System and method for destination predicting

Patent metadata

Field	Value
Publication number	US-2020221257-A1
Application number	US-202016798481-A
Country	US
Kind code	A1
Filing date	Feb 24, 2020
Priority date	Aug 24, 2017
Publication date	Jul 9, 2020
Grant date	—

Abstract

A system includes at least one non-transitory storage medium storing a set of instructions and at least one processor in communication with the at least one non-transitory storage medium. When executing the set of instructions, the at least one processor may be directed to cause the system to obtain a service request signal sent from a user terminal via wireless communication, wherein the service request signal encodes identifier data, a first departure location, and a first departure time; retrieve one or more historical records related to the identifier data, wherein a historical record includes a historical departure location, historical departure time and a historical destination location; determine, using a pre-stored destination matching algorithm, a selection probability of the one or more historical destination location; determine, based on the selection probability, a suggested destination location, which is the same as the one or more historical destination locations.

First claim

1 . A system configured to provide a predicted destination to a user, comprising:
at least one non-transitory storage medium including a set of instructions; and at least one processor in communication with the at least one non-transitory storage medium, wherein when executing the set of instructions, the at least one processor is directed to:
obtain a service request signal sent from a user terminal via wireless communication, wherein the service request signal encodes identifier data, a first departure location, and a first departure time;
retrieve one or more historical records related to the identifier data, wherein a historical record includes a historical departure location, historical departure time and a historical destination location;
determine, using a pre-stored destination matching algorithm, a selection probability of the one or more historical destination location;
determine, based on the selection probability, a suggested destination location, which is the same as the one or more historical destination locations; and
generate and display an indicator signifying the suggested destination location on a user interface of the user terminal.

2 . The system of claim 1 , wherein the at least one processor is further directed to:
determine the one more historical records matching the first departure location and/or the first departure time; determine the selection probability, for each historical destination location of the one or more historical records matching the first departure location and/or the first departure time.

3 . The system of claim 2 , wherein to determine the selection probability related to the first departure location and the first departure time for each historical destination location of the one or more historical records, the at least one processor is further directed to:
determine a first posterior probability, related to the first departure location, for each historical destination location of the one or more historical records, based on the historical departure location and the historical destination location of the one or more historical records; determine a second posterior probability, related to the first departure time, for each historical destination location of the one or more historical records, based on the historical departure time and the historical destination location of the one or more historical records; and determine the selection probability, related to the first departure location and the first departure time, for each historical destination location of the one or more historical records, based on the first posterior probability, the second posterior probability, and the prior probability.

4 . The system of claim 3 , wherein to determine the selection probability related to the first departure location and the first departure time for each historical destination location of the one or more historical records, the at least one processor is further directed to:
determine the selection probability according to equation:

P


(

D
m


F

,
T

)

=

P


(

F


D
m

)



P


(

T


D
m

)

*

P


(

D
m

)

∑

m
=
1

N





P


(

F


D
m

)



P


(

F
,

T


D
m

)

*

P


(

D
m

)

,

wherein D m denotes an mth historical destination location, F denotes the first departure location in the service request signal, T denotes the first departure time in the service request signal, P(F|D m ) denotes the first posterior probability, P(T|D m ) denotes the second posterior probability, P(D m ) denotes the prior probability, N denotes a total number of the historical destination locations in the one or more historical destination locations, wherein 1≤m≤N, and both N and m are integers.

5 . The system of claim 2 , wherein to determine the selection probability related to the first departure location and the departure time for each historical destination location of the one or more historical records, the at least one processor is further directed to:
determine a first posterior probability, related to the first departure location, for each historical destination location of the one or more historical records, based on the historical departure location and the historical destination location of the

Assignees

• Beijing Didi Infinity Technology & Dev Co Ltd

Inventors

• Zhang Lingyu

Classifications

• H04L67/52

  specially adapted for the location of the user terminal · CPC title

• H04W4/025 Primary

  using location based information parameters · CPC title

• G06F16/3346

  using probabilistic model · CPC title

• G01C21/3617 Primary

  using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement · CPC title

• G01C21/3484 Primary

  Personalized, e.g. from learned user behaviour or user-defined profiles · CPC title