# US 8,751,459 B2 · Method and system to analyze email addresses

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

- Number: US 8,751,459 B2
- Document ID: US8751459B2
- Status: Granted
- Kind: B2
- Application number: 13/480,217
- Filed: 2012-05-24
- Published: 2013-11-28
- Granted: 2014-06-10
- Earliest claimed: 2012-05-24
- Assignees: App Tsunami, Inc.
- Applicants: Stephen Chan; Edbert Chan
- Inventors: Stephen Chan; Edbert Chan
- Web page: https://patentgrep.com/patent/US8751459B2

## CPC

- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- G06Q 10/40: Business processes related to social networking or social networking services
- 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

Website and newsletter operators may only have users' email addresses but not their person names. It can be beneficial for such operators to derive additional information about the email address owners so they can improve their services. However, there is no easy way to retrieve owners' information based on only email addresses. The present disclosure provides information such as the owners' names, professional profiles and aggregated statistics with only a list of email addresses as the input.

## Claims

### Claim 1

A method for analyzing an email address, comprising:
(a) isolating the user name from the email address;
(b) extracting one or more strings from the user name which, in combination, represent a candidate full name of the owner of the email address;
(c) comparing each of the one or more strings to a table comprising a plurality of real world name components and, for each real world name component, a use frequency, thereby obtaining a use frequency for each string;
(d) calculating a likelihood score for the candidate full name to be a real world full name, which calculation takes the use frequencies obtained from step (c) as input;
(e) repeating steps (b)-(d) to generate likelihood scores for a plurality of candidate full names each as a combination of different strings obtained by extracting one or more different strings from the user name; and
(f) identifying the candidate full name, from the plurality of candidate full names, that has the highest likelihood score as an approximate full name of the owner of the email address,
wherein at least one of steps (a)-(f) is performed by a computer.

### Claim 2 (depends on 1)

The method of claim 1, wherein the calculation of the likelihood score comprises the use of a name recognition algorithm.

### Claim 3 (depends on 1)

The method of claim 1, wherein the calculation of the likelihood score further comprises increasing the likelihood score if the two or more strings are separated by a special character.

### Claim 4 (depends on 3)

The method of claim 3, wherein the special character comprises a dot (“.”) or an underscore sign (“_”).

### Claim 5 (depends on 1)

The method of claim 1, wherein a likelihood score is calculated for each order of combining the strings and each of the strings is compared to a table comprising a plurality of real world name components and, for each real world name component, a use frequency for the name component to be used at the position corresponding to the position of the string in the combination.

### Claim 6 (depends on 5)

The method of claim 5, wherein the likelihood score of the candidate full name corresponds to the highest likelihood score among the likelihood scores calculated for all different orders of combining the strings.

### Claim 7 (depends on 1)

The method of claim 1, further comprising, before step (b), removing digits and/or non-conventional characters from the user name.

### Claim 8 (depends on 1)

The method of claim 1, further comprising querying a profile database with the identified approximate full name, wherein the profile database comprises profiles for a plurality of persons.

### Claim 9 (depends on 8)

The method of claim 8, wherein the query is further conducted with the domain name extracted from the email address or the name of an organization associated with the domain name.

### Claim 10 (depends on 8)

The method of claim 8, wherein a match between the identified approximate full name and an entry in the database confirms the validity of the identified approximate full name.

### Claim 11 (depends on 10)

The method of claim 10, further comprising querying a demographic database with the matched profile of the identified approximate full name to obtain demographic statistics.

### Claim 12 (depends on 11)

The method of claim 11, further comprising applying the steps to one or more email addresses of an email list, thereby generating demographic statistics for the email list.

### Claim 13 (depends on 11)

The method of claim 11, wherein the demographic database comprises, for each name in the database, an ethnic origin probability, geographical location probability and/or gender probability.

### Claim 14 (depends on 1)

The method of claim 1, further comprising querying a demographic database with the name components of the identified approximate full name to obtain demographic statistics.

### Claim 15 (depends on 1)

The method of claim 1, further comprising applying the steps to one or more email addresses of an email list, thereby generating demographic statistics for the email list.

### Claim 16 (depends on 1)

The method of claim 1, wherein in step (b) at least two strings are extracted from the user name.

### Claim 17 (depends on 16)

The method of claim 16, wherein the strings are extracted by dividing the user name.

### Claim 18

A computer system comprising a processor, memory and program code which when executed, configures the system to:
(a) isolate the user name from the email address;
(b) extract one or more strings from the user name which, in combination, represent a candidate full name of the owner of the email address;
(c) compare each of the two or more strings to a table comprising a plurality of real world name components and, for each real world name component, a use frequency, thereby obtaining a use frequency for each string;
(d) calculate a likelihood score for the candidate full name to be a real world full name, which calculation takes the use frequencies obtained from step (c) as input;
(e) repeat steps (b)-(d) to generate likelihood scores for a plurality of candidate full names each as a combination of different strings obtained by extracting one or more different strings from the user name; and
(f) identify the candidate full name, from the plurality of candidate full names, that has the highest likelihood score as an approximate full name of the owner of the email address.

### Claim 19 (depends on 18)

The computer system of claim 18, wherein in step (b) at least two strings are extracted from the user name.