# US 2025/0094509 A1 · System and method for scanning faces and discovering scholary information

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

- Number: US 2025/0094509 A1
- Document ID: US20250094509A1
- Status: Published application
- Kind: A1
- Application number: 18/672,708
- Filed: 2024-05-23
- Published: 2025-03-20
- Earliest claimed: 2023-09-14
- Assignees: Mohamed bin Zayed University of Artificial Intelligence
- Applicants: Mohamed bin Zayed University of Artificial Intelligence
- Inventors: Wong Yu KANG; Toluwani AREMU; Younes BALAH; Abdulmotaleb EL SADDIK; Maryam NADEEM; Ivo Gollini NAVARRETE
- Web page: https://patentgrep.com/patent/US20250094509A1

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/532: Query formulation, e.g. graphical querying
- G06F 16/951: Indexing; Web crawling techniques
- G06F 40/166: Editing, e.g. inserting or deleting
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/172: {Classification, e.g. identification}
- G06V 40/168: {Feature extraction; Face representation}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A scholar system and method transforms search of academic knowledge. The system uses a combination of face recognition and language generation technology to effortlessly capture scholars in photos to give rich summaries of profiles of their work. The system also offers an interactive chat element for users to get more insights about a scholar, reducing online search efforts. The system ensures privacy and ethical compliance to rules and regulations.

## Claims

### Claim 1

A scholar information retrieval system, comprising:
a memory storing vectors of facial embeddings and associated links to scholar profiles; and
processing circuitry configured to
input a face image of a scholar,
recognize, by a facial recognition model, the face image and generate a live facial embedding,
search, in the memory, for vectors of facial embeddings matching the live facial embedding to obtain one or more links to textual scholar profiles related to the scholar,
generate a textual academic summary for the scholar based on the textual scholar profiles, and
display the academic summary for the scholar.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processing circuitry is further configured to
obtain, by a Web crawler, content for the textual scholar profiles, and
generate, by a large language model, the textual academic summary for a respective textual scholar profile from the obtained content.

### Claim 3 (depends on 2)

The system of claim 2, wherein the processing circuitry is further configured to
conduct, by a large language model for chat, a question-answer interaction with a user, wherein answers are generated by the large learning model based on the obtained content.

### Claim 4 (depends on 1)

The system of claim 1, further comprising a camera for temporarily capturing a face image of a scholar;
wherein the processing circuitry is further configured to recognize, by the facial recognition model, the face image directly captured by the camera, and generate the live facial embedding, and
wherein the processing circuitry deletes the face image immediately after generation of the live facial embedding.

### Claim 5 (depends on 1)

The system of claim 1, wherein the textual scholar profiles associated with a facial image are periodically updated.

### Claim 6 (depends on 1)

The system of claim 1, wherein the memory stores a database of scholar information,
wherein the processing circuitry is further configured to extract, by a user registration module, the facial embedding for a scholar face image to serve as a search key in the database.

### Claim 7 (depends on 1)

The system of claim 1, further comprising:
a scholar imaging system for creating a database of scholar information, including
a camera for capturing an image of a scholar's face;
a machine learning engine for generating a facial embedding vector using a facial recognition model on the face image; and
the memory for storing the facial embedding vector.

### Claim 8 (depends on 7)

The system of claim 7, further comprising:
a scholar profile database creation tool, including
an input for receiving the scholar information,
the processing circuitry configured to associate the scholar information with the facial embedding, and
storing the scholar information and the associated facial embedding in the database.

### Claim 9 (depends on 8)

The system of claim 8, further comprising:
a scholar registration interface for registering a new scholar,
wherein the new scholar registering includes capturing, by a camera, an image of the new scholar's face,
and inputting information about the new scholar, including inputting a name and a link to a scholar's webpage.

### Claim 10 (depends on 9)

The system of claim 9, wherein the inputting information about the new scholar further includes inputting a link to a textual scholar profile.

### Claim 11

A non-transitory computer-readable storage medium including computer executable instructions, wherein the instructions, when executed by a computer, cause the computer to perform a method for scholar information retrieval in a mobile device, the method comprising:
storing vectors of facial embeddings and associated links to textual scholar profiles;
inputting a face image of a scholar;
recognizing, by a facial recognition model, the face image and generate a live facial embedding;
searching for vectors of facial embeddings matching the live facial embedding to obtain one or more links to textual scholar profiles related to the scholar;
generating a textual academic summary for the scholar based on the scholar profiles; and
displaying the academic summary for the scholar.

### Claim 12 (depends on 11)

The computer-readable storage medium of claim 11, further comprising:
obtaining, by a Web crawler, content for the textual scholar profiles, and
generating, by a large language model, the academic summary for a respective scholar profile from the obtained content.

### Claim 13 (depends on 12)

The computer-readable storage medium of claim 12, further comprising
conducting, by a large language model for chat, a question-answer interaction with a user, wherein answers are generated by the large learning model based on the obtained content.

### Claim 14 (depends on 11)

The computer-readable storage medium of claim 11, further comprising:
temporarily capturing, via a camera, a face image of a scholar;
recognizing, by the facial recognition model, the face image directly captured by the camera, and generate the live facial embedding; and
discarding the face image immediately after generation of the live facial embedding.

### Claim 15 (depends on 11)

The computer-readable storage medium of claim 11, further comprising periodically updating the textual scholar profiles associated with a facial image.

### Claim 16 (depends on 11)

The computer-readable storage medium of claim 11, further comprising storing a database of scholar information, and extracting, by a user registration module, the facial embedding for a scholar face image to serve as a search key in the database.

### Claim 17 (depends on 11)

The computer-readable storage medium of claim 11, further comprising:
creating a vector database of scholar information, including
capturing, via a camera, an image of a scholar's face;
generating, via a machine learning engine, a facial embedding vector using a facial recognition model on the face image; and
storing the facial embedding in a local memory.

### Claim 18 (depends on 17)

The computer-readable storage medium of claim 17, further comprising:
a scholar profile database creation tool, including
receiving scholar information;
associating the scholar information with the stored facial embedding; and
storing the scholar information and the associated facial embedding in the vector database.

### Claim 19 (depends on 18)

The computer-readable storage medium of claim 18, further comprising:
a scholar registration interface for registering a new scholar;
wherein the new scholar registering includes capturing, by a camera, an image of the scholar's face,
and inputting information about the new scholar, including inputting a name and a link to a scholar's webpage.

### Claim 20 (depends on 19)

The computer-readable storage medium of claim 19, wherein the inputting information about the new scholar further includes inputting a link to a scholar profile.
