US 12,250,277 B2
Method for making recommendations to a user and apparatus, computing device, and storage medium
Zhijie Qiu, Shenzhen (CN); Jun Rao, Shenzhen (CN); Yi Liu, Shenzhen (CN); Zhou Su, Shenzhen (CN); Shukai Liu, Shenzhen (CN); Zhenlong Sun, Shenzhen (CN); Qi Liu, Shenzhen (CN); Liangdong Wang, Shenzhen (CN); Tiantian Shang, Shenzhen (CN); Mingfei Liang, Shenzhen (CN); Lei Chen, Shenzhen (CN); Bo Zhang, Shenzhen (CN); and Leyu Lin, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on May 24, 2021, as Appl. No. 17/329,128.
Application 17/329,128 is a continuation of application No. PCT/CN2020/078144, filed on Mar. 6, 2020.
Claims priority of application No. 201910312887.0 (CN), filed on Apr. 18, 2019.
Prior Publication US 2021/0279552 A1, Sep. 9, 2021
Int. Cl. G06F 17/10 (2006.01); G06F 17/16 (2006.01); G06F 18/213 (2023.01); G06N 3/04 (2023.01); G06N 3/042 (2023.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); H04L 67/306 (2022.01); H04L 67/50 (2022.01); G06V 40/20 (2022.01)
CPC H04L 67/306 (2013.01) [G06F 18/213 (2023.01); G06N 3/042 (2023.01); G06V 10/806 (2022.01); G06V 10/82 (2022.01); H04L 67/535 (2022.05); G06V 40/20 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A method for making recommendations to a user, performed by a computing device, the method comprising:
obtaining user attribute information, reading attribute information, reading history information, and candidate items;
performing intra-group information fusion on the reading attribute information according to preset groupings to obtain reading feature information;
obtaining a reading history weight according to the reading history information;
obtaining history feature information according to the reading history weight and the reading history information;
obtaining user feature information according to the user attribute information, the reading feature information, and the history feature information;
inputting the user feature information and the candidate items into a neural network, to determine similarity scores that describe degree of similarity between the user feature information and the candidate items by using an inner product algorithm or a cosine similarity; and
selecting a recommendation item from the candidate items according to the similarity scores, wherein a quantity of the candidate items exceeds 10 million, and distributed k-nearest neighbor (k-NN) servers are provided to complete on-line real-time recall for selecting the recommendation item.