US 12,224,914 B2
Method, apparatus, and device for data analytics and storage medium
Yingjie Hong, Guangdong (CN); Liang Wang, Guangdong (CN); and Liya Yuan, Guangdong (CN)
Assigned to ZTE CORPORATION, Guangdong (CN)
Appl. No. 17/642,157
Filed by ZTE CORPORATION, Guangdong (CN)
PCT Filed Aug. 4, 2020, PCT No. PCT/CN2020/106792
§ 371(c)(1), (2) Date Mar. 10, 2022,
PCT Pub. No. WO2021/047332, PCT Pub. Date Mar. 18, 2021.
Claims priority of application No. 201910860091.9 (CN), filed on Sep. 11, 2019.
Prior Publication US 2022/0329493 A1, Oct. 13, 2022
Int. Cl. H04L 29/08 (2006.01); H04L 41/14 (2022.01); H04L 41/16 (2022.01)
CPC H04L 41/145 (2013.01) [H04L 41/16 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A data analytics method, comprising:
determining, by NWDAF, analytics data according to a data analytics request received from a NWDAF service consumer,
determining an analytics model according to the data analytics request; and
obtaining a data analytics result according to the analytics data and the analytics model,
wherein the data analytics request comprises at least two of: a data analytics service type, a model identifier, or an analytics result policy,
wherein the analytics result policy comprises at least one of: an accuracy of analytics result, or a return time length of analytics result,
wherein the determining analytics data according to a data analytics request comprises:
acquiring the analytics data from a 3rd Generation Partnership Project (3GPP) network according to the data analytics service type in the data analytics request;
wherein determining an analytics model according to the data analytics request; and obtaining a data analytics result according to the analytics data and the analytics model by at least one of:
determining, by the NWDAF, an analytics model according to at least one of a model type identifier or a model identifier, and running the analytics model to analyze the analytics data and obtain the data analytics result;
training, by the NWDAF, an analytics model by using the analytics data to obtain a new analytics model; running the new analytics model to analyze the analytics data to obtain a new data analytics result, judging whether the new data analytics result satisfies the analytics result policy, and returning, in response to that the new data analytics result fails to satisfy the analytics result policy, to execute the operation of training the analytics model by using the analytics data to obtain a new analytics model, until the obtained data analytics result satisfies the analytics result policy; and
acquiring, by the NWDAF, an analytics model of a third-party model owner according to at least one of a model type identifier or a model identifier, and running the analytics model to analyze the analytics data to obtain the data analytics result;
wherein obtaining a data analytics result according to the analytics data and the analytics model further by:
feeding, by the NWDAF, the data analytics result back to an analytics result receiver, wherein the analytics result receiver is determined by an analytics result receiver address.