# US 2025/0156866 A1 · User authentication during an electronic signature workflow

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

- Number: US 2025/0156866 A1
- Document ID: US20250156866A1
- Status: Published application
- Kind: A1
- Application number: 18/507,724
- Filed: 2023-11-13
- Published: 2025-05-15
- Earliest claimed: 2023-11-13
- Assignees: Fmr LLC
- Applicants: Fmr LLC
- Inventors: Saloni Priyani; Prakhar Maheshwari; Samir Kakkar; Shruthi Kulkarni; Vipul Grover; Harshal Gordhandas Morparia; Vineela Gorentla
- Web page: https://patentgrep.com/patent/US20250156866A1

## CPC

- G06Q 20/4014: {Identity check for transactions}
- G06Q 50/18: Legal services
- G06F 21/316: {by observing the pattern of computer usage, e.g. typical user behaviour}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06Q 10/10: Office automation; Time management
- G06Q 20/3825: {Use of electronic signatures}
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06F 21/44: Program or device authentication
- 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

## Abstract

Methods and apparatuses are described for user authentication during an electronic signature workflow. A server authenticates user credentials included in an electronic signature request. The server generates activity variables based upon parameters associated with the electronic signature request. The server creates a multidimensional vector using the activity variables. The server executes a trained machine learning classification model on the multidimensional vector to generate an anomaly score for the electronic signature request. The server determines additional authentication requirements for the electronic signature request based upon the anomaly score. The server initiates the additional authentication requirements for the electronic signature request, including validating user authentication data received from remote computing devices.

## Claims

### Claim 1

A system for user authentication during an electronic signature workflow, the system comprising a server computing device having a memory for storing computer-executable instructions and a processor that executes the computer-executable instructions to:
authenticate user credentials included in an electronic signature request received from a client computing device;
generate a plurality of activity variables based upon parameters associated with the electronic signature request;
create a multidimensional vector using the activity variables, the vector including a plurality of values each associated with an activity variable and having a weight assigned to each value;
execute a trained machine learning classification model on the multidimensional vector to generate an anomaly score for the electronic signature request;
determine additional authentication requirements for the electronic signature request based upon the anomaly score; and
initiate the additional authentication requirements for the electronic signature request, including validating user authentication data received from one or more remote computing devices.

### Claim 2 (depends on 1)

The system of claim 1, wherein the user credentials comprise one or more of: a username, a password, a personal identification number (PIN), and a token.

### Claim 3 (depends on 1)

The system of claim 1, wherein the parameters associated with the electronic signature request comprise one or more of: an IP address of the client computing device, a MAC address of the client computing device, location coordinates associated with the client computing device, a transaction type, a request timestamp, and the user credentials.

### Claim 4 (depends on 3)

The system of claim 3, wherein the activity variables comprise a change in the IP address, a proximity of the IP address to a prior IP address of the client computing device, a proximity of the IP address to a postal address of the user, a deviation of the request timestamp from an expected request timestamp, a deviation of the transaction type from an expected transaction type, a change in the user credentials, an account lock event associated with the user, account activity associated with the user, and identification of the transaction type on a predetermined list of transactions.

### Claim 5 (depends on 1)

The system of claim 1, wherein the trained machine learning classification model comprises a K-nearest neighbor (KNN) algorithm.

### Claim 6 (depends on 5)

The system of claim 5, wherein the trained machine learning classification model generates the anomaly score based upon a distance measure between each of the weighted values of the multidimensional vector and values of one or more centroid vectors associated with the user.

### Claim 7 (depends on 6)

The system of claim 6, wherein the centroid vector is based upon historical authentication activity associated with one or more of: the user and the client computing device.

### Claim 8 (depends on 5)

The system of claim 5, wherein the server computing device retrains the trained machine learning classification model on updated user authentication data to derive new weights for multidimensional vectors.

### Claim 9 (depends on 1)

The system of claim 1, wherein the server computing device determines that no additional authentication requirements for the electronic signature request are required when the anomaly score falls below a predefined value.

### Claim 10 (depends on 1)

The system of claim 1, wherein the server computing device determines that multifactor authentication is required when the anomaly score is above a first threshold value.

### Claim 11 (depends on 10)

The system of claim 10, wherein initiating the additional authentication requirements for the electronic signature request comprises instructing a first remote computing device to issue a multifactor authentication request to the client computing device.

### Claim 12 (depends on 11)

The system of claim 11, wherein validating user authentication data received from one or more remote computing devices comprises receiving an indicator from the first remote computing device that the client computing device has successfully responded to the multifactor authentication request.

### Claim 13 (depends on 1)

The system of claim 1, wherein the server computing device determines that active identity proofing is required when the anomaly score is above a second threshold value.

### Claim 14 (depends on 13)

The system of claim 13, wherein initiating the additional authentication requirements for the electronic signature request comprises instructing a second remote computing device to request information comprising one or more of: personally identifying information, identification document information, and biometric identity information from the user of the client computing device.

### Claim 15 (depends on 14)

The system of claim 14, wherein validating user authentication data received from one or more remote computing devices comprises receiving an indicator from the second remote computing device that the user has successfully responded to the information request.

### Claim 16

A method of user authentication during an electronic signature workflow, the method comprising:
authenticating, by a server computing device, user credentials included in an electronic signature request received from a client computing device;
generating, by the server computing device, a plurality of activity variables based upon parameters associated with the electronic signature request;
creating, by the server computing device, a multidimensional vector using the activity variables, the vector including a plurality of values each associated with an activity variable and having a weight assigned to each value;
executing, by the server computing device, a trained machine learning classification model on the multidimensional vector to generate an anomaly score for the electronic signature request;
determining, by the server computing device, additional authentication requirements for the electronic signature request based upon the anomaly score; and
initiating, by the server computing device, the additional authentication requirements for the electronic signature request, including validating user authentication data received from one or more remote computing devices.

### Claim 17 (depends on 16)

The method of claim 16, wherein the user credentials comprise one or more of: a username, a password, a personal identification number (PIN), and a token.

### Claim 18 (depends on 16)

The method of claim 16, wherein the parameters associated with the electronic signature request comprise one or more of: an IP address of the client computing device, a MAC address of the client computing device, location coordinates associated with the client computing device, a transaction type, a request timestamp, and the user credentials.

### Claim 19 (depends on 18)

The method of claim 18, wherein the activity variables comprise a change in the IP address, a proximity of the IP address to a prior IP address of the client computing device, a proximity of the IP address to a postal address of the user, a deviation of the request timestamp from an expected request timestamp, a deviation of the transaction type from an expected transaction type, a change in the user credentials, an account lock event associated with the user, account activity associated with the user, and identification of the transaction type on a predetermined list of transactions.

### Claim 20 (depends on 16)

The method of claim 16, wherein the trained machine learning classification model comprises a K-nearest neighbor (KNN) algorithm.

### Claim 21 (depends on 20)

The method of claim 20, wherein the trained machine learning classification model generates the anomaly score based upon a distance measure between each of the weighted values of the multidimensional vector and values of one or more centroid vectors associated with the user.

### Claim 22 (depends on 21)

The method of claim 21, wherein the centroid vector is based upon historical authentication activity associated with one or more of: the user and the client computing device.

### Claim 23 (depends on 21)

The method of claim 21, wherein the server computing device retrains the trained machine learning classification model on updated user authentication data to derive new weights for multidimensional vectors.

### Claim 24 (depends on 16)

The method of claim 16, wherein the server computing device determines that no additional authentication requirements for the electronic signature request are required when the anomaly score falls below a predefined value.

### Claim 25 (depends on 16)

The method of claim 16, wherein the server computing device determines that multifactor authentication is required when the anomaly score is above a first threshold value.

### Claim 26 (depends on 25)

The method of claim 25, wherein initiating the additional authentication requirements for the electronic signature request comprises instructing a first remote computing device to issue a multifactor authentication request to the client computing device.

### Claim 27 (depends on 26)

The method of claim 26, wherein validating user authentication data received from one or more remote computing devices comprises receiving an indicator from the first remote computing device that the client computing device has successfully responded to the multifactor authentication request.

### Claim 28 (depends on 16)

The method of claim 16, wherein the server computing device determines that active identity proofing is required when the anomaly score is above a second threshold value.

### Claim 29 (depends on 28)

The method of claim 28, wherein initiating the additional authentication requirements for the electronic signature request comprises instructing a second remote computing device to request information comprising one or more of: personally identifying information, identification document information, and biometric identity information from the user of the client computing device.

### Claim 30 (depends on 29)

The method of claim 29, wherein validating user authentication data received from one or more remote computing devices comprises receiving an indicator from the second remote computing device that the user has successfully responded to the information request.
