Abstract: A method and apparatus for pushing information are provided. A specific embodiment of the method includes: sending, in response to receiving first search query sent by a terminal, a search result page including at least one image matching the first search query to the terminal, for a user to select a to-be-browsed target image from the at least one image, the target image being linked to a detail page having a search function including the target image; acquiring, in response to receiving a request for browsing the target image sent by the terminal, the detail page linked to the target image; generating recommendation information based on the target image and the first search query, and adding the recommendation information to the detail page; and pushing the detail page having the added recommendation information to the terminal. This embodiment realizes a targeted information push.

Abstract: A method and apparatus for identifying a demand are provided. A specific embodiment of the method includes: acquiring a user's query sentence and access data corresponding to a search result obtained by searching the user's query sentence; querying network data corresponding to the user's query sentence in a pre-stored query sentence dictionary; identifying the target category of demand of the user's query sentence using a trained demand identification model based on the network data; counting the access data based on categories of demand, to obtain access data distribution of the user's query sentence on each of the categories of demand; and determining a demand intensity of the target category of demand of the user's query sentence based on an identification result of the target category of demand of the user's query sentence and the access data distribution. The embodiment improves the accuracy in identifying a demand.

Abstract: Embodiments of the present invention disclose a query result bottom retrieval method and apparatus. The query result bottom retrieval method includes: acquiring, from a resource library and based on a user input target query, query resources associated with the user input target query; acquiring comparative scoring characteristics of each of the query resources, the comparative scoring characteristics including base relevance characteristics; inputting the comparative scoring characteristics of each of the query resources into a pre-trained rank model, to acquire relevance scoring values corresponding to the query resources and output by the rank model, the rank model being a GBRank model; and ranking the query resources based on the relevance scoring values, and selecting, according to the ranking result, a set number of target resources as a bottom retrieval result corresponding to the target query.

Abstract: The present disclosure provides a method and apparatus for sorting related searches RS, wherein the method comprises: obtaining a query and obtaining RSes corresponding to the query; determining estimated click rates of the RSes respectively according to a click estimating model obtained from pre-training; sorting the RSes in a descending order according to the estimated click rates. The solutions of the present disclosure can improve the accuracy of the sorting results.

Abstract: A method and apparatus for identifying a demand are provided. A specific embodiment of the method includes: acquiring a user's query sentence and access data corresponding to a search result obtained by searching the user's query sentence; querying network data corresponding to the user's query sentence in a pre-stored query sentence dictionary; identifying the target category of demand of the user's query sentence using a trained demand identification model based on the network data; counting the access data based on categories of demand, to obtain access data distribution of the user's query sentence on each of the categories of demand; and determining a demand intensity of the target category of demand of the user's query sentence based on an identification result of the target category of demand of the user's query sentence and the access data distribution. The embodiment improves the accuracy in identifying a demand.

Abstract: A method and apparatus for pushing information are provided. A specific embodiment of the method includes: sending, in response to receiving first search query sent by a terminal, a search result page including at least one image matching the first search query to the terminal, for a user to select a to-be-browsed target image from the at least one image, the target image being linked to a detail page having a search function including the target image; acquiring, in response to receiving a request for browsing the target image sent by the terminal, the detail page linked to the target image; generating recommendation information based on the target image and the first search query, and adding the recommendation information to the detail page; and pushing the detail page having the added recommendation information to the terminal. This embodiment realizes a targeted information push.

Abstract: The present disclosure provides a method and apparatus for sorting related searches RS, wherein the method comprises: obtaining a query and obtaining RSes corresponding to the query; determining estimated click rates of the RSes respectively according to a click estimating model obtained from pre-training; sorting the RSes in a descending order according to the estimated click rates. The solutions of the present disclosure can improve the accuracy of the sorting results.

Abstract: Embodiments of the present invention disclose a query result bottom retrieval method and apparatus. The query result bottom retrieval method includes: acquiring, from a resource library and based on a user input target query, query resources associated with the user input target query; acquiring comparative scoring characteristics of each of the query resources, the comparative scoring characteristics including base relevance characteristics; inputting the comparative scoring characteristics of each of the query resources into a pre-trained rank model, to acquire relevance scoring values corresponding to the query resources and output by the rank model, the rank model being a GBRank model; and ranking the query resources based on the relevance scoring values, and selecting, according to the ranking result, a set number of target resources as a bottom retrieval result corresponding to the target query.