# US 2021/0334686 A1 · Systems and methods for short identifier behavioral analytics

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

- Number: US 2021/0334686 A1
- Document ID: US20210334686A1
- Status: Published application
- Kind: A1
- Application number: 17/366,454
- Filed: 2021-07-02
- Published: 2021-10-28
- Earliest claimed: 2016-02-09
- Assignees: Upside Services, Inc
- Applicants: Upside Services, Inc
- Inventors: Alexander Kinnier; Richard McPhee
- Web page: https://patentgrep.com/patent/US20210334686A1

## CPC

- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06F 16/285: {Clustering or classification}
- G06F 16/29: Geographical information databases
- G06F 16/9537: Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
- G06N 20/00: Machine learning
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Embodiments relate to computing systems, methods, and non-transitory computer-readable storage media. Identifier collisions are determined in historical event data based on short identifiers associated with a first event location and short identifiers associated with a second event location geographically dispersed from the first event location. Behavior analytics are performed on short identifiers in the historical event data to generate behavioral models associated with the short identifiers. Adjusted behavioral models are generated based on the determined identifier collisions. A short identifier is obtained from a client device, and based on the short identifier, an adjusted behavioral model of the adjusted behavioral models is determined. An expected event frequency is determined based on the adjusted behavioral model and an actual event frequency is determined. An indication of a first new event value is transmitted to the client device based on a determination that the expected event frequency is less than the actual event frequency, whereby the client device displays a notification corresponding to the indication of the first new event value.

## Claims

### Claim 1

A computing system comprising:
one or more processors; and
a memory system comprising one or more computer-readable media, wherein the one or more computer-readable media contain instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
determining, in historical event data, identifier collisions based on short identifiers associated with a first event location and short identifiers associated with a second event location geographically dispersed from the first event location;
performing behavior analytics on a plurality of short identifiers in the historical event data to generate behavioral models associated with the plurality of short identifiers;
generating adjusted behavioral models based on the determined identifier collisions;
obtaining a short identifier from a client device;
determining, based on the short identifier from the client device, an adjusted behavioral model of the adjusted behavioral models;
determining an expected event frequency based on the adjusted behavioral model;
determining an actual event frequency; and
transmitting an indication of a first new event value to the client device based on a determination that the expected event frequency is less than the actual event frequency, whereby the client device displays a notification corresponding to the indication of the first new event value.

### Claim 2 (depends on 1)

The computing system of claim 1, wherein the plurality of short identifiers are integers.

### Claim 3 (depends on 2)

The system of claim 2, wherein the integers are stored as short integer variables.

### Claim 4 (depends on 2)

The computing system of claim 2, wherein the integers have a maximum of four digits.

### Claim 5 (depends on 1)

The computing system of claim 1, wherein:
the generating of the adjusted behavioral models is further based on a number of the determined identifier collisions and a total number of unique short identifiers at one or more of the first event location and the second event location.

### Claim 6 (depends on 1)

The computing system of claim 1, wherein the performing of the behavior analytics comprises:
performing a cohort analysis for a base time window by assigning each short identifier of the plurality of identifiers to a cohort of a plurality of cohorts associated with an event type based on a number of events of the event type associated with the short identifier.

### Claim 7 (depends on 6)

The computing system of claim 6, wherein the performing of the behavior analytics further comprises:
assigning a subsequent time window as a new base time window; and
performing a cohort analysis for the new base time window.

### Claim 8 (depends on 6)

The computing system of claim 6, wherein the behavior analytics are performed on each cohort of the plurality of cohorts.

### Claim 9 (depends on 1)

The computing system of claim 1, wherein the operations further comprise:
determining the first new event value based on an actual number of events, an expected number of events, a minimum value, and a weighting value.

### Claim 10 (depends on 1)

The computing system of claim 1, wherein the operations further comprise:
obtaining a second short identifier from a second client device;
determining that the second short identifier is not one the plurality of short identifiers;
transmitting an indication of a second new event value associated with a first event type to the second client device based on a determination that a total value of events of the first event type is less than or equal to a baseline value associated with the first event type; and
transmitting an indication of a third new event value associated with a second event type to the second client device based on a determination that the total value of the events of the first event type exceeds the baseline value of the first event type and a total value of events of the second event type exceeds a baseline value of the second event type.

### Claim 11

A method performed by a computing device, the method comprising:
determining, in historical event data, identifier collisions based on short identifiers associated with a first event location and short identifiers associated with a second event location geographically dispersed from the first event location;
performing behavior analytics on a plurality of short identifiers in the historical event data to generate behavioral models associated with the plurality of short identifiers;
generating adjusted behavioral models based on the determined identifier collisions;
obtaining a short identifier from a client device;
determining, based on the short identifier from the client device, an adjusted behavioral model of the adjusted behavioral models;
determining an expected event frequency based on the adjusted behavioral model based on the obtained short identifier from the client device;
determining an actual event frequency; and
transmitting an indication of a first new event value to the client device based on a determination that the expected event frequency is less than the actual event frequency, whereby the client device displays a notification corresponding to the indication of the first new event value.

### Claim 12 (depends on 11)

The method of claim 11, wherein the plurality of short identifiers are integers.

### Claim 13 (depends on 12)

The method of claim 12, wherein the integers are stored as short integer variables.

### Claim 14 (depends on 12)

The method of claim 12, wherein the integers have a maximum of four digits.

### Claim 15 (depends on 11)

The method of claim 11, wherein:
the generating of the adjusted behavioral models is further based on a number of the determined identifier collisions and a total number of unique short identifiers at one or more of the first event location and the second event location.

### Claim 16 (depends on 11)

The method of claim 11, wherein the performing of the behavior analytics comprises:
performing a cohort analysis for a base time window by assigning each short identifier of the plurality of identifiers to a cohort of a plurality of cohorts associated with an event type based on a number of events of the event type associated with the short identifier.

### Claim 17 (depends on 16)

The method of claim 16, wherein the performing of the behavior analytics further comprises:
assigning a subsequent time window as a new base time window; and
performing a cohort analysis for the new base time window.

### Claim 18 (depends on 16)

The method of claim 16, wherein the behavior analytics are performed on each cohort of the plurality of cohorts.

### Claim 19 (depends on 11)

The method of claim 11, further comprising:
determining the first new event value based on an actual number of events, an expected number of events, a minimum value, and a weighting value.

### Claim 20

A non-transitory computer-readable medium having instructions recorded thereon for at least one processor of a computing device, wherein the instructions configure the at least one processor to perform operations comprising:
determining, in historical event data, identifier collisions based on short identifiers associated with a first event location and short identifiers associated with a second event location geographically dispersed from the first event location;
performing behavior analytics on a plurality of short identifiers in the historical event data to generate behavioral models associated with the plurality of short identifiers;
generating adjusted behavioral models based on the determined identifier collisions;
obtaining a short identifier from a client device;
determining, based on the short identifier from the client device, an adjusted behavioral model of the adjusted behavioral models;
determining an expected event frequency based on the adjusted behavioral model based on the obtained short identifier from the client device;
determining an actual event frequency; and
transmitting an indication of a first new event value to the client device based on a determination that the expected event frequency is less than the actual event frequency, whereby the client device displays a notification corresponding to the indication of the first new event value.
