# US 2025/0375131 A1 · Driver attention monitoring

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

- Number: US 2025/0375131 A1
- Document ID: US20250375131A1
- Status: Published application
- Kind: A1
- Application number: 18/738,546
- Filed: 2024-06-10
- Published: 2025-12-11
- Earliest claimed: 2024-06-10
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Zhe Yan; Li Li Guan; Rong Zhao; Li Bo Zhang; Hao Xiang Wu
- Web page: https://patentgrep.com/patent/US20250375131A1

## CPC

- A61B 5/18: for vehicle drivers {or machine operators}
- A61B 5/162: {Testing reaction times}
- A61B 5/4803: {Speech analysis specially adapted for diagnostic purposes}
- A61B 5/6893: {Cars}
- A61B 5/7278: {Artificial waveform generation or derivation, e.g. synthesizing signals from measured signals}
- A61B 5/7465: {Arrangements for interactive communication between patient and care services, e.g. by using a telephone network (telemetry of measured physiological signal A61B5/0002)}
- B60Q 9/00: Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00 {, e.g. haptic signalling}
- G06Q 10/06398: {Performance of employee with respect to a job function}
- G06F 40/35: Discourse or dialogue representation
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- B60Q: ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Disclosed are a computer-implemented method, a system and a computer program product for monitoring driver attention. A traffic event occurring during a driving task of a driver on a road can be monitored. A behavior of the driver in response to the traffic event can be detected. An attention level of the driver can be determined at least based on a match of the detected behavior of the driver with an expected behavior in response to the traffic event. Accordingly, the attention level of the driver can be reliably predicted and the driver distraction can be efficiently prevented, thereby improving the driving safety.

## Claims

### Claim 1

A computer-implemented method for monitoring driver attention, comprising:
monitoring, by one or more processing units, a traffic event occurring during a driving task of a driver on a road;
detecting, by one or more processing units, a behavior of the driver in response to the traffic event; and
determining, by one or more processing units, an attention level of the driver at least based on a match of the detected behavior of the driver with an expected behavior in response to the traffic event.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
initiating, by one or more processing units, an interactive chat with the driver in response to the determined attention level of the driver falling below an attention threshold and/or a periodic timing for initiating the interactive chat having arrived.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, further comprising:
acquiring, by one or more processing units, an answer provided by the driver with respect to a question of the interactive chat; and
updating, by one or more processing units, the attention level of the driver based on a response time and/or response content of the answer provided by the driver.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein the question of the interactive chat is generated with the aid of a language model based on a context of the driving task, and
wherein the attention level of the driver is updated at least based on a match of the response content with an expected answer generated with the aid of the language model.

### Claim 5 (depends on 3)

The computer-implemented method of claim 3, wherein the question of the interactive chat is generated with the aid of a language model based on a context of the driving task, and
wherein the attention level of the driver is updated at least based on a semantic analysis of the response content in combination with the context of the driving task and the generated question with the aid of the language model.

### Claim 6 (depends on 3)

The computer-implemented method of claim 3, wherein the question of the interactive chat is selected from a plurality of different question types based on a context of the driving task and/or a preference of the driver.

### Claim 7 (depends on 3)

The computer-implemented method of claim 3, wherein the attention level is determined with the aid of a driving attention model specific to the driver, and
wherein the driving attention model is updated based on a frequency of the response time and/or response content of the answer not satisfying a predetermined condition.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein determining the attention level of the driver is further based on an explanation to the detected behavior provided by the driver.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein determining the attention level of the driver is further based on an elapsed time period of the driving task, one or more driver states of the driver, and/or one or more road conditions of the road.

### Claim 10 (depends on 9)

The computer-implemented method of claim 9, wherein the one or more driver states indicate one or more of an age, a gender, a driving experience and an emotional state of the driver.

### Claim 11 (depends on 9)

The computer-implemented method of claim 9, wherein the one or more road conditions indicate one or more of a type, a geometry and a traffic density of the road.

### Claim 12 (depends on 1)

The computer-implemented method of claim 1, further comprising:
sending, by one or more processing units, one or more control signals to one or more vehicle components for attention promotion in response to the attention level of the driver falling below an attention threshold.

### Claim 13 (depends on 1)

The computer-implemented method of claim 1, wherein the attention level is determined with the aid of a driving attention model specific to the driver, and wherein the driving attention model is updated based on a frequency of the detected behavior of the driver not matching the expected behavior.

### Claim 14 (depends on 13)

The computer-implemented method of claim 13, wherein the driving attention model is characterized by at least one of: a gradient parameter indicative of a degradation of the attention level of the driver over time, a reward parameter indicative of an increase in the attention level in response to an attention increasing event of the driver, and a punishment parameter indicative of a decrease in the attention level in response to an attention decreasing event of the driver, and
wherein at least one of the gradient parameter, the reward parameter and the punishment parameter of the driving attention model is updated based on the frequency of the detected behavior of the driver not matching the expected behavior.

### Claim 15 (depends on 13)

The computer-implemented method of claim 13, further comprising:
determining, by one or more processing units, an occurrence of an attention decreasing event of the driver; and
acquiring, by one or more processing units, a facial feature and/or a body pose of the driver captured in the attention decreasing event,
wherein the driving attention model is updated further based on the facial feature and/or the body pose such that the attention level of the driver is determined further based on subsequently captured facial features and/or body poses of the driver.

### Claim 16 (depends on 1)

The computer-implemented method of claim 1, wherein the attention level of the driver is determined based on an incremental value or a decremental value applied to a current attention level of the driver, and
wherein the incremental value or the decremental value is determined based on a match or mismatch of the detected behavior with the expected behavior.

### Claim 17

A system for monitoring driver attention, comprising:
one or more processors;
a memory coupled to at least one of the processors; and
a set of computer program instructions stored in the memory, which, when executed by at least one of the processors, perform actions of:
monitoring a traffic event occurring during a driving task of a driver on a road;
detecting a behavior of the driver in response to the traffic event; and
determining an attention level of the driver at least based on a match of the detected behavior of the driver with an expected behavior in response to the traffic event.

### Claim 18 (depends on 17)

The system of claim 17, wherein the set of computer program instructions, when executed by the at least one of the processors, further perform actions of:
initiating an interactive chat with the driver in response to the determined attention level of the driver falling below an attention threshold and/or a periodic timing for initiating the interactive chat having arrived.

### Claim 19 (depends on 18)

The system of claim 18, wherein the set of computer program instructions, when executed by the at least one of the processors, further perform actions of:
acquiring an answer provided by the driver with respect to a question of the interactive chat; and
updating the attention level of the driver based on a response time and/or response content of the answer provided by the driver.

### Claim 20

A computer program product for monitoring driver attention, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
monitor a traffic event occurring during a driving task of a driver on a road;
detect a behavior of the driver in response to the traffic event; and
determine an attention level of the driver at least based on a match of the detected behavior of the driver with an expected behavior in response to the traffic event.
