48 results about "Spoken dialog systems" patented technology

A spoken dialog system stores a history of dialog states in a memory, outputs a system response in a current dialog state, inputs a user utterance, performs speech recognition of the user utterance, to obtain one or a plurality of recognition candidates of the user utterance and likelihoods thereof with respect to the user utterance, calculates a degree of state conformance of each of the current and the preceding dialog states stored in the memory with respect to the user utterance, selects one of the current and the preceding dialog states and one of the recognition candidates based on a combination of the degree of state conformance of each dialog state and the likelihood of each recognition candidate, and performs transition from the current dialog state to a new dialog state based on dialog state selected and recognition candidate selected.

The invention discloses a medical interrogation dialogue system and a reinforcement learning method applied to the medical interrogation dialogue system, and relates to the technical field of medicalinformation. The system comprises a natural language understanding module used for classifying the intentions of users and filling slot values to form structured semantic frames; a dialogue managementmodule used for interacting with a user through a robot agent, inputting a dialogue state, performing action decision on the semantic frame through a decision network, and outputting final system action selection; a user simulator used for carrying out natural language interaction with the dialogue management module and outputting user action selection; a natural language generation module used for receiving system action selection and user action selection, enabling the user to check the selection through generating sentences similar to a human language by using a template-based method. According to the invention, the medical knowledge information between diseases and symptoms is introduced as a guide, and the inquiry historical experience is enriched through continuous interaction witha simulated patient. The reasonability of inquiry symptoms and the accuracy of disease diagnosis are improved, and the diagnosis result is higher in credibility.

The invention discloses a training method, a training device, a dialogue method and a dialogue system of a dialogue model. The training method comprises the steps of total error constructing, whereina total error function comprising a first error of a natural language understanding model and a second error of a strategy generating model are constructed simultaneously; joint training, wherein withthe target of reducing the total error function, a corpus sample is utilized to jointly train the natural language understanding model and the strategy generating model, input of the natural languageunderstanding model is dialogue sentences, output of the natural language understanding model is internal representation obtained by analyzing the dialogue sentences, input of the strategy generatingmodel at least comprises the output of the natural language understanding model, and output of the strategy generating model is motions aiming at the dialogue sentence. Compared with the prior art, when an error occurs on the natural language understanding model or the strategy generating model, the system can normally conduct dialogues, and the error transferring problem in a traditional methodcaused when the natural language understanding model and a dialogue management model are modeled respectively is solved.

An action is performed in a spoken dialog system in response to a user's spoken utterance. A policy which maps belief states of user intent to actions is retrieved or created. A belief state is determined based on the spoken utterance, and an action is selected based on the determined belief state and the policy. The action is performed, and in one embodiment, involves requesting clarification of the spoken utterance from the user. Creating a policy may involve simulating user inputs and spoken dialog system interactions, and modifying policy parameters iteratively until a policy threshold is satisfied. In one embodiment, a belief state is determined by converting the spoken utterance into text, assigning the text to one or more dialog slots associated with nodes in a probabilistic ontology tree (POT), and determining a joint probability based on probability distribution tables in the POT and on the dialog slot assignments.

The present invention relates to a method and apparatus for adding new vocabulary to interactive translation and dialogue systems. In one embodiment, a method for adding a new word to a vocabulary of an interactive dialogue includes receiving an input signal that includes at least one word not currently in the vocabulary, inserting the word into a dynamic component of a search graph associated with the vocabulary, and compiling the dynamic component independently of a permanent component of the search graph to produce a new sub-grammar, where the permanent component comprises a plurality of words that are permanently part of the search graph.

A method and system to parameterize a spoken language dialog system, includes providing a storage area to store at least one parameter value, integrating a subcomponent with at least one module of the spoken language dialog system, and configuring the subcomponent to access the at least one parameter value and to adjust an operation or output of the module based on the at least one parameter value.

The invention discloses a dialogue auxiliary system for team learning and hierarchical reasoning. The method is characterized in that firstly a generic industry knowledge map which comprises the universal entities and attribute entries outside the industry is crawled and generated, thereby conveniently meeting the requirement of a user for universal knowledge query, and facilitating the realization of the rapid migration of knowledge bases among the industries; secondly, a multi-level reasoning network provided by the invention can realize the complex semantic reasoning capability, can realizethe man-machine conversation based on a reasoning process, and can carry out the accurate service recommendation and product marketing through the reasoning network at the same time; and finally, thestrategy learning network based on reinforcement learning can learn the sorting strategy by utilizing the accumulated historical interaction experience, so that the user experience is continuously improved. The functional extension and effect upgrading of an original dialogue system can be realized by deploying the system, and the user experience is improved.

A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received. After all the training data is received, at least once, the method comprises building a third NLU model using all the labeling data, wherein the third NLU model is used in generating the spoken dialog service.

A spoken dialog system comprises a speech recognition unit for recognizing a user's input speech to generate a character sequence corresponding thereto; a sentence contents database for storing therein a plurality of sentence contents; a knowledge search unit for searching through the sentence contents to find a match for the character sequence, in the sentence contents database; a dialog model unit for delivering the character sequence to the knowledge search unit to receive the sentence contents therefrom, and setting a dialog model by using the sentence contents; a system response unit for generating an output sentence which harmonizes with the user's input speech or expresses a situation of the system; and a speech synthesis unit for converting the output sentence into the output speech.

The invention discloses a method and a system for information processing for a question and answer robot. The method comprises the following steps of obtaining multi-mode interaction information; calling user entity information from a memory system, wherein the user entity information is used for representing the habits, attributes, identity and behaviors of a user; according to the multi-mode interaction information and the user entity information, determining a result corresponding to a current question and answer process. The method has the advantages that on the basis of the multi-mode interaction, the user entity information is deeply mined, so that a user information support is provided for the whole multi-mode interaction process; compared with a traditional dialogue system which can only complete simple dialogues with the user, intents of the user can be more accurately guessed, an intimate answer is provided according to the actual conditions of the user, and the user experience is greatly improved.

The invention relates to an intention and slot joint recognition method based on multi-task learning. Input texts of a user, such as utterance / query are processed to output intention labels and slot labels. The method comprises the following steps of sequentially processing the text sequence input by the user through a long-term and short-term memory network and a convolutional neural network toform an LSTM-CNN shared representation feature; according to the difference between the intention label information and the slot position label information, respectively establishing a Bi-LSTM intention recognition model / slot position recognition model with an attention mechanism based on the shared representation features; and constructing a total loss function of the intention recognition modeland the slot position recognition model by using a weighted calculation method based on a gradient descent method, and performing joint optimization solution on the total loss function. The multi-tasklearning thought is applied to the construction process of the vertical dialogue system, joint recognition of the input text intention and the slot position can be achieved, and the recognition accuracy and F value of the input text intention and the slot position of the vertical dialogue system are effectively improved.

A spoken dialog system and method having a dialog management module are disclosed. The dialog management module includes a plurality of dialog motivators for handling various operations during a spoken dialog. The dialog motivators comprise an error-handling, disambiguation, assumption, confirmation, missing information, and continuation. The spoken dialog system uses the assumption dialog motivator in either a-priori or a-posteriori modes. A-priori assumption is based on predefined requirements for the call flow and a-posteriori assumption can work with the confirmation dialog motivator to assume the content of received user input and confirm received user input.

The present invention relates to a spoken dialog system and method based on dual dialog management using a hierarchical dialog task library that may increase reutilization of dialog knowledge by constructing and packaging the dialog knowledge based on a task unit having a hierarchical structure, and may construct and process the dialog knowledge using a dialog plan scheme about relationship therebetween by classifying the dialog knowledge based on a task unit to make design of a dialog service convenient, which is different from an existing spoken dialog system in which it is difficult to reuse dialog knowledge since a large amount of construction costs and time is required.

The invention discloses a method and a device for parsing a semantic meaning, an apparatus and a storage medium. The method comprises the following steps of obtaining to-be-parsed data in a current dialogue turn and a historical semantic meaning in a historical dialogue turn associated with the current dialogue turn; by using the historical semantic meaning and the to-be-parsed data as a whole, inputting into at least two semantic meaning analyzers respectively, and obtaining the semantic meaning parsed by each semantic meaning analyzer; integrating the obtained semantic meanings parsed out bythe semantic meaning analyzers, and using an integration result as the semantic meaning corresponding to the to-be-parsed data. According to the method provided by the embodiment of the invention, anexisting method for parsing the semantic meaning in a dialogue system is optimized; the diversity of the parsed out semantic meaning is increased; the interaction flexibility of a dialogue is improved, and the experience of a user is improved.

In order to solve a conventional problem that, after a series of dialog between a user and a spoken dialog device has progressed to some extent, that user or another user cannot see or recognize a previous dialog status, a cross-lingual spoken dialog system is provided wherein, in a case in which an instruction from a user terminal is received by a pairing server, dialog information stored in a storage medium is transmitted to the user terminal. Accordingly, even after a series of dialog between a user and the spoken dialog device has progressed to some extent, that user or another user can see or recognize a previous dialog status.

The present invention relates to queue-theoretic models for integration of automated call routing systems with human operators. Organizations are increasingly turning to spoken dialog systems for automated call routing to reduce call center costs. To maintain quality service even in cases of failure, these systems often resort to ad-hoc rules for dispatching calls to a human operator. The present invention provides queue-theoretic methods that provide a modeling and simulation capability in support of decisions about the staffing of call-handling centers based on the frequency of incoming calls and the competency of automated dialog systems. The methods include a procedure for identifying when callers should be transferred to operators. The procedure integrates models that predict when a call is likely to fail using spoken dialog features with queuing models of call center volume and service time.

A method (and system) of determining confusable list items and resolving this confusion in a spoken dialog system includes receiving user input, processing the user input and determining if a list of items needs to be played back to the user, retrieving the list to be played back to the user, identifying acoustic confusions between items on the list, changing the items on the list as necessary to remove the acoustic confusions, and playing unambiguous list items back to the user.

Example embodiments of the present invention may include a method that includes collecting caller response timings to each of a plurality of dialog states conducted during a call, and estimating a plurality of parameters based on the caller response timings. The method may also include selecting a response completeness value responsive to the estimated plurality of parameters, the response completeness value is used to calculate at least one optimal timeout value. The method may also include selecting the at least one optimal timeout value, and setting the at least one optimal timeout value for each of the corresponding dialog states. The timeout value(s) may be used for subsequent calls to provide optimal user satisfaction and call success rates.

A method (and system) of determining confusable list items and resolving this confusion in a spoken dialog system includes receiving user input, processing the user input and determining if a list of items needs to be played back to the user, retrieving the list to be played back to the user, identifying acoustic confusions between items on the list, changing the items on the list as necessary to remove the acoustic confusions, and playing unambiguous list items back to the user.

A spoken language understanding and rewriting method based on a commercial dialogue system comprises the following steps: identifying and acquiring domain information related to an utterance accordingto the utterance input by a user; according to the field related to the utterance, identifying and acquiring intention information contained in the utterance; detecting slot position information contained in the user utterance according to the intention information, and storing the detected slot position information; rewritting the utterance input by the user according to the domain information,the intention information and the stored slot position information, and complementing the utterance information; selecting the sub-dialogue system to provide service according to the domain information and intention information of the utterance input by the user. According to the method, the problem of semantic transmission blockage easily appearing in a commercial dialogue system can be solved. Through the application of the method, when the sub-dialogue system is switched due to the change of the user demand, the sub-dialogue system can know the user demand according to the rewritten user utterance and is not perceived by the user, so that the use experience of the user can be ensured to the maximum extent.

The invention discloses a game customer-service dialoguing system based on a deep neural network. The game customer-service dialoguing system based on the deep neural network comprises a dialoguing control module, a user querying module, a problem model module, an answer model module and a knowledge base querying module, wherein the dialoguing control module receives query languages from users andjudges to conduct knowledge base querying or switch a manual service; the problem model module encodes problems queried by the users through a Seq2Seq mechanism of the deep neural network, obtains formalized languages capable of being used for querying the knowledge base, and inputs the formalized languages to the knowledge base querying module; the knowledge base querying module receives the input result from the problem model module, queries a knowledge base, and outputs the query result to the answer model module; the answer model module encodes the query result of the knowledge base through the Seq2Seq mechanism of the deep neural network, and outputs natural languages capable of being understood by the users to a user interactive interface. By means of the game customer-service dialoguing system based on the deep neural network, game users can rapidly obtain feedback in the game playing process.

A dialog manager for a spoken dialog system. A decision module selects a path from a plurality of alternative paths for a given call, wherein each path implements one of a plurality of strategies for a call flow. A weighting module weights the path selection decision and is connected to a probability estimator for estimating the probability value that a given one of the plurality of paths is the best-performing path.

The invention discloses a method for extending spoken language dialogue system corpora. The method includes the steps that secondary semantic analysis is conducted on a sentence which cannot be analyzed to obtain a candidate analysis result; if a user selects a candidate from the candidate analysis result, a mapping rule is formed between the sentence and the candidate selected by the user, the generated rule is added into a user exclusive preprocessing rule library, and the candidate sentence selected by the user and corresponding semantic information are stored in an exclusive auxiliary corpus corresponding to the user; when the user sentence is analyzed, semantic analysis is conducted by means of the user exclusive preprocessing rule library and a rule-assisted main corpus generated on the basis of the auxiliary corpus. The invention further discloses a corresponding system. By means of the method and system, robustness of the corpora can be improved, the cost for maintaining the corpora is reduced, a spoken language system correction function is provided, and the usability of the spoken language system is enhanced.

A spoken dialog system and method having a dialog management module are disclosed. The dialog management module includes a plurality of dialog motivators for handling various operations during a spoken dialog. The dialog motivators comprise an error handling, disambiguation, assumption, confirmation, missing information, and continuation. The spoken dialog system uses the assumption dialog motivator in either a-priori or a-posteriori modes. A-priori assumption is based on predefined requirements for the call flow and a-posteriori assumption can work with the confirmation dialog motivator to assume the content of received user input and confirm received user input.

A method for multiple value confirmation and correction in spoken dialog systems. A user is allowed to correct errors in values captured by the spoken dialog system, such that the interaction necessary for error correction between the system and the user is reduced. When the spoken dialog system collects a set of values from a user, the system provides a spoken confirmation of the set of values to the user. The spoken confirmation comprises the set of values and possibly pause associated with each value. Upon hearing an incorrect value, the user may react and barge-in the spoken confirmation and provide a corrected value. Responsive to detecting the user interruption during the pause or after the system speaking of a value, the system halts the spoken confirmation and collects the corrected value. The system then provides a new spoken confirmation to the user, wherein the new spoken confirmation includes the corrected value.

A computer-implemented method, computer program product, and system are provided for providing a recommendation. The method includes receiving, by a conversation system, a query from a user. The method also includes inputting the query into an intent-entity model to obtain a first output. The method further includes inputting the query into a question-answering system to obtain a second output. The method additionally includes analyzing the first output from the intent-entity model to calculate a value of degree of ambiguity of the first output to the query. The method also includes analyzing the query and the second output from the question-answering system to calculate a value of extent of satisfaction to which the second output satisfies the query. The method further includes determining one or more recommendations using the degree of ambiguity and the extent of satisfaction. The method additionally includes outputting the one or more recommendations to the user.

A system and method are disclosed that improve automatic speech recognition in a spoken dialog system. The method comprises partitioning speech recognizer output into self-contained clauses, identifying a dialog act in each of the self-contained clauses, qualifying dialog acts by identifying a current domain object and / or a current domain action, and determining whether further qualification is possible for the current domain object and / or current domain action. If further qualification is possible, then the method comprises identifying another domain action and / or another domain object associated with the current domain object and / or current domain action, reassigning the another domain action and / or another domain object as the current domain action and / or current domain object and then recursively qualifying the new current domain action and / or current object. This process continues until nothing is left to qualify.

The invention presents a method for analyzing speech in a spoken dialog system, comprising the steps of: accepting an utterance by at least one means for accepting acoustical signals, in particular a microphone, analyzing the utterance and obtaining prosodic cues from the utterance using at least one processing engine, wherein the utterance is evaluated based on the prosodic cues to determine a prominence of parts of the utterance, and wherein the utterance is analyzed to detect at least one marker feature, e.g. a negative statement, indicative of the utterance containing at least one part to replace at least one part in a previous utterance, the part to be replaced in the previous utterance being determined based on the prominence determined for the parts of the previous utterance and the replacement parts being determined based on the prominence of the parts in the utterance, and wherein the previous utterance is evaluated with the replacement part(s).