609 results about "Dialog system" patented technology

A method for voice activation of a software agent from a standby mode. In one embodiment, an audio recording (2) is buffered in an audio buffer (6) and at the same time, the audio recording is input to a secondary voice recognition process (7) which is economical in terms of energy and has an increased false positive rate. When a keyword is recognized, a primary voice recognition process (8) is activated from an inactive state, which converts the audio buffer to text and inputs it to a dialog system (9) which analyzes as to whether there is a relevant question made by the user. If this is the case, the user gets an acoustic reply (3), and if this is not the case, the dialog system and the primary voice recognition process immediately return to the inactive state and transfer the control to the secondary voice recognition process.

Apparatus with accompanying subsystems and methods for developing conversational computer applications. As a user interface, the apparatus allows for a user to initiate the conversation. The apparatus also answers simple and complex questions, understands complex requests, pursues the user for further information when the request is incomplete, and in general provides customer support with a human like conversation while, at the same time, it is capable to interact with a company's proprietary database. As a development tool, the apparatus allows a software developer to implement a conversational system much faster than takes, with current commercial systems to implement basic dialog flows. The apparatus contains three major subsystems: a state transition inference engine, a heuristic answer engine and a parser generator with semantic augmentations. A main process broker controls the flow and the interaction between the different subsystems. The state transition inference engine handles requests that require processing a transaction or retrieving exact information. The heuristic answer engine answers questions that do not require exact answers but enough information to fulfill the user's request. The parser generator processes the user's natural language request, that is, it processes the syntactical structure of the natural language requests and it builds a conceptual structure of the request. After the parser generator processes the user's request, a main process broker feeds the conceptual structure to either the heuristic answer engine or to the state transition inference engine. The interaction between the main process broker and the subsystems creates a conversational environment between the user and the apparatus, while the apparatus uses information from proprietary databases to provide information, or process information, during the course of the conversation. The apparatus is equipped with a programming interface that allows implementers to declare and specify transactions based requests and answers to a multiplicity of questions. The apparatus may be used with a speech recognition interface, in which case, the apparatus improves the recognition results through the context implicitly created by the apparatus.

Systems and methods for constructing a series of interactions with a user to collect multiple pieces of related information for the purpose of accomplishing a specific goal or topic (a multi-slot dialog) using a component-based approach are disclosed. The method generally includes outputting a primary header prompt to elicit values for slots in a segment from the user, receiving a primary user response containing a value for each slot in at least a subset of the slots in the segment, processing the primary user response to determine at least one possible recognition value for each slot contained in the primary user response, filling each slot contained in the primary user response with a matched value selected from the corresponding possible recognition values, and repeating the outputting, receiving, processing and filling for any unfilled slots in the segment until all slots in the segment of slots are filled.

In order to handle portions of a recognized sentence having an error, a speaker or user is questioned about contents associated with the portions, and according to a user's answer a result is obtained. A speech recognition unit extracts a speech feature of a speech signal inputted from a user and finds a phoneme nearest to the speech feature to recognize a word. A recognition error determination unit finds a sentence confidence based on a confidence of the recognized word, performs examination of a semantic structure of a recognized sentence, and determines whether or not an error exists in the recognized sentence which is subject to speech recognition according to a predetermined criterion based on both the sentence confidence and a result of examining the semantic structure of the recognized sentence. Further, a meta-dialogue generation unit generates a question asking the user for additional information based on a content of a portion where the error exists and a type of the error.

The invention concerns a system and method of predicting problematic dialogs in a task classification system based on the user's input communications. The method may include determining whether a task classification decision can be made based on a first automated dialog exchange with the user. As such, if the task classification decision cannot be made, the method may determine whether the probability of conducting a successful automated dialog with the user based on whether the first dialog exchange exceeds a first threshold. The successful dialog may be defined as a dialog exchange between an automated dialog system and the user that results in at least one of processing of the user's input communication and routing the user's input communication. The method may further operate such that if the first threshold is exceeded, further dialog is conducted with the user. Otherwise, the user may be directed to a human for assistance.

A dialog system for use in a multi-user, multi-domain environment. The dialog system understands user requests when multiple users are interacting with each other as well as the dialog system. The dialog system uses multi-human conversational context to improve domain detection. Using interactions between multiple users allows the dialog system to better interpret machine directed conversational inputs in multi-user conversational systems. The dialog system employs topic segmentation to chunk conversations for determining context boundaries. Using general topic segmentation methods, as well as the specific domain detector trained with conversational inputs collected by a single user system, allows the dialog system to better determine the relevant context. The use of conversational context helps reduce the domain detection error rate, especially in certain domains, and allows for better interactions with users when the machine addressed turns are not recognized or are ambiguous.

Disclosed are systems, methods and computer-readable media for controlling a computing device to provide contextual responses to user inputs. The method comprises receiving a user input, generating a set of features characterizing an association between the user input and a conversation context based on at least a semantic and syntactic analysis of user inputs and system responses, determining with a data-driven machine learning approach whether the user input begins a new topic or is associated with a previous conversation context and if the received question is associated with the existing topic, then generating a response to the user input using information associated with the user input and any previous user input associated with the existing topic.

A method of rapidly and precisely managing a dialog turn between a user and an agent by using speech information, facial expression information, and delay time information includes generating first dialog turn information using dialog information analyzed from a speech uttered by the user, generating second dialog turn information using facial expression information analyzed from a face image of the user, and determining a final dialog turn using the first and second dialog turn information, information on a status of the spoken dialog system, information on whether the user speech is input, and information on a no-answer time of the user.

The invention discloses a dialogue automatic reply system based on deep learning and reinforcement learning. The dialogue automatic reply system comprises a user interaction module which receives question information inputted by a user in a dialogue system interface; a session management module which records the active state of the user, wherein the active state includes historical dialogue information, user position transformation information and user emotion change information; a user analysis module which analyzes registration information and the active state of the user and portraits for the user so as to obtain user portrait information; a dialogue module which generates reply information through a language module according to the question information of the user with combination of the portrait of the user; and a model learning module which updates the language model through the reinforcement learning technology according to the reply information generated by the language model. According to the dialogue automatic reply system based on deep learning and reinforcement learning, the reply of the dialogue meeting the personality of the user can be given according to the dialogue text inputted by the user with combination of context information, the personality characteristics of the user and the intentions in the dialogue.

Techniques are disclosed for combining natural language generation with query retrieval for context appropriate query recommendation. For example, a computer-implemented method for generating a recommended query for a conversation system in response to an original user query, wherein at least a portion of the original user query is not understandable to a query interpretation process, includes the following steps. Recommendation results are computed, in response to the original user query, using a natural language generation-based recommendation process. Recommendation results are computed, in response to the original user query, using a retrieval-based recommendation process. A recommended query is generated based on consideration of at least a portion of the natural language generation-based recommendation results and at least a portion of the retrieval-based recommendation results.

A method is provided for representing and updating the state of a dialog involving a series of queries and commands to an artificial intelligence system. Each statement within the dialogue may be modeled as a relational tree spanning nodes corresponding to named entities within the statement. A data structure may be used to store each of these trees and to modify them as the dialog progresses. A subsequent statement in the dialog may be parsed and its contents used to update an ongoing search initiated within that dialog. Statements may be used for the update process despite being fragmentary or not corresponding to any predetermined grammar. An algorithm is disclosed for updating the trees within the data structure after a new statement is parsed.

A system and method of presenting widgets to a user during a multi-modal interactive dialog between a user and a computer is presented. The system controls the multi-modal dialog; and when user input would help to clarify or speed up the presentation of requested information, the system presents a temporary widget to the user to elicit the user input in this regard. The system presents the widget on a display screen at a position that will not interfere with the dialog. Various types of widgets are available, such as button widgets, sliders and confirmation widgets, depending on the type of information that the system requires.

An automated system, apparatus and method for evaluation of comprehension are disclosed. The method includes receiving an input text and natural language processing the text to identify dependencies between text elements in the input text. Grammar rules are applied to generate questions and associated answers from the processed text, at least some of the questions being based on the identified dependencies. A set of the generated questions is posed to a reader of the input text and the comprehension of the reader evaluated, based on the reader's responses to the questions posed.

A dialog system and method may generate and maintain in parallel multiple dialog sessions, determine to which dialog session a user speech input applies, selectively provide control to one of the dialog sessions, at any one time, to output data to the user, synchronize multiple dialog sessions, and support user interruptions at any time during the dialog sessions.

A speech-enabled dialog system responds to a plurality of wake-up phrases. Based on which wake-up phrase is detected, the system's configuration is modified accordingly. Various configurable aspects of the system include selection and morphing of a text-to-speech voice; configuration of acoustic model, language model, vocabulary, and grammar; configuration of a graphic animation; configuration of virtual assistant personality parameters; invocation of a particular user profile; invocation of an authentication function; and configuration of an open sound. Configuration depends on a target market segment. Configuration also depends on the state of the dialog system, such as whether a previous utterance was an information query.

The invention relates to a system that interacts with a user in an automated dialog system (100). The system may include a communicative goal generator (210) that generates communicative goals based on a first communication received from the user. The generated communicative goals (210) may be related to information needed to be obtained from the user. The system may further include a sentence planning unit (220) that automatically plans one or more sentences based on the communicative goals generated by the communicative goal generator (210). At least one of the planned sentences may be then output to the user (230).

A method and method for natural language generation employ a natural language generation model which has been trained to assign an utterance label to a new text sequence, based on features extracted from the text sequence, such as parts-of-speech. The model assigns an utterance label to the new text sequence, based on the extracted features. The utterance label is used to guide the generation of a natural language utterance, such as a question, from the new text sequence. The system and method find application in dialog systems for generating utterances, to be sent to a user, from brief descriptions of problems or solutions in a knowledge base.

The present invention provides a method and apparatus for specifying and obtaining services through audio commands, resulting in a live conversation between a user and a selected service provider using an audio-transmission medium (the telephone). A service seeker locates a service provider by entering a keypad code corresponding to a field of service or by speaking the name of a profession, which is recognized by the system. The seeker can then specify, via voice or keypad entry, a price range, quality rating, language, and keyword descriptors of the service provider, such as a service provider code number. In response, the system offers currently available service providers. Once an available service provider is selected, the system connects the service seeker with the service provider for a live conversation. The system bills the seeker for the time spent conversing with the service provider and compensates the service provider accordingly.

This invention concerns a method and system for monitoring an automated dialog system for the automatic recognition of language understanding errors based on a user's input communications in a task classification system. The method may include determining whether the user's input communication can be understood in order to make a task classification decision. If the user's input communication cannot be understood and a task classification decision cannot be made, a probability of understanding the user's input communication may be determined. If the probability exceeds a first threshold, further dialog may be conducted with the user. Otherwise, the user may be directed to a human for assistance. In another possible embodiment, the method operates as above except that if the probability exceeds a second threshold, the second threshold being higher than the first, then further dialog may be conducted with the user using the current dialog strategy. However, if the probability falls between a first threshold and a second threshold, the dialog strategy may be adapted in order to improve the chances of conducting a successful dialog with the user. This process may be cumulative. In particular, the first dialog exchange may be stored in a database. Then, a second dialog exchange is conducted with the user. As a result, a second determination is made as to whether the user's input communication can be understood can be conducted based on the stored first exchange and the current second exchanges. This cumulative process may continue using a third and fourth exchange, if necessary.

Embodiments of a dialog system employing a discriminative action selection solution based on a trainable machine action model. The discriminative machine action selection solution includes a training stage that builds the discriminative model-based policy and a decoding stage that uses the discriminative model-based policy to predict the machine action that best matches the dialog state. Data from an existing dialog session is annotated with a dialog state and an action assigned to the dialog state. The labeled data is used to train the discriminative model-based policy. The discriminative model-based policy becomes the policy for the dialog system used to select the machine action for a given dialog state.

Systems and methods for generating prompts for further data from a user in a multi-turn interactive dialog. Embodiments improve searches for the most relevant items available for purchase in an electronic marketplace via a processed sequence of user inputs and machine-generated prompts. Question type prompts, validating statement type prompts, and recommendation type prompts may be selectively generated based on whether a user query has been sufficiently specified, user intent is ambiguous, or a search mission has changed. Detection of a new dominant object denotes search mission change. Contextual associations between prompts and user replies are maintained, but a search mission change results in previous context data being disregarded. Prompts can be directed to unspecified knowledge graph dimensions based on data element association strength values, relative data element positions and depths in the knowledge graph, and generated following a predetermined order of data element knowledge graph dimension types.

The invention provides an intelligent dialogue method and system based on emotion and semantics. The intelligent dialogue method based on the emotion and semantics includes the steps of firstly, obtaining multi-round dialogue information between a user and an intelligent dialogue system; secondly, determining the current emotion and semantics of the user based on the multi-round dialogue information; and thirdly, making a response conforming to the current emotion and semantics of the user according to the current emotion and semantics of the user. Compared with the prior art, the intelligent dialogue method provided by the invention can be used for making a response conforming to the current emotion and semantics of the user according to the current emotion and semantics of the user, make a different response for different emotions and semantics, enhancing the matching degree of the response and the emotion of the user, improving the matching degree of the response and the semantics of the user, and meanwhile improving the user experience.

A dialogue system that provides a driver with driving advice includes driving performance evaluation means for evaluating a driving performance of the driver estimated based on driving performance information using a normative driving performance as a reference; response evaluation means for evaluating a driver's response to the provided driving advice based on a change in the driving performance of the driver after provision of the driving advice; and output control means for adjusting contents of the driving advice provided to the driver based on the result of evaluation of the driving performance of the driver and setting a mode of expressing the driving advice based on the result of evaluation of the driver's response to the provided driving advice.

The invention relates to a man-machine multi-round dialogue method oriented to the travel field, which is used in the information technology field. The invention solves the problem that the current multi-round conversation system has difficulty in extracting the intention information and the slot information of the user question. The invention normalizes the short text question, extracts the intention information of the normalized short text question by using DAN, CNN or BLSTM model, and obtains Micro. F1 value was 93.47%. Using the BLSTM-CRF model to extract the slot information of the normalized short text questions, and the model achieves the ideal effect with F1 value of 89.47%. Taking the historical slot information and the slot information of the current question as inputs, the current conversation state information is determined, and the next reply strategy is determined according to the intention information of the current question. According to the determined reply strategy, the corresponding template is selected to reply to the user. The invention can be applied to the field of information technology.