Advanced New Technologies Co., Ltd.

Qing Lu

Tao Chen

Wei Xia

Xinyi Fu

Weijia Yang

Tengfei Liu

Systems, methods, and storage media for location information processing are disclosed. An example of a method comprises: obtaining transaction information from user terminals of a plurality of users using a service provided by a service provider, the transaction information comprising a plurality of pieces of location information of the user terminals; clustering, using an algorithm, the plurality of pieces of location information into a plurality of areas; determining a transaction attribute corresponding to each area in the plurality of areas, the transaction attribute comprising a number of users in a corresponding area and a number of transactions of users using the service in the corresponding area; determining, according to information entropy values of the transaction attributes, a dispersity of the service provided by the service provider according to a number of areas in the plurality of areas and a plurality of transaction attributes corresponding to the plurality of areas.

Location information processing method and apparatus

A computer-implemented method comprises: receiving a first address and a second address, the first address including n morphemes and the second address including m morphemes, wherein a morpheme is a smallest semantic unit in the address, and wherein n and m are both natural numbers; determining first correlation values between the n morphemes and the m morphemes; obtaining, based on the first correlation values and a preset algorithm, a second correlation value between the first address and the second address; and analyzing a correlation between the first address and the second address based on the second correlation value.

Address analysis using morphemes

One or more implementations of the present specification provide a risk identification model building method, and a risk identification method. From data of a target user, user state records of the target user within a predetermined duration of time are extracted, wherein the user state records include a plurality of user operations and/or a plurality of system events. The user state records are sorted based on corresponding occurrence times. A user state sequence is generated based on sorted user state records. The generated user state sequence is converted into a sequence feature. A risk identification result is generated based on a previously trained risk identification model that takes as input the sequence feature generated from the user state sequence.

Growing community of inventors

Hangzhou, China

Qing Lu