# US 10,372,893 B2 · Sensor-based authentication

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

- Number: US 10,372,893 B2
- Document ID: US10372893B2
- Status: Granted
- Kind: B2
- Application number: 15/340,373
- Filed: 2016-11-01
- Published: 2018-05-03
- Granted: 2019-08-06
- Earliest claimed: 2016-11-01
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Jing Li; Jie Ma; Li Jun Mei; Jian Wang
- Web page: https://patentgrep.com/patent/US10372893B2

## CPC

- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06F 21/316: {by observing the pattern of computer usage, e.g. typical user behaviour}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Embodiments of the present disclosure relate to a new approach for sensor-based authentication to enhance mobile security. In the computer-implemented method, motion related sensor data is obtained. A label of a behavior is determined wherein the behavior has a time information of the behavior. The label is associated with at least part of the motion related sensor data based on the time information of the behavior and the time information of the motion. At least one comparable motion is determined from the associated part of motion related sensor data. At least one motion passcode based on the determined comparable motion is identified.

## Claims

### Claim 1

A computer-implemented method comprising:
obtaining motion related sensor data, wherein the motion related sensor data includes time information of motion;
removing at least one unexpected movement interruption comprising interference from background motion related sensor data from the motion related sensor data;
determining a label of a behavior, wherein the behavior includes time information of the behavior;
associating the label with at least part of the motion related sensor data based on the time information of the behavior and the time information of motion;
determining at least one trajectory level of comparable motion from the at least part of the motion related sensor data associated with the label;
identifying a plurality of comparable motions corresponding to the label;
for each comparable motion in the plurality of comparable motions, calculating a sum of at least one similarity value, wherein, the similarity value is calculated by comparing the comparable motion with another identified comparable motion in the plurality of comparable motions; and
selecting a comparable motion with a maximum sum of the similarity value as a motion passcode corresponding to the label.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining a label of a behavior comprises:
obtaining an application level event; and
determining the label of the behavior and the time information based on the application level event.

### Claim 3 (depends on 1)

The method of claim 1, wherein the comparable motion further comprises a biometric level of comparable motion.

### Claim 4 (depends on 1)

The method of claim 1, wherein the associating the label with at least part of motion related sensor data comprises:
tailoring a piece of the motion related sensor data based on the time information; and
associating the label with the piece of motion related sensor data.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
prompting for the label of the motion passcode corresponding to the label;
obtaining current motion related sensor data corresponding to a behavior performed according to the label;
determining a comparable motion from the motion related sensor data;
comparing the motion passcode corresponding to the label with the determined comparable motion; and
authenticating based on the comparison.

### Claim 6 (depends on 5)

The method of claim 5, wherein the comparable motion further comprises a biometric level of comparable motion.

### Claim 7

A device comprising:
a processing unit;
a memory coupled to the processing unit and storing instructions thereon, the instructions, when executed by the processing unit, performing acts including:
obtaining motion related sensor data, wherein the motion related sensor data includes time information of motion;
removing at least one unexpected movement interruption comprising interference from background motion related sensor data from the motion related sensor data;
determining a label of a behavior, wherein the behavior includes a time information of the behavior;
associating the label with at least part of the motion related sensor data based on the time information of the behavior and the time information of motion;
determining at least one trajectory level of comparable motion from the at least part of the motion related sensor data associated with the label;
identifying a plurality of comparable motions corresponding to the label;
for each comparable motion in the plurality of comparable motions, calculating a sum of at least one similarity value, wherein, the similarity value is calculated by comparing the comparable motion with another identified comparable motion in the plurality of comparable motions; and
selecting a comparable motion with a maximum sum of the similarity value as a motion passcode corresponding to the label.

### Claim 8 (depends on 7)

The device of claim 7, wherein determining a label of a behavior comprises:
obtaining an application level event; and
determining the label of the behavior and the time information based on the application level event.

### Claim 9 (depends on 8)

The device of claim 8, wherein the comparable motion further comprises a biometric level of comparable motion.

### Claim 10 (depends on 8)

The device of claim 8, wherein the associating the label with at least part of motion related sensor data comprises:
tailoring a piece of the motion related sensor data based on the time information; and
associating the label with the piece of motion related sensor data.

### Claim 11

A computer program product being tangibly stored on a non-transient machine-readable medium and comprising machine-executable instructions, the instructions, when executed on an electronic device, performing acts including:
obtaining motion related sensor data, wherein the motion related sensor data include time information of motion;
removing at least one unexpected movement interruption comprising interference from background motion related sensor data from the motion related sensor data;
determining a label of a behavior, wherein the behavior includes a time information of the behavior;
associating the label with at least part of the motion related sensor data based on the time information of the behavior and the time information of motion;
determining at least one trajectory level of comparable motion from the at least part of the motion related sensor data associated with the label;
identifying a plurality of comparable motions corresponding to the label;
for each comparable motion in the plurality of comparable motions, calculating a sum of at least one similarity value, wherein, the similarity value is calculated by comparing the comparable motion with another identified comparable motion in the plurality of comparable motions; and
selecting a comparable motion with a maximum sum of the similarity value as a motion passcode corresponding to the label.

### Claim 12 (depends on 11)

The computer program product of claim 11, wherein determining a label of a behavior comprises:
obtaining an application level event; and
determining the label of the behavior and the time information based on the application level event.

### Claim 13 (depends on 11)

The computer program product of claim 11, wherein the comparable motion further comprises biometric level of comparable motion.

### Claim 14 (depends on 11)

The computer program product of claim 11, wherein the associating the label with at least part of motion related sensor data comprises:
tailoring a piece of the motion related sensor data based on the time information; and
associating the label with the piece of motion related sensor data.