WO2015018055A1 - Input method editor providing language assistance - Google Patents
Input method editor providing language assistance Download PDFInfo
- Publication number
- WO2015018055A1 WO2015018055A1 PCT/CN2013/081156 CN2013081156W WO2015018055A1 WO 2015018055 A1 WO2015018055 A1 WO 2015018055A1 CN 2013081156 W CN2013081156 W CN 2013081156W WO 2015018055 A1 WO2015018055 A1 WO 2015018055A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- suggestion
- word
- ime
- user
- recited
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
- G06F9/453—Help systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04845—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
- G06F40/129—Handling non-Latin characters, e.g. kana-to-kanji conversion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/274—Converting codes to words; Guess-ahead of partial word inputs
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
- G09B19/04—Speaking
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
- G09B19/06—Foreign languages
Definitions
- IMEs input method editors
- non-Latin characters e.g., Chinese characters
- IMEs are an indispensable tool for a significant portion of East Asian users.
- IMEs may also provide an English mode, wherein assistance is provided for non-native users creating English language documents. In the English mode, English assistance may be provided, such as word or spelling suggestions in response to problematic user typing. The assistance may also include automated spelling corrections, multiple word- choice suggestions and/or anticipated words suggestions, etc.
- known IMEs are intrusive, and tend to distract a user with unwanted suggestions. Turning such IMEs on and off as suggestions are needed is awkward.
- the user interfaces (UIs) of known IMEs are inflexible, and do not allow the user to optimally control intrusion of the IME.
- the IME may be configured to provide language assistance across a plurality of applications.
- an IME may be adapted for use by English-as-a-second-language (ESL) users.
- language assistance may be provided by first detecting a need to provide a suggestion to a user typing within an application.
- the suggestion may include a substitute word, substitute spelling or substitute grammar. The detection may be based on a probability that a current word or word-use is in error. If need for a suggestion is detected, a suggestion may be obtained for the word.
- the suggestion may be based on input from a cloud linguistic service (CLS).
- CLS cloud linguistic service
- a local lexicon and/or language- model may be used to obtain the suggestion.
- the suggestion may be displayed to the user.
- the display may include adjustable user interface element(s), which allow the user to minimize intrusiveness of the user interface when not needed.
- the IME may provide opportunities for interaction with the user. For example, the interaction may allow may allow the user to accept or reject the suggestion, or copy the suggestion to a clipboard for use by a plurality of applications. The interaction may allow the user to relocate or minimize user interface elements.
- FIG. 1 is a block diagram showing a client device having an example input method editor (IME).
- FIG. 2 shows an example division of functionality within an IME.
- FIG. 3 shows an example user interface for an IME.
- FIG. 4 shows a further example of the user interface, including an IME bar.
- FIG. 5 is a flow diagram showing an example method of operation of an IME, including techniques for detection, suggestion, display and interaction.
- FIG. 6 is a flow diagram showing several example detection techniques.
- FIG. 7 is a flow diagram showing several example suggestion techniques.
- FIG. 8 is a flow diagram showing several example display techniques.
- FIG. 9 is a flow diagram showing several example interaction techniques.
- the disclosure describes techniques for operation of an input method editor (IME) configured to provide language assistance across a plurality of applications.
- the IME provides an adjustable user interface that may be made unobtrusive if desired, to reduce cognitive overload of a user.
- the IME may be adapted for use by English-as-a-second-language (ESL) users.
- ESL English-as-a-second-language
- language assistance is provided by detecting a need to suggest a substitute word to a user who is typing within an application. The detection may be based on a probability that a current word is in error or by observation of the difficulty (typing speed, backspaces, etc.) of the user typing the word. If a need for assistance is detected, a suggestion may be obtained for the word.
- the suggestion may be obtained from a cloud linguistic service or from a local lexicon and/or language-model, if network connectivity is poor. Once obtained, the suggestion may be displayed to the user by a user interface. Aspects of the user interface may be adjustable by the user, and may particularly provide non- intrusive information to the user that does not distract from the user's focus on typing and input. Following the suggestion, interaction with the user allows the user to accept or reject the suggestion, and perform other functions, such as relocating user interface elements utilized by the display.
- FIG. 1 is a block diagram showing an example system 100 within which an input method editor (IME) may be operated.
- a client device 102 may connect over a network 104 (e.g., an intranet, wide area network (WAN), the Internet, etc.) with a cloud linguistic service(s) 106.
- the cloud linguistic service(s) 106 is shown as a single entity; however, the services could be provided by a number of entities, organizations, corporations, etc.
- the client device 102 may include one or more processors 108 in communication with one or more memory devices 110.
- a network connection 112 may provide an interface to the network 104.
- the client device 102 may include and/or communicate with one or more peripheral devices.
- a first example of a peripheral device, a display 114 can operate as an input and output peripheral with a touch screen, or as an output peripheral without a touch screen. Thus, display 114 may be provided to receive touch input and present visual output.
- input peripheral devices can include a hard and/or soft keyboard, a mouse or other pointing device, a microphone, and/or gestural input devices such a one or more cameras or other gesture sensors.
- output peripheral devices can include one or more speakers, a printer, auxiliary monitor, or other output devices.
- An application 120 may be defined within memory 110 and configured for operation and/or execution by the processor(s) 108.
- the application 120 may be configured for any of a wide variety of purposes, including word-processing and/or text-based data entry.
- application 120 may include a word processor, an Internet browser, an email client, or other application into which a user may type or otherwise input text.
- an IME may be configured to provide language assistance in a discrete manner to avoid or minimize cognitive overload to a user who is primarily involved in text input and to a lesser degree with text error correction.
- an EVIE may include an input method editor dynamic link library, e.g., EVIE DLL 122, an IME platform process 124 and a suggestion renderer 126.
- the IME may also provide a user interface, which may be rendered by the suggestion renderer 126 for presentation via display 114 according to the examples of FIGS. 3 and/or 4.
- the IME DLL 122 may be defined "in-process,” i.e., within the application 120.
- the IME DLL 122 may be configured to receive input, such as keystrokes, and pass them on to an IME platform process 124 and to the application 120.
- the IME platform process 124 is configured to receive a string of input words, detect if errors are present and if suggestions to overcome the errors are indicated, to process candidate suggestions (possibly from multiple local and remote sources), and to deliver the suggestions as output to the user for consideration.
- the IME platform process 124 may be defined "out-of-process," i.e., located within a defined memory address range separate and distinct from the address range within which the application 120 is defined.
- the IME platform process 124 receives keystrokes from the IME DLL 122. Using the keystrokes, the IME platform process 124 performs a detection process, by which spelling, word use, grammar and other errors are discovered.
- the IME platform process 124 may determine a suggestion that will assist the user.
- the IME platform process 124 manages a display function, wherein the suggestion is provided to the user by operation of a user interface in a non-intrusive manner.
- the IME platform process 124 may also interact with the user, such as to receive the user's acceptance or rejection of the suggestion, or to adjust the user interface location or operation, etc.
- the suggestion renderer 126 may be configured to provide and manage a user interface, such as seen in the examples of FIGS. 3 and/or 4. Through operation of the suggestion renderer 126, specific instances of language assistance may be provided to the user. For example, the suggestion renderer 126 may render text or graphics for a notification window, IME bar or other user interface icon, widget or display, etc. The suggestion renderer 126 may operate at the direction of the IME platform process 124, and may also receive input and/or direction from the user. For example, the user may select preferred options for display of the language assistance. The options may allow the user to position a user interface element (e.g., a notification window) in a preferred location. The options may allow the user to reduce distraction caused by the user interface, such as by minimizing all or part of the interface, particularly during times it is not needed by the user.
- a user interface element e.g., a notification window
- FIG. 2 shows an example system 200 illustrating one possible division of functionality within the IME platform process 124 of FIG. 1.
- the example functional division is for purposes of example only, and is therefore representative of techniques (not shown) that are within the scope of the discussion herein.
- Detection techniques 202 may detect or recognize a language problem associated with input entered by a user into an application (e.g., application 120 of FIG. 1, which may be a word processor or other text-using application).
- the detection techniques 202 may be configured to extract words from a stream of intercepted keystrokes as a step in the detection of an error by the user.
- the extraction of words may be performed by segmenting a character- or keystroke- stream into individual words.
- the IME platform process 124 determines word boundaries (e.g., by noting space characters or other delimiters) and extracts words as the user types.
- Such segmentation (or "word breaking") functionality and detection of potential errors may be performed by separating text using space characters, by using other punctuation and/or by using an appropriate rule -based method.
- the detection techniques 202 may be configured to detect or recognize when suggestions should be sought for possible errors in spelling, word use, grammar or other language issues.
- the suggestions may be sought from the suggestion techniques 204A, 204B, as will be discussed infra.
- the IME may be part of an operating system, such as Windows® or another operating system.
- characters e.g., keystrokes resulting from user operating a keyboard
- the IME DLL 122 may be loaded into a host application (e.g., application 120) operated by the user and configured to receive keyboard input from the user.
- the IME DLL 122 may forward keystroke characters to the IME platform process 124, which may be configured as a process running on the client device 102. As the user types, the IME platform process 124 may continue to monitor characters (keystrokes).
- the detection techniques 202 may maintain previously typed word(s) in memory, such as within the IME platform process 124 or other location. Such previously typed words may be used (e.g., by the IME platform process 124) to determine the appropriateness of a current word in terms of spelling, context of use, grammar and other linguistic considerations.
- the detection techniques 202 may utilize a test or check to determine whether suggestions are needed to replace a word typed by the user. Such testing may be based on a probability of correctness of a word typed by the user and intercepted and recognized by the IME platform process 124. The probability may be based on multiple factors and testing, which may be performed by one or both of local checks (e.g., performed on the client device 102) and remote checks (e.g., performed by the cloud linguist services 106). In an example of local checks, the intercepted word may be checked against a lexicon (e.g., a dictionary), as well as its likelihood of appearing near previously written (possibly adjacent) words.
- a lexicon e.g., a dictionary
- a sequence of words may be examined and a determination made if each word is correct and/or if a suggestion for replacement is needed.
- the determination may be based at least in part on a statistical language model (e.g., unigram models, N-gram models, etc.).
- the detection techniques 202 may include one or more statistical language models, which may operate on the IME platform process 124, on the cloud linguistic service(s) 106 or both. Consideration of network connectivity and speed may be used to determine if a local or cloud statistical model should be utilized. Generally, if sufficient network speed and bandwidth is available, statistical language model(s) on the cloud linguistic services 106 should be utilized.
- the cloud based models may have larger lexicon, better ability to process word sequences and better ability overall to detect errors in spelling, word use and/or grammar.
- Statistical language models operable in either location may detect errors utilizing factors such as input from a lexicon (dictionary, word list, technical vocabulary, etc.), typing speed and/or back-spacing or other corrections made by the user.
- detection techniques 202 may be performed using IME-based techniques.
- the EVIE DLL 122 may be loaded into each application in a configuration that will be able to intercept all keystrokes within the application and will be able to take into account specific input scopes (words, word sequences and/or word usages, etc.).
- the IME-based techniques also allow keystrokes to be processed in various ways, including forwarding all processing to a running application, a local service or an external service.
- the detection techniques 202 may be utilized in conjunction with non- IME based mechanisms, as well as the IME-based mechanisms previously described.
- APIs applications programming interfaces
- an operating system of the client device may be used directly to monitor keystrokes either by polling or subscribing to global events.
- Suggestion techniques 204A and 204B may be utilized to provide suggestions or alternatives to words indicated by the detection techniques 202 as having a high likelihood of error.
- the suggestion techniques may include remotely-based or cloud-implemented suggestion techniques 204A and locally- based suggestion techniques 204B.
- suggestion techniques 204A and 204B may be operated in an alternative, parallel and/or complementary manner(s).
- the remote suggestion techniques 204 A which may be based within the cloud linguistic services 106, may be the primary source of suggestions.
- the local suggestion techniques 204B may be utilized only when network connectivity does not allow use of the cloud-based suggestion techniques 204A.
- the suggestion techniques 204A available in the cloud linguistic services 106 may provide greater capacity and performance than is available from the suggestion techniques 204B operating on the EVIE platform process 124.
- suggestion techniques that are based on a particular technology may be more effective when provided by the cloud-based suggestion techniques 204A, due to computational advantages of the cloud over the IME platform process 124.
- Example technologies may include language models based at least in part on unigram model technology, N-gram model technologies, etc.
- Cloud-based word suggestion-generation resources may be configured to leverage computing power of the cloud, including faster execution, massive lexicons and computationally complex algorithms for which implementation may be impossible on the IME platform process 124.
- cloud linguistic services 106 may arbitrate between multiple cloud-based services or resources to collect candidate suggestions to replace word errors. The arbitration may be performed by comparison of suggestion provider- based design patterns, provider-used technologies, and how those patterns compare to the suggestion process.
- the cloud linguistic services 106 may return an ordered list of candidates to be suggested to the user to replace the word typed by the user.
- the suggestions on the list, obtained from cloud-based sources, may be derived from globally based statistical language model(s) and ranked by their respective confidence scores.
- the EVIE platform process 124 may also collect an ordered list from locally-determined suggestion candidates.
- the locally-based suggestion techniques 204B may be based at least in part on user-specific personalization within the application 120 (seen in FIG. 1), previous word use, a local lexicon (which may be associated with the application 120) and use of an edit distance algorithm.
- candidate suggestions to replace word errors may be either entirely locally-based or entirely cloud-based.
- the suggestions can be queried from multiple cloud- based services and aggregated on the client.
- a number of data sources e.g., cloud-based statistical language models, lexicons, etc.
- a single cloud linguistics service may be used as a point of entry to the IME platform 124.
- candidate suggestions for an erroneous word may be obtained more quickly.
- FIG. 3 shows an example user interface 300, including example operation with a word processing application 302.
- the system includes a visual display 114, which may be part of a client device (e.g., client device 102 of FIG. 1).
- an application e.g., the word processor 302
- Various display techniques shown by the example user interface 300 may be performed by the suggestion renderer 126 (as seen in FIG. 1).
- the display techniques may include receiving and displaying one or more candidate suggestions obtained by operation of the suggestions techniques operating on the IME platform process 124 and/or cloud linguistic services 106.
- the display techniques may include logic and rules governing how and when suggestions may be displayed to the user.
- the user may misspell a word, violate a rule of grammar or otherwise enter text that indicates that the user would benefit from assistance.
- the user has type "fizix,” a misspelling of the word "physics.”
- a notification window 304 opens, such as by operation of the suggestion renderer 126 of FIG. 1.
- the notification window 304 may resemble a "speech bubble” or “balloon” and may include a tail 306, which may be used to indicate association with an EVIE bar 308.
- the example notification window 304 is configured to allow the user to avoid unwanted distraction, and may provide a closure box 310, to allow the user to remove the notification window 304 portion of the user interface when it becomes a distraction.
- the preferred suggestion is provided if a confidence score is greater than a threshold value (e.g., 90%) that the suggestion is correct. Also, the preferred suggestion is provided if it can be obtained within a threshold period of time after the user typed the word thought to be erroneous.
- a threshold value e.g. 90%
- the notification window 304 may provide a suggestion 312 for a misspelled word, misused word, or grammatical error, etc.
- Three examples are representative of ways that the suggestion may be utilized by the user.
- the user may click command 314, to thereby replace the erroneously typed text with the suggestion 312.
- the user may click command 316 to copy the suggested change to the clipboard.
- the suggested text may be used in any application, and may be used with applications that fail to perform correctly if the command 314 selected.
- the user may simply copy the text seen at suggestion 312 by typing it into any application. Additionally, the user may turn off the English assistance by operation of command 318.
- FIG. 4 shows a further example of the user interface provided by an EVIE (e.g., the IME platform process 124 of FIG. 1).
- the user interface may include an IME bar 308 adapted for use with a plurality of different applications running on a client device.
- the EVIE bar 308 is enhanced by addition of an English indicator 400 and an event indicator 402.
- the English indicator 400 provides a reminder to the user that the EVIE is in an "English" mode.
- a user may type in English and create a document in English. Accordingly, typed characters are simply "passed through" the IME (and into the application) without action by the IME, unless a potential error is detected.
- Alternative modes of operation by the IME may be indicated by indicators (not shown) that are alternative to the English indicator 402.
- input is provided by a user typing "Roman" letters, and output is provided in symbols of a different language (e.g., Chinese characters).
- An event indicator 402 may be configured to appear and/or change in appearance (e.g., color) to indicate an event.
- the event indicator may be an exclamation mark or other symbol, typically indicating concern and/or urgency.
- the event or issue indicated by the event indicator 402 may include detection of an error or potential error in spelling, word use, grammar or other aspect checked by the IME.
- the user may "mouse over" or otherwise select the event indicator to receive a suggestion from the EVIE.
- the suggestion may be provided by appearance of the notification window 304 or other user interface element.
- selection of the event indicator 402 may result in appearance of, or change in the content of, the notification window 304.
- FIG. 5 is a flow diagram showing an example method 500 of operation of an IME.
- the IME operates out-of-process with respect to an application that involves user-entry of text.
- keystrokes are passed by an in-process EVIE DLL to the application and to the IME platform process.
- a detection process may employ one or more techniques to determine if a suggested replacement should be sought for a word typed by the user. If so, a suggestion process may employ one or more techniques to select and/or obtain a suggested word to replace the word typed by the user.
- a display process may employ one or more techniques to display the suggested word to the user (e.g. in a user interface having an unobtrusive appearance).
- An interactive process may employ one or more techniques to receive user input, such as to utilize the suggested word or to adjust the appearance of the user interface.
- a need to suggest a word to replace a word typed by a user is detected.
- the detection is in response to recognition that the word typed by the user is misspelled.
- the detection may result from recognition that the word is used in a grammatically incorrect manner or has otherwise been misused.
- the detection techniques 202 operating on the IME platform process 124 may perform the detection functionality.
- a suggestion is obtained for the word, e.g., in response to detection of the need for a suggestion.
- the suggestion may be obtained over a network and from cloud-based resources (e.g., cloud linguistic services 106 of FIGS. 1 and 2).
- the suggestion may be obtained locally, such as by operation of suggestion techniques 204B operating on a client device 102 and/or an IME platform process 124.
- the suggestion may be a correctly spelled word for which there is a high confidence level corresponds to the intended meaning of the user.
- the suggestion is displayed to the user, such as by operation of a user interface.
- the EVIE platform process 124 may provide data, and together with the suggestion renderer 126, may cause the suggestion to be presented.
- the user interface may be unobtrusive and/or may be regulated by the user to control a degree to which it intrudes on the user's operation of an application on the client device.
- FIGS. 3 and 4 show example user interfaces that may be utilized to display a suggestion for consideration by a user.
- the user may interact with the user interface.
- the user may provide input regarding: the detection process whereby a suggestion was found to be necessary; the suggestion process by which a replacement word was obtained; the display process by which the replacement word was presented to the user; or feedback as provided and/or supported by the IME.
- the user may interact with the user interface by click or rollover of the event indicator 402, the selection of a command or option provided by the notification window 304, etc.
- FIG. 6 is a flow diagram showing several example detection techniques 600 that may be used to configure an IME platform process to detect a need for a suggestion to replace a word typed by a user. Accordingly, one or more of the detection techniques 600 may optionally be utilized to perform all or part of the detection operation 502 of FIG. 5.
- words the application receives such as from a user typing, may be recorded. Alternatively, the received words may be obtained from speech recognition techniques or another text entry method. Accordingly, when a word is detected that may be incorrectly spelled and/or used, that detection may be made in the context of previously typed words.
- the detection techniques 202 may record words within the IME platform process 124.
- the recorded words are available for purposes of grammar, word context and usage, etc.
- a probability of correctness of the word typed by the user may be calculated. The calculated probability may be based in part on the words previously recorded. The probability of correctness may be based on local checks on a client or server side checks performed in the cloud and received at the client. The checks may include checks for the word in the local lexicon or a cloud-based lexicon. The probability may be based on operation of remote or local resources (e.g., a cloud linguistic service). The resources may include operation of statistical language model(s).
- a sequence of recorded words typed by the user may be examined to provide context for a current word typed by the user.
- the examination may be performed locally by the IME platform process 124 or in the cloud by one or more cloud linguistic services 106.
- a statistical language model may be used to detect a need for a suggestion.
- Such models may reside on the IME platform process 124, although larger and more comprehensive models may reside within cloud linguistic services 106.
- keystrokes are detected within an application by operation of an in-process IME dynamic link library (DLL).
- the EVIE DLL 122 detects keystrokes which are passed to the application 120.
- the keystrokes are forwarded to an out-of- process EVIE platform process.
- the keystrokes detected by the IME DLL 122 are also passed to the IME platform process 124.
- typing speed, typing speed changes, multiple typing of backspace characters, re -typing and/or the stopping of typing may be detected by the IME platform process.
- Such typing characteristics may be considered by the detection techniques 202 on the IME platform process 124, when attempting to detect a need to suggest a word to replace a word typed by a user.
- local- and/or server-based testing may be performed on one or more received words.
- the testing may be performed using local and/or cloud-based lexicon(s), statistical language model(s) and/or cloud-based linguistic service(s).
- Local testing may be performed by the IME platform process 124 and cloud-based testing may be performed by cloud linguistic services 106.
- the testing may be coordinated, and/or the results of the testing received, at the IME platform process.
- FIG. 7 is a flow diagram showing several example suggestion techniques 700 that may be used to configure an IME platform process to obtain a suggestion for use in replacing a word typed by a user.
- one or more of the suggestion techniques 700 may optionally be utilized to perform all or part of operation 504 of FIG. 5, wherein a suggestion is obtained, either from IME-based resources or cloud-based resources.
- a suggestion is obtained from a cloud linguistic service (CLS) that arbitrates between one or more cloud-based services. Accordingly, more than one service may be used, and a selection made from among the results.
- CCS cloud linguistic service
- a suggestion is obtained from a local lexicon and/or a local or remote statistical language model. The suggestion may be based at least in part on previously typed words.
- a confidence score may be utilized to determine whether to present the obtained suggestion.
- multiple cloud-based services may be queried for correction candidates and the results aggregated.
- the results may be aggregated by the IME platform process 124 (FIGS. 1 and 2).
- cloud-based services may be queried for correction candidates and probabilities.
- the probabilities may each be formed as a confidence score that an associated correction candidate is correct.
- the IME may determine if technologies employed by local and remote (e.g., server- or cloud-based) resources to suggest word replacements are similar.
- the remote resources are utilized.
- the IME platform and a cloud-based linguistic service may use a similar statistical language model, and the remote statistical model may be used. The computing power of the cloud may make this choice preferable.
- a suggestion may be obtained from a cloud linguistic service (CLS) that is configured to collect candidates for the suggestion to replace a word typed by the user. Such a suggestion may be obtained if network connectivity is adequate.
- a suggestion may be obtained from a local lexicon and/or language model if the network connectivity is not adequate.
- FIG. 8 is a flow diagram showing several example display techniques 800 that may be used within a user interface to display the suggestion, if obtained by the suggestion techniques. Accordingly, one or more of the display techniques 800 may optionally be utilized to perform all or part of operation of 506 of FIG. 5, wherein a suggestion is displayed.
- a word obtained as a suggestion for replacement of a word typed by the user may be provided to the user by displaying the suggestion using any user interface techniques, such as a notification bubble.
- the notification bubble 304 of FIG. 3 is one example of such presentation, but other techniques are also within the scope of the operation.
- the notification bubble may be displayed at a location that is based at least in part on location of an EVIE bar.
- FIG. 3 shows that the notification bubble 304 may be attached to the IME bar 308 by a tail 306. Movement of the IME bar 308 or notification bubble 304 may result in movement of both, depending on a selected configuration, setting or design.
- the user may be monitored by the IME to determine when the user stops typing. If the user stops typing, that may be a factor indicating or weighing toward uncertainty on the part of the user regarding the accuracy of one or more words the user has typed. Other factors indicating possible user confusion may include slowed typing, back-spacing and/or deleting, re-typing, and others.
- the user interface e.g., the notification bubble 304 of FIG. 3 may display the suggestion after the user has stopped typing. By waiting until the user stops or slows the typing process, performs one or more back-spaces and/or re -typing, the user interface is less likely to intrude on the user's thoughts with unnecessary suggestions.
- unwanted intrusion on the user may be prevented by binding, fixing or moving the notification bubble 304 to a location selected by the user.
- the display of the word suggestion e.g., the notification bubble
- the user may move the notification bubble and/or the IME bar to a location on a display (e.g., a video display screen, display of a mobile device, etc.) that is less intrusive and/or preferred for any reason.
- the notification bubble 304 and IME bar 308 move together (e.g., joined by the tail 306), and in other examples they are separately movable.
- the suggestion may be provided to the user in response to an indicator that a word suggestion is available.
- the event indicator 402 may appear and/or appear in bold, in color or in an otherwise recognizable "active" mode.
- the user may click or mouse-over the event indicator 402, thereby triggering appearance of a user interface device, such as the notification bubble 304.
- the suggestion for use in word replacement may be displayed if a confidence in the suggestion is greater than a threshold value.
- the threshold may be set at a level that does not interfere with the user unless the confidence level of a user error is sufficiently high.
- FIG. 9 is a flow diagram showing several example interaction techniques 900 that may be used to interact with a user, if a suggestion was displayed. Accordingly, one or more of the interaction techniques 900 may optionally be utilized to perform all or part of operation 508 of FIG. 5, wherein the IME interacts with a user.
- input may be received from the user to utilize the displayed suggestion.
- user indicates that the suggested word should in fact be substituted for the problematic word typed by the user.
- the user may select command 314 to replace the questionable word typed by the user with the word suggested by the EVIE.
- the EVIE may respond to user input to move the IME bar and/or the notification bubble.
- the notification bubble 304 and the EVIE bar 308 are shown in a lower portion of the visual display 114. However, these could be moved to a different location, if desired by the user, such as by manual manipulation by touch screen, mouse or pointing device.
- a location of user interface element(s) may be persisted over restarts or reboots of the user's computing device.
- the IME platform process 124 may maintain a location of user interface elements shown by FIGS. 3 and/or 4 over reboots or restarts of the client device 102.
- the location of user interface elements may be "roamed" or utilized by other machines used by the user.
- any changes to the user interface of one device may be transferred to, and utilized by, the other device as well. If the display screens are somewhat different, then changes to one device may be mapped to the other device in a manner that approximates a presentation on a user interface of the other device.
- the IME may receive a rejection from the user of the suggestion made by the EVIE to replace a word(s) typed by the user.
- the IME may reduce a likelihood of presenting any suggestion in the future under similar circumstances.
- the EVIE may reduce a likelihood of presenting the rejected suggestion if a suggestion is to be presented in the future under similar circumstances.
- Computer-readable media includes computer storage media and communication media.
- Computer storage media includes volatile and non- volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data.
- Computer storage media includes, but is not limited to, random access memory (RAM), read only memory (ROM), electrically erasable programmable ROM (EEPROM), flash memory or other memory technology, compact disk ROM (CD-ROM), digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store information for access by a computing device.
- communication media may embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave. As defined herein, computer storage media does not include communication media.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
- Stored Programmes (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
An input method editor (IME) configured to provide language assistance across a plurality of applications is disclosed. In one example, the IME is adapted for use by English-as-a-second-language (ESL) users. In a specific example, language assistance may be provided by first detecting a need to suggest a substitute word to a user who is typing within an application. The detection may be based on a probability that a current word is in error. If a need is detected, a suggestion may be obtained for the word, such as from a cloud linguistic service or from a local lexicon and language-model, if network connectivity is poor. Once obtained, the suggestion may be displayed to the user in a non-intrusive manner by user interface element(s). Interaction with the user allows the user to accept or reject the suggestion, and perform other functions, such as relocating user interface elements utilized by the display.
Description
INPUT METHOD EDITOR PROVIDING LANGUAGE ASSISTANCE
BACKGROUND
[0001] Today, input method editors (IMEs) may be used to input non-Latin characters (e.g., Chinese characters) into a computer program using a conventional keyboard. IMEs are an indispensable tool for a significant portion of East Asian users. IMEs may also provide an English mode, wherein assistance is provided for non-native users creating English language documents. In the English mode, English assistance may be provided, such as word or spelling suggestions in response to problematic user typing. The assistance may also include automated spelling corrections, multiple word- choice suggestions and/or anticipated words suggestions, etc. Unfortunately, known IMEs are intrusive, and tend to distract a user with unwanted suggestions. Turning such IMEs on and off as suggestions are needed is awkward. Moreover, the user interfaces (UIs) of known IMEs are inflexible, and do not allow the user to optimally control intrusion of the IME.
SUMMARY
[0002] Techniques to provide language assistance and operate an input method editor (IME) are disclosed. The IME may be configured to provide language assistance across a plurality of applications. In one example, an IME may be adapted for use by English-as-a-second-language (ESL) users. In a specific example, language assistance may be provided by first detecting a need to provide a suggestion to a user typing within an application. The suggestion may include a substitute word, substitute spelling or substitute grammar. The detection may be based on a probability that a current word or word-use is in error. If need for a suggestion is detected, a suggestion may be obtained for the
word. The suggestion may be based on input from a cloud linguistic service (CLS). If network connectivity is unavailable, a local lexicon and/or language- model may be used to obtain the suggestion. Once obtained, the suggestion may be displayed to the user. The display may include adjustable user interface element(s), which allow the user to minimize intrusiveness of the user interface when not needed. The IME may provide opportunities for interaction with the user. For example, the interaction may allow may allow the user to accept or reject the suggestion, or copy the suggestion to a clipboard for use by a plurality of applications. The interaction may allow the user to relocate or minimize user interface elements.
[0003] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. The term "techniques," for instance, may refer to device(s), system(s), method(s) and/or computer-readable instructions as indicated by the context above and throughout the document.
BRIEF DESCRIPTION OF THE DRAWINGS
[0004] The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to reference like features and components. Moreover, the figures are intended to illustrate general concepts, and not to indicate required and/or necessary elements.
[0005] FIG. 1 is a block diagram showing a client device having an example input method editor (IME).
[0006] FIG. 2 shows an example division of functionality within an IME.
[0007] FIG. 3 shows an example user interface for an IME.
[0008] FIG. 4 shows a further example of the user interface, including an IME bar.
[0009] FIG. 5 is a flow diagram showing an example method of operation of an IME, including techniques for detection, suggestion, display and interaction.
[0010] FIG. 6 is a flow diagram showing several example detection techniques.
[0011] FIG. 7 is a flow diagram showing several example suggestion techniques.
[0012] FIG. 8 is a flow diagram showing several example display techniques.
[0013] FIG. 9 is a flow diagram showing several example interaction techniques.
DETAILED DESCRIPTION
Overview
[0014] The disclosure describes techniques for operation of an input method editor (IME) configured to provide language assistance across a plurality of applications. In one example, the IME provides an adjustable user interface that may be made unobtrusive if desired, to reduce cognitive overload of a user. The IME may be adapted for use by English-as-a-second-language (ESL) users. In one example, language assistance is provided by detecting a need to suggest a substitute word to a user who is typing within an application. The detection may be based on a probability that a current word is in error or by observation of the difficulty (typing speed, backspaces, etc.) of the user typing the word. If a need for assistance is detected, a suggestion may be obtained for the word. The suggestion may be obtained from a cloud linguistic service or from a local lexicon and/or language-model, if network connectivity is poor. Once obtained, the suggestion may be displayed to the user by a user interface. Aspects of the user interface may be adjustable by the user, and may particularly provide non-
intrusive information to the user that does not distract from the user's focus on typing and input. Following the suggestion, interaction with the user allows the user to accept or reject the suggestion, and perform other functions, such as relocating user interface elements utilized by the display.
Example System and Techniques
[0015] FIG. 1 is a block diagram showing an example system 100 within which an input method editor (IME) may be operated. In an example of the system 100, a client device 102 may connect over a network 104 (e.g., an intranet, wide area network (WAN), the Internet, etc.) with a cloud linguistic service(s) 106. The cloud linguistic service(s) 106 is shown as a single entity; however, the services could be provided by a number of entities, organizations, corporations, etc.
[0016] In one example, the client device 102 may include one or more processors 108 in communication with one or more memory devices 110. A network connection 112 may provide an interface to the network 104. The client device 102 may include and/or communicate with one or more peripheral devices. A first example of a peripheral device, a display 114, can operate as an input and output peripheral with a touch screen, or as an output peripheral without a touch screen. Thus, display 114 may be provided to receive touch input and present visual output. In a second example of peripheral device(s) 116, input peripheral devices can include a hard and/or soft keyboard, a mouse or other pointing device, a microphone, and/or gestural input devices such a one or more cameras or other gesture sensors. In a third example of peripheral device(s) 118, output peripheral devices can include one or more speakers, a printer, auxiliary monitor, or other output devices.
[0017] An application 120 may be defined within memory 110 and configured for operation and/or execution by the processor(s) 108. The application 120 may
be configured for any of a wide variety of purposes, including word-processing and/or text-based data entry. Thus, application 120 may include a word processor, an Internet browser, an email client, or other application into which a user may type or otherwise input text.
[0018] In the example of FIG. 1, an IME may be configured to provide language assistance in a discrete manner to avoid or minimize cognitive overload to a user who is primarily involved in text input and to a lesser degree with text error correction. In the example of FIG. 1 , an EVIE may include an input method editor dynamic link library, e.g., EVIE DLL 122, an IME platform process 124 and a suggestion renderer 126. The IME may also provide a user interface, which may be rendered by the suggestion renderer 126 for presentation via display 114 according to the examples of FIGS. 3 and/or 4.
[0019] The IME DLL 122 may be defined "in-process," i.e., within the application 120. The IME DLL 122 may be configured to receive input, such as keystrokes, and pass them on to an IME platform process 124 and to the application 120.
[0020] In the example of FIG. 1, the IME platform process 124 is configured to receive a string of input words, detect if errors are present and if suggestions to overcome the errors are indicated, to process candidate suggestions (possibly from multiple local and remote sources), and to deliver the suggestions as output to the user for consideration. The IME platform process 124 may be defined "out-of-process," i.e., located within a defined memory address range separate and distinct from the address range within which the application 120 is defined. In at least one embodiment, the IME platform process 124 receives keystrokes from the IME DLL 122. Using the keystrokes, the IME platform process 124 performs a detection process, by which spelling, word use, grammar and other errors are discovered. Having detected an error or issue, the IME platform
process 124 may determine a suggestion that will assist the user. The IME platform process 124 manages a display function, wherein the suggestion is provided to the user by operation of a user interface in a non-intrusive manner. The IME platform process 124 may also interact with the user, such as to receive the user's acceptance or rejection of the suggestion, or to adjust the user interface location or operation, etc.
[0021] The suggestion renderer 126 may be configured to provide and manage a user interface, such as seen in the examples of FIGS. 3 and/or 4. Through operation of the suggestion renderer 126, specific instances of language assistance may be provided to the user. For example, the suggestion renderer 126 may render text or graphics for a notification window, IME bar or other user interface icon, widget or display, etc. The suggestion renderer 126 may operate at the direction of the IME platform process 124, and may also receive input and/or direction from the user. For example, the user may select preferred options for display of the language assistance. The options may allow the user to position a user interface element (e.g., a notification window) in a preferred location. The options may allow the user to reduce distraction caused by the user interface, such as by minimizing all or part of the interface, particularly during times it is not needed by the user.
[0022] FIG. 2 shows an example system 200 illustrating one possible division of functionality within the IME platform process 124 of FIG. 1. The example functional division is for purposes of example only, and is therefore representative of techniques (not shown) that are within the scope of the discussion herein.
[0023] Detection techniques 202 may detect or recognize a language problem associated with input entered by a user into an application (e.g., application 120 of FIG. 1, which may be a word processor or other text-using application). The
detection techniques 202 may be configured to extract words from a stream of intercepted keystrokes as a step in the detection of an error by the user. The extraction of words may be performed by segmenting a character- or keystroke- stream into individual words. In one example, the IME platform process 124 determines word boundaries (e.g., by noting space characters or other delimiters) and extracts words as the user types. Such segmentation (or "word breaking") functionality and detection of potential errors may be performed by separating text using space characters, by using other punctuation and/or by using an appropriate rule -based method.
[0024] The detection techniques 202 may be configured to detect or recognize when suggestions should be sought for possible errors in spelling, word use, grammar or other language issues. In the example shown, the suggestions may be sought from the suggestion techniques 204A, 204B, as will be discussed infra. In one implementation, the IME may be part of an operating system, such as Windows® or another operating system. According to the example, characters (e.g., keystrokes resulting from user operating a keyboard) may be intercepted by the IME dynamic link library (e.g., IME DLL 122 of FIG. 1). The IME DLL 122 may be loaded into a host application (e.g., application 120) operated by the user and configured to receive keyboard input from the user. In example operation, the IME DLL 122 may forward keystroke characters to the IME platform process 124, which may be configured as a process running on the client device 102. As the user types, the IME platform process 124 may continue to monitor characters (keystrokes).
[0025] The detection techniques 202 may maintain previously typed word(s) in memory, such as within the IME platform process 124 or other location. Such previously typed words may be used (e.g., by the IME platform process 124) to
determine the appropriateness of a current word in terms of spelling, context of use, grammar and other linguistic considerations.
[0026] The detection techniques 202 may utilize a test or check to determine whether suggestions are needed to replace a word typed by the user. Such testing may be based on a probability of correctness of a word typed by the user and intercepted and recognized by the IME platform process 124. The probability may be based on multiple factors and testing, which may be performed by one or both of local checks (e.g., performed on the client device 102) and remote checks (e.g., performed by the cloud linguist services 106). In an example of local checks, the intercepted word may be checked against a lexicon (e.g., a dictionary), as well as its likelihood of appearing near previously written (possibly adjacent) words. Thus, a sequence of words may be examined and a determination made if each word is correct and/or if a suggestion for replacement is needed. The determination may be based at least in part on a statistical language model (e.g., unigram models, N-gram models, etc.).
[0027] The detection techniques 202 may include one or more statistical language models, which may operate on the IME platform process 124, on the cloud linguistic service(s) 106 or both. Consideration of network connectivity and speed may be used to determine if a local or cloud statistical model should be utilized. Generally, if sufficient network speed and bandwidth is available, statistical language model(s) on the cloud linguistic services 106 should be utilized. The cloud based models may have larger lexicon, better ability to process word sequences and better ability overall to detect errors in spelling, word use and/or grammar. Statistical language models operable in either location may detect errors utilizing factors such as input from a lexicon (dictionary, word list, technical vocabulary, etc.), typing speed and/or back-spacing or other corrections made by the user.
[0028] Thus, detection techniques 202 may be performed using IME-based techniques. Using such techniques, the EVIE DLL 122 may be loaded into each application in a configuration that will be able to intercept all keystrokes within the application and will be able to take into account specific input scopes (words, word sequences and/or word usages, etc.). The IME-based techniques also allow keystrokes to be processed in various ways, including forwarding all processing to a running application, a local service or an external service.
[0029] The detection techniques 202 may be utilized in conjunction with non- IME based mechanisms, as well as the IME-based mechanisms previously described. For example, applications programming interfaces (APIs) provided by an operating system of the client device may be used directly to monitor keystrokes either by polling or subscribing to global events.
[0030] Suggestion techniques 204A and 204B may be utilized to provide suggestions or alternatives to words indicated by the detection techniques 202 as having a high likelihood of error. The suggestion techniques may include remotely-based or cloud-implemented suggestion techniques 204A and locally- based suggestion techniques 204B. Depending on implementation, suggestion techniques 204A and 204B may be operated in an alternative, parallel and/or complementary manner(s). In one example, the remote suggestion techniques 204 A, which may be based within the cloud linguistic services 106, may be the primary source of suggestions. The local suggestion techniques 204B may be utilized only when network connectivity does not allow use of the cloud-based suggestion techniques 204A. In some embodiments, the suggestion techniques 204A available in the cloud linguistic services 106 may provide greater capacity and performance than is available from the suggestion techniques 204B operating on the EVIE platform process 124. In particular, suggestion techniques that are based on a particular technology may be more effective when provided by the
cloud-based suggestion techniques 204A, due to computational advantages of the cloud over the IME platform process 124. Example technologies may include language models based at least in part on unigram model technology, N-gram model technologies, etc. Cloud-based word suggestion-generation resources may be configured to leverage computing power of the cloud, including faster execution, massive lexicons and computationally complex algorithms for which implementation may be impossible on the IME platform process 124. In additional examples, cloud linguistic services 106 may arbitrate between multiple cloud-based services or resources to collect candidate suggestions to replace word errors. The arbitration may be performed by comparison of suggestion provider- based design patterns, provider-used technologies, and how those patterns compare to the suggestion process.
[0031] In one example, the cloud linguistic services 106 may return an ordered list of candidates to be suggested to the user to replace the word typed by the user. The suggestions on the list, obtained from cloud-based sources, may be derived from globally based statistical language model(s) and ranked by their respective confidence scores. The EVIE platform process 124 may also collect an ordered list from locally-determined suggestion candidates. The locally-based suggestion techniques 204B may be based at least in part on user-specific personalization within the application 120 (seen in FIG. 1), previous word use, a local lexicon (which may be associated with the application 120) and use of an edit distance algorithm.
[0032] In other examples, candidate suggestions to replace word errors may be either entirely locally-based or entirely cloud-based. In one example of cloud- based suggestion generation, the suggestions can be queried from multiple cloud- based services and aggregated on the client. In the example, a number of data sources (e.g., cloud-based statistical language models, lexicons, etc.) may be
varied according to a required speed of the system. In a contrasting example, a single cloud linguistics service may be used as a point of entry to the IME platform 124. Generally, by reducing the number of data sources, candidate suggestions for an erroneous word may be obtained more quickly.
Example User Interface
[0033] FIG. 3 shows an example user interface 300, including example operation with a word processing application 302. In the example shown, the system includes a visual display 114, which may be part of a client device (e.g., client device 102 of FIG. 1). In the example of FIG. 3, an application (e.g., the word processor 302) provides a user interface window within the visual display 114. The user is able to enter text into the word processor 302 using a keyboard or other input peripheral.
[0034] Various display techniques shown by the example user interface 300 may be performed by the suggestion renderer 126 (as seen in FIG. 1). The display techniques may include receiving and displaying one or more candidate suggestions obtained by operation of the suggestions techniques operating on the IME platform process 124 and/or cloud linguistic services 106. The display techniques may include logic and rules governing how and when suggestions may be displayed to the user.
[0035] The user may misspell a word, violate a rule of grammar or otherwise enter text that indicates that the user would benefit from assistance. In the example of FIG. 3, the user has type "fizix," a misspelling of the word "physics." In response, a notification window 304 opens, such as by operation of the suggestion renderer 126 of FIG. 1. The notification window 304 may resemble a "speech bubble" or "balloon" and may include a tail 306, which may be used to indicate association with an EVIE bar 308. The example notification window 304
is configured to allow the user to avoid unwanted distraction, and may provide a closure box 310, to allow the user to remove the notification window 304 portion of the user interface when it becomes a distraction.
[0036] In one example, only the single most preferred suggestion for replacement of the detected erroneous word is displayed. The preferred suggestion is provided if a confidence score is greater than a threshold value (e.g., 90%) that the suggestion is correct. Also, the preferred suggestion is provided if it can be obtained within a threshold period of time after the user typed the word thought to be erroneous.
[0037] The notification window 304 may provide a suggestion 312 for a misspelled word, misused word, or grammatical error, etc. Three examples are representative of ways that the suggestion may be utilized by the user. In a first example, the user may click command 314, to thereby replace the erroneously typed text with the suggestion 312. In a second example, the user may click command 316 to copy the suggested change to the clipboard. Once on the clipboard, the suggested text may be used in any application, and may be used with applications that fail to perform correctly if the command 314 selected. In a third example, the user may simply copy the text seen at suggestion 312 by typing it into any application. Additionally, the user may turn off the English assistance by operation of command 318.
[0038] FIG. 4 shows a further example of the user interface provided by an EVIE (e.g., the IME platform process 124 of FIG. 1). The user interface may include an IME bar 308 adapted for use with a plurality of different applications running on a client device. In the example shown, the EVIE bar 308 is enhanced by addition of an English indicator 400 and an event indicator 402. The English indicator 400 provides a reminder to the user that the EVIE is in an "English" mode. Within English mode, a user may type in English and create a document in English.
Accordingly, typed characters are simply "passed through" the IME (and into the application) without action by the IME, unless a potential error is detected. Alternative modes of operation by the IME may be indicated by indicators (not shown) that are alternative to the English indicator 402. In one example of an alternative mode of IME operation, input is provided by a user typing "Roman" letters, and output is provided in symbols of a different language (e.g., Chinese characters).
[0039] An event indicator 402 may be configured to appear and/or change in appearance (e.g., color) to indicate an event. In one example, the event indicator may be an exclamation mark or other symbol, typically indicating concern and/or urgency. The event or issue indicated by the event indicator 402 may include detection of an error or potential error in spelling, word use, grammar or other aspect checked by the IME. To continue the example, upon appearance (or change in appearance) of the event indicator 402, the user may "mouse over" or otherwise select the event indicator to receive a suggestion from the EVIE. The suggestion may be provided by appearance of the notification window 304 or other user interface element. Thus, selection of the event indicator 402 may result in appearance of, or change in the content of, the notification window 304.
Example Methods
[0040] FIG. 5 is a flow diagram showing an example method 500 of operation of an IME. In one example, the IME operates out-of-process with respect to an application that involves user-entry of text. As the user enters text, keystrokes are passed by an in-process EVIE DLL to the application and to the IME platform process. A detection process may employ one or more techniques to determine if a suggested replacement should be sought for a word typed by the user. If so, a suggestion process may employ one or more techniques to select and/or obtain a
suggested word to replace the word typed by the user. A display process may employ one or more techniques to display the suggested word to the user (e.g. in a user interface having an unobtrusive appearance). An interactive process may employ one or more techniques to receive user input, such as to utilize the suggested word or to adjust the appearance of the user interface.
[0041] At operation 502, a need to suggest a word to replace a word typed by a user is detected. In some instances, the detection is in response to recognition that the word typed by the user is misspelled. Alternatively, the detection may result from recognition that the word is used in a grammatically incorrect manner or has otherwise been misused. In the examples of FIGS. 1 and/or 2, the detection techniques 202 operating on the IME platform process 124 may perform the detection functionality.
[0042] At operation 504, a suggestion is obtained for the word, e.g., in response to detection of the need for a suggestion. The suggestion may be obtained over a network and from cloud-based resources (e.g., cloud linguistic services 106 of FIGS. 1 and 2). Alternatively, the suggestion may be obtained locally, such as by operation of suggestion techniques 204B operating on a client device 102 and/or an IME platform process 124. In one example, the suggestion may be a correctly spelled word for which there is a high confidence level corresponds to the intended meaning of the user.
[0043] At operation 506, the suggestion is displayed to the user, such as by operation of a user interface. In one example, the EVIE platform process 124 may provide data, and together with the suggestion renderer 126, may cause the suggestion to be presented. The user interface may be unobtrusive and/or may be regulated by the user to control a degree to which it intrudes on the user's operation of an application on the client device. FIGS. 3 and 4 show example
user interfaces that may be utilized to display a suggestion for consideration by a user.
[0044] At operation 508, the user may interact with the user interface. In several examples, the user may provide input regarding: the detection process whereby a suggestion was found to be necessary; the suggestion process by which a replacement word was obtained; the display process by which the replacement word was presented to the user; or feedback as provided and/or supported by the IME. In the example of FIGS. 3 and 4, the user may interact with the user interface by click or rollover of the event indicator 402, the selection of a command or option provided by the notification window 304, etc.
[0045] FIG. 6 is a flow diagram showing several example detection techniques 600 that may be used to configure an IME platform process to detect a need for a suggestion to replace a word typed by a user. Accordingly, one or more of the detection techniques 600 may optionally be utilized to perform all or part of the detection operation 502 of FIG. 5. At operation 602, words the application receives, such as from a user typing, may be recorded. Alternatively, the received words may be obtained from speech recognition techniques or another text entry method. Accordingly, when a word is detected that may be incorrectly spelled and/or used, that detection may be made in the context of previously typed words. In the example of FIG. 2, the detection techniques 202 may record words within the IME platform process 124. The recorded words are available for purposes of grammar, word context and usage, etc. At operation 604, a probability of correctness of the word typed by the user may be calculated. The calculated probability may be based in part on the words previously recorded. The probability of correctness may be based on local checks on a client or server side checks performed in the cloud and received at the client. The checks may include checks for the word in the local lexicon or a cloud-based lexicon. The probability
may be based on operation of remote or local resources (e.g., a cloud linguistic service). The resources may include operation of statistical language model(s). At operation 606, a sequence of recorded words typed by the user may be examined to provide context for a current word typed by the user. The examination may be performed locally by the IME platform process 124 or in the cloud by one or more cloud linguistic services 106. At operation 608, a statistical language model may be used to detect a need for a suggestion. Such models may reside on the IME platform process 124, although larger and more comprehensive models may reside within cloud linguistic services 106.
[0046] In a further example, at operation 610 keystrokes are detected within an application by operation of an in-process IME dynamic link library (DLL). In the example of FIG. 1, the EVIE DLL 122 detects keystrokes which are passed to the application 120. At operation 612, the keystrokes are forwarded to an out-of- process EVIE platform process. In the example of FIG. 1, the keystrokes detected by the IME DLL 122 are also passed to the IME platform process 124. At operation 614, typing speed, typing speed changes, multiple typing of backspace characters, re -typing and/or the stopping of typing may be detected by the IME platform process. Such typing characteristics may be considered by the detection techniques 202 on the IME platform process 124, when attempting to detect a need to suggest a word to replace a word typed by a user.
[0047] At operation 616, local- and/or server-based testing may be performed on one or more received words. The testing may be performed using local and/or cloud-based lexicon(s), statistical language model(s) and/or cloud-based linguistic service(s). Local testing may be performed by the IME platform process 124 and cloud-based testing may be performed by cloud linguistic services 106. The testing may be coordinated, and/or the results of the testing received, at the IME platform process.
[0048] FIG. 7 is a flow diagram showing several example suggestion techniques 700 that may be used to configure an IME platform process to obtain a suggestion for use in replacing a word typed by a user. Accordingly, one or more of the suggestion techniques 700 may optionally be utilized to perform all or part of operation 504 of FIG. 5, wherein a suggestion is obtained, either from IME-based resources or cloud-based resources. In the example of operation 702, a suggestion is obtained from a cloud linguistic service (CLS) that arbitrates between one or more cloud-based services. Accordingly, more than one service may be used, and a selection made from among the results. In the example of operation 704, a suggestion is obtained from a local lexicon and/or a local or remote statistical language model. The suggestion may be based at least in part on previously typed words. In the example of operation 706, a confidence score may be utilized to determine whether to present the obtained suggestion.
[0049] In the example of operation 708, multiple cloud-based services may be queried for correction candidates and the results aggregated. The results may be aggregated by the IME platform process 124 (FIGS. 1 and 2). In one example, cloud-based services may be queried for correction candidates and probabilities. The probabilities may each be formed as a confidence score that an associated correction candidate is correct.
[0050] In the example of operation 710, the IME may determine if technologies employed by local and remote (e.g., server- or cloud-based) resources to suggest word replacements are similar. At operation 712, if the technologies are similar, then the remote resources are utilized. In one example, the IME platform and a cloud-based linguistic service may use a similar statistical language model, and the remote statistical model may be used. The computing power of the cloud may make this choice preferable.
[0051] In the example of operation 714, a suggestion may be obtained from a cloud linguistic service (CLS) that is configured to collect candidates for the suggestion to replace a word typed by the user. Such a suggestion may be obtained if network connectivity is adequate. Alternatively, at operation 716 a suggestion may be obtained from a local lexicon and/or language model if the network connectivity is not adequate.
[0052] FIG. 8 is a flow diagram showing several example display techniques 800 that may be used within a user interface to display the suggestion, if obtained by the suggestion techniques. Accordingly, one or more of the display techniques 800 may optionally be utilized to perform all or part of operation of 506 of FIG. 5, wherein a suggestion is displayed. In the example of operation 802, a word obtained as a suggestion for replacement of a word typed by the user may be provided to the user by displaying the suggestion using any user interface techniques, such as a notification bubble. The notification bubble 304 of FIG. 3 is one example of such presentation, but other techniques are also within the scope of the operation. In the example of operation 804, the notification bubble may be displayed at a location that is based at least in part on location of an EVIE bar. FIG. 3 shows that the notification bubble 304 may be attached to the IME bar 308 by a tail 306. Movement of the IME bar 308 or notification bubble 304 may result in movement of both, depending on a selected configuration, setting or design.
[0053] In the example of operation 806, the user may be monitored by the IME to determine when the user stops typing. If the user stops typing, that may be a factor indicating or weighing toward uncertainty on the part of the user regarding the accuracy of one or more words the user has typed. Other factors indicating possible user confusion may include slowed typing, back-spacing and/or deleting, re-typing, and others. At operation 808, the user interface (e.g., the notification
bubble 304 of FIG. 3) may display the suggestion after the user has stopped typing. By waiting until the user stops or slows the typing process, performs one or more back-spaces and/or re -typing, the user interface is less likely to intrude on the user's thoughts with unnecessary suggestions.
[0054] In the example of operation 810, unwanted intrusion on the user may be prevented by binding, fixing or moving the notification bubble 304 to a location selected by the user. At operation 812, the display of the word suggestion (e.g., the notification bubble) may be located adjacent to the IME bar. Thus, the user may move the notification bubble and/or the IME bar to a location on a display (e.g., a video display screen, display of a mobile device, etc.) that is less intrusive and/or preferred for any reason. In some examples, the notification bubble 304 and IME bar 308 move together (e.g., joined by the tail 306), and in other examples they are separately movable.
[0055] In the example of operation 814, the suggestion may be provided to the user in response to an indicator that a word suggestion is available. In the example of FIG. 4, the event indicator 402 may appear and/or appear in bold, in color or in an otherwise recognizable "active" mode. The user may click or mouse-over the event indicator 402, thereby triggering appearance of a user interface device, such as the notification bubble 304.
[0056] In the example of operation 816, the suggestion for use in word replacement may be displayed if a confidence in the suggestion is greater than a threshold value. In the example, the threshold may be set at a level that does not interfere with the user unless the confidence level of a user error is sufficiently high.
[0057] FIG. 9 is a flow diagram showing several example interaction techniques 900 that may be used to interact with a user, if a suggestion was displayed. Accordingly, one or more of the interaction techniques 900 may optionally be
utilized to perform all or part of operation 508 of FIG. 5, wherein the IME interacts with a user. In the example of operation 902, input may be received from the user to utilize the displayed suggestion. Thus, user indicates that the suggested word should in fact be substituted for the problematic word typed by the user. In the example of FIG. 3, the user may select command 314 to replace the questionable word typed by the user with the word suggested by the EVIE.
[0058] In the example of operation 904, the EVIE may respond to user input to move the IME bar and/or the notification bubble. In the example of FIG. 3, the notification bubble 304 and the EVIE bar 308 are shown in a lower portion of the visual display 114. However, these could be moved to a different location, if desired by the user, such as by manual manipulation by touch screen, mouse or pointing device. In the example of operation 906, a location of user interface element(s) may be persisted over restarts or reboots of the user's computing device. In the example of FIG. 1, the IME platform process 124 may maintain a location of user interface elements shown by FIGS. 3 and/or 4 over reboots or restarts of the client device 102. In the example of operation 908, the location of user interface elements may be "roamed" or utilized by other machines used by the user. In a particular example, if the user has two different client devices with similar display screen sizes and/or resolutions, then any changes to the user interface of one device may be transferred to, and utilized by, the other device as well. If the display screens are somewhat different, then changes to one device may be mapped to the other device in a manner that approximates a presentation on a user interface of the other device.
[0059] In the example of operation 910, the IME may receive a rejection from the user of the suggestion made by the EVIE to replace a word(s) typed by the user. At operation 912, in response to the rejection, the IME may reduce a likelihood of presenting any suggestion in the future under similar circumstances. At operation
914, the EVIE may reduce a likelihood of presenting the rejected suggestion if a suggestion is to be presented in the future under similar circumstances.
[0060] As used herein, "computer-readable media" includes computer storage media and communication media. Computer storage media includes volatile and non- volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read only memory (ROM), electrically erasable programmable ROM (EEPROM), flash memory or other memory technology, compact disk ROM (CD-ROM), digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store information for access by a computing device. In contrast, communication media may embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave. As defined herein, computer storage media does not include communication media.
Conclusion
[0061] Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as exemplary forms of implementing the claims.
Claims
1. One or more computer-readable media storing computer- executable instructions that, when executed, cause one or more processors to perform acts comprising:
detecting a need for a suggestion to assist with input of a word into an application, the detecting comprising:
accessing words entered into the application and recorded; and calculating a probability of correctness of the word input based at least in part on the recorded words;
obtaining a suggestion for replacement of the word, if indicated by the calculated probability, the obtaining comprising:
obtaining the suggestion from a cloud linguistic service (CLS); if network capability used to communicate with the CLS is limited or non-existent, then obtaining a suggestion from a local lexicon or statistical language-model, based at least in part on the recorded words previously entered into the application; and
utilizing a confidence score for an obtained suggestion to determine whether to present the obtained suggestion;
providing the obtained suggestion for display if indicated by the confidence score, the providing comprising:
providing the obtained suggestion for display within a notification bubble; and
providing the notification bubble for display at a location based at least in part on location of an input method editor (IME) bar; and moving the IME bar and/or the notification bubble in response to input signifying movement.
2. One or more computer-readable media as recited in claim 1, wherein detecting the need for the suggestion additionally comprises:
detecting typing speed, detecting typing stopping, detecting multiple backspaces, or detecting re-typing by the user.
3. One or more computer-readable media as recited in claim 1, wherein detecting the need for the suggestion additionally comprises:
detecting keystrokes within an application by operation of an in-process IME dynamic link library (DLL); and
forwarding the keystrokes to an out-of-process IME platform process.
4. One or more computer-readable media as recited in claim 1, wherein calculating the probability of correctness of the word is based on at least one of multiple factors, including:
local checks on a client or server side checks received at the client, the checks comprising checks for the word in the local lexicon or a cloud-based lexicon, respectively; or
examination of a sequence of the recorded words to provide context for the word.
5. One or more computer-readable media as recited in claim 1, wherein obtaining the suggestion comprises:
querying one or more cloud-based services for correction candidates and associated probabilities, each associated probability representing a confidence score that an associated correction candidate includes a correct suggestion; wherein the CLS is configured to arbitrate between multiple cloud-based services to collect candidates for suggestions.
6. One or more computer-readable media as recited in claim 1, wherein:
detecting the need for the suggestion includes monitoring to determine when text entry stops; and
providing the suggestion for display includes providing the suggestion for display after text entry stops.
7. One or more computer-readable media as recited in claim 1, additionally comprising:
persisting the location of the notification bubble over restarts; and roaming the location of the notification bubble.
8. An input method editor (IME), comprising:
an IME platform process configured to:
detect a need for a suggestion to fix a word entered into an application operating on a computing device;
obtain the suggestion from a cloud linguistic service (CLS) through a network connection on the computing device; and
obtain the suggestion from a local lexicon or language-model if network capability used to communicate with the CLS is limited or nonexistent; and
a suggestion renderer operating on the computing device and configured to prepare the suggestion for display, preparation of the suggestion for display comprising:
causing display of the suggestion within a notification bubble; and
binding the notification bubble according to received input.
9. The input method editor as recited in claim 8, wherein the EVIE platform process is additionally configured to:
receive instructions for use of the displayed suggestion; and
respond to input to move the notification bubble.
10. The input method editor as recited in claim 8, additionally comprising:
a dynamic link library (DLL) configured in-process and configured to relay keystrokes to the IME platform.
1 1. The input method editor as recited in claim 8, wherein the IME platform process and the suggestion renderer are configured out-of-process.
12. A method, comprising:
detecting, by operation of one or more processors configured with executable instructions, a need for a suggestion to an error in text entered into an application, the detecting comprising testing for whether suggestions are needed based on a probability of correctness of a word, wherein the probability is based on multiple factors, including local checks on a client or check by a server received at the client;
obtaining, by operation of the one or more processors configured with the executable instructions, a suggestion for a replacement for the word, the obtaining comprising querying services for correction candidates and probabilities, in the form of a confidence score, that the correction is likely; causing the suggestion to be displayed if a confidence in the suggestion is greater than an threshold, the displaying comprising:
providing the suggestion in response to selection of an indicator that a suggestion is available; and
locating a display of the suggestion adjacent to an input method editor (IME) bar; and
operating a user interface, the operating comprising:
receiving instructions for use of the displayed suggestion; and responding to input to move the displayed suggestion to a preferred screen location.
13. The method as recited in claim 12, wherein detecting the need for the suggestion additionally comprises:
detecting that text entry has slowed or stopped.
14. The method as recited in claim 12, wherein detecting the need for the suggestion additionally comprises:
detecting entered text within an application by operation of an in- process IME dynamic link library (DLL); and
forwarding the entered text to an out-of-process IME platform process.
15. The method as recited in claim 12, wherein detecting the need for the suggestion additionally comprises:
examining a sequence of words to provide context for the word; and using a statistical language model having input including the sequence of words.
16. The method as recited in claim 12, wherein obtaining the suggestion for the replacement additionally comprises:
obtaining the suggestion from a cloud linguistic service (CLS) if permitted by network capability; and
obtaining the suggestion from a local lexicon or language-model if network capability does not provide connection with the CLS.
17. The method as recited in claim 12, wherein obtaining the suggestion for the replacement additionally comprises:
querying multiple cloud-based services; and
aggregating results from the multiple services.
18. The method as recited in claim 12, wherein causing the suggestion to be displayed comprises:
monitoring to determine when text entry has stopped; and
displaying the suggestion after the text entry has stopped.
19. The method as recited in claim 12, wherein operating the user interface comprises:
receiving a rejection of the suggestion to replace the word;
reducing likelihood of the suggestion to replace the word in the future; and
reducing likelihood that the word will be considered problematic in the future.
20. The method as recited in claim 12, wherein obtaining the suggestion comprises:
determining if a technology of local functionality to suggest the replacement is similar to a technology of remote functionality used to suggest the replacement; and
using the remote functionality if the technologies are similar.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201380078787.7A CN105580004A (en) | 2013-08-09 | 2013-08-09 | Input method editor providing language assistance |
US14/911,247 US10656957B2 (en) | 2013-08-09 | 2013-08-09 | Input method editor providing language assistance |
EP13891201.9A EP3030982A4 (en) | 2013-08-09 | 2013-08-09 | Input method editor providing language assistance |
PCT/CN2013/081156 WO2015018055A1 (en) | 2013-08-09 | 2013-08-09 | Input method editor providing language assistance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2013/081156 WO2015018055A1 (en) | 2013-08-09 | 2013-08-09 | Input method editor providing language assistance |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015018055A1 true WO2015018055A1 (en) | 2015-02-12 |
Family
ID=52460549
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2013/081156 WO2015018055A1 (en) | 2013-08-09 | 2013-08-09 | Input method editor providing language assistance |
Country Status (4)
Country | Link |
---|---|
US (1) | US10656957B2 (en) |
EP (1) | EP3030982A4 (en) |
CN (1) | CN105580004A (en) |
WO (1) | WO2015018055A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105824795A (en) * | 2016-04-19 | 2016-08-03 | 智者四海(北京)技术有限公司 | Method and device for displaying error information in text |
CN106326204A (en) * | 2015-06-15 | 2017-01-11 | 微软技术许可有限责任公司 | Content-based detection and processing for mistakes in message |
US20180074998A1 (en) * | 2016-09-13 | 2018-03-15 | Microsoft Technology Licensing, Llc | Visual feedback for broken text selection |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9378290B2 (en) | 2011-12-20 | 2016-06-28 | Microsoft Technology Licensing, Llc | Scenario-adaptive input method editor |
CN110488991A (en) | 2012-06-25 | 2019-11-22 | 微软技术许可有限责任公司 | Input Method Editor application platform |
KR101911999B1 (en) | 2012-08-30 | 2018-10-25 | 마이크로소프트 테크놀로지 라이센싱, 엘엘씨 | Feature-based candidate selection |
JP2014211701A (en) * | 2013-04-17 | 2014-11-13 | ソニー株式会社 | Information processing apparatus, information processing method, and program |
US10289678B2 (en) * | 2013-12-16 | 2019-05-14 | Fairwords, Inc. | Semantic analyzer for training a policy engine |
US11501068B2 (en) * | 2013-12-16 | 2022-11-15 | Fairwords, Inc. | Message sentiment analyzer and feedback |
US9996532B2 (en) * | 2016-06-17 | 2018-06-12 | Microsoft Technology Licensing, Llc | Systems and methods for building state specific multi-turn contextual language understanding systems |
US10650621B1 (en) | 2016-09-13 | 2020-05-12 | Iocurrents, Inc. | Interfacing with a vehicular controller area network |
US10102196B2 (en) * | 2016-11-08 | 2018-10-16 | Motorola Solutions, Inc. | Expanding a selected area of text, associating a data label with the expanded area of text, and storing the expanded area of text and data label in a clipboard |
CN107122061A (en) * | 2017-03-15 | 2017-09-01 | 韦柳志 | A kind of is the method for the specified curing values of coded strings in input method |
US11263399B2 (en) * | 2017-07-31 | 2022-03-01 | Apple Inc. | Correcting input based on user context |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101276245A (en) * | 2008-04-16 | 2008-10-01 | 北京搜狗科技发展有限公司 | Reminding method and system for coding to correct error in input process |
US20100138210A1 (en) * | 2008-12-02 | 2010-06-03 | Electronics And Telecommunications Research Institute | Post-editing apparatus and method for correcting translation errors |
US20110202876A1 (en) * | 2010-02-12 | 2011-08-18 | Microsoft Corporation | User-centric soft keyboard predictive technologies |
US20120297294A1 (en) | 2011-05-17 | 2012-11-22 | Microsoft Corporation | Network search for writing assistance |
US8498864B1 (en) | 2012-09-27 | 2013-07-30 | Google Inc. | Methods and systems for predicting a text |
Family Cites Families (204)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU7529981A (en) | 1980-09-19 | 1982-03-25 | Hitachi Limited | Language analysis by pattern recognition |
US6236964B1 (en) | 1990-02-01 | 2001-05-22 | Canon Kabushiki Kaisha | Speech recognition apparatus and method for matching inputted speech and a word generated from stored referenced phoneme data |
JPH07160827A (en) | 1993-12-09 | 1995-06-23 | Matsushita Electric Ind Co Ltd | Handwritten stroke editing device and method therefor |
US5873107A (en) | 1996-03-29 | 1999-02-16 | Apple Computer, Inc. | System for automatically retrieving information relevant to text being authored |
US6014638A (en) | 1996-05-29 | 2000-01-11 | America Online, Inc. | System for customizing computer displays in accordance with user preferences |
US5995928A (en) | 1996-10-02 | 1999-11-30 | Speechworks International, Inc. | Method and apparatus for continuous spelling speech recognition with early identification |
US6092044A (en) | 1997-03-28 | 2000-07-18 | Dragon Systems, Inc. | Pronunciation generation in speech recognition |
WO1998044432A1 (en) | 1997-04-01 | 1998-10-08 | Yeong Kuang Oon | Didactic and content oriented word processing method with incrementally changed belief system |
US6076056A (en) | 1997-09-19 | 2000-06-13 | Microsoft Corporation | Speech recognition system for recognizing continuous and isolated speech |
US6377965B1 (en) | 1997-11-07 | 2002-04-23 | Microsoft Corporation | Automatic word completion system for partially entered data |
US6185534B1 (en) | 1998-03-23 | 2001-02-06 | Microsoft Corporation | Modeling emotion and personality in a computer user interface |
US6247043B1 (en) | 1998-06-11 | 2001-06-12 | International Business Machines Corporation | Apparatus, program products and methods utilizing intelligent contact management |
US6085160A (en) | 1998-07-10 | 2000-07-04 | Lernout & Hauspie Speech Products N.V. | Language independent speech recognition |
US6527715B2 (en) | 1998-10-30 | 2003-03-04 | The United States Of America As Represented By The Secretary Of The Army | System and method for predicting human cognitive performance using data from an actigraph |
JP2000148748A (en) | 1998-11-13 | 2000-05-30 | Nec Corp | Japanese syllbary-to-chinese character conversion and image retrieval and display system |
US7099876B1 (en) | 1998-12-15 | 2006-08-29 | International Business Machines Corporation | Method, system and computer program product for storing transliteration and/or phonetic spelling information in a text string class |
US6460015B1 (en) | 1998-12-15 | 2002-10-01 | International Business Machines Corporation | Method, system and computer program product for automatic character transliteration in a text string object |
US6363342B2 (en) | 1998-12-18 | 2002-03-26 | Matsushita Electric Industrial Co., Ltd. | System for developing word-pronunciation pairs |
JP2000221990A (en) | 1999-01-28 | 2000-08-11 | Ricoh Co Ltd | Voice recognizing device |
DE60026637T2 (en) | 1999-06-30 | 2006-10-05 | International Business Machines Corp. | Method for expanding the vocabulary of a speech recognition system |
US6848080B1 (en) * | 1999-11-05 | 2005-01-25 | Microsoft Corporation | Language input architecture for converting one text form to another text form with tolerance to spelling, typographical, and conversion errors |
US6578022B1 (en) | 2000-04-18 | 2003-06-10 | Icplanet Corporation | Interactive intelligent searching with executable suggestions |
US6963841B2 (en) | 2000-04-21 | 2005-11-08 | Lessac Technology, Inc. | Speech training method with alternative proper pronunciation database |
US7107204B1 (en) | 2000-04-24 | 2006-09-12 | Microsoft Corporation | Computer-aided writing system and method with cross-language writing wizard |
US7089504B1 (en) | 2000-05-02 | 2006-08-08 | Walt Froloff | System and method for embedment of emotive content in modern text processing, publishing and communication |
US7277732B2 (en) | 2000-10-13 | 2007-10-02 | Microsoft Corporation | Language input system for mobile devices |
US6731307B1 (en) | 2000-10-30 | 2004-05-04 | Koninklije Philips Electronics N.V. | User interface/entertainment device that simulates personal interaction and responds to user's mental state and/or personality |
JP2002258894A (en) | 2001-03-02 | 2002-09-11 | Fujitsu Ltd | Device and method of compressing decompression voice data |
US7308439B2 (en) | 2001-06-06 | 2007-12-11 | Hyperthink Llc | Methods and systems for user activated automated searching |
CN1391180A (en) | 2001-06-11 | 2003-01-15 | 国际商业机器公司 | Auxiliary foreign language writing methods and tools |
US7353247B2 (en) | 2001-10-19 | 2008-04-01 | Microsoft Corporation | Querying applications using online messenger service |
US7283992B2 (en) | 2001-11-30 | 2007-10-16 | Microsoft Corporation | Media agent to suggest contextually related media content |
US20030160830A1 (en) | 2002-02-22 | 2003-08-28 | Degross Lee M. | Pop-up edictionary |
US20030179229A1 (en) | 2002-03-25 | 2003-09-25 | Julian Van Erlach | Biometrically-determined device interface and content |
US20030220917A1 (en) | 2002-04-03 | 2003-11-27 | Max Copperman | Contextual search |
US7194538B1 (en) | 2002-06-04 | 2007-03-20 | Veritas Operating Corporation | Storage area network (SAN) management system for discovering SAN components using a SAN management server |
US7047193B1 (en) | 2002-09-13 | 2006-05-16 | Apple Computer, Inc. | Unsupervised data-driven pronunciation modeling |
US7293015B2 (en) | 2002-09-19 | 2007-11-06 | Microsoft Corporation | Method and system for detecting user intentions in retrieval of hint sentences |
US7552051B2 (en) | 2002-12-13 | 2009-06-23 | Xerox Corporation | Method and apparatus for mapping multiword expressions to identifiers using finite-state networks |
US7360151B1 (en) | 2003-05-27 | 2008-04-15 | Walt Froloff | System and method for creating custom specific text and emotive content message response templates for textual communications |
US20040243415A1 (en) | 2003-06-02 | 2004-12-02 | International Business Machines Corporation | Architecture for a speech input method editor for handheld portable devices |
US7881934B2 (en) | 2003-09-12 | 2011-02-01 | Toyota Infotechnology Center Co., Ltd. | Method and system for adjusting the voice prompt of an interactive system based upon the user's state |
US7389223B2 (en) | 2003-09-18 | 2008-06-17 | International Business Machines Corporation | Method and apparatus for testing a software program using mock translation input method editor |
US7447627B2 (en) | 2003-10-23 | 2008-11-04 | Microsoft Corporation | Compound word breaker and spell checker |
US7634720B2 (en) | 2003-10-24 | 2009-12-15 | Microsoft Corporation | System and method for providing context to an input method |
US7412385B2 (en) | 2003-11-12 | 2008-08-12 | Microsoft Corporation | System for identifying paraphrases using machine translation |
US7689412B2 (en) | 2003-12-05 | 2010-03-30 | Microsoft Corporation | Synonymous collocation extraction using translation information |
CN1898958A (en) | 2003-12-22 | 2007-01-17 | 皇家飞利浦电子股份有限公司 | Content- processing system, method, and computer program product for monitoring the viewer's mood |
US20050144162A1 (en) | 2003-12-29 | 2005-06-30 | Ping Liang | Advanced search, file system, and intelligent assistant agent |
US7590533B2 (en) | 2004-03-10 | 2009-09-15 | Microsoft Corporation | New-word pronunciation learning using a pronunciation graph |
US20050216253A1 (en) | 2004-03-25 | 2005-09-29 | Microsoft Corporation | System and method for reverse transliteration using statistical alignment |
EP1759278A4 (en) | 2004-04-19 | 2009-05-06 | Exbiblio Bv | Processing techniques for visual capture data from a rendered document |
US7451152B2 (en) | 2004-07-29 | 2008-11-11 | Yahoo! Inc. | Systems and methods for contextual transaction proposals |
US7725318B2 (en) | 2004-07-30 | 2010-05-25 | Nice Systems Inc. | System and method for improving the accuracy of audio searching |
WO2006011819A1 (en) | 2004-07-30 | 2006-02-02 | Eurekster, Inc. | Adaptive search engine |
US7505954B2 (en) | 2004-08-18 | 2009-03-17 | International Business Machines Corporation | Search bar with intelligent parametric search statement generation |
US7490033B2 (en) | 2005-01-13 | 2009-02-10 | International Business Machines Corporation | System for compiling word usage frequencies |
US7599915B2 (en) | 2005-01-24 | 2009-10-06 | At&T Intellectual Property I, L.P. | Portal linking tool |
US8694317B2 (en) | 2005-02-05 | 2014-04-08 | Aurix Limited | Methods and apparatus relating to searching of spoken audio data |
US7555713B2 (en) | 2005-02-22 | 2009-06-30 | George Liang Yang | Writing and reading aid system |
US9165280B2 (en) | 2005-02-22 | 2015-10-20 | International Business Machines Corporation | Predictive user modeling in user interface design |
GB2424091A (en) | 2005-03-11 | 2006-09-13 | Alamy Ltd | Ranking of images in the results of a search |
US7970812B2 (en) | 2005-03-17 | 2011-06-28 | Microsoft Corporation | Redistribution of space between text segments |
US7543244B2 (en) * | 2005-03-22 | 2009-06-02 | Microsoft Corporation | Determining and displaying a list of most commonly used items |
US7512904B2 (en) | 2005-03-22 | 2009-03-31 | Microsoft Corporation | Operating system launch menu program listing |
US20060224046A1 (en) | 2005-04-01 | 2006-10-05 | Motorola, Inc. | Method and system for enhancing a user experience using a user's physiological state |
CN1851617A (en) | 2005-04-22 | 2006-10-25 | 英华达(上海)电子有限公司 | Converting device and method for mobile device making OCR convenient and input to existing editor |
US7401073B2 (en) | 2005-04-28 | 2008-07-15 | International Business Machines Corporation | Term-statistics modification for category-based search |
US7277029B2 (en) | 2005-06-23 | 2007-10-02 | Microsoft Corporation | Using language models to expand wildcards |
JP2007024960A (en) | 2005-07-12 | 2007-02-01 | Internatl Business Mach Corp <Ibm> | System, program and control method |
WO2007016370A2 (en) | 2005-07-29 | 2007-02-08 | Eazypaper Inc. | Computer method and apparatus using embedded message window for displaying messages in a functional bar |
CN1908863A (en) | 2005-08-07 | 2007-02-07 | 黄金富 | Two language mixed input method and mobile phone with dictionary function |
US7844599B2 (en) | 2005-08-24 | 2010-11-30 | Yahoo! Inc. | Biasing queries to determine suggested queries |
US20070052868A1 (en) | 2005-09-02 | 2007-03-08 | Charisma Communications, Inc. | Multimedia accessible universal input device |
US7676517B2 (en) * | 2005-10-14 | 2010-03-09 | Microsoft Corporation | Search results injected into client applications |
US7565157B1 (en) | 2005-11-18 | 2009-07-21 | A9.Com, Inc. | System and method for providing search results based on location |
GB0524354D0 (en) | 2005-11-30 | 2006-01-04 | Ibm | Method, system and computer program product for composing a reply to a text message received in a messaging application |
US20070150279A1 (en) | 2005-12-27 | 2007-06-28 | Oracle International Corporation | Word matching with context sensitive character to sound correlating |
JP4816409B2 (en) | 2006-01-10 | 2011-11-16 | 日産自動車株式会社 | Recognition dictionary system and updating method thereof |
US20070192710A1 (en) | 2006-02-15 | 2007-08-16 | Frank Platz | Lean context driven user interface |
US7953730B1 (en) | 2006-03-02 | 2011-05-31 | A9.Com, Inc. | System and method for presenting a search history |
US7676460B2 (en) | 2006-03-03 | 2010-03-09 | International Business Machines Corporation | Techniques for providing suggestions for creating a search query |
US7983910B2 (en) | 2006-03-03 | 2011-07-19 | International Business Machines Corporation | Communicating across voice and text channels with emotion preservation |
US7831911B2 (en) | 2006-03-08 | 2010-11-09 | Microsoft Corporation | Spell checking system including a phonetic speller |
US7593927B2 (en) | 2006-03-10 | 2009-09-22 | Microsoft Corporation | Unstructured data in a mining model language |
US8725729B2 (en) | 2006-04-03 | 2014-05-13 | Steven G. Lisa | System, methods and applications for embedded internet searching and result display |
US20070255567A1 (en) | 2006-04-27 | 2007-11-01 | At&T Corp. | System and method for generating a pronunciation dictionary |
US7849115B2 (en) | 2006-06-05 | 2010-12-07 | Bruce Reiner | Method and apparatus for adapting computer-based systems to end-user profiles |
US7818332B2 (en) | 2006-08-16 | 2010-10-19 | Microsoft Corporation | Query speller |
US9318108B2 (en) | 2010-01-18 | 2016-04-19 | Apple Inc. | Intelligent automated assistant |
US7647351B2 (en) | 2006-09-14 | 2010-01-12 | Stragent, Llc | Web scrape template generation |
WO2008040585A1 (en) | 2006-10-02 | 2008-04-10 | International Business Machines Corporation | Method and system of automatically adapting a user interface |
US8511565B2 (en) | 2006-10-17 | 2013-08-20 | Silverbrook Research Pty Ltd | Method of providing information via context searching of a printed graphic image |
JP4888071B2 (en) | 2006-11-15 | 2012-02-29 | 富士通株式会社 | Program, copy and paste processing method, apparatus and recording medium |
US7957955B2 (en) | 2007-01-05 | 2011-06-07 | Apple Inc. | Method and system for providing word recommendations for text input |
US7742774B2 (en) | 2007-01-11 | 2010-06-22 | Virgin Mobile Usa, L.P. | Location-based text messaging |
US7912700B2 (en) * | 2007-02-08 | 2011-03-22 | Microsoft Corporation | Context based word prediction |
US8677281B2 (en) | 2007-02-09 | 2014-03-18 | Intel-Ge Care Innovations Llc | System, apparatus and method for emotional experience time sampling via a mobile graphical user interface |
US7991609B2 (en) | 2007-02-28 | 2011-08-02 | Microsoft Corporation | Web-based proofing and usage guidance |
US8285745B2 (en) | 2007-03-01 | 2012-10-09 | Microsoft Corporation | User query mining for advertising matching |
WO2008106655A1 (en) | 2007-03-01 | 2008-09-04 | Apapx, Inc. | System and method for dynamic learning |
CN101286154B (en) * | 2007-04-09 | 2016-08-10 | 谷歌股份有限公司 | Input method editor user profiles |
CN105589571A (en) | 2007-04-09 | 2016-05-18 | 谷歌股份有限公司 | Client input method, input method editor, and editor server |
CN105117376B (en) | 2007-04-10 | 2018-07-10 | 谷歌有限责任公司 | Multi-mode input method editor |
CN105204617B (en) | 2007-04-11 | 2018-12-14 | 谷歌有限责任公司 | The method and system integrated for Input Method Editor |
CN104866469B (en) | 2007-04-11 | 2018-10-02 | 谷歌有限责任公司 | Input Method Editor with secondary language mode |
US7930676B1 (en) | 2007-04-27 | 2011-04-19 | Intuit Inc. | System and method for adapting software elements based on mood state profiling |
US8799307B2 (en) | 2007-05-16 | 2014-08-05 | Google Inc. | Cross-language information retrieval |
US20080294982A1 (en) | 2007-05-21 | 2008-11-27 | Microsoft Corporation | Providing relevant text auto-completions |
KR20100029221A (en) | 2007-06-01 | 2010-03-16 | 구글 인코포레이티드 | Detecting name entities and new words |
CN102124459B (en) | 2007-06-14 | 2013-06-12 | 谷歌股份有限公司 | Dictionary word and phrase determination |
CN101779200B (en) | 2007-06-14 | 2013-03-20 | 谷歌股份有限公司 | Dictionary word and phrase determination |
WO2009000103A1 (en) * | 2007-06-25 | 2008-12-31 | Google Inc. | Word probability determination |
US20090002178A1 (en) | 2007-06-29 | 2009-01-01 | Microsoft Corporation | Dynamic mood sensing |
US20090043584A1 (en) | 2007-08-06 | 2009-02-12 | Lawrence Brooke Frank Philips | System and method for phonetic representation |
US20090043741A1 (en) | 2007-08-09 | 2009-02-12 | Dohyung Kim | Autocompletion and Automatic Input Method Correction for Partially Entered Search Query |
US7917355B2 (en) | 2007-08-23 | 2011-03-29 | Google Inc. | Word detection |
US8661340B2 (en) | 2007-09-13 | 2014-02-25 | Apple Inc. | Input methods for device having multi-language environment |
US8694483B2 (en) | 2007-10-19 | 2014-04-08 | Xerox Corporation | Real-time query suggestion in a troubleshooting context |
US20090128567A1 (en) | 2007-11-15 | 2009-05-21 | Brian Mark Shuster | Multi-instance, multi-user animation with coordinated chat |
US7728735B2 (en) | 2007-12-04 | 2010-06-01 | At&T Intellectual Property I, L.P. | Methods, apparatus, and computer program products for estimating a mood of a user, using a mood of a user for network/service control, and presenting suggestions for interacting with a user based on the user's mood |
EP2227757A4 (en) | 2007-12-06 | 2018-01-24 | Google LLC | Cjk name detection |
US7953692B2 (en) * | 2007-12-07 | 2011-05-31 | Microsoft Corporation | Predicting candidates using information sources |
US8165406B2 (en) | 2007-12-12 | 2012-04-24 | Microsoft Corp. | Interactive concept learning in image search |
US20090177976A1 (en) | 2008-01-09 | 2009-07-09 | Bokor Brian R | Managing and presenting avatar mood effects in a virtual world |
US7984004B2 (en) | 2008-01-17 | 2011-07-19 | Microsoft Corporation | Query suggestion generation |
US8196042B2 (en) | 2008-01-21 | 2012-06-05 | Microsoft Corporation | Self-revelation aids for interfaces |
US8473276B2 (en) * | 2008-02-19 | 2013-06-25 | Google Inc. | Universal language input |
US8010465B2 (en) * | 2008-02-26 | 2011-08-30 | Microsoft Corporation | Predicting candidates using input scopes |
US7917488B2 (en) | 2008-03-03 | 2011-03-29 | Microsoft Corporation | Cross-lingual search re-ranking |
US7472061B1 (en) | 2008-03-31 | 2008-12-30 | International Business Machines Corporation | Systems and methods for building a native language phoneme lexicon having native pronunciations of non-native words derived from non-native pronunciations |
US20090249198A1 (en) | 2008-04-01 | 2009-10-01 | Yahoo! Inc. | Techniques for input recogniton and completion |
CN106598266B (en) | 2008-05-19 | 2019-07-02 | 上海触乐信息科技有限公司 | The method and system of multilingual Mixed design |
US8677251B2 (en) | 2008-05-30 | 2014-03-18 | Microsoft Corporation | Creation and suggestion of contact distribution lists |
US20090313239A1 (en) | 2008-06-16 | 2009-12-17 | Microsoft Corporation | Adaptive Visual Similarity for Text-Based Image Search Results Re-ranking |
US8745051B2 (en) | 2008-07-03 | 2014-06-03 | Google Inc. | Resource locator suggestions from input character sequence |
EP4083968A1 (en) | 2008-07-28 | 2022-11-02 | Breakthrough Performancetech, LLC | Systems and methods for computerized interactive skill training |
CN101661474B (en) | 2008-08-26 | 2012-07-04 | 华为技术有限公司 | Search method and system |
US20110107265A1 (en) | 2008-10-16 | 2011-05-05 | Bank Of America Corporation | Customizable graphical user interface |
US8584031B2 (en) | 2008-11-19 | 2013-11-12 | Apple Inc. | Portable touch screen device, method, and graphical user interface for using emoji characters |
WO2010085186A1 (en) | 2009-01-21 | 2010-07-29 | Telefonaktiebolaget L M Ericsson (Publ) | Generation of annotation tags based on multimodal metadata and structured semantic descriptors |
US8539359B2 (en) | 2009-02-11 | 2013-09-17 | Jeffrey A. Rapaport | Social network driven indexing system for instantly clustering people with concurrent focus on same topic into on-topic chat rooms and/or for generating on-topic search results tailored to user preferences regarding topic |
US8564541B2 (en) | 2009-03-16 | 2013-10-22 | Apple Inc. | Zhuyin input interface on a device |
WO2010105440A1 (en) * | 2009-03-20 | 2010-09-23 | Google Inc. | Interaction with ime computing device |
CN101848272B (en) | 2009-03-25 | 2013-08-28 | 鸿富锦精密工业(深圳)有限公司 | Input method switching method of mobile phones |
US11076189B2 (en) | 2009-03-30 | 2021-07-27 | Time Warner Cable Enterprises Llc | Personal media channel apparatus and methods |
US8230336B2 (en) | 2009-04-22 | 2012-07-24 | Microsoft Corporation | Efficient discovery, display, and autocompletion of links to wiki resources |
CN101901235B (en) | 2009-05-27 | 2013-03-27 | 国际商业机器公司 | Method and system for document processing |
US9104244B2 (en) | 2009-06-05 | 2015-08-11 | Yahoo! Inc. | All-in-one Chinese character input method |
US20100315266A1 (en) * | 2009-06-15 | 2010-12-16 | Microsoft Corporation | Predictive interfaces with usability constraints |
US20110014952A1 (en) | 2009-07-15 | 2011-01-20 | Sony Ericsson Mobile Communications Ab | Audio recognition during voice sessions to provide enhanced user interface functionality |
US8479094B2 (en) | 2009-09-08 | 2013-07-02 | Kenneth Peyton Fouts | Interactive writing aid to assist a user in finding information and incorporating information correctly into a written work |
US20110066431A1 (en) | 2009-09-15 | 2011-03-17 | Mediatek Inc. | Hand-held input apparatus and input method for inputting data to a remote receiving device |
TW201113870A (en) | 2009-10-09 | 2011-04-16 | Inst Information Industry | Method for analyzing sentence emotion, sentence emotion analyzing system, computer readable and writable recording medium and multimedia device |
KR101743122B1 (en) | 2009-11-27 | 2017-06-15 | 구글 인코포레이티드 | Client-server input method editor architecture |
US8612206B2 (en) | 2009-12-08 | 2013-12-17 | Microsoft Corporation | Transliterating semitic languages including diacritics |
EP2339576B1 (en) | 2009-12-23 | 2019-08-07 | Google LLC | Multi-modal input on an electronic device |
US8631004B2 (en) * | 2009-12-28 | 2014-01-14 | Yahoo! Inc. | Search suggestion clustering and presentation |
US20110178981A1 (en) | 2010-01-21 | 2011-07-21 | International Business Machines Corporation | Collecting community feedback for collaborative document development |
US20110184723A1 (en) | 2010-01-25 | 2011-07-28 | Microsoft Corporation | Phonetic suggestion engine |
US20110191321A1 (en) | 2010-02-01 | 2011-08-04 | Microsoft Corporation | Contextual display advertisements for a webpage |
KR101220709B1 (en) | 2010-02-03 | 2013-01-10 | 삼성전자주식회사 | Search apparatus and method for document mixing hangeul and chinese characters using electronic dictionary |
WO2011098343A1 (en) | 2010-02-12 | 2011-08-18 | Xelion B.V. | Type and select data input field |
US20110219299A1 (en) | 2010-03-07 | 2011-09-08 | DSNR Labs Ltd. | Method and system of providing completion suggestion to a partial linguistic element |
CN102193643B (en) | 2010-03-15 | 2014-07-02 | 北京搜狗科技发展有限公司 | Word input method and input method system having translation function |
WO2011127640A1 (en) | 2010-04-12 | 2011-10-20 | Google Inc. | Extension framework for input method editor |
US20110258535A1 (en) | 2010-04-20 | 2011-10-20 | Scribd, Inc. | Integrated document viewer with automatic sharing of reading-related activities across external social networks |
US8161073B2 (en) | 2010-05-05 | 2012-04-17 | Holovisions, LLC | Context-driven search |
US20110289105A1 (en) | 2010-05-18 | 2011-11-24 | Tabulaw, Inc. | Framework for conducting legal research and writing based on accumulated legal knowledge |
US8694899B2 (en) | 2010-06-01 | 2014-04-08 | Apple Inc. | Avatars reflecting user states |
JP5455232B2 (en) | 2010-06-25 | 2014-03-26 | Kddi株式会社 | Image selection apparatus, method and program |
CN102314441A (en) | 2010-06-30 | 2012-01-11 | 百度在线网络技术(北京)有限公司 | Method for user to input individualized primitive data and equipment and system |
CN102314461B (en) | 2010-06-30 | 2015-03-11 | 北京搜狗科技发展有限公司 | Navigation prompt method and system |
US8463592B2 (en) | 2010-07-27 | 2013-06-11 | International Business Machines Corporation | Mode supporting multiple language input for entering text |
US20120036468A1 (en) | 2010-08-03 | 2012-02-09 | Nokia Corporation | User input remapping |
US8473289B2 (en) | 2010-08-06 | 2013-06-25 | Google Inc. | Disambiguating input based on context |
US20120060113A1 (en) | 2010-09-08 | 2012-03-08 | Nuance Communications, Inc. | Methods and apparatus for displaying content |
US8594997B2 (en) | 2010-09-27 | 2013-11-26 | Sap Ag | Context-aware conversational user interface |
US9141285B2 (en) | 2010-11-05 | 2015-09-22 | Apple Inc. | Device, method, and graphical user interface for manipulating soft keyboards |
CN102012748B (en) | 2010-11-30 | 2012-06-27 | 哈尔滨工业大学 | Statement-level Chinese and English mixed input method |
US8712989B2 (en) | 2010-12-03 | 2014-04-29 | Microsoft Corporation | Wild card auto completion |
US9009030B2 (en) | 2011-01-05 | 2015-04-14 | Google Inc. | Method and system for facilitating text input |
US8738356B2 (en) * | 2011-05-18 | 2014-05-27 | Microsoft Corp. | Universal text input |
WO2012159249A1 (en) | 2011-05-20 | 2012-11-29 | Microsoft Corporation | Advaced prediction |
US8446432B2 (en) | 2011-07-12 | 2013-05-21 | Sony Corporation | Context aware user interface system |
US8762356B1 (en) | 2011-07-15 | 2014-06-24 | Google Inc. | Detecting change in rate of input reception |
US8564684B2 (en) | 2011-08-17 | 2013-10-22 | Digimarc Corporation | Emotional illumination, and related arrangements |
US20130054617A1 (en) | 2011-08-30 | 2013-02-28 | Alison Williams Colman | Linking Browser Content to Social Network Data |
US20130091409A1 (en) | 2011-10-07 | 2013-04-11 | Agile Insights, Llc | Method and system for dynamic assembly of multimedia presentation threads |
US10264102B2 (en) | 2011-11-03 | 2019-04-16 | Aaron Nahumi | System, methods and computer readable medium for augmented personalized social network |
US8612414B2 (en) | 2011-11-21 | 2013-12-17 | Google Inc. | Grouped search query refinements |
US20150370833A1 (en) | 2011-11-28 | 2015-12-24 | Google Inc. | Visual refinements in image search |
US8566340B2 (en) * | 2011-12-07 | 2013-10-22 | Microsoft Corporation | Provision of query suggestions independent of query logs |
US9378290B2 (en) | 2011-12-20 | 2016-06-28 | Microsoft Technology Licensing, Llc | Scenario-adaptive input method editor |
US8996356B1 (en) * | 2012-04-10 | 2015-03-31 | Google Inc. | Techniques for predictive input method editors |
US20150127748A1 (en) | 2012-04-13 | 2015-05-07 | Google Inc. | Recommendations for enhanced content in social posts |
US20130282624A1 (en) * | 2012-04-20 | 2013-10-24 | Glenn Schackmuth | Restaurant Equipment Monitoring and Control System and Method |
EP2842090A4 (en) | 2012-04-27 | 2015-12-09 | Blackberry Ltd | Systems and methods for providing files in relation to a calendar event |
US20150088927A1 (en) | 2012-04-27 | 2015-03-26 | Blackberry Limited | Systems and Methods for Establishing and Using a Personal Linking Graph |
CN110488991A (en) | 2012-06-25 | 2019-11-22 | 微软技术许可有限责任公司 | Input Method Editor application platform |
CN104412212A (en) | 2012-06-29 | 2015-03-11 | 微软公司 | Input method editor |
WO2014000267A1 (en) | 2012-06-29 | 2014-01-03 | Microsoft Corporation | Cross-lingual input method editor |
US8959109B2 (en) | 2012-08-06 | 2015-02-17 | Microsoft Corporation | Business intelligent in-document suggestions |
KR101911999B1 (en) | 2012-08-30 | 2018-10-25 | 마이크로소프트 테크놀로지 라이센싱, 엘엘씨 | Feature-based candidate selection |
-
2013
- 2013-08-09 CN CN201380078787.7A patent/CN105580004A/en active Pending
- 2013-08-09 US US14/911,247 patent/US10656957B2/en active Active
- 2013-08-09 WO PCT/CN2013/081156 patent/WO2015018055A1/en active Application Filing
- 2013-08-09 EP EP13891201.9A patent/EP3030982A4/en not_active Ceased
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101276245A (en) * | 2008-04-16 | 2008-10-01 | 北京搜狗科技发展有限公司 | Reminding method and system for coding to correct error in input process |
US20100138210A1 (en) * | 2008-12-02 | 2010-06-03 | Electronics And Telecommunications Research Institute | Post-editing apparatus and method for correcting translation errors |
US20110202876A1 (en) * | 2010-02-12 | 2011-08-18 | Microsoft Corporation | User-centric soft keyboard predictive technologies |
US20120297294A1 (en) | 2011-05-17 | 2012-11-22 | Microsoft Corporation | Network search for writing assistance |
US8498864B1 (en) | 2012-09-27 | 2013-07-30 | Google Inc. | Methods and systems for predicting a text |
Non-Patent Citations (1)
Title |
---|
See also references of EP3030982A4 |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106326204A (en) * | 2015-06-15 | 2017-01-11 | 微软技术许可有限责任公司 | Content-based detection and processing for mistakes in message |
CN105824795A (en) * | 2016-04-19 | 2016-08-03 | 智者四海(北京)技术有限公司 | Method and device for displaying error information in text |
US20180074998A1 (en) * | 2016-09-13 | 2018-03-15 | Microsoft Technology Licensing, Llc | Visual feedback for broken text selection |
Also Published As
Publication number | Publication date |
---|---|
US20160196150A1 (en) | 2016-07-07 |
US10656957B2 (en) | 2020-05-19 |
EP3030982A4 (en) | 2016-08-03 |
CN105580004A (en) | 2016-05-11 |
EP3030982A1 (en) | 2016-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10656957B2 (en) | Input method editor providing language assistance | |
US9552125B2 (en) | Input method editor | |
US10019435B2 (en) | Space prediction for text input | |
US11188308B2 (en) | Interactive code editing | |
KR101522375B1 (en) | Input method editor | |
EP2696273B1 (en) | Responding to selection of a displayed character string | |
US20130061139A1 (en) | Server-based spell checking on a user device | |
US11126794B2 (en) | Targeted rewrites | |
JP2012529108A (en) | Lighting system and language detection | |
US20150331855A1 (en) | Translation and dictionary selection by context | |
US20140297276A1 (en) | Editing apparatus, editing method, and computer program product | |
US20220188514A1 (en) | System for analyzing and prescribing content changes to achieve target readability level | |
US20130060560A1 (en) | Server-based spell checking | |
JP7374756B2 (en) | Information processing device, information processing method, and program | |
JP2019212115A (en) | Inspection device, inspection method, program, and learning device | |
US11899904B2 (en) | Text input system with correction facility | |
EP3131093B1 (en) | Information processing device, information processing method, and program | |
JP2012511759A (en) | User specified phrase input learning | |
US20140359433A1 (en) | Text selection paragraph snapping | |
KR20130065965A (en) | Method and apparautus of adaptively adjusting appearance of virtual keyboard | |
US20140267047A1 (en) | Handling inappropriate input method use | |
US20230325613A1 (en) | Smart translation systems | |
KR102138095B1 (en) | Voice command based virtual touch input apparatus | |
GB2506193A (en) | Display of first and terminating sentences of a textual paragraph |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201380078787.7 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13891201 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2013891201 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14911247 Country of ref document: US |