Systems and methods for cohort identification and reporting

• US 9,454,726 B1
• Filed: 06/06/2013
• Issued: 09/27/2016
• Est. Priority Date: 06/06/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Baldwin, Andrew, Thakkar, Hetal, Yao, Jin, Lee, Calvin, Moon, Hui Sok
• Primary Examiner(s): Rifkin, Ben
• Application Number:
  US13/911,879
• Time in Patent Office: 1,209 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/0204 Market segmentation

Abstract

Systems and methods for defining a custom segment in a set of behavioral data are provided. A described method includes receiving a set of behavioral data associated with a plurality of user devices and identifying multiple cohort groups, each of the cohort groups including one or more of the user devices. The behavioral data includes a behavior metric for each of the user devices and the cohort groups are identified based on the behavior metric for each of the user devices. The method further comprises generating a segmentation interface including a graphical visualization of the multiple cohort groups and causing the segmentation interface to be presented via a user interface device. The method further comprises defining a custom segment of the behavioral data based on a user selection of one or more of the multiple cohort groups via the segmentation interface.

Claims

1. An automated computer-implemented method for defining a custom segment in a set of behavioral data, the method comprising:

receiving, at a processing circuit, a set of behavioral data associated with a plurality of user devices, the behavioral data including a behavior metric for each of the user-devices resulting from interactions on each of the user devices with at least one of (i) an application having a unique application identifier and (ii) a distributed content item having a unique content item identifier, the behavior metric identifying a particular device of the plurality of user devices, wherein the behavioral data includes retention data for each of the plurality of user devices, the retention data for each user device comprising;

a first behavior metric indicating a time at which the user device first launched an application, the time of first launch occurring within a first time period; and

a second behavior metric indicating whether the user device launched the application during one or more time periods subsequent to the first time period;

identifying, by the processing circuit, multiple cohort groups, each of the cohort groups including one or more of the user devices, the cohort groups are identified based on the behavior metric for each of the user devices, wherein identifying the multiple cohort groups includes;

identifying a plurality of discrete first-launch periods;

dividing the plurality of user devices into first-launch groups, wherein each first-launch group is associated with one of the first-launch periods and wherein a user device is assigned to a first-launch group if the time at which the user device first launched the application occurred during the first-launch period associated with the first-launch group; and

for each first-launch group;

identifying one or more discrete time periods which have elapsed since an end of the first-launch period associated with the first-launch group, and

assigning each of the user devices within the first-launch group to one or more cohort groups, wherein each cohort group is associated with one of the discrete time periods and wherein a user device is assigned to a cohort group if the user device launched the application during the discrete time period associated with the cohort group;

generating, by the processing circuit, a segmentation interface including a graphical visualization of the multiple cohort groups and causing the segmentation interface to be presented via a user interface device, each of the cohort groups in the segmentation interface is presented as a selectable icon;

receiving a user selection of one or more of the cohort groups by receiving a selection of one or more of the selectable icons presented via the segmentation interface;

defining, by the processing circuit, a custom segment of the behavioral data in response to the user selection, the custom segment is a subset of the behavioral data and is associated with a subset of the user devices; and

storing an indication of the custom segment in a non-volatile data storage device.

2. The method of claim 1, further comprises:

generating a reporting interface separate from the segmentation interface and causing the reporting interface to be presented via a user interface device, the reporting interface including a selectable representation of the custom segment;

retrieving the indication of the custom segment from the data storage device in response to a user selection of the selectable representation of the custom segment;

applying the custom segment to a second dataset associated with a plurality of user devices;

selecting a portion of the second dataset for inclusion in an analytical report, wherein the portion of the second dataset is selected based on the application of the custom segment; and

generating an analytical report using the selected portion of the second dataset, wherein the analytical report analyzes a behavior metric other than the behavior metric used to identify the cohort groups.

3. The method of claim 2, wherein the second dataset is one or more of:

the set of behavioral data received at the processing circuit;

a set of behavioral data including some of the behavioral data received at the processing circuit and some additional behavioral data; and

a set of third-party behavioral data including none of the behavioral data received at the processing circuit.

4. The method of claim 1, wherein the set of behavioral data received at the processing circuit is received from the plurality of user devices.

5. The method of claim 1, wherein the behavioral data includes multiple behavior metrics for each of the user devices, the method further comprising:

receiving a customizable user selection of a first behavior metric, wherein the multiple cohort groups are defined using the first behavior metric.

6. The method of claim 5, further comprising:

receiving a customizable user selection of a second behavior metric, wherein the multiple cohort groups are defined using both the first behavior metric and the second behavior metric.

7. A data management system for defining a custom segment in a set of behavioral data, the data management system comprising a processing circuit configured to:

receive a set of behavioral data associated with a plurality of user devices, the behavioral data including a behavior metric for each of the user devices resulting from interactions on each of the user devices with at least one of (i) an application having a unique application identifier and (ii) a distributed content item having a unique content item identifier, the behavior metric identifying a particular device of the plurality of user devices, wherein the behavioral data includes retention data for each of the plurality of user devices, the retention data for each user device comprising;

a first behavior metric indicating a time at which the user device first launched an application, the time of first launch occurring within a first time period; and

a second behavior metric indicating whether the user device launched the application during one or more time periods subsequent to the first time period;

identify multiple cohort groups, each of the cohort groups including one or more of the user devices, the cohort groups are identified based on the behavior metric for each of the user devices, wherein identifying the multiple cohort groups includes;

identifying a plurality of discrete first-launch periods;

dividing the plurality of user devices into first-launch groups, wherein each first-launch group is associated with one of the first-launch periods and wherein a user device is assigned to a first-launch group if the time at which the user device first launched the application occurred during the first-launch period associated with the first-launch group; and

for each first-launch group;

identifying one or more discrete time periods which have elapsed since an end of the first-launch period associated with the first-launch group, and

assigning each of the user devices within the first-launch group to one or more cohort groups, wherein each cohort group is associated with one of the discrete time periods and wherein a user device is assigned to a cohort group if the user device launched the application during the discrete time period associated with the cohort group;

generate a segmentation interface including a graphical visualization of the multiple cohort groups and cause the segmentation interface to be presented via a user interface device, each of the cohort groups in the segmentation interface is presented as a selectable icon;

receive a user selection of one or more of the cohort groups by receiving a selection of one or more of the selectable icons presented via the segmentation interface;

define a custom segment of the behavioral data in response to the user selection, the custom segment is a subset of the behavioral data and is associated with a subset of the user devices; and

store an indication of the custom segment in a non-volatile data storage device.

8. The data management system of claim 7, wherein the processing circuit is further configured to:

generate a reporting interface separate from the segmentation interface and cause the reporting interface to be presented via a user interface device, the reporting interface including a selectable representation of the custom segment;

retrieve the indication of the custom segment from the data storage device in response to a user selection of the selectable representation of the custom segment;

apply the custom segment to a second dataset associated with a plurality of user devices;

select a portion of the second dataset for inclusion in an analytical report, wherein the portion of the second dataset is selected based on the application of the custom segment; and

generate an analytical report using the selected portion of the second dataset, wherein the analytical report analyzes a behavior metric other than the behavior metric used to identify the cohort groups.

9. The data management system of claim 8, wherein the second dataset is one or more of:

the set of behavioral data received at the processing circuit;

a set of behavioral data including some of the behavioral data received at the processing circuit and some additional behavioral data; and

a set of third-party behavioral data including none of the behavioral data received at the processing circuit.

10. The data management system of claim 7, wherein the set of behavioral data received at the processing circuit is received from the plurality of user devices.

11. The data management system of claim 7, wherein the behavioral data includes multiple behavior metrics for each of the user devices, wherein the processing circuit is further configured to:

receive a user selection of a first customizable behavior metric, wherein the multiple cohort groups are defined using the first behavior metric.

12. The data management system of claim 11, wherein the processing circuit is further configured to:

receive a user selection of a second customizable behavior metric, wherein the multiple cohort groups are defined using both the first behavior metric and the second behavior metric.

13. One or more non-transitory computer-readable media having instructions stored therein, the instructions being executable by one or more processors to cause the one or more processors to perform operations comprising:

receiving a set of behavioral data associated with a plurality of user devices, the behavioral data including a behavior metric for each of the user devices resulting from interactions on each of the user devices with at least one of (i) an application having a unique application identifier and (ii) a distributed content item having a unique content item identifier, the behavior metric identifying a particular device of the plurality of user devices, wherein the behavioral data includes retention data for each of the plurality of user devices, the retention data for each user device comprising;

a first behavior metric indicating a time at which the user device first launched an application, the time of first launch occurring within a first time period; and

a second behavior metric indicating whether the user device launched the application during one or more time periods subsequent to the first time period;

identifying multiple cohort groups, each of the cohort groups including one or more of the user devices, the cohort groups are identified based on the behavior metric for each of the user devices, wherein identifying the multiple cohort groups includes;

identifying a plurality of discrete first-launch periods;

dividing the plurality of user devices into first-launch groups, wherein each first-launch group is associated with one of the first-launch periods and wherein a user device is assigned to a first-launch group if the time at which the user device first launched the application occurred during the first-launch period associated with the first-launch group; and

for each first-launch group;

identifying one or more discrete time periods which have elapsed since an end of the first-launch period associated with the first-launch group, and

assigning each of the user devices within the first-launch group to one or more cohort groups, wherein each cohort group is associated with one of the discrete time periods and wherein a user device is assigned to a cohort group if the user device launched the application during the discrete time period associated with the cohort group;

generating a segmentation interface including a graphical visualization of the multiple cohort groups and causing the segmentation interface to be presented via a user interface device, each of the cohort groups in the segmentation interface is presented as a selectable icon;

receiving a user selection of one or more of the cohort groups by receiving a selection of one or more of the selectable icons presented via the segmentation interface;

defining a custom segment of the behavioral data in response to the user selection, the custom segment is a subset of the behavioral data and is associated with a subset of the user devices; and

storing an indication of the custom segment in a non-volatile data storage device.

14. The non-transitory computer-readable media of claim 13, wherein the instructions stored therein further cause the one or more processors to perform operations comprising:

generating a reporting interface separate from the segmentation interface and causing the reporting interface to be presented via a user interface device, the reporting interface including a selectable representation of the custom segment;

retrieving the indication of the custom segment from the data storage device in response to a user selection of the selectable representation of the custom segment;

applying the custom segment to a second dataset associated with a plurality of user devices;

selecting a portion of the second dataset for inclusion in an analytical report, wherein the portion of the second dataset is selected based on the application of the custom segment; and

generating an analytical report using the selected portion of the second dataset, wherein the analytical report analyzes a behavior metric other than the behavior metric used to identify the cohort groups.