# US 10,872,317 B2 · Biometric-based punch-in/punch-out management

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

- Number: US 10,872,317 B2
- Document ID: US10872317B2
- Status: Granted
- Kind: B2
- Application number: 16/170,624
- Filed: 2018-10-25
- Published: 2019-04-25
- Granted: 2020-12-22
- Earliest claimed: 2017-10-25
- Assignees: About Time Technologies, LLC
- Applicants: About Time Technologies, LLC
- Inventors: Russell I. Hanson; Ryan Remkes; Michael T. Merrill; Kory Tanner
- Web page: https://patentgrep.com/patent/US10872317B2

## CPC

- G06Q 10/1091: Recording time for administrative or management purposes
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 40/40: Spoof detection, e.g. liveness detection
- G06V 40/70: Multimodal biometrics, e.g. combining information from different biometric modalities
- H04L 63/0861: {using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231)}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06V 40/12: Fingerprints or palmprints
- G06V 40/18: Eye characteristics, e.g. of the iris
- G10L 17/00: Speaker identification or verification techniques
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

For managing a biometric punch-in system, a method captures training biometrics for a plurality of users. The method further trains a biometric algorithm with the training biometrics. The method presents a threshold user interface to an administrator that compares one or more identification biometrics that do not satisfy a match threshold for the plurality of users and a match threshold control for adjusting the match threshold. The method further adjusts the match threshold in response to the match threshold control. The method determines a match level for the identification biometric based on the biometric algorithm. In response to the match level not satisfying the match threshold, the method presents an attendance user interface including punch-in/punch-out times, corresponding identification biometrics and match levels, and attendance information for the first user, wherein suspect identification biometrics are highlighted.

## Claims

### Claim 1

A method comprising:
capturing, by use of a processor, training biometrics for a plurality of users;
training a biometric algorithm with the training biometrics;
presenting a threshold user interface to an administrator that compares a punch-in match level and a punch-out match level for one or more identification biometrics that do not satisfy a match threshold for the plurality of users and a match threshold control for adjusting the match threshold;
adjusting the match threshold in response to the match threshold control;
capturing an identification biometric in a punch-in operation/punch-out operation for a first user of the plurality of users;
determining a match level for the identification biometric based on the biometric algorithm;
in response to the match level not satisfying the match threshold during the punch-in operation/punch-out operation, presenting an attendance user interface comprising punch-in/punch-out times, corresponding identification biometrics and match levels, and attendance information for the first user, wherein suspect identification biometrics are highlighted; and
receiving a validation or invalidation of the punch-in operation/punch-out operation from the administrator.

### Claim 2 (depends on 1)

The method of claim 1, the method further comprising determining an identification biometric location.

### Claim 3 (depends on 2)

The method of claim 2, wherein the suspect identification biometrics are identified as a function of one or more of the punch-in/punch-out times, the corresponding match levels, the attendance information, the identification biometric location relative to a geo-fence, a time discrepancy, a manual override, a punch-in device, and tangible assets.

### Claim 4 (depends on 3)

The method of claim 3, wherein the punch-in/punch-out times, the corresponding match levels, the attendance information, the identification biometric location relative to the geofence, the time discrepancy, the manual override, the punch-in device, and the tangible assets are searchable.

### Claim 5 (depends on 1)

The method of claim 1, the method further comprising automatically validating the identification biometric if the match level satisfies the match threshold.

### Claim 6 (depends on 1)

The method of claim 1, wherein the biometrics are a biometric type selected from the group consisting of an image, a voice print, a retina scan, and a fingerprint.

### Claim 7 (depends on 1)

The method of claim 1, the method further comprising recursively training the biometric algorithm with the suspect identification biometrics.

### Claim 8 (depends on 1)

The method of claim 1, wherein the training biometrics are filtered by one or more of the punch-in/punch-out times, the corresponding match levels, the attendance information, an identification biometric location relative to a geofence, a time discrepancy, a manual override, a punch-in device, and tangible assets.

### Claim 9 (depends on 1)

The method of claim 1, wherein the biometric algorithm is selected from the group consisting of a statistical algorithm, a recursive neural network, a convolutional neural network, and a long short term memory (LSTM) network.

### Claim 10

An apparatus comprising:
a processor;
a memory storing code executable by the processor to perform:
capturing training biometrics for a plurality of users;
training a biometric algorithm with the training biometrics;
presenting a threshold user interface to an administrator that compares a punch-in match level and a punch-out match level for one or more identification biometrics that do not satisfy a match threshold for the plurality of users and a match threshold control for adjusting the match threshold;
adjusting the match threshold in response to the match threshold control;
capturing an identification biometric in a punch-in operation/punch-out operation for a first user of the plurality of users;
determining a match level for the identification biometric based on the biometric algorithm; and
in response to the match level not satisfying the match threshold during the punch-in operation/punch-out operation, presenting an attendance user interface comprising punch-in/punch-out times, corresponding identification biometrics and match levels, and attendance information for the first user, wherein suspect identification biometrics are highlighted, and
receiving a validation or invalidation of the punch-in operation/punch-out operation from the administrator.

### Claim 11 (depends on 10)

The apparatus of claim 10, the processor further determining an identification biometric location.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the suspect identification biometrics are identified as a function of one or more of the punch-in/punch-out times, the corresponding match levels, the attendance information, the identification biometric location relative to a geo-fence, a time discrepancy, a manual override, a punch-in device, and tangible assets.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein the punch-in/punch-out times, the corresponding match levels, the attendance information, the identification biometric location relative to the geofence, the time discrepancy, the manual override, the punch-in device, and the tangible assets are searchable.

### Claim 14 (depends on 10)

The apparatus of claim 10, the processor further automatically validating the identification biometric if the match level satisfies the match threshold.

### Claim 15 (depends on 10)

The apparatus of claim 10, wherein the biometrics are a biometric type selected from the group consisting of an image, a voice print, a retina scan, and a fingerprint.

### Claim 16 (depends on 10)

The apparatus of claim 10, the method further comprising recursively training the biometric algorithm with the suspect identification biometrics.

### Claim 17 (depends on 10)

The apparatus of claim 10, wherein the training biometrics are filtered by one or more of the punch-in/punch-out times, the corresponding match levels, the attendance information, an identification biometric location relative to a geofence, a time discrepancy, a manual override, a punch-in device, and tangible assets.

### Claim 18 (depends on 10)

The apparatus of claim 10, wherein the biometric algorithm is selected from the group consisting of a statistical algorithm, a recursive neural network, a convolutional neural network, and a long short term memory (LSTM) network.

### Claim 19

A program product comprising a non-transitory computer readable storage medium storing code executable by a processor to perform:
capturing training biometrics for a plurality of users;
training a biometric algorithm with the training biometrics;
presenting a threshold user interface to an administrator that compares a punch-in match level and a punch-out match level for one or more identification biometrics that do not satisfy a match threshold for the plurality of users and a match threshold control for adjusting the match threshold;
adjusting the match threshold in response to the match threshold control;
capturing an identification biometric in a punch-in operation/punch-out operation for a first user of the plurality of users;
determining a match level for the identification biometric based on the biometric algorithm;
in response to the match level not satisfying the match threshold during the punch-in operation/punch-out operation, presenting an attendance user interface comprising punch-in/punch-out times, corresponding identification biometrics and match levels, and attendance information for the first user, wherein suspect identification biometrics are highlighted; and
receiving a validation or invalidation of the punch-in operation/punch-out operation from the administrator.

### Claim 20 (depends on 19)

The program product of claim 19, wherein the suspect identification biometrics are identified as a function of one or more of the punch-in/punch-out times, the corresponding match levels, the attendance information, the identification biometric location relative to a geo-fence, a time discrepancy, a manual override, a punch-in device, and tangible assets.