# US 2021/0173822 A1 · Data harmonization across multiple sources

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

- Number: US 2021/0173822 A1
- Document ID: US20210173822A1
- Status: Published application
- Kind: A1
- Application number: 16/782,754
- Filed: 2020-02-05
- Published: 2021-06-10
- Earliest claimed: 2019-12-06
- Assignees: AT&T Intellectual Property I, L.P.
- Applicants: AT&T Intellectual Property I, L.P.
- Inventors: Prince Paulraj; Shilpi Harpavat; Weiping Liu; Shreyash Taywade; Arjun Coimbatore Nagarasan; Yukun Zeng; Prabhu Gururaj
- Web page: https://patentgrep.com/patent/US20210173822A1

## CPC

- G06F 16/2272: {Management thereof}
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 30/016: After-sales
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

## Abstract

In another example, a device includes a processor and a computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations. The operations include acquiring a plurality of data items from a plurality of data sources, wherein the at least two data sources data sources of the plurality of data sources are maintained by different entities, normalizing attributes of the plurality of data items, using a first machine learning technique, matching at least two data items of the plurality of data items to form a grouping, wherein the matching is based on similarities observed in the attributes of the at least two data items subsequent to the normalizing, and creating a single profile for an individual associated with the at least two data items, based on the grouping, wherein the single profile consolidates the attributes of the at least two data items.

## Claims

### Claim 1

A method, comprising:
acquiring, by a processing system including at least one processor, a plurality of data items from a plurality of data sources, wherein the at least two data sources data sources of the plurality of data sources are maintained by different entities;
normalizing, by the processing system, attributes of the plurality of data items, using a first machine learning technique;
matching, by the processing system, at least two data items of the plurality of data items to form a grouping, wherein the matching is based on similarities observed in the attributes of the at least two data items subsequent to the normalizing; and
creating, by the processing system, a single profile for an individual associated with the at least two data items, based on the grouping, wherein the single profile consolidates the attributes of the at least two data items.

### Claim 2 (depends on 1)

The method of claim 1, wherein the different entities comprise different consumer service providers.

### Claim 3 (depends on 2)

The method of claim 2, wherein the plurality of data items comprise a plurality of customer profiles for customers of the consumer service providers.

### Claim 4 (depends on 3)

The method of claim 3, wherein the individual is one of the customers.

### Claim 5 (depends on 1)

The method of claim 1, wherein the different entities comprise different affiliates of a parent enterprise.

### Claim 6 (depends on 1)

The method of claim 1, wherein the attributes define characteristics of individuals associated with the plurality of data items, including the individual.

### Claim 7 (depends on 1)

The method of claim 1, wherein the first machine learning technique comprises a supervised machine learning technique.

### Claim 8 (depends on 1)

The method of claim 1, wherein the first machine learning technique is domain-specific.

### Claim 9 (depends on 1)

The method of claim 1, wherein the matching is performed using a second machine learning technique.

### Claim 10 (depends on 9)

The method of claim 9, wherein the second machine learning technique comprises an unsupervised machine learning technique paired with word embedding models.

### Claim 11 (depends on 9)

The method of claim 9, wherein the second machine learning technique is domain-specific.

### Claim 12 (depends on 1)

The method of claim 1, further comprising, subsequent to the matching but prior to the creating:
sending, by the processing system, the grouping to an endpoint device of the individual;
receiving, by the processing system, feedback from the individual; and
updating, by the processing system, the grouping based on the feedback.

### Claim 13 (depends on 12)

The method of claim 12, wherein the feedback comprises an indication that at least one of the at least two data items is not associated with the individual.

### Claim 14 (depends on 12)

The method of claim 12, wherein the feedback comprises an edit to at least one attribute of at least one data item of the at least two data items.

### Claim 15 (depends on 1)

The method of claim 1, further comprising:
generating, by the processing system, a recommendation for the individual, wherein the recommendation is based on an analysis of the single profile; and
sending, by the processing system, the recommendation to an endpoint device of the individual.

### Claim 16 (depends on 15)

The method of claim 15, wherein the recommendation comprises a recommended change to a service to which the individual subscribes, wherein the recommended change is expected to improve an experience of the individual with the service.

### Claim 17 (depends on 16)

The method of claim 16, wherein the service is a telecommunications service.

### Claim 18 (depends on 16)

The method of claim 16, wherein the service is a financial service.

### Claim 19

A device comprising:
a processor; and
a computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising:
acquiring a plurality of data items from a plurality of data sources, wherein the at least two data sources data sources of the plurality of data sources are maintained by different entities;
normalizing attributes of the plurality of data items, using at least one machine learning technique;
matching at least two data items of the plurality of data items to form a grouping, wherein the matching is based on similarities observed in the attributes of the at least two data items subsequent to the normalizing; and
creating a single profile for an individual associated with the at least two data items, based on the grouping, wherein the single profile consolidates the attributes of the at least two data items.

### Claim 20

A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising:
acquiring a plurality of data items from a plurality of data sources, wherein the at least two data sources data sources of the plurality of data sources are maintained by different entities;
normalizing attributes of the plurality of data items, using at least one machine learning technique;
matching at least two data items of the plurality of data items to form a grouping, wherein the matching is based on similarities observed in the attributes of the at least two data items subsequent to the normalizing; and
creating a single profile for an individual associated with the at least two data items, based on the grouping, wherein the single profile consolidates the attributes of the at least two data items.
