Text entry with word prediction, completion, or correction supplemented by search of shared corpus

Patent metadata

Field	Value
Publication number	US-9626429-B2
Application number	US-94385610-A
Country	US
Kind code	B2
Filing date	Nov 10, 2010
Priority date	Nov 10, 2010
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

Searching a shared corpus is used to supplement word prediction, completion, and/or correction of text entry. A user input device at a client device receives user entry of text input comprising a string of symbols. The client device wirelessly transmits instructions to a remote site to conduct a search of a corpus using the string as a contiguous search term. From the remote site, the client device receives results of the search, including multiple sets of one or more words, each set occurring in the corpus immediately after the search term. The client device uses the received sets in word prediction, completion, and/or correction.

First claim

The claimed invention is:

1. A method for any of word prediction, word completion, or word correction at a client device, the client device having a memory and a processor in communication with the memory, wherein the processor performs the method comprising:
storing a local primary vocabulary at the client device, wherein the local primary vocabulary pertains to any of a language, a subject matter, a functional purpose, or a content;
receiving a sequence of one or more symbols from a user through entry of a sequence of keypresses by the user;
transmitting at least a most recent portion of the sequence over a network after each of the keypresses;
updating the locally stored primary vocabulary from a corresponding remote vocabulary of a plurality of remote vocabularies over the network that pertains to the transmitted most recent portion of the sequence after each of the keypresses, when the transmitted portion of the sequence includes one or more words that overlaps both the corresponding remote vocabulary and the locally stored primary vocabulary;
receiving a new vocabulary of the plurality of remote vocabularies over the network that pertains to the transmitted most recent portion of the sequence after each of the keypresses, wherein the new vocabulary pertains to a topic, wherein the new vocabulary includes a plurality of words that correspond to the topic, when the transmitted most recent portion of the sequence includes one or more words that overlap the new vocabulary, such that the new vocabulary has associated therewith a measure of confidence above a prescribed threshold with respect to the transmitted most recent portion of the sequence, wherein the transmitted most recent portion of the sequence significantly overlaps the new vocabulary while lacking significant overlaps with the locally stored primary vocabulary and others of the plurality of remote vocabularies, wherein receiving the new vocabulary comprises
receiving a notice over the network that a new vocabulary is available that pertains to the transmitted sequence, and
downloading the new vocabulary over the network in response to the received notice;

locally storing the received new vocabulary at the client device;
receiving text entered by the user; and
for the received text, using the updated locally stored primary vocabulary or the locally stored new vocabulary for any of word prediction, completion, or word correction.

2. The method of claim 1 , further comprising:
pre-defining a profile for the user;
wherein the received new vocabulary depends on a property of the pre-defined user profile.

3. The method of claim 1 , wherein the received new vocabulary is based on any of a different language, a subject matter, a functional purposes, or a content.

4. The method of claim 1 , wherein the received new vocabulary depends on any of the client device, an application running on the client device, and a property of the user.

5. The method of claim 1 , wherein using the locally stored new vocabulary for any of word prediction, completion, or word correction comprises using the locally stored new vocabulary in combination with the locally stored primary vocabulary as a contiguous body of words.

6. The method of claim 1 , wherein using the locally stored new vocabulary for any of word prediction, completion, or word correction comprises ranking next word and word completion proposals for the user.

7. The method of claim 1 , further comprising:
transmitting an opt-in or acceptance from the user over the network to receive a new vocabulary that includes or is dedicated to profanity;
wherein the received new vocabulary includes or is dedicated to the profanity;
such that the received new vocabulary is only received by the user if wanted by the user, and is not received by the user if the new vocabulary is unwanted by the user.

8. The method of claim 1 , wherein the receiving the new vocabulary is dependent on a subscription agreement for the client device.

9. A client device, comprising:
a processor programmed to perform operations including:
storing a local primary vocabulary at the client device, wherein the local primary vocabulary pertains to any of a language, a subject matter, a functional purpose, or a content;
receiving a sequence of one or more symbols from a user through entry of a sequence of keypresses by the user;
transmitting at least a most recent portion of the sequence over a network after each of the keypresses;
updating the locally stored primary vocabulary from a corresponding remote vocabulary of a plurality of remote vocabularies over the network that pertains to the transmitted most recent portion of the sequence after each of the keypresses, when the transmitted most recent portion of the sequence includes one or more words that overlaps both the corresponding remote vocabulary and the locally stored primary vocabulary;
receiving a new vocabulary of the plurality of remote vocabularies over the network that pertains to the transmitted most recent portion of the sequence after each of the keypresses, wherein the new vocabulary pertains to a topic, when the new vocabulary includes a plurality of words that correspond to the topic, and wherein the transmitted most recent portion of the sequence includes one or more words that overlap the new vocabulary, such that the new vocabulary has associated therewith a measure of confidence above a prescribed threshold with respect to the transmitted most recent portion of the sequence, wherein the transmitted most recent portion of the sequence significantly overlaps the new vocabulary while lacking significant overlaps with the locally stored primary vocabulary and others of the plurality of remote vocabularies, wherein receiving the new vocabulary comprises
receiving a notice over the network that the new vocabulary is available that pertains to the transmitted sequence, and
downloading the new vocabulary over the network in response to the received notice;

locally storing the received new vocabulary at the apparatus;
receiving text entered by the user; and
for the received text, using the locally stored vocabulary for any of word prediction, completion, or word correction.

10. The client device of claim 9 , wherein using the locally stored new vocabulary for any of word prediction, completion, or word correction comprises using the locally new stored vocabulary in combination with the locally stored primary vocabulary as a contiguous body of words.

11. The client device of claim 9 , wherein using the locally stored new vocabulary for any of word prediction, completion, or word correction comprises ranking next word and word completion proposals for the user.

12. The client device of claim 9 , wherein the processor is further programmed to perform an operation of pre-defining a profile for the user, wherein the received new vocabulary depends on a property of the pre-defined user profile.

13. The client device of claim 9 , wherein the received new vocabulary is based on any of a different language, a subject matter, a functional purposes, or a content.

14. The client device of claim 9 , wherein the received new vocabulary depends on any of the client device, an application running on the client device, and a property of the user.

15. The client device of claim 9 , wherein the processor is further programmed to perform an operation of
transmitting an opt-in or acceptance from the user over the network to receive a new vocabulary that includes or is dedicated to profanity;
wherein the received new vocabulary includes or is dedicated to the profanity;
such that the r

Assignees

• Unruh Erland
• Nuance Communications Inc

Inventors

• Unruh Erland

Classifications

• G06F3/0237

  using prediction or retrieval techniques · CPC title

• G06F16/3322 Primary

  using system suggestions (G06F16/3325 takes precedence) · CPC title

• G06F40/232

  Orthographic correction, e.g. spell checking or vowelisation · CPC title

• G06F40/274

  Converting codes to words; Guess-ahead of partial word inputs · CPC title

• G06F17/273

  Physics · mapped topic