Alibaba Group Holding Limited

Ning Guo

Qin Zhang

Fei Xing

Lei Hou

Yuheng Xie

Jing Dong

Tao Zhang

Jiaqing Guo

Liang Zhang

Yizhe Liu

Song Yang

Guang Qiu

Weidong Yin

A method for generating a search result includes: receiving, by an information search system, a search request; obtaining, by searching, a plurality of pieces of matching information that match the search request; obtaining a respective amount of user response associated with each of the plurality of pieces of matching information and further obtaining a total amount of user response associated with a respective categories to which each of the plurality of pieces of matching information belongs; and ranking the plurality of pieces of information to generate a search result based on the total amount of user response associated with the respective category to which each of the plurality of pieces of matching information belongs. By using the above technical scheme, a result of more rational ranking of matching information can be displayed to a user when the user performs a search, thus improving experience of the user.

Method for generating search result and system for information search

A search method is disclosed. In the method, a data rewriting system obtains, from a database, one or more search term candidates that are relevant to a present search term. The data rewriting system retrieves properties of the present search term and the one or more search term candidates, where the properties describe respective matching results of the present search term and the one or more search term candidates. Based on the matching results, the data rewriting system determines whether the present search term needs to be rewritten, and rewrites the present search term based on the matching results to provide a rewritten present search term in response to determining that the present search term needs to be rewritten. A search engine performs a search based on the rewritten present search term.

Search method, apparatus and system based on rewritten search term

Generating ranked search results includes receiving a plurality of matching information items that match a search request, ranking at least some of the plurality of matching information items using a linear ranking model that linearly combines a first plurality of feature values to obtain a first set of ranked results, ranking at least some of the first set of ranked results using a nonlinear ranking model that nonlinearly combines a second plurality of feature values to obtain a second set of ranked results, and provide a search response based on the second set of ranked results.

Generating ranked search results using linear and nonlinear ranking models

Techniques for returning estimated value of search keywords of an entire account include, for the entire account, obtaining one or more selected search keywords and their respective forecast periods and parameter settings. An estimated value of a respective search keyword in the respective forecast period is forecasted. Based on stored historical data and parameter settings of the respective search keyword, the estimated value of the respective search keyword is modified to obtain a modified estimated value. The modified estimated value of each search keyword is added up to generate an estimated value of the entire account. The estimated value of the entire account is returned to a client terminal from which the entire account is logged in. The present disclosure modifies the respective search keyword's estimated value so that the estimated value of the entire account satisfies the expected value of the client.

Returning estimated value of search keywords of entire account

Ranking search results, comprises retrieving search results that include target strings that relate to a query string; segmenting the query string and each of the target strings; pairing segments in the query string with respective segments in the target strings to form combinations; retrieving weights that correspond to the combinations; and determining a weighted word length based on the weights corresponding to each of the target strings; and ranking the target strings based on their respective weighted word lengths. Alternatively, ranking search results includes determining a minimum weight of each inserted word with respect to segments in the query string; determining a minimum weight of each deleted word with respect to segments in the target strings; determining a total edit distance for each target string; and ranking the target strings based on the total edit distances.

Ranking search results based on word weight

A method and an apparatus for identifying synonym and utilizing such synonym to conduct search is disclosed. The disclosed method includes: obtaining arbitrary two words to be identified; determining whether a shortest edit distance between the two words less than or equal to an edit distance threshold; determining whether the two words to be identified exist in a preset knowledge database, and if an answer is yes then searching a smallest granularity type with highest weight value for each word in the knowledge database; and if the two word have the same smallest granularity type with highest weight value, then determining such two words are synonyms, or non-synonym otherwise. The disclosed techniques greatly improve accuracy of synonym identification and guarantee effect of synonym identification.

Method and apparatus for identifying synonyms and using synonyms to search

Determining recommendation data is disclosed, including: extracting a first set of keywords from a set of user action logs that occurred prior to a predetermined time point and determining a weight value for at least one of the first set of keywords; extracting a second set of keywords from a set of user action logs that occurred subsequent to the predetermined time point and determining a weight value for at least one of the second set of keywords; merging at least a portion of the first set of keywords and at least a portion of the second set of keywords to obtain a third set of keywords and determining a weight value for at least one of the third set of keywords; matching the third set of keywords to a database of data that can potentially be recommended to a user; and in the event that a piece of data is determined to match at least one keyword from the third set of keywords, determine that the piece of data is to be recommended to the user.

Determination of recommendation data

A search system includes: a data rewriting system that obtains, from a database, one or more search term candidates that are relevant to a present search query. The data rewriting system retrieves properties of the present search query and the one or more search term candidates, where the properties describe respective matching results of the present search query and the one or more search term candidates. Based at least in part on the matching results, the data rewriting system determines whether or not the present search query needs to be rewritten, and rewrites the present search query based at least in part on the matching results to provide a rewritten present search query if it is determined that the present search query needs to be rewritten. A search engine performs a search based at least in part on the rewritten present search query.

Method, apparatus and system, for rewriting search queries

The present disclosure discloses a method for generating a search result and an information search system. The method for generating a search result includes: receiving, by an information search system, a search request; obtaining, by searching, a plurality of pieces of matching information that match the search request; obtaining a respective amount of user response associated with each of the plurality of pieces of matching information and further obtaining a total amount of user response associated with a respective categories to which each of the plurality of pieces of matching information belongs; and ranking the plurality of pieces of information to generate a search result based on the total amount of user response associated with the respective category to which each of the plurality of pieces of matching information belongs. By using the above technical scheme, a result of more rational ranking of matching information can be displayed to a user when the user performs a search, thus improving experience of the user.

The present disclosure introduces a method, an apparatus and memory of predicting a user behavior number of a word for reducing the amount and the complexity of operation, saving the consumption of the equipment, and improving the accuracy and reliability of predictions. In an embodiment, a historical data sequence of the user behavior number of a word is converted from a time domain to a frequency domain. Based on the converted frequency domain, each estimated cycle and its effect rate value of the historical data sequence are ascertained. If the historical data sequence is stable, an average value of user behavior numbers of some historical data points before a prediction point is calculated as a user behavior number of the prediction point. Otherwise, the user behavior number is calculated based on a selected main cycle and a selected singularity.

Predicting a user behavior number of a word

Providing online advertisements includes selecting, among a plurality of advertising sources provided by a seller, a selected plurality of advertising sources that meet a predefined condition; generating a plurality of keyword sets that correspond to the selected plurality of advertising sources; establishing a programming model according to a set of predefined constraints, wherein the programming model represents match of the selected plurality of advertising sources and the plurality of keyword sets; and determining a substantially optimal match between at least some of the plurality of advertising sources and the plurality of keyword sets by solving the programming model.

Matching of advertising sources and keyword sets in online commerce platforms

Determining recommendation data is disclosed, including: extracting a first set of keywords from a set of user action logs that occurred prior to a predetermined time point; extracting a second set of keywords from a set of user action logs that occurred subsequent to the predetermined time point; merging at least a portion of the first set of keywords and at least a portion of the second set of keywords to obtain a third set of keywords; matching the third set of keywords to a database of data that can potentially be recommended to a user; and in the event that a piece of data is determined to match at least one keyword from the third set of keywords, determine that the piece of data is to be recommended to the user.

Growing community of inventors

Hangzhou, China

Ning Guo