# US 12,001,434 B2 · Method for monitoring user behavior when interacting with content and a system for its implementation

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

- Number: US 12,001,434 B2
- Document ID: US12001434B2
- Status: Granted
- Kind: B2
- Application number: 17/339,333
- Filed: 2021-06-04
- Published: 2021-09-23
- Granted: 2024-06-04
- Earliest claimed: 2017-09-13
- Assignees: Alemira AG
- Applicants: Alemira AG
- Inventors: Dmitrij Vladimirovich Istomin; Alexander Borisovich Khalfin; Andrej Sergeevich Sheka
- Web page: https://patentgrep.com/patent/US12001434B2

## CPC

- G06F 16/24558: {Binary matching operations}
- G06F 11/302: {where the computing system component is a software system}
- G06F 11/3438: {monitoring of user actions (tracking the activity of the user H04L67/535)}
- G06F 16/2379: {Updates performed during online database operations; commit processing}
- G06F 16/9035: Filtering based on additional data, e.g. user or group profiles
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The present invention relates to information technology and can be used for monitoring the behavior of a user during interaction with content in order to obtain relevant feedback from content consumers, inter alia, based on non-verbal signals. The technical result is that of simplifying the procedure for transmitting user behavior data from a user device to a server, and at the same time speeding up said procedure. The system comprises a server equipped with a database and a central unit for storing conditions of the occurrence of user behavioral events, and at least one user device equipped with a data collection unit, an event recognition unit, and a local unit for storing conditions of the occurrence of user behavioral events. The data collection unit is intended for the collection of primary data. The event recognition unit is intended for extracting features of user behavioral events, generating a vector of values of said attributes, correlating said vector with predetermined conditions of the occurrence of events, and transmitting data about the occurrence of an event to the server.

## Claims

### Claim 1

A method of providing value to a behavior associated with a user interaction event with a computing device, the method comprising:
defining a plurality of signs associated with the behavior, thereby forming a plurality of dimensions;
assigning a value for each sign, thereby forming at least one assigned vector of values descriptive of such signs, wherein the behavior is associated with the at least one assigned vector of values, wherein the vector of values includes the plurality of dimensions corresponding to associated instants of time responsible for the user interaction event;
monitoring the user behavior in interacting with the user device;
for each sign, determining the difference in values between the measured value and the assigned value, thereby forming at least one measured vector of values descriptive of the interaction event; and
according to at least one condition for the occurrence of the interaction event, determining the difference between the assigned vector of values descriptive of the behavior, and the measured vector of values descriptive of the interaction event, thereby providing value to the behavior associated with the user's interaction event with the computing device.

### Claim 2 (depends on 1)

The method of claim 1, wherein the behavior associated with the user's interaction with the computing device is defined by more than one vector of values.

### Claim 3 (depends on 2)

The method of claim 2, wherein the behavior is attention to content displayed on the computing device, and the signs are at least one of:
a facial expression, and a head pose.

### Claim 4 (depends on 3)

The method of claim 3, wherein the values associated with facial expression comprise:
a) a number of key points on the user face (m);
b) maximum value of horizontal coordinate of the display (W); and
c) maximum value of vertical coordinate of the display (H).

### Claim 5 (depends on 4)

The method of claim 4, wherein the assigned vector of values describing the coordinates of the key points of the user's face is represented by:
[x1,y1, . . . ,xm.Ym],xϵ[O,W],yϵ[O,H]
wherein—m is the assigned number of key points on the user's face;
W is the maximum value of horizontal coordinate of the display; and
H is the maximum value of vertical coordinate of the display.

### Claim 6 (depends on 3)

The method of claim 3, wherein the values associated with the head pose comprise assigning values to each of the user's head pitch, roll and yaw by assigning each of the pitch, and yaw a range of degrees from −90° to +90°, and to the roll from 0° to 180.

### Claim 7 (depends on 3)

The method of claim 3, wherein the behavior is the user's involvement with content displayed on the computing device, and the signs are at least one of: a level of expression on the user's face, and a user's level of attention.

### Claim 8 (depends on 7)

The method of claim 7, wherein the assigned vector of values describing the user's involvement with content displayed on the computing device is represented by:
[e,a],e,aϵ[0,100],
Wherein—e is the assigned level of expression on the user's face; and
a is the assigned user's level of attention.

### Claim 9 (depends on 8)

The method of claim 8, wherein the level of expression is further obtained from a combination of different assigned vector of values.

### Claim 10 (depends on 8)

The method of claim 8, wherein the level of expression is obtained from at least one of: the assigned vector of values describing the coordinates of the key points of the user's face, and the assigned vector of values describing the head pose.