is generated based on the reservation or purchase information and provided to the user, simplifying the payment process and facilitating convenient payment and settlement. Instant feedback is provided to the user regarding reservation success or failure after payment. In case of reservation failure or conflict, relevant information is promptly provided, and alternative solutions are offered if necessary.

[0042] 4. Construct a database to record merchants' sales, inventory, and financial information. Develop a plugin based on a large language model to access this database and obtain information such as sales data, inventory levels, and cost expenditures. When the large language model completes a user-initiated reservation or purchase request, it automatically records the transaction data into the database. Merchants' own inventory and financial changes can also be stored in the database manually or with the assistance of the large language model. When merchants need to analyze their business performance, the large language model reads this information, calculates key indicators such as sales revenue, profit margin, and inventory turnover, compares it with historical and industry data, analyzes business trends and potential problems, and generates a business performance analysis report, which is then fed back to the merchant through the large language model.

[0043] 5. Collect user review data from multiple channels, including online reviews, social media, and merchants' own review systems, by accessing various websites. Input the collected user review data into a large language model for classification, keyword extraction, and sentiment analysis to determine user satisfaction and key concerns. The large language model further categorizes and summarizes specific user opinions and suggestions, such as evaluations of food taste, service quality, environmental comfort, and price reasonableness. The analysis results and suggestions are then provided to merchants, offering directions for improvement and optimization through comprehensive analysis of a large amount of review data.

[0044] Government Back-End Management Assistant Module: This module provides the government with a variety of key functions through a large language model, including tourism revenue reporting, industry supervision, and emergency command; specifically, it includes the following functions:

[0045] 1. Integrate transaction and revenue data interfaces from various merchants (such as scenic spots and hotels) to automatically collect revenue data from different sources, including scenic spots, hotels, restaurants, and travel agencies. Simultaneously, utilize big data analytics to clean the data, removing invalid or erroneous data and categorizing and summarizing the data. Input the collected valid data into a large language model to build a trend prediction model, analyze tourism revenue trends, generate detailed monthly, quarterly, and annual reports, and present the analysis results to government management departments in chart and text format. This allows the government to intuitively understand the overall status and growth trend of tourism revenue, providing data support for decision-making.

[0046] 2. User review data is collected from various websites and channels. This review information, along with the collected transaction and revenue data, is input into a large language model. The large language model extracts key information from this textual and structured data to assess merchants' business practices and identify irregularities and risks. Compared to manual processing of this industry regulatory data, this method improves the efficiency and effectiveness of industry supervision. If the large language model detects irregularities in a merchant's behavior, it will prompt government regulatory departments to conduct manual review and confirmation.

[0047] 3. By establishing real-time data interaction interfaces with monitoring systems for meteorology, transportation, and public safety, the system utilizes large language models to perform real-time analysis of information related to these sectors, quickly identifying key issues and needs. In the event of an emergency, based on the analysis results and the model, the system uses large language models combined with manually defined emergency response rules to generate emergency command strategies and action plans, providing support for rapid response and effective handling by the government. This function can coordinate relevant departments and resources to achieve rapid response and effective handling of emergencies, ensuring the safety of tourists and the public.

[0048] Corresponding to the aforementioned embodiment of a multi-role assistant system based on a large language model in a cultural and tourism scenario, the present invention also provides an embodiment of a multi-role assistant device based on a large language model in a cultural and tourism scenario.

[0049] See Figure 2 The present invention provides a multi-role assistant device based on a large language model in a cultural and tourism scenario, comprising a memory and one or more processors. The memory stores executable code, and when the processor executes the executable code, it is used to implement a multi-role assistant system based on a large language model in a cultural and tourism scenario as described in the above embodiment.

[0050] The embodiment of the multi-role assistant device based on a large language model in a cultural tourism scenario provided by this invention can be applied to any device with data processing capabilities, such as a computer. The device embodiment can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of any data processing device reading the corresponding computer program instructions from non-volatile memory into memory and executing them. From a hardware perspective, such as... Figure 2 The diagram shown is a hardware structure diagram of any device with data processing capabilities, which is a multi-role assistant device based on a large language model in a cultural tourism scenario provided by the present invention. (Except for...) Figure 2 In addition to the processor, memory, network interface, and non-volatile memory shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0051] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0052] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0053] This invention also provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements a multi-role assistant system based on a large language model in a cultural and tourism scenario as described in the above embodiments.

[0054] The computer-readable storage medium can be an internal storage unit of any data processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device of any data processing device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of any data processing device. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing device, and can also be used to temporarily store data that has been output or will be output.

[0055] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the aforementioned multi-role assistant system based on a large language model in a cultural and tourism scenario.

[0056] The above embodiments are used to explain and illustrate the present invention, but not to limit the present invention. Any modifications and changes made to the present invention within the spirit and scope of the claims shall fall within the protection scope of the present invention.

Claims

1. A multi-role assistant system based on a large language model for cultural tourism scenarios, characterized in that, The system includes: The Tourist Assistant module constructs a tourism database containing information on tourist attractions. Based on tourists' travel needs, it generates travel route suggestions using a large language model based on information from the tourism database, and generates transportation suggestions by combining information from a transportation data platform. It also filters the business information of desired merchants based on a merchant database. Specifically, the Tourist Assistant module connects and interacts with the real-time transportation data platform to obtain transportation information for attractions, including operating hours, routes, fares, and real-time road conditions for transportation vehicles, as well as operating hours and fares for sightseeing buses and cable cars within the scenic area. The large language model then generates route planning, transportation information, and merchant information using text descriptions, charts, and map annotations. Furthermore, it engages in multi-turn dialogues based on user needs to modify the information. The Merchant Assistant module builds a database of merchants' sales, inventory, and financial information. When the large language model completes a user-initiated reservation or purchase request, it automatically records the transaction data into the database. Merchants' own inventory and financial changes are also stored in the database through manual entry or large language model-assisted entry. Based on tourist inquiries, the large language model filters eligible merchants from the database and provides their business information to the tourist. Furthermore, based on the tourist's reservation needs, it extracts key reservation information from the user's question and sends it to the online reservation platform, processing reservations according to reservation rules and priorities. Through the online reservation platform's API interface, the Merchant Assistant module can interact with the platform, extracting relevant information... The system completes the booking process based on the received booking information; it uses the payment platform's payment system to generate a payment link or QR code based on the booking or purchase information and provides feedback to the tourist; after the payment is completed, it provides the tourist with immediate feedback on whether the booking was successful or unsuccessful; it uses a large language model to deeply mine and analyze the merchant's sales information, calculate operating indicators, and perform sentiment analysis and keyword extraction on the text data of tourist reviews, classifying and summarizing tourist satisfaction, opinions, and suggestions; when the merchant needs to conduct an operating status analysis, it uses a large language model to read inventory and financial change information from the database, calculates key indicators such as sales volume, profit margin, and inventory turnover rate, analyzes operating trends and potential problems by comparing with historical and industry data, and generates an operating status analysis report, which is then fed back to the merchant through the large language model. The government back-end management assistant module collects transaction and revenue data from scenic area merchants, as well as user review data. It analyzes tourism revenue trends through large language models and extracts key information by combining text and structured data to evaluate the business behavior of merchants. The government back-end management assistant module also interacts with meteorological, traffic, and public safety monitoring systems in real time. It uses large language models to analyze meteorological and traffic information in real time, quickly identify key issues and needs, and generate emergency command strategies and action plans by combining manually set emergency plan rules.

2. The multi-role assistant system based on a large language model in a cultural tourism scenario according to claim 1, characterized in that, The tourist assistant module's tourism database periodically collects and updates detailed information about tourist destinations from public databases and online resources, including attraction information, opening hours, distances between attractions, and transportation methods.

3. A multi-role assistant system based on a large language model in a cultural tourism scenario according to claim 1, characterized in that, The merchant's business information includes the merchant's operating hours, business scope, product information, and preferential policies.

4. A multi-role assistant system based on a large language model in a cultural tourism scenario according to claim 1, characterized in that, The Merchant Assistant module builds and maintains a question bank for tourists, categorizes and statistically analyzes common tourist questions and answers from a large language model, and adds them to the list of common questions.

5. A multi-role assistant system based on a large language model in a cultural tourism scenario according to claim 1, characterized in that, The government back-end management assistant module uses a large language model to generate detailed monthly, quarterly, and annual reports, which are presented in a combination of charts and text.

6. A multi-role assistant device based on a large language model for cultural and tourism scenarios, comprising a memory and one or more processors, wherein the memory stores executable code, characterized in that, When the processor executes the executable code, it implements a multi-role assistant system based on a large language model in a cultural and tourism scenario as described in any one of claims 1-5.

Images