US 12,314,984 B2
Method and apparatus for displaying product review information, electronic device and storage medium
Yingshuai Wang, Beijing (CN); Xiaoxia Li, Beijing (CN); and Shiyu Miao, Beijing (CN)
Assigned to BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY CO., LTD., Beijing (CN); and BEIJING JINGDONG CENTURY TRADING CO., LTD., Beijing (CN)
Appl. No. 17/635,016
Filed by BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY CO., LTD., Beijing (CN); and BEIJING JINGDONG CENTURY TRADING CO., LTD., Beijing (CN)
PCT Filed Mar. 27, 2020, PCT No. PCT/CN2020/081573
§ 371(c)(1), (2) Date Feb. 14, 2022,
PCT Pub. No. WO2021/036250, PCT Pub. Date Mar. 4, 2021.
Claims priority of application No. 201910807718.4 (CN), filed on Aug. 29, 2019.
Prior Publication US 2022/0292587 A1, Sep. 15, 2022
Int. Cl. G06Q 30/00 (2023.01); G06F 40/30 (2020.01); G06F 40/44 (2020.01); G06Q 30/0282 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 30/0282 (2013.01) [G06F 40/30 (2020.01); G06F 40/44 (2020.01); G06Q 30/0641 (2013.01)] 15 Claims
OG exemplary drawing
 
7. A method for displaying product comment information, executed by a server and comprising:
acquiring product comment information of a user, wherein the product comment information comprises a comment text;
in response to determining that the product comment information further comprises a comment image, inputting both of the comment text and the comment image together into a pre-established first model for an image-text consistency detection, and in response to detecting that the comment text and the comment image are consistent, saving the product comment information having the consistent comment text and comment image into a display list; and
returning the product comment information in the display list to a user terminal to display to the user;
wherein after conducting a word segmentation on a pre-processed comment text by using a word segmentation logic, the method further comprises:
for the comment text, determining a value of the comment text regarding to each of preset text feature types based on the preset text feature types and value ranges corresponding to respective preset text feature types, and determining comment feature values of the comment text based on values of the comment text regarding to respective text feature types,
wherein the text feature type is used to describe different types of features that the comment text has, and the comment feature values are a collection of specific values determined for respective text feature types of the comment text; and
wherein returning the product comment information in the display list to the user terminal to display to the user comprises:
acquiring personalized comment demand information of the user, wherein the personalized comment demand information comprises the comment feature values;
based on the comment feature values contained in the personalized comment demand information, determining a comment text that conforms to the comment feature values from the display list;
screening out product comment information corresponding to the determined comment text that conforms to the comment feature values to generate the screened product comment information; and
returning the screened product comment information to the user terminal to display to the user.