168 results about "Dialogue management" patented technology

The invention provides a dialogue management method, terminal, and system, relates to the technical field of communication, and aims to solve the problem that in the prior art, when a dialogue in an inactivated state, a UPF entity cannot be relocated. The method comprises following steps: establishing first protocol data unit (PDU) dialogue in user equipment (UE); sending service request information to an Action Message Format (AMF) entity; receiving first information sent by the AMF entity by UE; and based on first information, reestablishing or modifying the first PDU dialogue. UE sends service request information to the AMF entity, then the AMF entity sends first information to UE so as to rebuild or modify the first PDU dialogue, and before data for rebuilding first PDU dialogue is transmitted or received, the subsequent transmitted data or received data is not lost.

The invention discloses a man-machine conversation system applied to an advanced service robot. The man-machine conversation system is characterized in that a voice recognition module, a natural language understanding module, a background service processing module, a natural language generating module and a voice generating module are included and are respectively and independently connected with a conversation management module and used for bidirectional data transmission. The man-machine conversation system has the advantages that the advanced service robot can directly communicate with the human language, the influence caused by a traditional communication way on communication efficiency is avoided, the convenience of man-machine communication is greatly improved, and the aim that the service robot directly listens to human voice instructions is achieved.

The invention discloses an intelligent question answering method based on task-driven multi-round dialogue. The specific method comprises preparing data according to different tasks; obtaining intention classification model and element extraction model through training; promoting each round of dialogue through multi-round dialogue management mechanism and decision-making mechanism to complete theintelligent question answering method; wherein the intention classification model and element extraction model are used to analyze the intention and key elements of the user's questions or answers. The multi-round dialogue management mechanism and the decision-making mechanism are used for effectively assisting a user to complete multi-round dialogues around a task by continuously making decisionson the next optimal action to be taken according to the current state. Compared with the prior art, the intelligent question answering method based on task-driven multi-round dialogue realizes automatic initiation, guidance and multi-round dialogue within a limited range, improves the success probability of human-computer interaction, and can meet the requirements of people for obtaining information quickly and accurately.

The invention provides a method, system and computer program product for creating a form definition data file using a visual programming development environment on a computer system. The data file is for interpretation by a dialogue management system and is XML-based markup. A graphical program representation of the data file is created in the development environment and is then compiled and executed in order to generate the data file. The program itself is built by linking a main Java bean component and a plurality of Java bean sub-components, all containing characteristic data file information. On running the executable, the main Java bean outputs its respective data file information into the data file and does this by creating a file output stream and writing its respective data file information to that output stream. This action also causes the next and subsequent java bean components to output their respective data file information into the data file.

The present invention discloses a portable digital mobile communication apparatus with voice operation system and controlling method of voice operation. The feature vector sequences of speech are quantify encoded when the speech is recognized, and in decoding operation, each code in efficiency speech character codes are directly looked up observation probability of on search path from the probability schedule in the decode operation. In association with the present invention, full syllabic speech recognition can be achieved in mobile telephone without the need of training, and input Chinese characters by speech and speech prompting with full syllable. This system comprises semantic analysis, dialogue management and language generation module, and it can also process complicated dialog procedure and feed flexible prompting message back to the user. The present invention can also customize speech command and prompting content by user.

The invention discloses a multi-turn dialog management method for hierarchical attention LSTM and knowledge graph, and belongs to the field of natural language processing. The method has the core idea: taking conversation contents of the user and the system in the conversation as a context, extracting the context deep semantic through important and timing information of the word and sentence level, specifically in two steps, firstly extracting sentence semantics at the word level by utilizing the first attention mechanism LSTM, and then extracting context semantics through the second attentionmechanism LSTM at the sentence level; the attention mechanism keeps important information, and the attention mechanism is realized through the knowledge graph as external knowledge, the LSTM retainstiming information that collectively identifies the user intent and the recognition result is used to determine whether to open the next session. According to the multi-turn dialog management method for hierarchical attention LSTM and knowledge graph, the knowledge graph and the LSTM are utilized to learn the contextual deep semantics, the attention mechanism is utilized to filter out useless information, and therefore the user intention identification efficiency and accuracy are improved.

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.

The invention particularly relates to a method for realizing the dialogue management in intelligent dialogue. The method for realizing the dialogue management in intelligent dialogue realizes intention jump in the process of dialogue by creating intention flow and intention structure of dialogue management, optimizing slot extraction flow, adding intention jump mechanism, fusing the information inthe dialogue below, integrating slot extraction and historical information, multi-round dialogue tasks, and reducing system response time. The method realizes the session management in intelligent session, can not only quickly and accurately identify the intention of the user input corpus and extract the slot value, but also make two or more inquiries about the intention of vague or lack of slot,and in the interactive process, support the jump of the user's intention, the system can respond to the questions of different topics of the user.

Provided is a man-machine dialogue anomaly detection system and method. The method includes steps: acquiring and marking historical dialogue data, training an anomaly detection model by employing the marked data, conducting anomaly detection by employing the trained anomaly detection model when receiving real-time dialogue data, and obtaining a result. The system comprises an automatic speech recognition module (ASR module), a text-to-speech module (TTS module), a spoken language understanding module (SLU module), a dialogue state tracking module (DST module), a dialogue management module (DM module), a database query module (DATA module), a natural language generation module (NLG module), and an anomaly detection and processing module. According to the system and method, replies given by a machine can be reliable, and the system and method can be applied to any scene.

The invention discloses a man-machine cooperation telephone customer service system. The system comprises a voice robot, a manual service agent group, an incoming call answering device, a telephone call-out device and a record storage device. The voice robot is used for dialogue interaction processing of basic service content with a client and comprises an intention recognition unit, a voice recognition unit, a voice synthesis unit and a dialogue management unit. The incoming call answering device is used for getting through an incoming call of a client and forwarding the incoming call to thevoice robot or the manual service agent group. The telephone call-out device creates a call-out task, different call-out units are selected for dialing operation according to different types of call-out tasks, and the call-out units comprise a predictive call-out unit and a preview call-out unit. In addition, the invention also discloses a man-machine cooperation telephone customer service method.By the adoption of the telephone customer service method and system, the customer experience is improved while the call loss rate is reduced, the advantage of cooperation of the voice robot and the manual service agents can be brought into play, and the operation efficiency of a call center is greatly improved.

The aim of this invention is to propose a method for allowing the use of several virtual machines including a plurality of applications and to federate these applications in order to form services. The method includes managing applications, making use of at least two physical machines linked by communication means. These machines comprise a physical structure on which a first software layer adapted to the physical machines is loaded. The machines also include a second layer forming a virtual layer on which virtual machines will operate. The second layer includes at least one application. The method includes loading a virtual machine control program associated with the virtual layer, connecting at least two physical machines to form a physical machine network, wherein the physical machine network includes the virtual layer, establishing a dialogue between the virtual machine control program and a system management process, defining a service containing several applications wherein the service is defined by the system management process, communicating between the management process and each of the virtual layer in order to determine the status of the virtual machines associated with the corresponding virtual layer and assigning a virtual machine to the corresponding virtual layer taking into account the characteristics of the application.

The invention provides a conversation processing method and a conversation management system. The method comprises the following steps: obtaining user demand data related with a task; updating a user conversation state according to the user demand data and preconfigured task parameters related with the task; generating one or more candidate action data according to the conversation state; generating response text data according to the one or more candidate action data.

Systems and method for conversation management and opinion tracking systems, whereby a conversation management engine can generate on-line conversations based on rules sets such that the generated conversation and the content submitted by participants conforms to a conversation or debate style. The conversation management engine can further implement curation policies that can curate content presented to a conversation such that the presented conversation fits curation rules of the policies. An opinion tracking engine can identify opinions regarding conversation topics based on the submitted contents and detect differences or changes in opinion.

The invention discloses a voice communication management system, comprising a communication management device, a state machine model and a state machine; the communication management device is used for storing and maintaining all current effective communication processes, receiving semantic information of a user and providing a corresponding response through the state machine; the state machine model is used for storing all information of a communication field structure, is a static description file of a communication field, and can perform state maintenance and generate a system response according to the field rule described by the state machine model in the operation process; the state machine is used for tracking the state information of the communication progress during the operation, updating the communication state when the user generates an input operation, and dynamically generating a corresponding response according to the current communication state; the particular field information that the state machine relates to is appointed by the state machine model. The voice communication management system can perform customization on a specific communication flow through embedding the JavaScript codes and can realize more flexible communication management.

The invention provides a scenarized semantic comprehension and dialogue generation method and a scenarized semantic comprehension and dialogue generation system. The method comprises the steps of: establishing a user scene model, selecting and determining the field of a current conversation according to a result of a word segmentation system; understanding an interactive content of the round based on a corresponding scenarized user model by use of a selected scene semantic parser; and calling a dialogue generator in a corresponding scene, carrying out a dialogue synthesis and generating a dialogue result after interaction of the round in combination with an intermediate state of dialogue management. According to the scenarized semantic comprehension and dialogue generation method and the scenarized semantic comprehension and dialogue generation system, natural language understanding for a sentence and a phrase is simply and efficiently realized, and the situation that a computer automatically and completely understands a short text is realized. Automatic deep understanding and dialogue interaction of the computer for the sentence or the phrase of a natural language are realized and the purpose that a user needs a machine to understand the interaction language use automatically and accurately is achieved.

The invention discloses a hospital guide method of an intelligent hospital guide service robot. The method comprises the following specific steps: acquiring information inquired by a user through a voice recognition technology; enabling the obtained information to enter a system dialogue management module; using a multimode matching algorithm and a related natural language processing technology inthe system to be combined with an existing medical knowledge base and a knowledge graph association relationship to recognize the intention of the patient or give a consultation result so as to achieve the purpose of human-computer interaction; when a patient interacts with the system, carrying out voice inquiry, collecting a voice input signal for voice recognition; converting the voice input signal into a text and extracting symptom information; comparing the symptom information with a symptom index table; sorting possible diseases according to relevancy, obtaining diagnosis results, recommending registered departments to patients according to the disease diagnosis results and the department recommendation table, wherein more related information of the diseases can be checked. Self-service hospital guide is basically achieved, the service quality of hospitals is improved, and the burden of medical staff is greatly relieved.

The invention provides a system and a method for human and machine voice interaction based on Java Map. The system comprises a voice identifying module, a spoken language comprehending module, a dialogue management module, a language generating module and a voice synthesizing module, wherein the voice identifying module is used for receiving voice information inputted by a user, and identifying the voice information into text data, the spoken language comprehending module is used for performing semantic mining on the text data, and converting the text data into a type which can be identified by a machine, the semantic mining is used for integrating contextual information inputted by the user according to a storage and utilization strategy of context key semantic elements of the Java Map, and extracting semantic key elements of the identified text, the dialogue management module is used for controlling the dialogue process of the human and machine interaction, the language generating module is used for integrating fragmentary answers to obtain a fluent text which meets the logic language expression type of people, and the voice synthesizing module is used for converting the generated answer text into voice information, and broadcasting the voice information to the user.

Speech of a user is recognized in a speech recognizing unit. Based on a result of the speech recognition, a language processing unit, a dialog managing unit and a response generating unit cooperatively created a dialog sentence for exchanging a dialog with the user. Also, based on the speech recognition result, the dialog managing unit collects user information regarding, e.g., interests and tastes of the user. Therefore, the user information regarding, the interests and tastes of the user can be easily collected.