Bing has announced the launch of a new feature called “Deep Search” that aims to provide more relevant and detailed answers to complex search queries. The feature uses advanced natural language processing and deep learning techniques to understand the intent and context of the user’s query and then generate a comprehensive answer from multiple sources of information.
Según Bing, la ‘Búsqueda profunda’ puede manejar consultas que involucran múltiples entidades, atributos, comparaciones o condiciones, como “las mejores computadoras portátiles para juegos por menos de $ 1000” o “las 10 mejores películas de 2023 según la clasificación de IMDb”. La función también puede responder preguntas que requieren razonamiento o inferencia, como “por qué el cielo es azul” o “cómo prevenir el calentamiento global”.
The feature is designed to help users save time and effort by providing them with a single answer that covers all aspects of their query, rather than having to navigate through multiple web pages or links. The feature also allows users to refine or expand their query by using interactive filters or suggestions that appear below the answer.
Bing says ‘Deep Search’ is the result of years of research and development, and leverages the latest innovations in artificial intelligence and big data. Currently, the feature is available in English for selected topics and domains, such as products, movies, health and education. Bing plans to expand the coverage and scope of the feature in the future, as well as support more languages and regions.
Microsoft Bing is getting a new “Deep Search” feature powered by OpenAI’s GPT-4. The feature is designed to provide users with more relevant and complete answers to complex search queries. Microsoft notes that Deep Search does not replace Bing’s existing Web search, but is an enhancement that enables deeper exploration of the Web.
In a blog post, Microsoft explains that the new feature builds on Bing’s existing Web index and ranking system and enhances it with GPT-4, which takes the search query and turns it into a more complete description of what the results should include.
For example, suppose a user searches for loyalty programs in different countries and enters the query: “How do points systems work in Japan?”. Deep Search would take the query and expand it to the following:
Provide an explanation of how the various loyalty card programs work in Japan, including the benefits, requirements and limitations of each. Include examples of popular loyalty cards from different categories, such as convenience stores, supermarkets and restaurants. Show a comparison of the advantages and disadvantages of using loyalty cards versus other payment methods in Japan, including current rewards and benefits. Highlight the most popular services and participating merchants.
With this extended description, you will be able to explain your intention better than with a few words.
In cases where your search query is more ambiguous, Deep Search will find all possible intents and create a full description for each of them. Deep Search then shows you these intents, allowing you to select the correct one.
Below is an example of how deep search works in practice:
How do point systems work in Japan?
In-depth search Intent 1: Provide an overview of how points systems work in Japan, including the history, culture and legal aspects of loyalty programs. Explain how points are earned, redeemed and exchanged in different scenarios. Compare Japan’s points systems with those of other countries, such as the U.S., U.K. and China.
Deep Search Intent 2: Provide guidance on how to use points systems in Japan, including tips on how to register, manage and maximize your points. Recommend the best loyalty cards for different purposes, such as travel, shopping, dining and entertainment. Provide links to useful resources and websites for finding deals and discounts with points.
In-depth search intent 3: Provide a review of how points systems work in Japan, including the pros and cons of loyalty programs. Share your personal experience and opinion on the use of points in Japan. Discuss the challenges and opportunities of points systems in Japan, such as fraud prevention, customer satisfaction and innovation.
You can choose one of these intentions or enter a different query if none of them match your needs.
`
Bing has introduced a new feature called Deep Search that allows users to get more detailed and relevant results for complex queries. Deep Search works by creating an expanded description of the user’s query based on their intent and context. For example, if a user searches for “how to use loyalty points in Japan,” Deep Search will generate a description that includes information such as the types of loyalty programs available in Japan, the best ones for travelers, how to redeem them and how to manage them with phone apps.
Deep Search then uses this description to find web pages that may not contain the exact keywords in the query, but are still relevant and informative. Deep Search also rewrites the query in different ways to cover different aspects of the topic. For example, Deep Search can also search for “loyalty card programs in Japan,” “best loyalty cards for travelers in Japan,” “loyalty program comparison by category in Japan,” “redeem loyalty cards in Japan,” and “manage loyalty points with phone apps.”
Deep Search then ranks web pages based on how well they match the extended description. Deep Search considers factors such as topic relevance, level of detail, trustworthiness, freshness and page popularity. In this way, Deep Search can provide users with more complete and targeted answers than Bing’s normal search.
Deep search is an optional feature that can take up to 30 seconds to complete. It is not designed for all queries or users, but for those who want to explore a topic in depth and get more information. Users who prefer faster and simpler results can still use the normal Bing search without Deep Search.
