# US 2021/0279370 A1 · Pseudonymizing sensitive objects in online content exchanges

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

- Number: US 2021/0279370 A1
- Document ID: US20210279370A1
- Status: Published application
- Kind: A1
- Application number: 16/807,484
- Filed: 2020-03-03
- Published: 2021-09-09
- Earliest claimed: 2020-03-03
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Sushain Pandit; Qin Qiong Zhang; Su Liu
- Web page: https://patentgrep.com/patent/US20210279370A1

## CPC

- G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification}
- G06F 21/6263: {during internet communication, e.g. revealing personal data from cookies}
- G06F 2221/2111: Location-sensitive, e.g. geographical location, GPS
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for protecting content of online conversational content. The method provides for scanning content of an online conversational exchange between a first device and a second device. A sensitive object included in the content of the online conversation exchange is identified, based on object type information accessible from a protection policy included in respective user profiles. A pseudonymized-object-holder is assigned to the identified sensitive object according to the protection policy of the respective user profiles, and the identified sensitive object identified in the content of the online conversation exchange and stored on both the first device and the second device is replaced with a pseudonymized-object-holder, based on the sensitive-object protection policy of the respective user profiles.

## Claims

### Claim 1

A method for protecting content of online conversation data, the method comprising:
one or more processors scanning content of an online conversation exchange between a first device and a second device;
the one or more processors identifying a sensitive object included in the content of the online conversation exchange, based on a sensitive-object protection policy included in respective user profiles of the first device and the second device;
the one or more processors assigning a replacement term to the identified sensitive object according to the sensitive-object protection policy included in the respective user profiles; and
the one or more processors replacing the identified sensitive object with the replacement term in the content of the online conversation exchange between the first device and the second device, stored on both the first device and the second device, based on the sensitive-object protection policy included in the respective user profiles.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
the one or more processors determining a type of a sensitive object within the content of the online conversation exchange between the first device and the second device, based on labeled data included in training activity of sensitive-object type identification.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
the one or more processors including two or more levels of classification of sensitive-object identification in a sensitive-object protection policy of the first device; and
the one or more processors providing customization of a sensitive-object type in the sensitive-object protection policy of the first device, wherein one level of classification of sensitive-object identification is customizable by a user of the first device.

### Claim 4 (depends on 3)

The method of claim 3, wherein the one level of classification of sensitive-object identification is customizable by an assigned administrator including sensitive-object types and retention periods complying with regulations.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
the one or more processors including in sensitive-object protection policies, a retention period associated with a sensitive-object type;
the one or more processors tracking a duration of time subsequent to detection of the sensitive object; and
the one or more processors performing a pseudonymization action directed at the sensitive object, subsequent to determining an expiration of the retention period associated with the sensitive-object type of the identified sensitive object.

### Claim 6 (depends on 1)

The method of claim 1, wherein the sensitive-object protection policy included in the respective user profiles includes sensitive-object types, classification of the sensitive-object types, and a retention period associated with the sensitive-object types.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
the one or more processors receiving location-specific sensitive-object types and user-based sensitive-object types;
the one or more processors receiving classification and retention period information associated respectively with the received location-specific sensitive-object types and the user-based sensitive-object types;
the one or more processors performing a training function identifying sensitive-object types by iterative processing of labeled example sensitive-object types included in online content exchanges;
the one or more processors generating a sensitive-object protection policy based on the training function identifying the sensitive-object types; and
the one or more processors providing the sensitive-object protection policy to the user profile of respective users.

### Claim 8 (depends on 1)

The method of claim 1, wherein the sensitive-object protection policy includes a set of policies structured in two or more levels, wherein each level includes identification criteria of sensitive-object types, retention period defining a time duration prior to performing pseudonymization of the identified sensitive object, and criteria for replacement of the sensitive object with a pseudonymized-object-holder as the replacement term of the sensitive object, designated during the pseudonymization.

### Claim 9

A computer program product for protecting content of online conversation data, 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:
program instructions to scan content of an online conversation exchange between a first device and a second device;
program instructions to identify a sensitive object included in the content of the online conversation exchange, based on a sensitive-object protection policy included in respective user profiles of the first device and the second device;
program instructions to assign a replacement term to the identified sensitive object according to the sensitive-object protection policy included in the respective user profiles; and
program instructions to replace the identified sensitive object with the replacement term in the content of the online conversation exchange between the first device and the second device, stored on both the first device and the second device, based on the sensitive-object protection policy included in the respective user profiles.

### Claim 10 (depends on 9)

The computer program product of claim 9, further comprising:
program instructions to determine a type of a sensitive object within the content of the online conversation exchange between the first device and the second device, based on labeled data included in training activity of sensitive-object type identification.

### Claim 11 (depends on 9)

The computer program product of claim 9, further comprising:
program instructions to include in a sensitive-object protection policy of the first device, two or more levels of classification of sensitive-object identification; and
program instructions to provide customization of a sensitive-object type in the sensitive-object protection policy of the first device, wherein one level of classification of sensitive-object identification is customizable by a user of the first device.

### Claim 12 (depends on 9)

The computer program product of claim 9, wherein at least one level of classification of sensitive-object identification is customizable by an assigned administrator including sensitive-object types and retention periods complying with regulations.

### Claim 13 (depends on 9)

The computer program product of claim 9, further comprising:
program instructions to include in sensitive-object protection policies, a retention period associated with a sensitive-object type;
program instructions to track a duration of time subsequent to detection of the sensitive object; and
program instructions to perform a pseudonymization action directed at the sensitive object, subsequent to determining an expiration of the retention period associated with the sensitive-object type of the identified sensitive object.

### Claim 14 (depends on 9)

The computer program product of claim 9, wherein the sensitive-object protection policy included in the respective user profiles includes sensitive-object types, classification of the sensitive-object types, and a retention period associated with the sensitive-object types.

### Claim 15 (depends on 9)

The computer program product of claim 9, further comprising:
the one or more processors receiving location-specific sensitive-object types and user-based sensitive-object types;
the one or more processors receiving classification and retention period information associated respectively with the received location-specific sensitive-object types and the user-based sensitive-object types;
the one or more processors performing a training function identifying sensitive-object types by iterative processing of labeled example sensitive-object types included in online content exchanges;
the one or more processors generating a sensitive-object protection policy based on the training function identifying the sensitive-object types; and
the one or more processors providing the sensitive-object protection policy to the user profile of respective users.

### Claim 16

A computer system for protecting content of online conversation data, the computer system comprising:
one or more computer processors;
one or more computer readable storage media; and
program instructions stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to scan content of an online conversation exchange between a first device and a second device;
program instructions to identify a sensitive object included in the content of the online conversation exchange, based on a sensitive-object protection policy included in respective user profiles of the first device and the second device;
program instructions to assign a replacement term to the identified sensitive object according to the sensitive-object protection policy included in the respective user profiles; and
program instructions to replace the identified sensitive object with the replacement term in the content of the online conversation exchange between the first device and the second device, stored on both the first device and the second device, based on the sensitive-object protection policy of the respective user profiles.

### Claim 17 (depends on 16)

The computer system of claim 16, further comprising:
program instructions to determine a type of a sensitive object within the content of the online conversation exchange between the first device and the second device, based on labeled data included in training activity of sensitive-object type identification;
program instructions to include two or more levels of classification of sensitive-object type identification in a sensitive-object protection policy of the first device;
program instructions to provide customization of a sensitive-object type of one level of classification of sensitive-object identification by a user of the first device; and
program instructions to provide customization of one level of classification of sensitive-object identification by an assigned administrator including sensitive-object types and retention periods complying with regulations.

### Claim 18 (depends on 16)

The computer system of claim 16, wherein the sensitive-object protection policy included in the respective user profiles includes sensitive-object types, classification of the sensitive-object types, and a retention period associated with the sensitive-object types.

### Claim 19 (depends on 16)

The computer system of claim 16, further comprising:
program instructions to receive location-specific sensitive-object types and user-based sensitive-object types;
program instructions to receive classification and retention period information associated respectively with the received location-specific sensitive-object types and the user-based sensitive-object types; and
program instructions to perform a training function identifying sensitive-object types by iterative processing of labeled example sensitive-object types included in online content exchanges;
program instructions to generate a sensitive-object protection policy based on the training function identifying the sensitive-object types; and
program instructions to provide the sensitive-object protection policy to the user profile of respective users.

### Claim 20 (depends on 16)

The computer system of claim 16, wherein the sensitive-object protection policy includes a set of policies structured in two or more levels, wherein each level includes identification criteria of sensitive-object types, retention period defining a time duration prior to performing pseudonymization of the identified sensitive object, and the criteria for replacement of the sensitive object with a pseudonymized-object-holder as the replacement term, designated during the pseudonymization.
