# US 11,113,419 B2 · Selective enforcement of privacy and confidentiality for optimization of voice applications

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

- Number: US 11,113,419 B2
- Document ID: US11113419B2
- Status: Granted
- Kind: B2
- Application number: 16/681,048
- Filed: 2019-11-12
- Published: 2020-03-12
- Granted: 2021-09-07
- Earliest claimed: 2017-08-24
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Nathalie Baracaldo Angel; Heiko H. Ludwig; Robert J. Moore; Guangjie Ren
- Web page: https://patentgrep.com/patent/US11113419B2

## CPC

- G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification}
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 21/60: Protecting data
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G10L 15/08: Speech classification or search
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 21/0208: Noise filtering
- G10L 21/0364: for improving intelligibility
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- H04K 1/04: by frequency scrambling, i.e. by transposing or inverting parts of the frequency band or by inverting the whole band
- H04K 1/06: by transmitting the information or elements thereof at unnatural speeds or in jumbled order or backwards
- H04L 63/0414: {during transmission, i.e. party's identity is protected against eavesdropping, e.g. by using temporary identifiers, but is known to the other party or parties involved in the communication}
- G10L 15/063: {Training}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 17/08: Use of distortion metrics or a particular distance between probe pattern and reference templates
- G10L 21/00: Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility (G10L19/00 takes precedence)
- H04W 12/02: Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- H04K: SECRET COMMUNICATION; JAMMING OF COMMUNICATION
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A computer-implemented method includes identifying a plurality of protected pieces from a conversation. The computer-implemented method further includes generating one or more confidence scores for each protected piece, wherein a confidence score is a degree of associativity between a protected piece and a type of sensitive information. The computer-implemented method further includes determining that the protected piece is associated with the type of sensitive information. The computer-implemented method further includes determining a type of protection action for each protected piece in the plurality of protected pieces. The computer-implemented method further includes performing the type of protection action for each protected piece in the plurality of protected pieces to form a modified conversation that is devoid of the sensitive information. A corresponding computer system and computer program product are also disclosed.

## Claims

### Claim 1

A computer-implemented method comprising:
identifying a first protected piece from a conversation, wherein the first protected piece corresponds to a portion of the conversation that includes sensitive information;
selecting, from a plurality of types of protection actions, a first type of protection action for the first protected piece, wherein a type of sensitive information associated with the first protected piece and a type of medium in which the protected piece is stored indicates from which of the plurality of types of protection actions to select; and
performing the first type of protection action on the first protected piece to form a modified conversation, wherein the modified conversation is devoid of the sensitive information.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
requesting additional clarifying information about the first protected piece based on a confidence score associated with the first protected piece falling below a given threshold level;
adjusting the confidence score, in response to receiving the additional clarifying information, to form an adjusted confidence score; and
determining that the first protected piece is associated with the first type of sensitive information based on the adjusted confidence score exceeding the given threshold level.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, further comprising:
identifying a first portion of the conversation corresponding to the first protected piece;
identifying a second portion of the conversation corresponding to a second protected piece; and
determining that the first portion corresponding to the first protected piece and the second portion corresponding to the second protected piece overlap.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, further comprising determining a conflicting overlap based, at least in part, on:
identifying the first type of protection action for the first protected piece;
identifying a second type of protection action for the second protected piece; and
determining that the first type of protection action and the second type of protection action are incompatible.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, further comprising resolving the conflicting overlap based on:
determining that a first confidence score corresponding to the first protected piece is higher than a second confidence score corresponding to the second protected piece; and
performing the first protection action for the first protected piece and the second protected piece based on the first protected piece having a higher confidence score.

### Claim 6 (depends on 4)

The computer-implemented method of claim 4, further comprising resolving the conflicting overlap based on:
determining that a first hierarchical position corresponding to the first type of protection action is higher than a second hierarchical position corresponding to the second type of protection action; and
performing the first type of protection action for the first protected piece and the second protected piece based on the first protected piece having a higher hierarchical position.

### Claim 7 (depends on 4)

The computer-implemented method of claim 4, further comprising resolving the conflicting overlap based on:
requesting additional clarifying information about the conflicting overlap; and
performing a same type of protection action for the first protected piece and the second protected piece based on the additional clarifying information.

### Claim 8

A computer program product, the computer program product comprising one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising instructions to:
identify a first protected piece from a conversation, wherein the first protected piece corresponds to a portion of the conversation that includes sensitive information;
select, from a plurality of types of protection actions, a first type of protection action for the first protected piece, wherein a type of sensitive information associated with the first protected piece and a type of medium in which the protected piece is stored indicates from which of the plurality of types of protection actions to select; and
perform the first type of protection action on the first protected piece to form a modified conversation, wherein the modified conversation is devoid of the sensitive information.

### Claim 9 (depends on 8)

The computer program product of claim 8, further comprising program instructions to:
request additional clarifying information about the first protected piece based on a confidence score associated with the first protected piece falling below a given threshold level;
adjust the confidence score, in response to receiving the additional clarifying information, to form an adjusted confidence score; and
determine that the first protected piece is associated with the first type of sensitive information based on the adjusted confidence score exceeding the given threshold level.

### Claim 10 (depends on 8)

The computer program product of claim 8, further comprising program instructions to:
identify a first portion of the conversation corresponding to the first protected piece;
identify a second portion of the conversation corresponding to a second protected piece; and
determining that the first portion corresponding to the first protected piece and the second portion corresponding to the second protected piece overlap.

### Claim 11 (depends on 10)

The computer program product of claim 10, further comprising determining a conflicting overlap based, at least in part, on program instructions to:
identify the first type of protection action for the first protected piece;
identify a second type of protection action for the second protected piece; and
determine that the first type of protection action and the second type of protection action are incompatible.

### Claim 12 (depends on 11)

The computer program product of claim 11, further comprising resolving the conflicting overlap based on program instructions to:
identify a highest confidence score between a first confidence score corresponding to the first protected piece and a second confidence score corresponding to the second protected piece; and
perform a protection action corresponding to a protected piece with the highest confidence score for each of the first protected piece and the second protected piece.

### Claim 13 (depends on 11)

The computer program product of claim 11, further comprising resolving the conflicting overlap based on program instructions to:
identify a highest hierarchical position between a first protection action corresponding to the first protected piece and a second protection action corresponding to the second protected piece; and
perform a protection action with the highest hierarchical position for each of the first protected piece and the second protected piece.

### Claim 14 (depends on 11)

The computer program product of claim 11, further comprising resolving the conflicting overlap based on program instructions to:
request additional clarifying information about the conflicting overlap; and
perform a same type of protection action for the first protected piece and the second protected piece based on the additional clarifying information.

### Claim 15

A computer system, comprising:
one or more computer processors;
one or more computer readable storage media;
computer program instructions;
the computer program instructions being stored on the one or more computer readable storage media for execution by the one or more computer processors; and
the computer program instructions comprising instructions to:
identify a first protected piece from a conversation, wherein the first protected piece corresponds to a portion of the conversation that includes sensitive information;
select, from a plurality of types of protection actions, a first type of protection action for the first protected piece, wherein a type of sensitive information associated with the first protected piece and a type of medium in which the protected piece is stored indicates from which of the plurality of types of protection actions to select; and
perform the first type of protection action on the first protected piece to form a modified conversation, wherein the modified conversation is devoid of the sensitive information.

### Claim 16 (depends on 15)

The computer system of claim 15, further comprising program instructions to:
request additional clarifying information about the first protected piece based on a confidence score associated with the first protected piece falling below a given threshold level;
adjust the confidence score, in response to receiving the additional clarifying information, to form an adjusted confidence score; and
determine that the first protected piece is associated with the first type of sensitive information based on the adjusted confidence score exceeding the given threshold level.

### Claim 17 (depends on 15)

The computer system of claim 15, further comprising program instructions to:
identify a first portion of the conversation corresponding to the first protected piece;
identify a second portion of the conversation corresponding to a second protected piece; and
determining that the first portion corresponding to the first protected piece and the second portion corresponding to the second protected piece overlap.