# US 2022/0044276 A1 · Apparatus, computer-implemented methods, and computer program products for providing dynamic data-driven profile based persona dimensional promotion selection

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

- Number: US 2022/0044276 A1
- Document ID: US20220044276A1
- Status: Published application
- Kind: A1
- Application number: 17/445,662
- Filed: 2021-08-23
- Published: 2022-02-10
- Earliest claimed: 2014-06-30
- Assignees: Groupon, Inc.
- Applicants: Groupon, Inc.
- Inventors: Sridatta VISWANATH; Amber Roy CHOWDHURY; Roger Henry CASTILLO; Sri SUBRAMANIAM; Lawrence Lee WAI; Bhupesh BANSAL; Vijay KUMAR
- Web page: https://patentgrep.com/patent/US20220044276A1

## CPC

- G06Q 30/0243: {Comparative campaigns}
- G06Q 30/0249: {based upon budgets or funds}
- G06Q 30/0252: {based on events or environment, e.g. weather or festivals}
- G06Q 30/0261: {based on user location}
- G06Q 30/0264: {based upon schedule}
- 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

## Abstract

Embodiments are provided that improve persona tracking and use to improve the accuracy of determinations and actions that rely on such persona(s). Some example embodiments track user information associated with a profile. Example embodiments further generate personas associated with the profile based on the user information. Example embodiments further receive time data and/or location data from a user device. Example embodiments further determine a selected persona based on the time data and/or the location data. Example embodiments further determine a preference dimension value based on the selected persona. Example embodiments further identify promotion data representing a plurality of promotions. Example embodiments further, for each promotion, generate a first dimension score corresponding to the preference dimension value based on the selected persona. Example embodiments further determine a ranking for the promotions based on the first dimension score for each promotion.

## Claims

### Claim at position 1

1-42. (canceled)

### Claim 43

An apparatus comprising at least one processor and at least one non-transitory memory including computer-coded instructions thereon, the computer coded instructions, with the at least one processor, cause the apparatus to:
track user information associated with a profile, the user information aggregated from a plurality of separate computing devices;
generate a plurality of personas associated with the profile based at least in part on the user information;
receive at least time data and/or location data from a user device associated with the profile;
determine a selected persona based at least in part on the time data and/or the location data;
determine at least one preference dimension value based at least in part on the selected persona associated with the profile;
identify promotion data representing a plurality of promotions;
for each promotion of the plurality of promotions, generate at least a first dimension score corresponding to the at least one preference dimension value based at least in part on the selected persona; and
determine a ranking for the plurality of promotions based at least in part on the first dimension score for each promotion of the plurality of promotions.

### Claim 44 (depends on 43)

The apparatus according to claim 43, the apparatus further caused to:
generate an impression indicating one or more promotions from the plurality of promotions based at least in part on the ranking for the plurality of promotions.

### Claim 45 (depends on 43)

The apparatus according to claim 43, the apparatus further caused to:
track, using a machine learning process, historical responses to at least one impression previously provided to at least one profile of a plurality of profiles;
determine, using the machine learning process tracking the historical responses, a first weighting value for at least the first dimension score and a second weighting value for a second dimension score associated with a second dimension value for each promotion; and
determine a multi-dimension score for each promotion of the plurality of promotions based at least in part on the first weighting value, the second weighting value, the first dimension score for the promotion and the second dimension score,
wherein the ranking score of the promotions is determined based at least in part on the multi-dimension score for each promotion.

### Claim 46 (depends on 43)

The apparatus according to claim 43, wherein the plurality of separate computing devices comprises the user device, a merchant device, and at least one third-party device.

### Claim 47 (depends on 43)

The apparatus according to claim 43, wherein the selected persona is determined based at least in part on a current time value associated with the user device or a future time value associated with the user device.

### Claim 48 (depends on 43)

The apparatus according to claim 43, wherein the selected person is determined based at least in part on a current location value associated with the user device or a future location value associated with the user device.

### Claim 49 (depends on 43)

The apparatus according to claim 43, the apparatus further caused to:
receive new consumer information associated with the profile; and
continuously update at least one persona of the plurality of personas based at least in part on the new consumer information.

### Claim 50 (depends on 43)

The apparatus according to claim 43, the apparatus further caused to:
receive new consumer information associated with the profile; and
generate a new persona based at least in part on the new consumer information, wherein the plurality of personas further comprises at least the new persona.
generate an impression indicating one or more promotions from the plurality of promotions based at least in part on the ranking for the plurality of promotions.

### Claim 51

computer-implemented method comprising:
tracking user information associated with a profile, the user information aggregated from a plurality of separate computing devices;
generating a plurality of personas associated with the profile based at least in part on the user information;
receiving at least time data and/or location data from a user device associated with the profile;
determining a selected persona based at least in part on the time data and/or the location data;
determining at least one preference dimension value based at least in part on the selected persona associated with the profile;
identifying promotion data representing a plurality of promotions;
for each promotion of the plurality of promotions, generating at least a first dimension score corresponding to the at least one preference dimension value based at least in part on the selected persona; and
determining a ranking for the plurality of promotions based at least in part on the first dimension score for each promotion of the plurality of promotions.

### Claim 52 (depends on 51)

The computer-implemented method according to claim 51, the computer-implemented method further comprising:
generating an impression indicating one or more promotions from the plurality of promotions based at least in part on the ranking for the plurality of promotions.

### Claim 53 (depends on 51)

The computer-implemented method according to claim 51, the computer-implemented method further comprising:
tracking, using a machine learning process, historical responses to at least one impression previously provided to at least one profile of a plurality of profiles;
determining, using the machine learning process tracking the historical responses, a first weighting value for at least the first dimension score and a second weighting value for a second dimension score associated with a second dimension value for each promotion; and
determining a multi-dimension score for each promotion of the plurality of promotions based at least in part on the first weighting value, the second weighting value, the first dimension score for the promotion and the second dimension score,
wherein the ranking score of the promotions is determined based at least in part on the multi-dimension score for each promotion.

### Claim 54 (depends on 51)

The computer-implemented method according to claim 51, wherein the plurality of separate computing devices comprises the user device, a merchant device, and at least one third-party device.

### Claim 55 (depends on 51)

The computer-implemented method according to claim 51, wherein the selected persona is determined based at least in part on a current time value associated with the user device or a future time value associated with the user device.

### Claim 56 (depends on 51)

The computer-implemented method according to claim 51, wherein the user information associated with the profile comprises real-time historical time data and real-time historical location data, the real-time historical time data and real-time historical location data utilized to associate each persona of the plurality of personas with a particular time and/or a particular location.

### Claim 57 (depends on 51)

The computer-implemented method according to claim 51, the computer-implemented method further comprising:
receiving new consumer information associated with the profile; and
continuously updating at least one persona of the plurality of personas based at least in part on the new consumer information.

### Claim 58 (depends on 51)

The computer-implemented method according to claim 51, the computer-implemented method further comprising:
receiving new consumer information associated with the profile; and
generating a new persona based at least in part on the new consumer information, wherein the plurality of personas further comprises at least the new persona.

### Claim 59

A computer program product comprising at least one non-transitory computer-readable storage medium having computer program instructions stored thereon that, in execution with at least one processor, configure the computer program product for:
tracking user information associated with a profile, the user information aggregated from a plurality of separate computing devices;
generating a plurality of personas associated with the profile based at least in part on the user information;
receiving at least time data and/or location data from a user device associated with the profile;
determining a selected persona based at least in part on the time data and/or the location data;
determining at least one preference dimension value based at least in part on the selected persona associated with the profile;
identifying promotion data representing a plurality of promotions;
for each promotion of the plurality of promotions, generating at least a first dimension score corresponding to the at least one preference dimension value based at least in part on the selected persona; and
determining a ranking for the plurality of promotions based at least in part on the first dimension score for each promotion of the plurality of promotions.

### Claim 60 (depends on 59)

The computer program product according to claim 59, the computer program product further configured for:
generating an impression indicating one or more promotions from the plurality of promotions based at least in part on the ranking for the plurality of promotions.

### Claim 61 (depends on 59)

The computer program product according to claim 59, the computer program product further configured for:
tracking, using a machine learning process, historical responses to at least one impression previously provided to at least one profile of a plurality of profiles;
determining, using the machine learning process tracking the historical responses, a first weighting value for at least the first dimension score and a second weighting value for a second dimension score associated with a second dimension value for each promotion; and
determining a multi-dimension score for each promotion of the plurality of promotions based at least in part on the first weighting value, the second weighting value, the first dimension score for the promotion and the second dimension score,
wherein the ranking score of the promotions is determined based at least in part on the multi-dimension score for each promotion.

### Claim 62 (depends on 59)

The computer program product according to claim 59, the computer program product further configured for:
receiving new consumer information associated with the profile; and
continuously updating at least one persona of the plurality of personas based at least in part on the new consumer information.
