# US 2021/0084145 A1 · Method for conversion and classification of data based on context

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

- Number: US 2021/0084145 A1
- Document ID: US20210084145A1
- Status: Published application
- Kind: A1
- Application number: 16/939,759
- Filed: 2020-07-27
- Published: 2021-03-18
- Earliest claimed: 2019-09-17
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Vincent PHAM; Fardin Abdi Taghi ABAD; Reza FARIVAR; Kate KEY; Anh TRUONG; Jeremy GOODSITT; Austin WALTERS
- Web page: https://patentgrep.com/patent/US20210084145A1

## CPC

- H04M 3/42221: {Conversation recording systems (at the subscriber's set H04M1/656)}
- G06F 16/3329: Natural language query formulation
- G06F 16/355: Creation or modification of classes or clusters
- G06F 16/685: {using automatically derived transcript of audio data, e.g. lyrics (speech recognition G10L15/00)}
- G06N 20/00: Machine learning
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- H04M 3/42042: {Notifying the called party of information on the calling party (details within substation equipment H04M1/57, signalling details H04Q3/72)}
- H04M 3/5166: {in combination with interactive voice response systems or voice portals, e.g. as front-ends}
- H04M 3/5175: {Call or contact centers supervision arrangements}
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- H04M 2201/18: Comparators
- H04M 2201/38: Displays
- H04M 2201/40: using speech recognition
- H04M 2203/2061: Language aspects
- H04M 2203/357: Autocues for dialog assistance
- H04M 2203/401: Performance feedback
- H04M 2203/551: Call history
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

When a new communication is received at a server, the system can generate machine readable data pertaining to the communication, e.g., a transcript for the communication. Using the transcript, the system can utilize natural language processing techniques to find at least one request in the communication. The system can search summaries of prior communications, and if there is a communication including a similar request, the system can display a record of the prior communication.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method comprising:
providing a database including a plurality of transcripts of phone calls and chat messages, each transcript being associated with at least one discussion attribute label selected from a group of labels including a plurality of discussion attribute labels;
receiving, at a chatbot, a first chat message including a first transcript;
performing a natural language processing technique to determine a first discussion attribute of the first transcript;
associating, using a machine learning model, the first transcript with a first discussion attribute label selected from the group of labels;
determining whether the first discussion attribute label matches the one discussion attribute label associated with any of the plurality of transcripts;
in response to a determination that the first discussion attribute label matches the one discussion attribute label, displaying a first report of a first matched transcript which is the transcript associated with the one discussion attribute label, wherein the first report of the transcript includes a summary of the first matched transcript; and
in response to a determination that the first discussion attribute label does not match the one discussion attribute label, displaying a message indicating that there is no match in the database.

### Claim 22 (depends on 21)

The method of claim 21, wherein the chatbot is a computer program configured to conducts a conversation via auditory methods or textual methods.

### Claim 23 (depends on 21)

The method of claim 21, wherein, in response to receiving a message from a user, the chatbot is configured to classify information included in the message.

### Claim 24 (depends on 21)

The method of claim 21, wherein the chatbot is configured to transfer a conversation to a user.

### Claim 25 (depends on 21)

The method of claim 21, wherein the first report includes an identity of a participant in a chat conversation associated with the first matched transcript.

### Claim 26 (depends on 21)

The method of claim 21, wherein the first report includes a statement of a problem discussed in the first matched transcript.

### Claim 27 (depends on 21)

The method of claim 21, wherein the natural language processing technique uses a second machine learning model.

### Claim 28 (depends on 27)

The method of claim 27, further comprising receiving a feedback input reflecting a quality of the determination of the first discussion attribute of the first transcript.

### Claim 29 (depends on 28)

The method of claim 28, further comprising training the second machine learning model using the feedback input as training data.

### Claim 30 (depends on 21)

The method of claim 21, further comprising receiving a feedback input reflecting a quality of the association of the first transcript with the first discussion attribute label.

### Claim 31 (depends on 30)

The method of claim 30, further comprising training the machine learning model using the feedback input as training data.

### Claim 32 (depends on 21)

The method of claim 21, further comprising:
performing the natural language processing technique to determine a second discussion attribute of the first transcript;
associating, using the machine learning model, the first transcript with a second discussion attribute label selected from the group of labels;
determining whether the second discussion attribute label matches the one discussion attribute label associated with any of the plurality of transcripts;
in response to a determination that the second discussion attribute label matches the one discussion attribute label, displaying a combined report; and
in response to a determination that the second discussion attribute label does not match the one discussion attribute label of any of the plurality of transcripts, continue displaying the first report.

### Claim 33 (depends on 32)

The method of claim 32, wherein the combined report includes:
the first report; and
a second report of a second matched transcript which is the transcript associated with the one discussion attribute label matching the second discussion attribute label, wherein the second report includes a summary of the second matched transcript.

### Claim 34 (depends on 32)

The method of claim 32, wherein the combined report includes a problem statement associated with the first matched transcript and a problem statement associated with the second matched transcript.

### Claim 35 (depends on 32)

The method of claim 32, wherein the combined report includes a time from the first matched transcript and a time from the second matched transcript.

### Claim 36 (depends on 32)

The method of claim 32, wherein the combined report includes an identity of an individual from the first matched transcript and an identity of an individual from the second matched transcript.

### Claim 37 (depends on 21)

The method of claim 21, wherein the natural language processing technique uses keywords to prepare the first report.

### Claim 38 (depends on 37)

The method of claim 37, wherein the keywords indicate parts of the first transcript that are relevant.

### Claim 39 (depends on 38)

The method of claim 38, wherein the parts of the first transcript that are relevant are a problem statement, a resolution statement, a cause of the problem, or a possible solution offered to the problem.

### Claim 40 (depends on 39)

The method of claim 39, wherein the problem statement, the resolution statement, the cause of the problem, or the possible solution are stored in association with the first matched transcript.
