# US 2021/0081385 A1 · Systems and methods for providing searchable customer call indexes

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

- Number: US 2021/0081385 A1
- Document ID: US20210081385A1
- Status: Published application
- Kind: A1
- Application number: 17/106,452
- Filed: 2020-11-30
- Published: 2021-03-18
- Earliest claimed: 2012-12-17
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Nikhil Murgai
- Web page: https://patentgrep.com/patent/US20210081385A1

## CPC

- G06F 16/2228: {Indexing structures}
- G06F 16/258: {Data format conversion from or to a database}
- G06F 16/61: Indexing; Data structures therefor; Storage structures
- G06F 21/6209: {to a single file or object, e.g. in a secure envelope, encrypted and accessed using a key, or with access control rules appended to the object itself}
- G10L 15/08: Speech classification or search
- G10L 25/90: Pitch determination of speech signals
- H04M 3/2218: {Call detail recording}
- H04M 3/5175: {Call or contact centers supervision arrangements}
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- H04M 3/51: Centralised call answering arrangements requiring operator intervention {, e.g. call or contact centers for telemarketing}
- H04M 2201/40: using speech recognition
- H04M 2203/2038: Call context notifications
- 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
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

A system and method is provided for providing searchable customer call indexes. Consistent with disclosed embodiments, a system may receive call information associated with telephone conversations between callers and a vendor, the call information including an audio recording or transcript for each telephone conversation. The system may also identify one or more keywords from the audio recordings or transcripts and index the call information into one or more indexes based on the identified keywords. Finally, the system may determine search results responsive to a search query based on the indexing. In some embodiments, changes to customer service may be identified based on the search results.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A system for grouping and analyzing call information using searchable call storage, comprising:
one or more memory devices storing instructions; and
one or more processors configured to execute the instructions to perform operations comprising:
receiving call information associated with a plurality of calls between a caller and a vendor;
identifying a first set of the calls based on a first frequency of at least one of a keyword, a phrase, or a stress feature identified in content of the calls;
identifying a second set of the calls based on a second frequency of at least one of a keyword, a phrase, or a stress feature identified in content of the calls;
storing, in a first storage location, first call information associated with the first set of calls;
storing, in a second storage location, second call information associated with the second set of calls;
generating search results from a search of at least one of the first or second storage locations according to a search query; and
analyzing the search results to determine patterns in the search results.

### Claim 22 (depends on 21)

The system of claim 21, the operations further comprising identifying agents, associated with a vendor, who are insufficiently trained in resolving caller issues, according to customer interaction criteria.

### Claim 23 (depends on 22)

The system of claim 22, the operations further comprising analyzing the search results to identify calls in which at least one of the agents acted in an undesired manner toward a caller in at least one of the calls, according to the customer interaction criteria.

### Claim 24 (depends on 21)

The system of claim 21, wherein:
the call information comprises voiceprints of the calls;
the operations further comprise identifying a stress feature in at least one of the voiceprints; and
identifying the first set of calls comprises identifying the first set of calls based on the stress feature.

### Claim 25 (depends on 24)

The system of claim 24, wherein identifying the stress feature comprises determining, in a first portion of one of the calls, a change in at least one of volume, speed, or pitch of a voice of a caller as compared to a second portion of the one of the calls.

### Claim 26 (depends on 21)

The system of claim 21, the operations further comprising designing company changes based on the determined patterns.

### Claim 27 (depends on 26)

The system of claim 26, wherein the company changes comprise training an agent, associated with the vendor, in accordance with customer interaction criteria.

### Claim 28

A method for searchable call storage analysis, comprising:
receiving call information associated with a plurality of calls between a caller and a vendor;
identifying a first set of the calls based on a first frequency of at least one of: a keyword, a phrase, or a stress feature identified in content of the calls;
identifying a second set of the calls based on a second frequency of at least one of: a keyword, a phrase, or a stress feature identified in content of the calls;
storing, in a first storage location, first call information associated with the first set of calls;
storing, in a second storage location, second call information associated with the second set of calls;
generating search results from a search of at least one of the first or second storage locations according to a search query; and
analyzing the search results to determine patterns in the search results.

### Claim 29 (depends on 28)

The method of claim 28, further comprising identifying agents, associated with a vendor, who are insufficiently trained in resolving caller issues, according to customer interaction criteria.

### Claim 30 (depends on 29)

The method of claim 29, further comprising analyzing the search results to identify calls in which at least one of the agents acted in an undesired manner toward a caller in at least one of the calls, according to the customer interaction criteria.

### Claim 31 (depends on 28)

The method of claim 28, wherein:
the call information comprises voiceprints of the calls;
the method further comprises identifying a stress feature in at least one of the voiceprints; and
identifying the first set of calls comprises identifying the first set of calls based on the stress feature.

### Claim 32 (depends on 31)

The method of claim 31, wherein identifying the stress feature comprises determining, in a first portion of one of the calls, a change in at least one of volume, speed, or pitch of a voice of a caller as compared to a second portion of the one of the calls.

### Claim 33 (depends on 28)

The method of claim 28, further comprising designing company changes based on the determined patterns.

### Claim 34 (depends on 33)

The method of claim 33, wherein the company changes comprise training an agent, associated with the vendor, in accordance with customer interaction criteria.

### Claim 35

A non-transitory computer readable medium including instructions that, when executed by at least one processor, cause the at least one processor to perform operations for designing company changes based on analysis of searchable call storage, the operations comprising:
receiving call information associated with a plurality of calls between a caller and a vendor;
identifying a first set of the calls based on a first frequency of at least one of: a keyword, a phrase, or a stress feature identified in content of the calls;
identifying a second set of the calls based on a second frequency of at least one of: a keyword, a phrase, or a stress feature identified in content of the calls;
storing, in a first storage location, first call information associated with the first set of calls;
storing, in a second storage location, second call information associated with the second set of calls;
generating search results from a search of at least one of the first or second storage locations according to a search query;
analyzing the search results to determine patterns in the search results; and
designing company changes based on the patterns.

### Claim 36 (depends on 35)

The non-transitory computer readable medium of claim 35, further comprising identifying agents, associated with a vendor, who are insufficiently trained in resolving caller issues, according to customer interaction criteria.

### Claim 37 (depends on 36)

The non-transitory computer readable medium of claim 36, further comprising analyzing the search results to identify calls in which at least one of the agents acted in an undesired manner toward a caller in at least one of the calls, according to the customer interaction criteria.

### Claim 38 (depends on 35)

The non-transitory computer readable medium of claim 35, wherein:
the call information comprises voiceprints of the calls;
the operations further comprise identifying a stress feature in at least one of the voiceprints; and
identifying the first set of calls comprises identifying the first set of calls based on the stress feature.

### Claim 39 (depends on 38)

The non-transitory computer readable medium of claim 38, wherein identifying the stress feature comprises determining, in a first portion of one of the calls, a change in at least one of volume, speed, or pitch of a voice of a caller as compared to a second portion of the one of the calls.

### Claim 40 (depends on 35)

The non-transitory computer readable medium of claim 35, wherein the company changes comprise training an agent, associated with the vendor, in accordance with customer interaction criteria.
