Blending customized user dictionaries based on frequency of usage

Patent metadata

Field	Value
Publication number	US-9977774-B2
Application number	US-201514956122-A
Country	US
Kind code	B2
Filing date	Dec 1, 2015
Priority date	Feb 14, 2012
Publication date	May 22, 2018
Grant date	May 22, 2018

Abstract

A set of customized dictionaries may be constructed for a particular user, each of the customized dictionaries including a different blending of one or more frequently used words collected from texts submitted by one or more users. A copy of the customized dictionaries may be sent to each of a plurality of electronic devices associated with the particular user to be stored on the electronic device and to aid the particular user in inputting text to the electronic device.

First claim

What is claimed is:

1. A method comprising:
collecting words entered as textual input across a plurality of communication channels and dimensions;
wherein each communication channel comprises an object being used for communication of the textual input or an input device used to submit the textual input; and
wherein each dimension comprises one of a geographic location of the communication, a culture, a form of communication, or an intended recipient;
analyzing a usage frequency of each word in each communication category, wherein a communication category is a channel-dimension combination;
sorting the words in each communication category from most frequently used to least frequently used according to the usage frequency;
constructing one or more customized dictionaries, each of the customized dictionaries comprising a different blend of a number of the most frequently used words from selected communication categories, wherein the communication categories are selected based on the intended use of the dictionary; and
sending, to each of one or more electronic devices, the one or more customized dictionaries.

2. The method of claim 1 , comprising:
receiving a selection of a word from one of the plurality of customized dictionaries from an electronic device.

3. The method of claim 2 , comprising:
determining one or more customized advertisements based on the selected word; and
sending, to an electronic device, information to present one or more of the customized advertisements on the electronic device.

4. The method of claim 1 , comprising:
determining customized advertisements based on one or more words included in one of the customized dictionaries; and
sending, to an electronic device having the one of the customized dictionaries, information to present one or more of the customized advertisements on the electronic device.

5. The method of claim 1 , comprising:
collecting additional words entered as textual input across the plurality of communication channels; and
updating the plurality of customized dictionaries according to the additional words.

6. The method of claim 1 further comprising:
assigning a coefficient to each connection category or to a number of the most frequently used words in each connection category;
wherein the blending of the most frequently used words in the selected connection categories can be adjusted by adjusting the assigned coefficients.

7. The method of claim 6 wherein the assigned coefficients may be adjusted based upon an affinity, the affinity being based upon a user's historical activity.

8. The method of claim 6 wherein the assigned coefficients may be adjusted based upon social information of a user maintained on a social networking website.

9. A system comprising:
memory to store instructions to manage custom dictionaries; and
a processor coupled to the memory, the processor to execute the instructions to:
collect words entered as textual input across a plurality of communication channels and dimensions;
wherein each communication channel comprises an object being used for communication of the textual input or an input device used to submit the textual input; and
wherein each dimension comprises one of a geographic location of the communication, a culture, a form of communication, or an intended recipient;
analyze a usage frequency of each word in each communication category, wherein a communication category is a channel-dimension combination;
sort the words in each communication category from most frequently used to least frequently used according to the usage frequency; and
construct one or more customized dictionaries, each customized dictionary to comprise a different blend of a number of the most frequently used words from selected communication categories, wherein the communication categories are selected based on the intended use of the dictionary.

10. The system of claim 9 , the processor to execute the instructions to receive a selection of a word from one of the plurality of customized dictionaries from an electronic device.

11. The system of claim 10 , the processor to execute the instructions to determine one or more customized advertisements based on the selected word or on one or more words included in one of the plurality of customized dictionaries, and to send, to the electronic device, information to present one or more of the customized advertisements on the electronic device.

12. The system of claim 9 , the processor to execute the instructions to collect additional words entered as textual input across the plurality of communication channels and to update the plurality of customized dictionaries according a usage frequency of the additional words.

13. The system of claim 9 , the processor to execute the instructions to:
assign a coefficient to each connection category or to a number of the most frequently used words in each connection category;
wherein the blending of the most frequently used words in the selected connection categories can be adjusted by adjusting the assigned coefficients.

14. The system of claim 13 , wherein the assigned coefficients may be adjusted based upon an affinity, the affinity being based upon a user's historical activity, or upon social information of a user maintained on a social networking website.

15. One or more non-transitory computer-readable storage media embodying software operable when executed by one or more computer systems to:
collect words entered as textual input across a plurality of communication channels and dimensions;
wherein each communication channel comprises an object being used for communication of the textual input or an input device used to submit the textual input; and
wherein each dimension comprises one of a geographic location of the communication, a culture, a form of communication, or an intended recipient;
analyze a usage frequency of each word in each communication category, wherein a communication category is a channel-dimension combination;
sort the words in each connection category from most frequently used to least frequently used according to the usage frequency;
construct one or more customized dictionaries, each of the customized dictionaries comprising a different blend of a number of the most frequently used words from selected communication categories, wherein the communication categories are selected based on the intended use of the dictionary; and
send, to an electronic device, the one or more customized dictionaries.

16. The non-transitory computer-readable storage media of claim 15 , embodying software operable when executed by the one or more computer systems to:
receive a selection of a word from one of the plurality of customized dictionaries from an electronic device.

17. The non-transitory computer-readable storage media of claim 15 , embodying software operable when executed by one of the one or more computer systems to:
determine one or more customized advertisements based on the selected word, or on one or more words included in one of the customized dictionaries; and
send, to an electronic device, information to present one or more of the customized advertisements on the electronic device.

18. The non-transitory computer-readable storage media of claim 15 , embodying software operable when executed by the one or more computer systems to:
collect additional words entered as textual input across the plurality of communication channels; and
update the plurality of customized dictionaries according to a usage frequency of the additional words.

Assignees

• Facebook Inc

Inventors

• Tseng Erick
• Gandhi Shaheen Ashok
• Kramer Adam D I
• St Clair Luke

Classifications

• G06F40/232 Primary

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

• G06F40/274

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

• G06F40/242 Primary

  Dictionaries · CPC title

• G06F40/263

  Language identification · CPC title

• G06F17/276

  Physics · mapped topic