摘要:
In a method for a direct answer for search, a search query is received over a network, one or more answer candidate snippets for the search query are received, with an answer candidate snippet having at least a portion of content available over the network for an answer candidate, one or more answer entities are determined within a selected answer candidate snippet, a frequency of the one or more answer entities found within the one or more answer candidate snippets for the search query is determined, a confidence score is adjusted for the selected answer candidate in accordance with the frequency of the one or more answer entities found within the one or more answer candidate snippets, and at least one answer candidate snippet is sent for a response to the search query.
摘要:
In a method for a direct answer for search, a search query is received over a network, one or more answer candidate snippets for the search query are received, with an answer candidate snippet having at least a portion of content available over the network for an answer candidate, one or more answer entities are determined within a selected answer candidate snippet, a frequency of the one or more answer entities found within the one or more answer candidate snippets for the search query is determined, a confidence score is adjusted for the selected answer candidate in accordance with the frequency of the one or more answer entities found within the one or more answer candidate snippets, and at least one answer candidate snippet is sent for a response to the search query.
摘要:
In a method for a direct answer for search, a search query is received over a network, one or more answer entities are determined from one or more answer candidate snippets, with an answer candidate snippet having at least a portion of content available over the network for an answer candidate, a content identifier is determined for an answer candidate, a title is tokenized for the content identifier, a comparison is performed between a vector of tokens for the title and a vector of the one or more answer entities, an indicator of the relevance is adjusted for the content identifier in accordance with the comparison, and at least one answer candidate snippet is sent for a response to the search query.
摘要:
In a method for a direct answer for search, a search query is received over a network, one or more answer entities are determined from one or more answer candidate snippets, with an answer candidate snippet having at least a portion of content available over the network for an answer candidate, a content identifier is determined for an answer candidate, a title is tokenized for the content identifier, a comparison is performed between a vector of tokens for the title and a vector of the one or more answer entities, an indicator of the relevance is adjusted for the content identifier in accordance with the comparison, and at least one answer candidate snippet is sent for a response to the search query.
摘要:
A correlator extracts a plurality of related queries corresponding to each one of a plurality of answers. A classifier matches each one of the related queries corresponding to the answer with a category. A statistical tool determines the relevance of each category relative to the categories matched to the related queries corresponding to the answers.
摘要:
Methods and systems for generating query and result-based relevance indexes are provided. For one embodiment, a plurality of queries is received from a plurality of users. Each query of the plurality of queries is measured based on one or more metrics. The measured data of each query is stored. The queries are associated into topical query categories. A performance of a first query category is calculated based on at least one metric of the one or more metrics. A metric data request for a select category is received from a client. Lastly, the stored measured data of the selected category is transmitted to the client in response to the metric data request.
摘要:
The invention provides a computer system, including a memory, a plurality of answers stored in the memory, and a classifier for matching each one of the answers with a category among a plurality of categories.
摘要:
Methods and systems for generating query and result-based relevance indexes are provided. For one embodiment, a plurality of queries is received from a plurality of users. Each query of the plurality of queries is measured based on one or more metrics. The measured data of each query is stored. The queries are associated into topical query categories. A performance of a first query category is calculated based on at least one metric of the one or more metrics. A metric data request for a select category is received from a client. Lastly, the stored measured data of the selected category is transmitted to the client in response to the metric data request.
摘要:
According to one aspect of the invention, a method for managing the navigation of a visitor to the World Wide Web is provided. A target profile is determined based on a combination of at least two known properties and a navigation path is associated with the target profile. The at least two known properties are related to the at least one of a query, world knowledge, and information about a visitor to the World Wide Web. The visitor may be automatically directed along the navigation path.
摘要:
Methods and systems for providing a response to a query. Multiple users' search engine activity in regard to a query is correlated. A response is provided based upon this correlated search engine activity information. For one embodiment of the invention, in the context of search engine result optimization, the user activity and/or user information of multiple users, during a search session, is correlated with queries to effect an evolving association between queries and the organization and presentation of documents. Systems in accordance with such embodiments employ the ability to store users' activity over the entire search session, thus making possible the correlation of a number of different types of user activity and user information. The use of correlated user input allows such systems to provide relevant search results without the limitations imposed by the key-word-based systems of the prior art.