# US 10,372,818 B2 · User based text prediction

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

- Number: US 10,372,818 B2
- Document ID: US10372818B2
- Status: Granted
- Kind: B2
- Application number: 15/157,774
- Filed: 2016-05-18
- Published: 2017-01-19
- Granted: 2019-08-06
- Earliest claimed: 2015-07-17
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Yogesh A. Bute; Sandip P. Thube
- Web page: https://patentgrep.com/patent/US10372818B2

## CPC

- G06F 40/274: Converting codes to words; Guess-ahead of partial word inputs
- G06F 16/313: {Selection or weighting of terms for indexing}
- G06F 40/242: Dictionaries
- H04L 67/306: User profiles
- H04W 8/205: {Transfer to or from user equipment or user record carrier}
- H04L 51/063: Content adaptation, e.g. replacement of unsuitable content
- H04L 67/00: Network arrangements or protocols for supporting network services or applications (user-to-user messaging H04L51/00; network arrangements, protocols or services for supporting real-time applications in data packet communications networks H04L65/00)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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

In an approach to text prediction, a computer detects an initialization of a text-based communication between a first user and a second user. The computer determines whether a predictive text dictionary associated with the second user exists, wherein the predictive text dictionary is based, at least in part, on a history of communication between the first user and the second user. Responsive to determining a predictive text dictionary associated with the second user exists, the computer receives the text-based communication. The computer determines whether one or more words are detected in the text-based communication that do not exist in the predictive text dictionary associated with the second user. Responsive to determining one or more words are detected that do not exist in the predictive text dictionary associated with the second user, the computer adds the one or more new words to the predictive text dictionary associated with the second user.

## Claims

### Claim 1

A method for text prediction, the method comprising:
detecting, by one or more computer processors, an initialization of a text-based communication between devices associated with three or more members of a group;
determining, by the one or more computer processors, whether a group predictive text dictionary associated with the group exists, wherein a predictive text dictionary is used by a text-based application to predict and insert text into a text-based communication for a user, and wherein the group predictive text dictionary is based, at least in part, on a history of communication between the three or more members of the group;
determining, by the one or more computer processors, whether a first predictive text dictionary exists, wherein the first predictive dictionary is based, at least in part, on a history of communication between a first member of the group and a second member of the group;
determining, by the one or more computer processors, whether a second predictive text dictionary exists, wherein the second predictive text dictionary is based, at least in part, on a history of communication between the first member of the group and a third member of the group;
responsive to determining the first predictive text dictionary and the second predictive text dictionary exist, determining, by the one or more computer processors, an intersection of the first predictive text dictionary and the second predictive text dictionary, wherein the intersection is a subset of the first predictive text dictionary and the second predictive text dictionary that is common to both the first predictive text dictionary and the second predictive text dictionary;
responsive to determining a group predictive text dictionary exists, merging, by the one or more computer processors, the intersection with the group predictive text dictionary;
receiving, by the one or more computer processors, the text-based communication;
determining, by the one or more computer processors, whether one or more words are detected in the text-based communication that do not exist in the group predictive text dictionary; and
responsive to determining one or more words are detected that do not exist in the group predictive text dictionary, adding, by the one or more computer processors, the one or more new words to the group predictive text dictionary.

### Claim 2 (depends on 1)

The method of claim 1, further comprising, responsive to determining a group predictive text dictionary does not exist, creating, by the one or more computer processors, a group predictive text dictionary based, at least in part, on the text-based communication between the three or more members of the group.

### Claim 3 (depends on 1)

The method of claim 1, further comprising predicting, by the one or more computer processors, text to be added to the text-based communication by the first member of the group, based, at least in part, on the group predictive text dictionary.

### Claim 4 (depends on 1)

The method of claim 1, further comprising, responsive to determining one or more words are detected that do exist in the group predictive text dictionary increasing, by the one or more computer processors, a weight associated with the one or more words.

### Claim 5 (depends on 4)

The method of claim 4, further comprising predicting, by the one or more computer processors, text to be added to the text-based communication by the first member of the group, based, at least in part, on the weight associated with the one or more words.

### Claim 6 (depends on 1)

The method of claim 1, wherein the group predictive text dictionary includes a base predictive text dictionary.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
collecting, by the one or more computer processors, data from a user profile associated with the second member of the group;
extracting, by the one or more computer processors, one or more words from the collected data that are not included in the group predictive text dictionary for the second member of the group; and
adding, by the one or more computer processors, the extracted one or more words to the group predictive text dictionary for the second member of the group.

### Claim 8 (depends on 1)

The method of claim 1, wherein the one or more words include one or more phrases.