# US 12,192,402 B2 · Customer distress assistance

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

- Number: US 12,192,402 B2
- Document ID: US12192402B2
- Status: Granted
- Kind: B2
- Application number: 17/869,292
- Filed: 2022-07-20
- Published: 2024-01-25
- Granted: 2025-01-07
- Earliest claimed: 2022-07-20
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Salik Shah; Jennifer Kwok; Abhay Donthi; Dwij Trivedi; Leeyat Bracha Tessler
- Web page: https://patentgrep.com/patent/US12192402B2

## CPC

- H04M 3/2281: {Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls}
- A61B 5/0205: Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B 5/165: {Evaluating the state of mind, e.g. depression, anxiety}
- A61B 5/4803: {Speech analysis specially adapted for diagnostic purposes}
- A61B 5/6898: {Portable consumer electronic devices, e.g. music players, telephones, tablet computers}
- A61B 5/7267: {involving training the classification device}
- G06F 40/30: Semantic analysis
- A61B 5/024: Measuring pulse rate or heart rate
- G10L 25/63: for estimating an emotional state
- H04M 2203/6027: Fraud preventions
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Disclosed aspects and embodiments pertain to customer distress assistance. A call can be detected to a callee from a caller. The call can be analyzed and determined to be a fraud or spam risk. In response, callee monitoring is triggered. The monitoring can capture biometrics or speech of the callee. Distress in the callee can be determined through analysis of the biometrics or speech and comparison to reference biometrics or speech of the callee. An individual associated with the callee can be selected based on determining the distress in the customer. The individual can be contacted through a notification or a call to assist the callee in distress.

## Claims

### Claim 1

A system, comprising:
a processor coupled to a memory that includes instructions that, when executed by the processor, cause the processor to:
detect an incoming phone call;
analyze the incoming phone call between a caller and a callee in real time with conversational analysis;
classify the incoming phone call as a fraud risk based on the conversational analysis;
trigger monitoring of a physical metric of the callee based on the classification of the incoming call as a fraud risk;
compare the physical metric to a reference physical metric to determine a divergence between the physical metric and the reference physical metric;
detect a sign of distress of the callee based on the divergence;
select an individual associated with the callee after detection of the sign of distress, wherein the individual is selected based on determining availability of a set of individuals; and
send a notification in real time to the individual associated with the callee, wherein the notification reveals the sign of distress to the callee.

### Claim 2 (depends on 1)

The system of claim 1, wherein the instructions further cause the processor to collect biometric data from a sensor to monitor the physical metric.

### Claim 3 (depends on 1)

The system of claim 1, wherein the instructions further cause the processor to invoke a conversational model trained to recognize problem words and phrases with natural language processing to classify the phone call as a fraud risk.

### Claim 4 (depends on 1)

The system of claim 1, wherein the instructions further cause the processor to:
detect the caller is originating from a blocklist source; and
classify the incoming phone call as a fraud risk based on the conversational analysis and the detection of the caller as originating from the blocklist source.

### Claim 5 (depends on 1)

The system of claim 1, wherein the instructions further cause the processor to:
access contact information of the individual; and
automatically join the individual to the phone call.

### Claim 6 (depends on 1)

The system of claim 1, wherein the instructions further cause the processor to activate a security control for the phone call that is a fraud risk, wherein the security control is one of mute, interrupt prompt, forced disconnect, or automated transfer of the phone call to the individual.

### Claim 7 (depends on 1)

The system of claim 1, wherein the instructions further cause the processor to access social media data of the individual to determine availability.

### Claim 8 (depends on 1)

The system of claim 1, wherein the instructions further cause the processor to collect biometric data from a wearable device to monitor the physical metric.

### Claim 9

A method, comprising:
executing, on a processor, instructions that cause the processor to perform operations, the operations comprising:
detecting an incoming call;
analyzing a conversation between a caller and a callee in real time with conversation analysis;
classifying the incoming call as a fraud risk to a callee based on the conversation analysis;
triggering monitoring of a physical metric of the callee in response to the classification of the incoming call as a fraud risk;
comparing the physical metric to a reference physical metric to determine a divergence between the physical metric and the reference physical metric;
detecting a sign of distress of the callee based on the divergence;
selecting an individual associated with the callee after detection of the sign of distress, wherein the individual is selected from a set of available individuals associated with the callee; and
transmitting a notification in real time to a selected individual that reveals the sign of distress of the callee.

### Claim 10 (depends on 9)

The method of claim 9, wherein the monitoring comprises collecting biometric data from the callee from a sensor.

### Claim 11 (depends on 10)

The method of claim 10, further comprising collecting the biometric data from a sensor of a wearable device.

### Claim 12 (depends on 9)

The method of claim 9, wherein analyzing the conversation comprises invoking a conversational model trained to recognize problem words and phrases with natural language processing to classify the call as a fraud risk.

### Claim 13 (depends on 9)

The method of claim 9, wherein the operations further comprise:
detecting the incoming call originates from a source that is on a blocklist of known fraudulent callers; and
classifying the incoming call as fraudulent based on the conversation analysis and the detection of the incoming call as originating from the source.

### Claim 14 (depends on 9)

The method of claim 9, wherein the operations further comprise determining availability of an individual based on social media data of the individual.

### Claim 15 (depends on 9)

The method of claim 9, wherein the operations further comprise:
accessing contact information of the individual that is selected; and
joining the individual to the call with the caller and callee.

### Claim 16 (depends on 9)

The method of claim 9, wherein the operations further comprise activating a security control for the callee that blocks transactions to a financial account of the callee.

### Claim 17

A method of distress assistance, comprising:
detecting an incoming call with a call manager executing on a computing device;
analyzing a conversation between a caller and callee in near real time;
classifying the incoming call as a spam risk based on conversation analysis;
automatically triggering, by the call manager, monitoring of a physical metric of the callee based on the classification of the incoming call as a spam risk;
detecting distress of the callee based on divergence of the physical metric of the callee from a reference physical metric;
selecting an individual associated with the callee in response to detecting the distress, wherein the individual is selected based on determining availability of a set of individuals; and
sending a notification of the distress of the callee in near-real time to a selected individual.

### Claim 18 (depends on 17)

The method of claim 17, analyzing the conversation further comprising:
monitoring a voice characteristic of the callee;
comparing the voice characteristic of the callee to a voice profile characteristic of the callee;
detecting a distress sentiment based on determining a difference between the voice characteristic and the voice profile characteristic; and
identifying distress of the callee based on the distress sentiment.

### Claim 19 (depends on 17)

The method of claim 17, further comprising:
pausing the conversation between the caller and the callee; and
calling the individual selected to provide assistance to the callee.

### Claim 20 (depends on 17)

The method of claim 17, further comprising activating a security control to at least one of mute, interrupt prompt, or forced disconnect of the call in response to classification as a spam risk.