JTB and two other Japanese companies said Wednesday that they will launch services employing drones to shoot videos from the sky of customers at tourist spots. The travel agency, drone business operator Fly and Japan Airlines expect their services to help spread the attractions of tourist spots. Drones will start video-recording after customers scan quick response codes prepared at tourist spots and complete payments via a website. Customers will receive one or two minutes of video footage edited automatically by artificial intelligence about 30 minutes after recording. The services will cost 2,000 per use.

Chat dialogues contain considerable useful information about a speaker's interests, preferences, and experiences.Thus, knowledge from open-domain chat dialogue can be used to personalize various systems and offer recommendations for advanced information.This study proposed a novel framework SumRec for recommending information from open-domain chat dialogue.The study also examined the framework using ChatRec, a newly constructed dataset for training and evaluation. To extract the speaker and item characteristics, the SumRec framework employs a large language model (LLM) to generate a summary of the speaker information from a dialogue and to recommend information about an item according to the type of user.The speaker and item information are then input into a score estimation model, generating a recommendation score.Experimental results show that the SumRec framework provides better recommendations than the baseline method of using dialogues and item descriptions in their original form. Our dataset and code is publicly available at https://github.com/Ryutaro-A/SumRec

In today's society, information overload presents challenges in providing optimal recommendations. Consequently, the importance of dialogue systems that can discern and provide the necessary information through dialogue is increasingly recognized. However, some concerns existing dialogue systems rely on pre-trained models and need help to cope with real-time or insufficient information. To address these concerns, models that allow the addition of missing information to dialogue robots are being proposed. Yet, maintaining the integrity of previous conversation history while integrating new data remains a formidable challenge. This paper presents a novel system for dialogue robots designed to remember user-specific characteristics by retaining past conversation history even as new information is added.

In recent years, large language models (LLMs) have rapidly proliferated and have been utilized in various tasks, including research in dialogue systems. We aimed to construct a system that not only leverages the flexible conversational abilities of LLMs but also their advanced planning capabilities to reduce the speaking load on human interlocutors and efficiently plan trips. Furthermore, we propose a method that divides the complex task of a travel agency into multiple subtasks, managing each as a separate phase to effectively accomplish the task. Our proposed system confirmed a certain level of success by achieving fourth place in the Dialogue Robot Competition 2023 preliminaries rounds. We report on the challenges identified through the competition.

An AI has created hilarious postcard images of popular British tourist attractions, based solely on snippets from one-star Trip Advisor reviews. Text-to-image tool DALL-E, released by artificial intelligence firm OpenAI, is able to create images and artwork from text prompts. UK rental agency My Favourite Cottages used it to reimagine tourist spots including Stonehenge, Angel of the North, Brighton Palace Pier and Cornwall's Eden Project. Some of the results have a passing resemblance to the real thing, while others are like a window into a dystopian nightmare. DALL-E relies on artificial neural networks (ANNs), which simulate the way the brain works in order to learn.

China's internet giant Baidu has started mass producing the country's first autonomous minibus as the company prepares to roll them out in tourist spots and airports. The eight-seater Apolong, about one-third of the size of a normal bus, has no steering wheel, driver's seat, accelerator or brake, Baidu announced on Wednesday at its annual developers' conference in Beijing. The driverless bus was co-developed by Baidu and Chinese commercial vehicle maker King Long and is powered by Apollo's autonomous driving operating system, Apollo 3.0. China's internet giant Baidu has started mass producing the country's first autonomous minibus as the company prepares to roll them out in tourist spots and airports Robin Li, CEO of search giant Baidu, speaks in front of an image of the Apolong, China's first L4 fully autonomous bus, during the Baidu Create 2018 held in Beijing on Wednesday The autonomous bus can complete obstacle avoidance, swerving and automatic transshipment without any human intervention, according to Xinhua News. Video footage released by Baidu - often referred to as China's Google - shows the company's massive manufacturing facility in Xiamen, in south-east China's Fujian province.

Travel-planning app Gogobot will help you find fun things to do, whether you are traveling for work, on vacation, or just hanging out in your home town. The company just released a new version makes that's even smarter in finding out exactly what you might want to do. It's now using "artificial intelligence to predict what you are looking for and highlight recommendations before you even start typing," CEO Travis Katz tells tells us. Gogobot's claim to fame is a concept called "tribes" in which you match yourself to others with similar interests. This might be foodies, budget-conscious students, adventurer and/or families.