# US 2013/0159920 A1 · Scenario-adaptive input method editor

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

- Number: US 2013/0159920 A1
- Document ID: US20130159920A1
- Status: Published application
- Kind: A1
- Application number: 13/331,023
- Filed: 2011-12-20
- Published: 2013-06-20
- Earliest claimed: 2011-12-20
- Assignees: Microsoft Corporation
- Inventors: Matthew Robert Scott; Huihua Hou; Weipeng Liu; Hao Wei; Chiwei Che; Byron Huntley Changuion; Weijian Xu; Xi Chen
- Web page: https://patentgrep.com/patent/US20130159920A1

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/9537: Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
- G06F 40/166: Editing, e.g. inserting or deleting
- G06F 40/274: Converting codes to words; Guess-ahead of partial word inputs
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An input method editor (IME) described herein couples scenarios of the input of the user with specific network services to offer more relevant and richer candidates for higher input productivity. Data relating to a computer application in which the input candidates are to be input and/or context relating to a user-submitted query is collected and analyzed to determine a scenario. The input candidates may include text candidates and rich candidates. The IME may select a scenario-tuned and type specific engine to identify the text candidates and/or rich candidates. The scenario-tuned text candidate engines leverage scenario-tuned language models and lexicons, and the scenario-tuned rich candidate engines leverage scenario-relevant web services, such as image, mapping, and video search, when available and appropriate.

## Claims

### Claim 1

A method comprising:
determining that a user is using an input method editor (IME) to input one or more input candidates into a user interface of a computer application;
determining a scenario of an input of the user;
determining one or more queries input by the user into a user interface of the IME;
determining a desired type of input candidate to be presented at the user interface of the IME at least partly based on the scenario; and
identifying or generating the one or more input candidates at least partly based on their relevancies to the scenario, the queries, and the desired type of input candidates.

### Claim 2 (depends on 1)

A method as recited in claim 1, further comprising ranking the one or more input candidates at least partly based on their relevancies to the scenario.

### Claim 3 (depends on 1)

A method as recited in claim 1, wherein determining the scenario of the input of the user comprises:
collecting data relating to the scenario of the input of the user; and
analyzing the collected data to determine the scenario of the input of the user.

### Claim 4 (depends on 3)

A method as recited in claim 3, wherein the data comprise data relating to a scenario of the computer application to which the user is to input the input candidates.

### Claim 5 (depends on 3)

A method as recited in claim 3, wherein the data comprise a context of the queries in view of contents displayed at a user interface of the computer application.

### Claim 6 (depends on 1)

A method as recited in claim 1, the desired type of input candidate comprises a text candidate, a rich candidate, or both of a text candidate and a rich candidate.

### Claim 7 (depends on 1)

A method as recited in claim 1, wherein the identifying comprises:
identifying an engine pool, the engine pool including a plurality of input search engines, each input search engine being preset to search a specific type of input candidate applicable to a specific scenario;
selecting an input search engine preset for the specific type of input candidate applicable to the specific scenario; and
using the input search engine to identify the input candidates.

### Claim 8 (depends on 1)

A method as recited in claim 1, further comprising presenting the input candidates including both text candidates and rich candidates at the user interface of the IME.

### Claim 9 (depends on 1)

A method as recited in claim 1, wherein the user interface includes a text candidate window and a rich candidate window; and the presenting comprises:
presenting the text candidates in a text candidate window; and
presenting the rich candidates in a rich candidate window.

### Claim 10

One or more computer storage media having stored thereupon a plurality of computer executable instructions that, when executed a processor, causes the processor to perform operations comprising:
determining that a user is using an input method editor (IME) to input one or more input candidates into a user interface of a computer application;
determining a scenario of an input of the user;
determining one or more queries input by the user into a user interface of the IME;
determining that a desired type of input candidate to be presented at the user interface of the IME includes one or more rich candidates; and
identifying or generating the rich candidates at least partly based on their relevancies to the scenario and the queries.

### Claim 11 (depends on 10)

One or more computer storage medium as recited in claim 10, wherein the rich candidates include an image, a video, or an address book entry.

### Claim 12 (depends on 10)

One or more computer storage medium as recited in claim 10, wherein the rich candidates include an optimal representation form of an input candidate in view of the scenario.

### Claim 13 (depends on 10)

One or more computer storage medium as recited in claim 10, wherein the identifying comprises:
finding different sources of the rich candidates; and
representing the different sources in the user interface for the user to view rich candidates from each source.

### Claim 14 (depends on 10)

One or more computer storage medium as recited in claim 10, wherein the identifying comprises using web services to search rich candidates by using the scenario and queries as parameters.

### Claim 15 (depends on 10)

One or more computer storage medium as recited in claim 10, wherein the identifying or generating comprises:
storing an authentication credential of a user to a web service;
accessing the web service by using the authentication credential;
searching information stored at the web service based on the queries to identify the rich candidates.

### Claim 16 (depends on 10)

One or more computer storage medium as recited in claim 10, further comprising presenting the rich candidates in an embedded web browser using a hypertext markup language (HTML) 5.0 format.

### Claim 17

A system comprising:
memory storing one or more modules;
one or more processors operably coupled to the memory to execute one or more modules, the one or more modules including:
a user interface that receives one or more queries from a user;
a collection component that collects data relating to a scenario of an input of the user, the data including data relating to a scenario of a computer application to which the user is to input one or more input candidates and a context of the queries in view of contents displayed at a user interface of the computer application;
an analysis component that analyzes the collected data to determine a desired type of input candidate to request and the scenario, the type of input candidates including a text candidate and a rich candidate;
a selection component that selects a scenario-tuned and type-specific input candidate engine from an engine pool based on the queries, the scenario, and the determined desired type of input candidates to identify the input candidates; and
a presentation component that displays the identified input candidates at the user interface.

### Claim 18 (depends on 17)

The system as recited in claim 17, wherein the engine pool includes one or more scenario-tuned text candidate input candidate engines and one or more scenario-tuned rich candidate engines, the scenario-tuned text candidate input candidate engine having a scenario-tuned language model and a scenario-tuned lexicon, the scenario-tuned rich candidate input candidate engine including a web service for the scenario.

### Claim 19 (depends on 17)

The system as recited in claim 17, where in the engine pool is separate from a client device where the queries are received and input candidates are presented.

### Claim 20 (depends on 17)

The system as recited in claim 17, where in the engine pool is located at a client device where the queries are received and input candidates are presented.
