US20120271625A1 - Multimodal natural language query system for processing and analyzing voice and proximity based queries - Google Patents

Multimodal natural language query system for processing and analyzing voice and proximity based queries Download PDF

Info

Publication number
US20120271625A1
US20120271625A1 US13431966 US201213431966A US2012271625A1 US 20120271625 A1 US20120271625 A1 US 20120271625A1 US 13431966 US13431966 US 13431966 US 201213431966 A US201213431966 A US 201213431966A US 2012271625 A1 US2012271625 A1 US 2012271625A1
Authority
US
Grant status
Application
Patent type
Prior art keywords
query
natural language
server
user
text
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US13431966
Inventor
David E. Bernard
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Portal Communications LLC
Original Assignee
Intellection Group Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Family has litigation

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/20Handling natural language data
    • G06F17/27Automatic analysis, e.g. parsing
    • G06F17/2785Semantic analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/30017Multimedia data retrieval; Retrieval of more than one type of audiovisual media
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/3061Information retrieval; Database structures therefor ; File system structures therefor of unstructured textual data
    • G06F17/30634Querying
    • G06F17/30637Query formulation
    • G06F17/30654Natural language query formulation or dialogue systems
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/08Speech classification or search
    • G10L15/18Speech classification or search using natural language modelling
    • G10L15/1815Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/912Applications of a database
    • Y10S707/918Location

Abstract

The present disclosure provides a natural language query system and method for processing and analyzing multimodally-originated queries, including voice and proximity-based queries. The natural language query system includes a Web-enabled device including a speech input module for receiving a voice-based query in natural language form from a user and a location/proximity module for receiving location/proximity information from a location/proximity device. The query system also includes a speech conversion module for converting the voice-based query in natural language form to text in natural language form and a natural language processing module for converting the text in natural language form to text in searchable form. The query system further includes a semantic engine module for converting the text in searchable form to a formal database query and a database-look-up module for using the formal database query to obtain a result related to the voice-based query in natural language form from a database.

Description

    CROSS-REFERENCE TO RELATED APPLICATION(S)
  • This application is a continuation of copending U.S. application Ser. No. 12/979,758 filed on Dec. 28, 2010, and entitled “MULTIMODAL NATURAL LANGUAGE QUERY SYSTEM FOR PROCESSING AND ANALYZING VOICE AND PROXIMITY-BASED QUERIES,” which is a continuation-in-part U.S. Pat. No. 7,873,654 issued Jan. 18, 2011, and entitled “MULTIMODAL NATURAL LANGUAGE QUERY SYSTEM AND ARCHITECTURE FOR PROCESSING AND ANALYZING VOICE AND PROXIMITY-BASED QUERIES,” which is a continuation-in-part of U.S. Pat. No. 7,376,645 issued May 20, 2008, and entitled “MULTIMODAL NATURAL LANGUAGE QUERY SYSTEM AND ARCHITECTURE FOR PROCESSING VOICE AND PROXIMITY-BASED QUERIES,” the contents of each are incorporated in full by reference herein.
  • FIELD OF THE INVENTION
  • The present invention relates generally to a multimodal natural language query system for processing voice and proximity-based queries. More specifically, the present invention relates to a multimodal natural language query system for processing voice and proximity-based queries including a location or proximity system or device, such as a global positioning system (GPS), radio frequency identification (RFID) device, or the like. This location or proximity system or device provides the multimodal natural language query system and architecture with a plurality of advanced capabilities.
  • BACKGROUND OF THE INVENTION
  • The use of personal computers (PCs), personal digital assistants (PDAs), Web-enabled phones, smart phones, tablet devices, wireline and wireless networks, the Internet, Web-based query systems and engines, and the like has gained relatively widespread acceptance in recent years. This is due, in large part, to the relatively widespread availability of high-speed, broadband Internet access through digital subscriber lines (DSLs) (including asymmetric digital subscriber lines (ADSLs) and very-high-bit-rate digital subscriber lines (VDSLs)), cable modems, satellite modems, wireless local area networks (WLANs), 3G/4G wireless systems, and the like. Thus far, user interaction with PCs, PDAs, smart phones, tablet devices, Web-enabled phones, wireline and wireless networks, the Internet, Web-based query systems and engines, and the like has been primarily non-voice-based, through keyboards, mice, intelligent electronic pads, monitors, touch screens, printers, and the like. This has limited the adoption and use of these devices and systems somewhat, and it has long been felt that allowing for accurate, precise, and reliable voice-based user interaction, mimicking normal human interaction, would be advantageous. For example, allowing for accurate, precise, and reliable voice-based user interaction would certainly draw more users to e-commerce, e-support, e-learning, etc., and reduce learning curves.
  • In this context, “mimicking normal human interaction” means that a user would be able to speak a question into a Web-enabled device or the like and the Web-enabled device or the like would respond quickly with an appropriate answer or response, through text, graphics, or synthesized speech, the Web-enabled device or the like not simply converting the user's question into text and performing a routine search, but truly understanding and interpreting the user's question. Thus, if the user speaks a non-specific or incomplete question into the Web-enabled device or the like, the Web-enabled device or the like would be capable of inferring the user's meaning based on context or environment. This is only possible through multimodal input.
  • Several software products currently allow for limited voice-based user interaction with PCs, PDAs, and the like. Such software products include, for example, ViaVoice™ by International Business Machines Corp. and Dragon NaturallySpeaking™ by Scansoft, Inc. These software products, however, allow a user to perform dictation, voice-based command-and-control functions (opening files, closing files, etc.), and voice-based searching (using previously-trained uniform resource locators (URLs)), only after time-consuming, and often inaccurate, imprecise, and unreliable, voice training Their accuracy rates are inextricably tied to a single user that has provided the voice training.
  • Typical efforts to implement voice-based user interaction in a support and information retrieval context may be seen in U.S. Pat. No. 5,802,526, to Fawcett et al. (Sep. 1, 1998). Typical efforts to implement voice-based user interaction in an Internet context may be seen in U.S. Pat. No. 5,819,220, to Sarukkai et al. (Oct. 6, 1998).
  • U.S. Pat. No. 6,446,064, to Livowsky (Sep. 3, 2002), discloses a system and method for enhancing e-commerce using a natural language interface. The natural language interface allows a user to formulate a query in natural language form, rather than using conventional search terms. In other words, the natural language interface provides a “user-friendly” interface. The natural language interface may process a query even if there is not an exact match between the user-formulated search terms and the content in a database. Furthermore, the natural language interface is capable of processing misspelled queries or queries having syntax errors. The method for enhancing e-commerce using a natural language interface includes the steps of accessing a user interface provided by a service provider, entering a query using a natural language interface, the query being formed in natural language form, processing the query using the natural language interface, searching a database using the processed query, retrieving results from the database, and providing the results to the user. The system for enhancing e-commerce on the Internet includes a user interface for receiving a query in natural language form, a natural language interface coupled to the user interface for processing the query, a service provider coupled to the user interface for receiving the processed query, and one or more databases coupled to the user interface for storing information, wherein the system searches the one or more databases using the processed query and provides the results to the user through the user interface.
  • U.S. Pat. No. 6,615,172, to Bennett et al. (Sep. 2, 2003), discloses an intelligent query system for processing voice-based queries. This distributed client-server system, typically implemented on an intranet or over the Internet accepts a user's queries at the user's PC, PDA, or workstation using a speech input interface. After converting the user's query from speech to text, a two-step algorithm employing a natural language engine, a database processor, and a full-text structured query language (SQL) database is implemented to find a single answer that best matches the user's query. The system, as implemented, accepts environmental variables selected by the user and is scalable to provide answers to a variety and quantity of user-initiated queries.
  • U.S. Patent Application Publication No. 2001/0039493, to Pustejovsky et al. (Nov. 8, 2001), discloses, in an exemplary embodiment, a system and method for answering voice-based queries using a remote mobile device, e.g., a mobile phone, and a natural language system.
  • U.S. Patent Application Publication No. 2003/0115192, to Kil et al. (Jun. 19, 2003), discloses, in various embodiments, an apparatus and method for controlling a data mining operation by specifying the goal of data mining in natural language, processing the data mining operation without any further input beyond the goal specification, and displaying key performance results of the data mining operation in natural language. One specific embodiment includes providing a user interface having a control for receiving natural language input describing the goal of the data mining operation from the control of the user interface. A second specific embodiment identifies key performance results, providing a user interface having a control for communicating information, and communicating a natural language description of the key performance results using the control of the user interface. In a third specific embodiment, input data determining a data mining operation goal is the only input required by the data mining application.
  • U.S. Patent Application Publication No. 2004/0044516, to Kennewick et al. (Mar. 4, 2004), discloses systems and methods for receiving natural language queries and/or commands and executing the queries and/or commands. The systems and methods overcome some of the deficiencies of other speech query and response systems through the application of a complete speech-based information query, retrieval, presentation, and command environment. This environment makes significant use of context, prior information, domain knowledge, and user-specific profile data to achieve a natural language environment for one or more users making queries or commands in multiple domains. Through this integrated approach, a complete speech-based natural language query and response environment may be created. The systems and methods create, store, and use extensive personal profile information for each user, thereby improving the reliability of determining the context and presenting the expected results for a particular question or command.
  • U.S. Patent Application Publication No. 2004/0117189, to Bennett (Jun. 17, 2004), discloses an intelligent query system for processing voice-based queries. This distributed client-server system, typically implemented on an intranet or over the Internet, accepts a user's queries at the user's PC, PDA, or workstation using a speech input interface. After converting the user's query from speech to text, a natural language engine, a database processor, and a full-text Structured Query Language (SQL) database are implemented to find a single answer that best matches the user's query. Both statistical and semantic decoding are used to assist and improve the performance of the query recognition.
  • Each of the systems, apparatuses, software products, and methods described above suffers from at least one of the following shortcomings. Several of the systems, apparatuses, software products, and methods require time-consuming, and often inaccurate, imprecise, and unreliable, voice training Several of the systems, apparatuses, software products, and methods are single-modal, meaning that a user may interact with each of the systems, apparatuses, software products, and methods in only one way, i.e. each utilizes only a single voice-based input. As a result of this single-modality, there is no context or environment within which a voice-based search is performed and several of the systems, apparatuses, software products, and methods must perform multiple iterations to pinpoint a result or answer related to the voice-based search.
  • Thus, what is needed are natural language query systems and methods for processing voice and proximity-based queries that do not require time-consuming, and often inaccurate, imprecise, and unreliable, voice training. What is also needed are natural language query systems and methods that are multimodal, meaning that a user may interact with the natural language query systems and methods in a number of ways simultaneously and that the natural language query systems and methods utilize multiple inputs in order to create and take into consideration a context or environment within which a voice and/or proximity-based search or the like is performed. In other words, what is needed are natural language query systems and methods that mimic normal human interaction, attributing meaning to words based on the context or environment within which they are spoken. What is further needed are natural language query systems and methods that perform only a single iteration to pinpoint a result or answer related to a voice and/or proximity-based search or the like.
  • BRIEF SUMMARY OF THE INVENTION
  • In various embodiments, the present invention provides a natural language query system and method for processing voice and proximity-based queries that do not require time-consuming, and often inaccurate, imprecise, and unreliable, voice training The present invention also provides a natural language query system and method that are multimodal, meaning that a user may interact with the natural language query system and method in a number of ways simultaneously and that the natural language query system and method utilize multiple inputs in order to create and take into consideration a context or environment within which a voice and/or proximity-based search or the like is performed. In other words, the present invention provides a natural language query system and method that mimic normal human interaction, attributing meaning to words based on the context or environment within which they are spoken. This context or environment may be prior information-based, domain knowledge-based, user-specific profile data-based, and/or, preferably, location or proximity-based. The present invention further provides a natural language query system and method that perform only a single iteration to pinpoint a result or answer related to a voice and/or proximity-based search or the like.
  • Functionally, the present invention provides a natural language query system and method that do more than simply convert speech to text, use this text to search a database, and convert text to speech. The natural language query system and method of the present invention are capable of understanding speech and providing appropriate and useful responses. Off-the-shelf tools are used to incorporate and combine speech recognition, natural language processing (NLP), also referred to as natural language understanding, and speech synthesis technologies. NLP understands grammar (how words connect and how their definitions relate to one another), context, and environment.
  • In an exemplary embodiment, a query system includes a computing device communicatively coupled to a network and configured to receive audio input and determine location information; and a server communicatively coupled to the computing device via the network, wherein the server is configured to: receive a query from the computing device; perform natural language processing on the query using lexicons and grammar rules to determine a meaning of the query; utilize location information to further determine the meaning of the query; and perform a database look up based on the determined meaning of the query. Optionally, the computing device includes one of a smart phone or tablet device. The computing device may include Global Positioning Satellite functionality providing the location information. The computing device further may include a Radio Frequency Identification scanner providing the location information. The query system may further include a user database configured to store a plurality of queries from a plurality of users, and the server is further configured to determine the meaning of the query based upon data in the user database. The query system may further include a plurality of databases communicatively coupled to the server. The query system may further include a middleware application executed on the server, wherein the middleware application is configured to route the query to one or more of the plurality of databases and to rank accuracy of results from the one or more of the plurality of databases. The query system may further include a semantic engine module executed on the server for converting the determined query to a formal database query. The query system may further include a speech conversion module executed on the server for converting the query in audio and natural language form to text in natural language form. The query system may further include a natural language processing module executed on the server for converting the text in natural language form to text in searchable form using lexicons and grammar rules to parse sentences and determine underlying meanings of the query.
  • In another exemplary embodiment, a mobile device query method, includes receiving an audio query from a user; determining location information of the user based on Global Positioning Satellite functionality or Radio Frequency Identification readings; transmitting the audio query and the location information to a server; and receiving a plurality of responses to the audio query from the server, each of the plurality of responses is ranked by the server using an accuracy algorithm.
  • In yet another exemplary embodiment, a query method includes receiving an audio query and location information; converting the audio query into text in a natural language form; converting the text in a natural language form to text in searchable form using lexicons and grammar rules to parse sentences and determine underlying meanings of the audio query; determining a formal database query from the text in searchable form; and performing a database lookup based on the formal database query. The query method of may further include sending the formal database query to a plurality of databases including constrained semantic models; and ranking results from the plurality of databases.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • The present invention is illustrated and described herein with reference to the various drawings, in which like reference numbers denote like method steps and/or system components, respectively, and in which:
  • FIG. 1 is a schematic diagram illustrating one embodiment of the multimodal natural language query system and architecture for processing voice and proximity-based queries of the present invention;
  • FIG. 2 is a flow chart illustrating one embodiment of the multimodal natural language query method for processing voice and proximity-based queries of the present invention;
  • FIG. 3 is a continuing flow chart illustrating one embodiment of the multimodal natural language query method for processing voice and proximity-based queries of the present invention; and
  • FIG. 4 is a diagram illustrating an exemplary embodiment of the present invention with a Web-enabled device connected to the speech server, a remote server, and the like to perform a natural language query over a network, such as the Internet or the like.
  • DETAILED DESCRIPTION OF THE INVENTION
  • In general, the natural language query system and method of the present invention may incorporate and combine the following technologies:
  • 1. Speech Processing—Speech processing allows PCs, PDAs, Web-enabled phones, smart phones, tablet devices, and the like to recognize—and, to some extent, understand—spoken language. Spoken language is “eyes free” and “hands free”, allowing a PC, PDA, Web-enabled phone, smart phone, tablet device, or the like to be used anywhere. This technology has engendered two types of software products: continuous-speech recognition software products and command-and-control software products. Because a context-free grammar allows a speech recognition engine to reduce recognized words to those contained in a predetermined list, high degrees of speech recognition may be achieved in a speaker-independent environment. A context-free grammar may be used with relatively inexpensive microphones, limited central processing units (CPUs), and no time-consuming, and often inaccurate, imprecise, and unreliable, voice training Although speech processing technology is not new, speech recognition accuracy rates are just now becoming acceptable for natural language discourse.
  • 2. Speech Synthesis—The ability to mimic speech is useful for applications that require spontaneous user interaction, or in situations where viewing or reading are impractical, such as, for example, when a PC, PDA, Web-enabled phone, smart phone, tablet device, or the like provide driving directions or instructions to the driver of a vehicle. In software products aimed at the average user, it is important that output sounds are pleasant and sound human enough to encourage regular use. Several software products now bring relatively inexpensive and effective conversational access to information applications and accelerate the acceptance of speech as a user interface alternative for Web-based and mobile applications, including, for example, Microsoft Speech Server by Microsoft Corp. Microsoft Speech Server currently supports eight languages and is based on the open-standard Speech Application Language Tags (SALT) specification, which extends familiar mark-up languages and leverages the existing Web-development paradigm.
  • 3. Natural Language Processing (NLP) systems interpret written, rather than spoken, language and may be found in speech processing systems that begin by converting spoken input into text. Using lexicons and grammar rules, NLP parses sentences, determines underlying meanings, and retrieves or constructs responses. NLP technology's main use is in enabling databases to answer queries presented in the form of questions. Another use is in handling high-volume email. NLP performance may be improved by incorporating a common sense knowledge base—that is, a set of real-world rules. Almost all of the database query languages tend to be rigid and difficult to learn, and it is often difficult for even the most experienced user to get desired information out of a database. A natural language interface to the SQL language overcomes the need for users to master the complexities of the SQL language.
  • 4. English Query—English query (EQ) is a component of Microsoft SQL Server 2000 by Microsoft Corp. that allows users to query databases using plain English. The EQ engine creates a database query that may be executed under program control to return a formatted answer. The development process is at a higher level than traditional programming, but may be mastered by non-programmers with some database background. In order to implement natural language searching, an authoring tool is used to provide domain knowledge to the EQ engine, and to relate database entities to objects in the domain. EQ uses verb relationships and the like to perform natural language parsing of users' questions, which provides better search results than keyword-based technologies. The goal of EQ is to identify and model all of the relationships between entities in a database, creating a semantic model that defines a knowledge domain. This enables EQ to provide answers to a relatively wide range of questions without having to identify those questions in advance.
  • 5. Input Devices—Adding speech recognition capability to an EQ application with a microphone or the like allows a user to type or speak a question to the EQ application. Such a speech interface may also be incorporated into a PDA, smart phone, tablet device, etc. with wireless networking capability. The combination of speech recognition and EQ represents a powerful method for a user to quickly access information in a SQL Server database. Additionally, other mechanisms can be utilized for the speech input, such as voice over Internet Protocol (VoIP) and other Internet telephony mechanisms, instant messenger (IM), and the like.
  • 6. Multimodality—Multimodality combines graphics, text, audio, and avatar output with text, ink, speech, body attitude, gaze, RFID, GPS, and touch input to provide a greatly enhanced user experience. It is enabled by the convergence of voice, data, and content, and by multimedia, Internet protocol (IP), speech, and wireless technologies hosted on a wide range of devices and device combinations. As compared to single- modal visual and voice applications, multimodal applications are more intuitive and easier to use. A user may select how to best interact with an application, which is especially useful with newer, smaller-form-factor devices. When modalities are used contemporaneously, the resulting decrease in mutual disambiguation (MD) input error rates improve accuracy, performance, and robustness.
  • 7. Radio Frequency Identification—RFID is a generic term for technologies that automatically identify one or more objects via radio waves, using a unique serial number stored in a RFID tag. The RFID tag's antenna, tuned to receive a RFID reader's electromagnetic waves in real time, is able to transmit identification information to the RFID reader. The RFID reader converts the radio waves received from the RFID tag into digital information which, in turn, may be passed on to a business system for processing and/or storage. RFID reader technology may be integrated with PDAs via a PC Card implementation. RFID tags tend to be small and lightweight and may be read through nonmetallic materials. The RFID reader does not have to touch a RFID tag, making RFID ideal for adverse and/or unclean environments. Likewise, RFID does not require line of sight between a tag and a reader, allowing the tags to be hidden under the skin, inside clothes, within the pages of a book, etc., preserving the items usability and aesthetics. RFID tags come in two varieties: passive (low power, short range, and relatively inexpensive) and active (high power, long range, and relatively expensive). Preferably, the natural language query system and method of the present invention utilize active RFID tags that run on their own power and transmit over long distances. The battery life of a typical active RFID tag is about five years.
  • In an exemplary embodiment, the natural language query system and method of the present invention incorporate and combine the following exemplary components:
    • Web/Speech/Data Server Running Microsoft Windows 2003
    • Web Server: Microsoft Internet Information Services (IIS) 6.0
    • Database: Microsoft SQL Server 2000 SP4
    • Microsoft SQL Server 2000 English Query with Visual Studio .NET 2003 tools
    • Microsoft SQL server 2000 Full-Text Indexing
    • Microsoft Speech Server 1.0
    • Microsoft Speech Application SDK Version 1.0
    • Simple Object Access Protocol (SOAP) 3.0
    • HP iPAQ h5550 Pocket PC Running Microsoft Pocket PC 2003 Premium
    • HP iPAQ FA120A PC Card Expansion Pack Plus
    • Identec Solutions iCard III RFID Reader
    • Identec Solutions iD2, iQ32, and iQ8 RFID Tags
    • Speech Add-In For Microsoft Pocket Internet Explorer
    • D-Link DI-614+ Wireless Broadband Router
    • Speech Application Language tags (SALT) Protocol
    • DHTML, JavaScript, VBScript (ASP), CSS
    • Microsoft Visual FoxPro 8.0 SP1
    • Microsoft Component Services
    • Visual BASIC .NET using Visual Studio .NET 2003
  • It should be noted that components performing similar functions and/or achieving similar results may also be used, and are contemplated by the present invention.
  • Referring to FIG. 1, in an exemplary embodiment of the present invention, the natural language query system 10 includes a Web-enabled device 12, such as a portable PC (a laptop PC or the like), a PDA, a Web-enabled phone, or the like capable of accessing one or more interactive Hyper Text Mark-Up Language (HTML) or Dynamic Hyper Text Mark-Up Language (DHTML) Web pages 14 (each utilizing JavaScript, Visual basic Scripting Edition (VBScript), Active Server Pages (ASPs), Cascading Style Sheets (CSSs), etc.) via the Internet using a resident browser application 16, such as Internet Explorer or the like. It should be understood that FIG. 1 is a simplified representation of the natural language query system 10 for purposes of explanation. Further, it should be appreciated that FIG. 1 depicts the natural language query system 10 in an oversimplified manner, and a practical embodiment may include additional components and suitably configured processing logic to support known or conventional operating features that are not described in detail herein.
  • Preferably, the Web-enabled device 12 is mobile and may be relatively easily carried by a user. For example, the Web-enabled device 12 may include any of a laptop, a smart phone, a PDA, a tablet device, and the like. The Web-enabled device 12 includes a speech plug-in 18, such as Speech Plug-In for Microsoft Pocket Internet Explorer or the like, and is in communication with a speech server 20, such as Microsoft Speech Server 1.0 or the like. Together, the speech plug-in 18 and the speech server 20 provide the Web-enabled device 12 with the ability to receive a voice-based query from a user and convert the speech to text. Specifically, once a speak button or the like associated with the Web-enabled device 12 has been pushed, the speech plug-in 18 detects that a voice-based query has begun, records the voice-based query, and continues until silence is detected. Optionally, the display of the Web-enabled device 12 may display an audio meter that provides the user with real time feedback regarding volume, background noise, and word gaps that provide the user with an improved interactive experience with the Web-enabled device 12. The speech plug-in 18 then sends the recorded voice-based query to the speech server 20, which converts the voice-based query to text and returns the text to the Web-enabled device 12. Preferably, the user's interaction with the Web-enabled device 12 takes place through a speech-enabled Web-page resident on a remote server 22 running one or more Active Server Pages (ASPs) 24. This Web page is displayed on the display of the Web-enabled device 12.
  • The Web-enabled device 12 also includes a location or proximity system or device, such as a GPS or RFID device. In the event that a RFID device is utilized, the Web-enabled device 12 includes an RFID reader 26, such as an Identec Solutions iCard III RFID Reader or the like. The RFID reader 26 automatically and wirelessly detects and receives information continuously and in real time from one or more active RFID tags 28, such as one or more Identec Solutions iD2 RFID Tags or the like, in the vicinity, each of the one or more RFID tags 28 associated with and containing information about an article of interest, place of interest, etc. Optionally, the RFID reader component 26 includes RFID tag reader class software that controls the interface between the browser of the web-enabled device 12 and the RFID reader engine. This RFID tag reader class software incorporates complex fuzzy logic and enables the accurate reading of the RFID tags 28 in real time in support of a mobile user. In general, the RFID reader 26 (or GPS) provides location or proximity information to the Web-enabled device 12 and the natural language query system 10. This location or proximity information and the converted text associated with the user's voice-based query are sent to the remote server 22 for subsequent processing. That is, the natural language query system 10 may utilize the location or proximity information in conjunction with the user's voice-based query for understanding or analyzing the user's voice-based query. Based on the location or proximity information received from the RFID reader 26 and the Web-enabled device 12, the remote server 22 retrieves a relevant set of information, images, and/or links which are sent to the Web-enabled device 12 and displayed in the form of one or more Web-pages on the display of the Web-enabled device 12. As those of ordinary skill in the art will appreciate, most conventional Web-enabled devices 12 include GPS functionality, and the present invention contemplates utilizing this GPS functionality to provide the location or proximity information.
  • If there are no problems with the converted text associated with the user's voice-based query, NLP is then carried out at the remote server 22. First, a semantic engine “interprets” the text associated with the user's voice-based query and converts the text into a formal database query. The semantic engine includes an English query run-time engine 30 and a compiled English query model 32. A database look-up is then performed using the formal database query and the result is sent back to the remote server 22 and finally the Web-enabled device 12, which may form one or more Web-pages incorporating the result. The database look-up may be performed by Microsoft Visual FoxPro COM+DLL 34 or the like, a full-text catalog 36, and a SQL server 38. Advantageously, the location or proximity information and the converted text associated with the user's voice-based query received from the Web-enabled device 12 represent multimodal inputs. The location or proximity information provide a context or environment that is used to narrow and streamline the database look-up related to the converted text associated with the user's voice-based query. This is illustrated in the example below.
  • Optionally, the remote server 22 may also create a voice-based response that is sent to the Web-enabled device 12 and converted into a speech output. Additionally, the remote server 22 can be configured to produce a “conversational agent” or “avatar”, i.e. a three-dimensional on-screen “face” that realistically expresses the words by meshing Text-to-Speak (TTS) output with a talking head. Because the natural language query system 10 is multimodal, the user can react with the natural language query system 10 by either speaking or by tapping the display of the Web-enabled device 12. For example, when link in the results Web page is tapped, more detail, including images, may be returned to the Web-enabled device 12.
  • Referring to FIGS. 2 and 3, in another exemplary embodiment of the present invention, the natural language query method 40 includes receiving a voice-based query from a user using, for example, the speech plug-in 18 (FIG. 1) of the Web-enabled device 12 (FIG. 1) (Block 42) and converting the voice-based query to text using the speech server 20 (FIG. 1) (Block 46). Specifically, once the speak button or the like associated with the Web-enabled device 12 has been pushed, the speech plug-in 18 detects that a voice-based query has begun, records the voice-based query, and continues until silence is detected. For example, if the user is a patron visiting a particular exhibit in an art museum, the user's query may be “who painted this picture?” As described above, the display of the Web-enabled device 12 may display an audio meter that provides the user with real time feedback regarding volume, background noise, and word gaps that provide the user with an improved interactive experience with the Web-enabled device 12. The speech plug-in 18 then sends the recorded voice-based query to the speech server 20 (Block 44), which converts the voice-based query to text (Block 46) and returns the converted text to the Web-enabled device 12 (Block 48). Preferably, the user's interaction with the Web-enabled device 12 takes place through a speech-enabled Web-page resident on the remote server 22 (FIG. 1) running one or more ASPs 24 (FIG. 1). This Web page is displayed on the display of the Web-enabled device 12.
  • As described above, the RFID reader 26 (FIG. 1) provides location or proximity information to the Web-enabled device 12 and the natural language query system 10 (FIG. 1). This location or proximity information and the converted text associated with the user's voice-based query are sent to the remote server 22 for subsequent processing (Blocks 50 and 52). For example, each of the exhibits in the art museum is preferably equipped with a corresponding RFID tag 28 (FIG. 1). Thus, the Web-enabled device 12 and the natural language query system 10 “know” which painting the user is standing in proximity to when the user asks “who painted this picture?” Based on the location or proximity information received from the RFID reader 26 and the Web-enabled device 12, the remote server 22 retrieves a relevant set of information, images, and/or links which are sent to the Web-enabled device 12 and displayed in the form of one or more Web-pages on the display of the Web-enabled device 12.
  • If there are no problems with the converted text associated with the user's voice-based query, NLP is then carried out at the remote server 22. First, a semantic engine “interprets” the text associated with the user's voice-based query and converts the text into a formal database query (Block 54). The semantic engine includes an English query run-time engine 30 (FIG. 1) and a compiled English query model 32 (FIG. 1). A database look-up is then performed using the formal database query (Block 56) and the result is sent back to the remote server 22 and finally the Web-enabled device 12 (Block 58), which forms one or more Web-pages incorporating the result. Advantageously, the location or proximity information and the converted text associated with the user's voice-based query received from the Web-enabled device 12 represent multimodal inputs. The location or proximity information provide a context or environment that is used to narrow and streamline the database look-up related to the converted text associated with the user's voice-based query.
  • As described above, the natural language query system 10 is configured to analyze and process a query, such as, for example “who painted this picture?” A logical extension to making a query is in merging a command or directive with the query to enhance the end result. For example, take the simple query “How many three bedroom houses are for sale on Elm Street in Scranton?” A user may state the “question” as part of a command and simultaneous add value to the request: “Map all three bedroom houses that are for sale on Elm Street in Scranton and email that to Fred Jones”. The natural language query system 10 may be configured to receive this command and process accordingly. Other examples of similar verb-based requests are chart and sort/order by.
  • Referring to FIG. 4, in an exemplary embodiment of the present invention, the Web-enabled device 12 connects to the speech server 20, the remote server 22, and the like to perform a natural language query over a network 62, such as the Internet or the like. The network 62 connection can include a wireless, wired, or the like connection. The present invention contemplates any physical network 62 connection and network protocol, such as IP, VoIP, Public Switched Telephone Network (PSTN), DSL, WLAN, Cellular (e.g., CDMA, GSM, and the like), cable modem, and the like. In an exemplary embodiment, the Web-enabled device 12 may include, for example, a laptop, a smart phone, a tablet device, a personal digital assistant, or the like. Further, the present invention contemplates a variety of applications for communication over the network 62, such as, but not limited to, Twitter, Instant Messaging (IM), Short Message Service (SMS), Multimedia Messaging Service (MMS), and the like.
  • Optionally, the servers 20,22 can connect to a user database 66 such as through a local area network (LAN) connection, the Internet, or the like. The user database 66 provides an infrastructure to capture detailed information about user behaviors through the Web-enabled device 12, such as (1) the physical location of the user when a question was asked (e.g., based on the RFID tag on the Web-enabled device 12), (2) the question asked by the user, (3) the SQL query generated by the server 20,22 or an error condition, if applicable, and (4) the answer generated by the server 20,22. For example, the user database 66 can be configured to capture this information and other information based on user queries from multiple Web-enabled devices 12. This captured information is, in effect, capturing behavior and insights into user's thinking not possible before. Aggregated across many users, organizational behaviors can be gleaned.
  • This information allows for interesting analytics to be explored. For example, the user database 66 can be connected to the Internet or a LAN and accessed by a network administrator or the like over a computer 68 for performing analysis of data stored in the user database 66. Because a question can be asked in a myriad of ways, but will generate the same SQL query, this information can correlate result frequencies back to questions. Because the natural language query system of the present invention removes many of the current barriers to getting questions answered in a timely fashion, implementation of a system is likely to unleash a flood of questions that people have wanted to ask in the past, but did not because (1) it took too long to get an answer via traditional methods or (2) because they did not have access to any tools that could do the job adequately.
  • Advantageously, the natural language query system removes obstacles to capture some potentially very interesting and never before measured behaviors and insights into user's thinking For example, a user could perform frequency analysis on questions and results to get an idea of what kinds of information people in an organization are looking for the most. This could be used for optimization within the organization. Also, it is possible to discover “interesting” questions that someone deep down in the organization is asking, which may not have been noticed before. This leads to more of an atmosphere of “information democratization”, where more people in the organization become more valuable because the cost to test their ideas goes to almost zero. The user database 66 could be accessed through standard mechanisms known in the art and the computer 68 could include custom analysis tools or off-the-shelf tools, such as spreadsheets, database access modules, and the like, to perform such analysis.
  • It follows that one unique way of presenting analytics may include a standard visual “dashboard” in which each metric is represented by an English language question/query. Dashboard presentation approaches are common in current business intelligence (BI) implementations, displaying multiple metrics at once in separate panes, often in the form of charts and graphs. Business intelligence (BI) refers to computer-based techniques used in spotting, digging-out, and analyzing business data, such as sales revenue by products and/or departments, or by associated costs and incomes. BI technologies provide historical, current, and predictive views of business operations. Common functions of business intelligence technologies are reporting, online analytical processing, analytics, data mining, business performance management, benchmarking, text mining, and predictive analytics. However, specifying how to calculate each metric is tedious in conventional BI systems; using plain English questions to generate the metric results would be a major innovation in the space. For example, the present invention may be utilized as a front-end interface to various BI systems.
  • In another exemplary embodiment, the present invention has the ability to trace the “steps” of a person's search in chronological order, which can render the “decision tree” they used to get to their answer. For example, many users will go through a series of related questions in order to refine their search criteria; this would allow interesting types of analysis to be done across all users. An analogue to this is clinical pathways, a large standard decision tree used by physicians to analyze patient conditions and come to a diagnosis; pathways are based on a great deal of prior collected knowledge. Anaphoric referencing (meaning that you can refer to earlier queries), is used to help make the query session more natural to a human. For example, the query “Who received the highest bonus?” might be followed by “Who is his manager?” Or, for example, a person asks a question like “How many houses in Apple County have 4 bedrooms?” and the system responds “554 homes”. Then the user immediately asks “How many of those have a pool?” The system recognizes that “those” refers to the most immediate past question by that user and we run a subset of that query.
  • Currently, research indicates high accuracy rates when a “domain” of information is constrained. For example, a system may work against a particular database (e.g., airline flights, real estate listings, etc.) and the system may render very accurate results for all kinds of questions associated with the constrained information. However, this does not scale well when applied to broader more general topics (such as the entire Google database). In an exemplary embodiment, a middleware layer may be created that can analyze an incoming question and automatically route it to one or more constrained semantic models simultaneously, and then determine which of the attempts returned the best answer instead of using a broad database. This may include an accuracy algorithm that determines accuracy on an individual domain query, “scorecarding” and ranking results from multiple domains and returning the best results to the user.
  • Although the present invention has been illustrated and described herein with reference to preferred embodiments and specific examples thereof, it will be readily apparent to those of ordinary skill in the art that other embodiments and examples may perform similar functions and/or achieve like results. All such equivalent embodiments and examples are within the spirit and scope of the present invention and are intended to be covered by the following claims.

Claims (12)

  1. 1. A query system, comprising:
    a computing device communicatively coupled to a network and configured to receive audio input comprising a query and determine location information; and
    a server communicatively coupled to the computing device via the network, wherein the server is configured to:
    receive the query from the computing device;
    perform natural language processing on the query using lexicons and grammar rules to determine a meaning of the query, wherein the natural language processing comprises converting text in natural language form to text in searchable form using the lexicons and grammar rules to determine the meaning of the query;
    utilize location information to further determine the meaning of the query;
    perform a database look up based on the determined meaning of the query, wherein the database look up is provided with a context and environment for narrowing and streamlining the database look up utilizing the location information and rank responses of the database lookup using an accuracy algorithm.
  2. 2. The query system of claim 1, wherein the computing device comprises one of a smart phone or tablet device.
  3. 3. The query system of claim 2, wherein the computing device comprises Global Positioning Satellite functionality providing the location information.
  4. 4. The query system of claim 3, wherein the computing device further comprises a Radio Frequency Identification scanner providing the location information.
  5. 5. The query system of claim 1, further comprising a user database configured to store a plurality of queries from a plurality of users.
  6. 6. The query system of claim 5, wherein the server is further configured to:
    determine the meaning of the query based upon data in the user database.
  7. 7. The query system of claim 1, further comprising a plurality of databases communicatively coupled to the server.
  8. 8. The query system of claim 7, further comprising a middleware application executed on the server, wherein the middleware application is configured to route the query to one or more of the plurality of databases and to rank accuracy of results from the one or more of the plurality of databases.
  9. 9. The query system of claim 1, further comprising a semantic engine module executed on the server for converting the determined query to a formal database query.
  10. 10. The query system of claim 1, further comprising a speech conversion module executed on the server for converting the query in audio and natural language form to text in natural language form.
  11. 11. The query system of claim 10, further comprising a natural language processing module executed on the server for converting the text in natural language form to text in searchable form using lexicons and grammar rules to parse sentences and determine underlying meanings of the query.
  12. 12. A mobile device query method, comprising:
    receiving an audio query from a user;
    determining location information of the user based on Global Positioning Satellite functionality or Radio Frequency Identification readings;
    transmitting the audio query and the location information to a server; and
    receiving a plurality of responses to the audio query from the server, each of the plurality of responses is ranked by the server using an accuracy algorithm; wherein the server is configured to:
    perform natural language processing on the audio query using lexicons and grammar rules to parse sentences and determine a meaning of the audio query, wherein the natural language processing comprises converting text in natural language form to text in searchable form using the lexicons and grammar rules to determine the meaning of the audio query;
    utilize the location information to further determine the meaning of the audio query; and
    perform a database look up based on the determined meaning of the audio query, wherein the database look up is provided with a context and environment for narrowing and streamlining the database look up utilizing the location information.
US13431966 2005-01-24 2012-03-27 Multimodal natural language query system for processing and analyzing voice and proximity based queries Abandoned US20120271625A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US12979758 US8150872B2 (en) 2005-01-24 2010-12-28 Multimodal natural language query system for processing and analyzing voice and proximity-based queries
US13431966 US20120271625A1 (en) 2010-12-28 2012-03-27 Multimodal natural language query system for processing and analyzing voice and proximity based queries

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US13431966 US20120271625A1 (en) 2010-12-28 2012-03-27 Multimodal natural language query system for processing and analyzing voice and proximity based queries
US13655403 US9223776B2 (en) 2012-03-27 2012-10-18 Multimodal natural language query system for processing and analyzing voice and proximity-based queries

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US12979758 Continuation US8150872B2 (en) 2004-11-29 2010-12-28 Multimodal natural language query system for processing and analyzing voice and proximity-based queries

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US13655403 Continuation-In-Part US9223776B2 (en) 2010-12-28 2012-10-18 Multimodal natural language query system for processing and analyzing voice and proximity-based queries

Publications (1)

Publication Number Publication Date
US20120271625A1 true true US20120271625A1 (en) 2012-10-25

Family

ID=47022009

Family Applications (2)

Application Number Title Priority Date Filing Date
US12979758 Active US8150872B2 (en) 2004-11-29 2010-12-28 Multimodal natural language query system for processing and analyzing voice and proximity-based queries
US13431966 Abandoned US20120271625A1 (en) 2005-01-24 2012-03-27 Multimodal natural language query system for processing and analyzing voice and proximity based queries

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US12979758 Active US8150872B2 (en) 2004-11-29 2010-12-28 Multimodal natural language query system for processing and analyzing voice and proximity-based queries

Country Status (1)

Country Link
US (2) US8150872B2 (en)

Cited By (60)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140201241A1 (en) * 2013-01-15 2014-07-17 EasyAsk Apparatus for Accepting a Verbal Query to be Executed Against Structured Data
US8892446B2 (en) 2010-01-18 2014-11-18 Apple Inc. Service orchestration for intelligent automated assistant
US9190062B2 (en) 2010-02-25 2015-11-17 Apple Inc. User profiling for voice input processing
US9262612B2 (en) 2011-03-21 2016-02-16 Apple Inc. Device access using voice authentication
US9300784B2 (en) 2013-06-13 2016-03-29 Apple Inc. System and method for emergency calls initiated by voice command
US9330720B2 (en) 2008-01-03 2016-05-03 Apple Inc. Methods and apparatus for altering audio output signals
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
US9368114B2 (en) 2013-03-14 2016-06-14 Apple Inc. Context-sensitive handling of interruptions
US9424840B1 (en) * 2012-08-31 2016-08-23 Amazon Technologies, Inc. Speech recognition platforms
US9430463B2 (en) 2014-05-30 2016-08-30 Apple Inc. Exemplar-based natural language processing
US9483461B2 (en) 2012-03-06 2016-11-01 Apple Inc. Handling speech synthesis of content for multiple languages
US9495129B2 (en) 2012-06-29 2016-11-15 Apple Inc. Device, method, and user interface for voice-activated navigation and browsing of a document
US9502031B2 (en) 2014-05-27 2016-11-22 Apple Inc. Method for supporting dynamic grammars in WFST-based ASR
US9535906B2 (en) 2008-07-31 2017-01-03 Apple Inc. Mobile device having human language translation capability with positional feedback
US9576574B2 (en) 2012-09-10 2017-02-21 Apple Inc. Context-sensitive handling of interruptions by intelligent digital assistant
US9582608B2 (en) 2013-06-07 2017-02-28 Apple Inc. Unified ranking with entropy-weighted information for phrase-based semantic auto-completion
US9620104B2 (en) 2013-06-07 2017-04-11 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9620105B2 (en) 2014-05-15 2017-04-11 Apple Inc. Analyzing audio input for efficient speech and music recognition
US9626955B2 (en) 2008-04-05 2017-04-18 Apple Inc. Intelligent text-to-speech conversion
US9633004B2 (en) 2014-05-30 2017-04-25 Apple Inc. Better resolution when referencing to concepts
US9633674B2 (en) 2013-06-07 2017-04-25 Apple Inc. System and method for detecting errors in interactions with a voice-based digital assistant
US9646609B2 (en) 2014-09-30 2017-05-09 Apple Inc. Caching apparatus for serving phonetic pronunciations
US9646614B2 (en) 2000-03-16 2017-05-09 Apple Inc. Fast, language-independent method for user authentication by voice
US9668121B2 (en) 2014-09-30 2017-05-30 Apple Inc. Social reminders
US9697822B1 (en) 2013-03-15 2017-07-04 Apple Inc. System and method for updating an adaptive speech recognition model
US9697820B2 (en) 2015-09-24 2017-07-04 Apple Inc. Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks
US9711141B2 (en) 2014-12-09 2017-07-18 Apple Inc. Disambiguating heteronyms in speech synthesis
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
US9721566B2 (en) 2015-03-08 2017-08-01 Apple Inc. Competing devices responding to voice triggers
US9734193B2 (en) 2014-05-30 2017-08-15 Apple Inc. Determining domain salience ranking from ambiguous words in natural speech
US9760559B2 (en) 2014-05-30 2017-09-12 Apple Inc. Predictive text input
US9785630B2 (en) 2014-05-30 2017-10-10 Apple Inc. Text prediction using combined word N-gram and unigram language models
US9798393B2 (en) 2011-08-29 2017-10-24 Apple Inc. Text correction processing
US9818400B2 (en) 2014-09-11 2017-11-14 Apple Inc. Method and apparatus for discovering trending terms in speech requests
US9842101B2 (en) 2014-05-30 2017-12-12 Apple Inc. Predictive conversion of language input
US9842105B2 (en) 2015-04-16 2017-12-12 Apple Inc. Parsimonious continuous-space phrase representations for natural language processing
US9858925B2 (en) 2009-06-05 2018-01-02 Apple Inc. Using context information to facilitate processing of commands in a virtual assistant
US9865280B2 (en) 2015-03-06 2018-01-09 Apple Inc. Structured dictation using intelligent automated assistants
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US9886432B2 (en) 2014-09-30 2018-02-06 Apple Inc. Parsimonious handling of word inflection via categorical stem + suffix N-gram language models
US9899019B2 (en) 2015-03-18 2018-02-20 Apple Inc. Systems and methods for structured stem and suffix language models
US9922642B2 (en) 2013-03-15 2018-03-20 Apple Inc. Training an at least partial voice command system
US9934775B2 (en) 2016-05-26 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters
US9953088B2 (en) 2012-05-14 2018-04-24 Apple Inc. Crowd sourcing information to fulfill user requests
US9959870B2 (en) 2008-12-11 2018-05-01 Apple Inc. Speech recognition involving a mobile device
US9966068B2 (en) 2013-06-08 2018-05-08 Apple Inc. Interpreting and acting upon commands that involve sharing information with remote devices
US9966065B2 (en) 2014-05-30 2018-05-08 Apple Inc. Multi-command single utterance input method
US9971774B2 (en) 2012-09-19 2018-05-15 Apple Inc. Voice-based media searching
US9972304B2 (en) 2016-06-03 2018-05-15 Apple Inc. Privacy preserving distributed evaluation framework for embedded personalized systems
US10043516B2 (en) 2016-09-23 2018-08-07 Apple Inc. Intelligent automated assistant
US10049668B2 (en) 2015-12-02 2018-08-14 Apple Inc. Applying neural network language models to weighted finite state transducers for automatic speech recognition
US10049663B2 (en) 2016-06-08 2018-08-14 Apple, Inc. Intelligent automated assistant for media exploration
US10057736B2 (en) 2011-06-03 2018-08-21 Apple Inc. Active transport based notifications
US10067938B2 (en) 2016-06-10 2018-09-04 Apple Inc. Multilingual word prediction
US10074360B2 (en) 2014-09-30 2018-09-11 Apple Inc. Providing an indication of the suitability of speech recognition
US10078631B2 (en) 2014-05-30 2018-09-18 Apple Inc. Entropy-guided text prediction using combined word and character n-gram language models
US10079014B2 (en) 2012-06-08 2018-09-18 Apple Inc. Name recognition system
US10083688B2 (en) 2015-05-27 2018-09-25 Apple Inc. Device voice control for selecting a displayed affordance
US10089072B2 (en) 2016-06-11 2018-10-02 Apple Inc. Intelligent device arbitration and control
US10101822B2 (en) 2015-06-05 2018-10-16 Apple Inc. Language input correction

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7516190B2 (en) * 2000-02-04 2009-04-07 Parus Holdings, Inc. Personal voice-based information retrieval system
EP2137641B1 (en) * 2007-04-13 2015-11-04 Massachusetts Institute of Technology Speech data retrieval apparatus, speech data retrieval method, speech data retrieval program and computer usable medium having computer readable speech data retrieval program embodied therein
US9792640B2 (en) 2010-08-18 2017-10-17 Jinni Media Ltd. Generating and providing content recommendations to a group of users
US9263045B2 (en) * 2011-05-17 2016-02-16 Microsoft Technology Licensing, Llc Multi-mode text input
CA2873240A1 (en) 2012-05-16 2013-11-21 Xtreme Interactions Inc. System, device and method for processing interlaced multimodal user input
US20130346068A1 (en) * 2012-06-25 2013-12-26 Apple Inc. Voice-Based Image Tagging and Searching
US9123335B2 (en) * 2013-02-20 2015-09-01 Jinni Media Limited System apparatus circuit method and associated computer executable code for natural language understanding and semantic content discovery
US9715877B2 (en) * 2014-06-25 2017-07-25 GM Global Technology Operations LLC Systems and methods for a navigation system utilizing dictation and partial match search
US10025819B2 (en) * 2014-11-13 2018-07-17 Adobe Systems Incorporated Generating a query statement based on unstructured input
US20160342895A1 (en) * 2015-05-21 2016-11-24 Baidu Usa Llc Multilingual image question answering
US9799324B2 (en) 2016-01-28 2017-10-24 Google Inc. Adaptive text-to-speech outputs

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5727057A (en) * 1994-12-27 1998-03-10 Ag Communication Systems Corporation Storage, transmission, communication and access to geographical positioning data linked with standard telephony numbering and encoded for use in telecommunications and related services
US20020169611A1 (en) * 2001-03-09 2002-11-14 Guerra Lisa M. System, method and computer program product for looking up business addresses and directions based on a voice dial-up session
US20030023440A1 (en) * 2001-03-09 2003-01-30 Chu Wesley A. System, Method and computer program product for presenting large lists over a voice user interface utilizing dynamic segmentation and drill down selection
US6934684B2 (en) * 2000-03-24 2005-08-23 Dialsurf, Inc. Voice-interactive marketplace providing promotion and promotion tracking, loyalty reward and redemption, and other features
US7493259B2 (en) * 2002-01-04 2009-02-17 Siebel Systems, Inc. Method for accessing data via voice
US20100005081A1 (en) * 1999-11-12 2010-01-07 Bennett Ian M Systems for natural language processing of sentence based queries

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5802526A (en) * 1995-11-15 1998-09-01 Microsoft Corporation System and method for graphically displaying and navigating through an interactive voice response menu
US5819220A (en) * 1996-09-30 1998-10-06 Hewlett-Packard Company Web triggered word set boosting for speech interfaces to the world wide web
US6446064B1 (en) * 1999-06-08 2002-09-03 Albert Holding Sa System and method for enhancing e-commerce using natural language interface for searching database
US6615172B1 (en) * 1999-11-12 2003-09-02 Phoenix Solutions, Inc. Intelligent query engine for processing voice based queries
US20010039493A1 (en) * 2000-04-13 2001-11-08 Pustejovsky James D. Answering verbal questions using a natural language system
US6952471B1 (en) * 2000-06-09 2005-10-04 Agere Systems Inc. Handset proximity muting
US20020169735A1 (en) * 2001-03-07 2002-11-14 David Kil Automatic mapping from data to preprocessing algorithms
US7233655B2 (en) * 2001-10-03 2007-06-19 Accenture Global Services Gmbh Multi-modal callback
US7398209B2 (en) * 2002-06-03 2008-07-08 Voicebox Technologies, Inc. Systems and methods for responding to natural language speech utterance
US7142894B2 (en) * 2003-05-30 2006-11-28 Nokia Corporation Mobile phone for voice adaptation in socially sensitive environment
US20050113115A1 (en) * 2003-10-31 2005-05-26 Haberman William E. Presenting broadcast received by mobile device based on proximity and content

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5727057A (en) * 1994-12-27 1998-03-10 Ag Communication Systems Corporation Storage, transmission, communication and access to geographical positioning data linked with standard telephony numbering and encoded for use in telecommunications and related services
US20100005081A1 (en) * 1999-11-12 2010-01-07 Bennett Ian M Systems for natural language processing of sentence based queries
US6934684B2 (en) * 2000-03-24 2005-08-23 Dialsurf, Inc. Voice-interactive marketplace providing promotion and promotion tracking, loyalty reward and redemption, and other features
US20020169611A1 (en) * 2001-03-09 2002-11-14 Guerra Lisa M. System, method and computer program product for looking up business addresses and directions based on a voice dial-up session
US20030023440A1 (en) * 2001-03-09 2003-01-30 Chu Wesley A. System, Method and computer program product for presenting large lists over a voice user interface utilizing dynamic segmentation and drill down selection
US7493259B2 (en) * 2002-01-04 2009-02-17 Siebel Systems, Inc. Method for accessing data via voice

Cited By (76)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9646614B2 (en) 2000-03-16 2017-05-09 Apple Inc. Fast, language-independent method for user authentication by voice
US8930191B2 (en) 2006-09-08 2015-01-06 Apple Inc. Paraphrasing of user requests and results by automated digital assistant
US8942986B2 (en) 2006-09-08 2015-01-27 Apple Inc. Determining user intent based on ontologies of domains
US9117447B2 (en) 2006-09-08 2015-08-25 Apple Inc. Using event alert text as input to an automated assistant
US9330720B2 (en) 2008-01-03 2016-05-03 Apple Inc. Methods and apparatus for altering audio output signals
US9865248B2 (en) 2008-04-05 2018-01-09 Apple Inc. Intelligent text-to-speech conversion
US9626955B2 (en) 2008-04-05 2017-04-18 Apple Inc. Intelligent text-to-speech conversion
US9535906B2 (en) 2008-07-31 2017-01-03 Apple Inc. Mobile device having human language translation capability with positional feedback
US10108612B2 (en) 2008-07-31 2018-10-23 Apple Inc. Mobile device having human language translation capability with positional feedback
US9959870B2 (en) 2008-12-11 2018-05-01 Apple Inc. Speech recognition involving a mobile device
US9858925B2 (en) 2009-06-05 2018-01-02 Apple Inc. Using context information to facilitate processing of commands in a virtual assistant
US8903716B2 (en) 2010-01-18 2014-12-02 Apple Inc. Personalized vocabulary for digital assistant
US8892446B2 (en) 2010-01-18 2014-11-18 Apple Inc. Service orchestration for intelligent automated assistant
US9548050B2 (en) 2010-01-18 2017-01-17 Apple Inc. Intelligent automated assistant
US9318108B2 (en) 2010-01-18 2016-04-19 Apple Inc. Intelligent automated assistant
US10049675B2 (en) 2010-02-25 2018-08-14 Apple Inc. User profiling for voice input processing
US9190062B2 (en) 2010-02-25 2015-11-17 Apple Inc. User profiling for voice input processing
US9633660B2 (en) 2010-02-25 2017-04-25 Apple Inc. User profiling for voice input processing
US10102359B2 (en) 2011-03-21 2018-10-16 Apple Inc. Device access using voice authentication
US9262612B2 (en) 2011-03-21 2016-02-16 Apple Inc. Device access using voice authentication
US10057736B2 (en) 2011-06-03 2018-08-21 Apple Inc. Active transport based notifications
US9798393B2 (en) 2011-08-29 2017-10-24 Apple Inc. Text correction processing
US9483461B2 (en) 2012-03-06 2016-11-01 Apple Inc. Handling speech synthesis of content for multiple languages
US9953088B2 (en) 2012-05-14 2018-04-24 Apple Inc. Crowd sourcing information to fulfill user requests
US10079014B2 (en) 2012-06-08 2018-09-18 Apple Inc. Name recognition system
US9495129B2 (en) 2012-06-29 2016-11-15 Apple Inc. Device, method, and user interface for voice-activated navigation and browsing of a document
US9424840B1 (en) * 2012-08-31 2016-08-23 Amazon Technologies, Inc. Speech recognition platforms
US10026394B1 (en) 2012-08-31 2018-07-17 Amazon Technologies, Inc. Managing dialogs on a speech recognition platform
US9576574B2 (en) 2012-09-10 2017-02-21 Apple Inc. Context-sensitive handling of interruptions by intelligent digital assistant
US9971774B2 (en) 2012-09-19 2018-05-15 Apple Inc. Voice-based media searching
US20140201241A1 (en) * 2013-01-15 2014-07-17 EasyAsk Apparatus for Accepting a Verbal Query to be Executed Against Structured Data
US9368114B2 (en) 2013-03-14 2016-06-14 Apple Inc. Context-sensitive handling of interruptions
US9697822B1 (en) 2013-03-15 2017-07-04 Apple Inc. System and method for updating an adaptive speech recognition model
US9922642B2 (en) 2013-03-15 2018-03-20 Apple Inc. Training an at least partial voice command system
US9582608B2 (en) 2013-06-07 2017-02-28 Apple Inc. Unified ranking with entropy-weighted information for phrase-based semantic auto-completion
US9966060B2 (en) 2013-06-07 2018-05-08 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9633674B2 (en) 2013-06-07 2017-04-25 Apple Inc. System and method for detecting errors in interactions with a voice-based digital assistant
US9620104B2 (en) 2013-06-07 2017-04-11 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9966068B2 (en) 2013-06-08 2018-05-08 Apple Inc. Interpreting and acting upon commands that involve sharing information with remote devices
US9300784B2 (en) 2013-06-13 2016-03-29 Apple Inc. System and method for emergency calls initiated by voice command
US9620105B2 (en) 2014-05-15 2017-04-11 Apple Inc. Analyzing audio input for efficient speech and music recognition
US9502031B2 (en) 2014-05-27 2016-11-22 Apple Inc. Method for supporting dynamic grammars in WFST-based ASR
US9633004B2 (en) 2014-05-30 2017-04-25 Apple Inc. Better resolution when referencing to concepts
US9966065B2 (en) 2014-05-30 2018-05-08 Apple Inc. Multi-command single utterance input method
US9842101B2 (en) 2014-05-30 2017-12-12 Apple Inc. Predictive conversion of language input
US10083690B2 (en) 2014-05-30 2018-09-25 Apple Inc. Better resolution when referencing to concepts
US9760559B2 (en) 2014-05-30 2017-09-12 Apple Inc. Predictive text input
US10078631B2 (en) 2014-05-30 2018-09-18 Apple Inc. Entropy-guided text prediction using combined word and character n-gram language models
US9785630B2 (en) 2014-05-30 2017-10-10 Apple Inc. Text prediction using combined word N-gram and unigram language models
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
US9734193B2 (en) 2014-05-30 2017-08-15 Apple Inc. Determining domain salience ranking from ambiguous words in natural speech
US9430463B2 (en) 2014-05-30 2016-08-30 Apple Inc. Exemplar-based natural language processing
US9668024B2 (en) 2014-06-30 2017-05-30 Apple Inc. Intelligent automated assistant for TV user interactions
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
US9818400B2 (en) 2014-09-11 2017-11-14 Apple Inc. Method and apparatus for discovering trending terms in speech requests
US10074360B2 (en) 2014-09-30 2018-09-11 Apple Inc. Providing an indication of the suitability of speech recognition
US9646609B2 (en) 2014-09-30 2017-05-09 Apple Inc. Caching apparatus for serving phonetic pronunciations
US9886432B2 (en) 2014-09-30 2018-02-06 Apple Inc. Parsimonious handling of word inflection via categorical stem + suffix N-gram language models
US9668121B2 (en) 2014-09-30 2017-05-30 Apple Inc. Social reminders
US9986419B2 (en) 2014-09-30 2018-05-29 Apple Inc. Social reminders
US9711141B2 (en) 2014-12-09 2017-07-18 Apple Inc. Disambiguating heteronyms in speech synthesis
US9865280B2 (en) 2015-03-06 2018-01-09 Apple Inc. Structured dictation using intelligent automated assistants
US9721566B2 (en) 2015-03-08 2017-08-01 Apple Inc. Competing devices responding to voice triggers
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US9899019B2 (en) 2015-03-18 2018-02-20 Apple Inc. Systems and methods for structured stem and suffix language models
US9842105B2 (en) 2015-04-16 2017-12-12 Apple Inc. Parsimonious continuous-space phrase representations for natural language processing
US10083688B2 (en) 2015-05-27 2018-09-25 Apple Inc. Device voice control for selecting a displayed affordance
US10101822B2 (en) 2015-06-05 2018-10-16 Apple Inc. Language input correction
US9697820B2 (en) 2015-09-24 2017-07-04 Apple Inc. Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks
US10049668B2 (en) 2015-12-02 2018-08-14 Apple Inc. Applying neural network language models to weighted finite state transducers for automatic speech recognition
US9934775B2 (en) 2016-05-26 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters
US9972304B2 (en) 2016-06-03 2018-05-15 Apple Inc. Privacy preserving distributed evaluation framework for embedded personalized systems
US10049663B2 (en) 2016-06-08 2018-08-14 Apple, Inc. Intelligent automated assistant for media exploration
US10067938B2 (en) 2016-06-10 2018-09-04 Apple Inc. Multilingual word prediction
US10089072B2 (en) 2016-06-11 2018-10-02 Apple Inc. Intelligent device arbitration and control
US10043516B2 (en) 2016-09-23 2018-08-07 Apple Inc. Intelligent automated assistant

Also Published As

Publication number Publication date Type
US20110093271A1 (en) 2011-04-21 application
US8150872B2 (en) 2012-04-03 grant

Similar Documents

Publication Publication Date Title
Oviatt et al. Designing the user interface for multimodal speech and pen-based gesture applications: state-of-the-art systems and future research directions
Gray et al. Modelling and using sensed context information in the design of interactive applications
US7869998B1 (en) Voice-enabled dialog system
US7197460B1 (en) System for handling frequently asked questions in a natural language dialog service
US7552053B2 (en) Techniques for aiding speech-to-speech translation
Johnston et al. MATCH: An architecture for multimodal dialogue systems
US7216080B2 (en) Natural-language voice-activated personal assistant
US20070106497A1 (en) Natural language interface for driving adaptive scenarios
US8447607B2 (en) Mobile systems and methods of supporting natural language human-machine interactions
US8073700B2 (en) Retrieval and presentation of network service results for mobile device using a multimodal browser
US20070124263A1 (en) Adaptive semantic reasoning engine
US20030182113A1 (en) Distributed speech recognition for mobile communication devices
US20140074470A1 (en) Phonetic pronunciation
US20070136222A1 (en) Question and answer architecture for reasoning and clarifying intentions, goals, and needs from contextual clues and content
US20090216691A1 (en) Systems and Methods for Generating and Implementing an Interactive Man-Machine Web Interface Based on Natural Language Processing and Avatar Virtual Agent Based Character
US20110153324A1 (en) Language Model Selection for Speech-to-Text Conversion
US8326634B2 (en) Systems and methods for responding to natural language speech utterance
US8620659B2 (en) System and method of supporting adaptive misrecognition in conversational speech
US20150032443A1 (en) Self-learning statistical natural language processing for automatic production of virtual personal assistants
Schnelle Context Aware Voice User Interfaces for Workflow Support
US20140365209A1 (en) System and method for inferring user intent from speech inputs
US20070203869A1 (en) Adaptive semantic platform architecture
US8219406B2 (en) Speech-centric multimodal user interface design in mobile technology
US8255224B2 (en) Voice recognition grammar selection based on context
US20110184740A1 (en) Integration of Embedded and Network Speech Recognizers

Legal Events

Date Code Title Description
AS Assignment

Owner name: PORTAL COMMUNICATIONS, LLC, TEXAS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:THE INTELLECTION GROUP, INC.;REEL/FRAME:044755/0289

Effective date: 20180124

AS Assignment

Owner name: THE INTELLECTION GROUP, INC., GEORGIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:BERNARD, DAVID E.;REEL/FRAME:044874/0896

Effective date: 20101228