# US 2015/0309962 A1 · Method and apparatus for modeling a population to predict individual behavior using location data from social network messages

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2015/0309962 A1
- Document ID: US20150309962A1
- Status: Published application
- Kind: A1
- Application number: 14/262,391
- Filed: 2014-04-25
- Published: 2015-10-29
- Earliest claimed: 2014-04-25
- Assignees: Xerox Corporation
- Applicants: Xerox Corporation
- Inventors: MOSHE LICHMAN; Wei Peng; Tong Sun; Ming Yang
- Web page: https://patentgrep.com/patent/US20150309962A1

## CPC

- H04L 51/52: for supporting social networking services
- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06Q 10/063: Operations research, analysis or management
- G06Q 10/10: Office automation; Time management
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- H04L 67/52: specially adapted for the location of the user terminal
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- H04W 4/029: Location-based management or tracking services
- G06F 2221/2111: Location-sensitive, e.g. geographical location, GPS
- G06Q 10/40: Business processes related to social networking or social networking services
- H04L 51/222: using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area
- H04W 4/02: Services making use of location information
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method, non-transitory computer readable medium, and apparatus for predicting a location behavior of at least one individual are disclosed. For example, the method receives a plurality of social networking messages having spatial location data and user identification information, filters the plurality of social networking messages to remove one or more of the plurality of social networking messages that are not related to mobility of a user to create a filtered plurality of social networking messages, creates a population model by applying a kernel density estimation to the filtered plurality of social networking messages, creates an individual model for each different user identification by applying the kernel density estimation to a subset of the filtered plurality of social networking messages for the each different user identification and generates a probability density function map that predicts the location behavior of the at least one individual.

## Claims

### Claim 1

A method for predicting a location behavior of at least one individual, comprising:
receiving, by a processor, a plurality of social networking messages having spatial location data and user identification information;
filtering, by the processor, the plurality of social networking messages to create a filtered plurality of social networking messages related to mobility of users;
creating, by the processor, a population model by applying a kernel density estimation to the filtered plurality of social networking messages;
creating, by the processor, an individual model for each different user identification by applying the kernel density estimation to a subset of the filtered plurality of social networking messages for the each different user identification; and
generating, by the processor, a probability density function map that predicts the location behavior of the at least one individual using a mixture model based upon the individual model of the at least one individual and the population model.

### Claim 2 (depends on 1)

The method of claim 1, wherein the at least one individual comprises a group of individuals.

### Claim 3 (depends on 1)

The method of claim 1, wherein the spatial location data comprises global positioning system (GPS) coordinates.

### Claim 4 (depends on 1)

The method of claim 1, wherein the filtering comprises:
removing, by the processor, a first one or more of the plurality of social networking messages that are from stationary bots;
combining, by the processor, a second one or more of the plurality of social networking messages that are from a user within a predefined time period and within a predefined distance; and
removing, by the processor, a third one or more of the plurality of social networking messages that are from a weekend.

### Claim 5 (depends on 1)

The method of claim 1, wherein the kernel density estimation function is calculated in accordance with a first equation:
pdf

(
x
)
=
1
n

∑
i
=
1
n


K
H

(
x
-
x
i
)
,
n
=

D

,
wherein pdf(x) is a probability density function of a location vector x comprising (x,y) coordinates, KH is a kernel function of the location vector x and an individual location vector xi and |D| is a total number of the filtered plurality of social networking messages.

### Claim 6 (depends on 5)

The method of claim 5, wherein the kernel function KH is calculated in accordance with a second equation:
K
H

(
x
)
=

H

-
0.5
*
(
2

π
)
-
d
2


-
1
2

x
T

H
-
0.5

x
,
wherein H represents a bandwidth on each dimension, d, of a density of each training data point and T represents a transpose function.

### Claim 7 (depends on 6)

The method of claim 6, wherein H is a diagonal matrix with diagonal values of 0:001.

### Claim 8 (depends on 1)

The method of claim 1, wherein mixture model comprises an equation:
pdf(xi)=α*ModelDi+(1−α)*ModelD,
wherein α is a value that varies based upon a number of filtered social networking messages available for an individual, ModelDi represents the individual model created by the kernel density estimation and ModelD represents the population model created by the kernel density estimation.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
calculating, by the processor, a surprise index value based upon a comparison of a location of the at least one individual determined from a new social networking message and a probability that the at least one individual is at the location obtained from the probability density function map of the at least one individual.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
detecting, by the processor, an event based on the surprise index value exceeding a threshold value.

### Claim 11 (depends on 10)

The method of claim 10, wherein the event comprises a fraud event.

### Claim 12

A non-transitory computer-readable medium storing a plurality of instructions which, when executed by a processor, cause the processor to perform operations for predicting a location behavior of at least one individual, the operations comprising:
receiving a plurality of social networking messages having spatial location data and user identification information;
filtering the plurality of social networking messages to remove one or more of the plurality of social networking messages that are not related to mobility of a user to create a filtered plurality of social networking messages;
creating a population model by applying a kernel density estimation to the filtered plurality of social networking messages;
creating an individual model for each different user identification by applying the kernel density estimation to a subset of the filtered plurality of social networking messages for the each different user identification; and
generating a probability density function map that predicts the location behavior of the at least one individual using a mixture model based upon the individual model of the at least one individual and the population model.

### Claim 13 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein the filtering comprises:
removing a first one or more of the plurality of social networking messages that are from stationary bots;
combining a second one or more of the plurality of social networking messages that are from a user within a predefined time period and within a predefined distance; and
removing a third one or more of the plurality of social networking messages that are from a weekend.

### Claim 14 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein the kernel density estimation function is calculated in accordance with a first equation:
pdf

(
x
)
=
1
n

∑
i
=
1
n


K
H

(
x
-
x
i
)
,
n
=

D

,
wherein pdf(x) is a probability density function of a location vector x comprising (x,y) coordinates, KH is a kernel function of the location vector x and an individual location vector xi and |D| is a total number of the filtered plurality of social networking messages.

### Claim 15 (depends on 14)

The non-transitory computer-readable medium of claim 14, wherein the kernel function KH is calculated in accordance with a second equation:
K
H

(
x
)
=

H

-
0.5
*
(
2

π
)
-
d
2


-
1
2

x
T

H
-
0.5

x
,
wherein H represents a bandwidth on each dimension, d, of a density of each training data point and T represents a transpose function.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein H is a diagonal matrix with diagonal values of 0:001.

### Claim 17 (depends on 12)

The non-transitory computer-readable medium of claim 12, wherein mixture model comprises an equation:
pdf(xi)=α*ModelDi+(1−α)*ModelD,
wherein α is a value that varies based upon a number of filtered social networking messages available for an individual, ModelDi represents the individual model created by the kernel density estimation and ModelD represents the population model created by the kernel density estimation.

### Claim 18 (depends on 12)

The non-transitory computer-readable medium of claim 12, further comprising:
calculating a surprise index value based upon a comparison of a location of the at least one individual determined from a new social networking message and a probability that the at least one individual is at the location obtained from the probability density function map of the at least one individual.

### Claim 19 (depends on 12)

The non-transitory computer-readable medium of claim 12, further comprising:
detecting an event based on the surprise index value exceeding a threshold value.

### Claim 20

A method for predicting a location behavior of at least one individual, comprising:
receiving, by a processor, a plurality of social networking messages within a region having global positioning satellite coordinates and user identification information;
filtering, by the processor, the plurality of social networking messages to remove one or more of the plurality of social networking messages that are not related to mobility of a user to create a filtered plurality of social networking messages;
creating, by the processor, a population model by applying a kernel density estimation to the filtered plurality of social networking messages;
creating, by the processor, an individual model for each different user identification by applying the kernel density estimation to a subset of the filtered plurality of social networking messages for the each different user identification; and
generating, by the processor, a probability density function map that predicts the location behavior of the at least one individual as a percentage value in a plurality of different locations within the region and outside of the region using a mixture model based upon the individual model of the at least one individual and the population model, wherein the mixture model weights the population model greater as a number of data points used for the individual model decreases.
