Beijing Didi Infinity Technology and Development Co., Ltd.

Beijing Xiaomi Mobile Software Co., Ltd.

Beijing Xiaomi Pinecone Electronics Co., Ltd.

Zhihua Chang

Zang Li

Lifeng Cao

Hongbo Ling

Fan Yang

Yuexiang Liu

Bin Qin

Wenjun Yang

Xiang Xu

Ranran Hou

Chengzhen Duan

A method includes obtaining a query content. The query content includes segment information representing a to-be-recognized audio. The method further includes selecting the preset quantity of candidate audios corresponding to the query content from a preset library. Each candidate audio includes a candidate audio segment matched with the segment information. The method further includes inputting the candidate audio segment into a trained detection model so as to obtain target segment information including the segment information and a target audio where the target segment information is located.

Audio recognition method, electronic device and storage medium

A method for user mining is provided. The method may include obtaining a plurality of first feature vectors of a plurality of positive samples and a plurality of second feature vectors of a plurality of negative samples, and generating a plurality of expanded first feature vectors based on the plurality of first feature vectors and second feature vectors and expanded second feature vectors. Each first feature vector may include first feature information that describes a plurality of features of a corresponding positive sample. Each second feature vector may include second feature information that describes a plurality of features of a corresponding negative sample. The method may further include determining one or more core features related to the plurality of positive samples among the plurality of features corresponding to the plurality of first feature vectors based on a trained binary model.

Systems and methods for user analysis

A method for querying data is provided. The method may include determining a characteristic value of a selected feature dimension among feature values of the selected feature dimension of plurality of entities and establishing a corresponding relationship between the characteristic value and the selected feature dimension. The method may also include caching the corresponding feature value into a cache memory for each entity having a feature value of the selected feature dimension being unequal to the characteristic value, and leaving the corresponding feature value without caching for each entity having a feature value of the selected feature dimension being equal to the characteristic value. The method may further include performing a first search in the cache memory to produce a first search result in response to a query request related to the plurality of entities, and generating a query result based on the corresponding relationship and the first search result.

Systems and methods for data processing

Growing community of inventors

Beijing, China

Zhihua Chang