45 results about "Natural language interaction" patented technology

A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application. Optimizations to the candidate natural language interaction application are carried out and an optimized natural language interaction application is deployed into production and stored in the solution data repository.

The invention discloses a method and a neural network system used for a man-machine conversation, and user equipment. The method used for the man-machine conversation comprises the following steps that: carrying out vectorization on a natural language problem and a knowledge base; through vector computation, obtaining an intermediate result vector which is based on the knowledge base and expresses similarity between the natural language problem and a knowledge base answer through vector computation; and according to a problem vector and the intermediate result vector, carrying out computation to obtain a correct natural language answer based on facts. By use of the method provided by the invention, the conversation and the questions and answers based on the knowledge base are combined, natural language interaction can be carried out with users, and on the basis of the knowledge base, the natural language answer based on the facts can be given.

Aspects of the invention generally relate to systems and methods for deriving structured data from natural language interactions and using it to measure and optimize the content and effectiveness of subsequent natural language interactions and other marketing activities.

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 present invention described secures a computer account against unauthorized access caused as a result of identity-theft, and insider-espionage using artificial intelligence and behavioral modeling methods. The present invention has the ability to detect intruders or impersonators by observing “suspicious” activity under a computer account. When it sees such suspicious behavior, it uses artificial intelligence to authenticate the suspect by interrogation. The present invention asks the suspect questions that only the legitimate computer account owner can verify correctly. If the suspect fails the interrogation, that proves that he / she is an impersonator and therefore further access to the computer account is denied immediately. On the other hand if the suspect passes, access to the computer account is restored. The present invention uses a Programmable Artificial Intelligence Engine (PAIE) to interact with computer users in human natural language. The PAIE can also be programmed to suit other applications where natural language interaction with humans is helpful.

The invention discloses a method, computer system and computer program of interacting with a user of a messaging client. In the method a transactive engine engages via an agent, a natural language interaction with a user of a messaging client in order to initiate a transaction and determines, based on an adaptive script of the agent, the semantics of natural language input from the user. The existing form of the script is adapted to take into account historical interaction between the agent and the user and historical interaction between other users and the agent. The transactive engine constructs at least one command necessary to execute the transaction and transmitting the at least one command to at least one information system in order to execute the transaction. Furthermore, the transactive engine receives information about the executed transaction from the at least one information system, processes the received information relating to the executed transaction to form a natural language response to the user of the messaging client, and sends the natural language response to the messaging client.

The invention belongs to the technical field of human-computer interaction, and provides a human-computer interaction method and system based on multi-modal emotion and face attribute identification.The method includes the steps: acquiring a face image and sound information of a user; transforming the sound information into text information; distinguishing emotions according to the face image, the sound information and the text information; determining emotion vectors; determining face attribute characteristics according to the face image; analyzing the emotion vectors, the face attribute characteristics and the text information according to replying strategies, and outputting feedback texts. According to the human-computer interaction method and system based on multi-modal emotion and face attribute identification, face attributes can be completely identified, multi-modal face emotion identification accuracy is improved, the multi-modal emotions, the face attributes and natural language interaction information are combined, and more natural and intelligent human-computer interaction experience is provided.

An embodiment of the invention discloses a training method of a reply message generating model and a reply message generating method. The training method includes: acquiring first input sequence; using a first decoding hidden state vector as the initial value of the hidden layer of a first encoder, and using the first encoder to encode the first input sequence to obtain a second encoding hidden state vector; using a decoder to decode the second encoding hidden state vector to obtain first output sequence; calculating the error between standard output sequence and the first output sequence; ifthe error is higher than a preset termination threshold, updating the parameters of the first encoder and the decoder according to the error. When the reply message generating model obtained by the training method is used to generate reply messages, the dialogue information of a previous round or several previous rounds can be introduced into the generation process of the reply messages of the next-round dialogue, and accordingly accurate reply messages can be generated, and the generated reply messages conform to the natural language interaction habits of users.

The invention discloses a method, computer system and computer program of interacting with a user of a messaging client. In the method a transactive engine engages via an agent, a natural language interaction with a user of a messaging client in order to initiate a transaction and determines, based on an adaptive script of the agent, the semantics of natural language input from the user. The existing form of the script is adapted to take into account historical interaction between the agent and the user and historical interaction between other users and the agent. The transactive engine constructs at least one command necessary to execute the transaction and transmitting the at least one command to at least one information system in order to execute the transaction. Furthermore, the transactive engine receives information about the executed transaction from the at least one information system, processes the received information relating to the executed transaction to form a natural language response to the user of the messaging client, and sends the natural language response to the messaging client.

The invention relates to a system for calling vast intelligence applications through natural language interaction. The system comprises a voice input module, a voice recognition module, a semantic extracting module, a third-party application service interface and a third-party application service module. According to the system, normative signal language is used for performing guide so as to improve the accuracy of a question; the semantics obtained after the voice recognition can be processed through customized keywords, keyword combinations and threshold management, thus achieving accurate calling of the voice on different application services; the third-party application interface can be used for performing centralized management on the vast application services, so that the problem that a plurality of application services are needed to be independently downloaded and different applications are frequently switched during use can be solved, and as a result, the application service efficiency can be improved, and the user experience can be increased.

A method and associated systems for automating natural-language interactions between an expert system and a user. Characteristics of and relationships among elements of a set of business processes are captured, organized into a data structure, and stored as a set of business process models. The format, contents, and organization of these models are chosen to facilitate translating characteristics of the business processes into a format that may be stored in a knowledgebase of an expert system. The structured business-process models are then translated into a component of a knowledgebase from which an expert system may infer rules that guide its natural-language user interactions that relate to the business processes. In some embodiments, a similar method may be used to automatically translate business-process metadata, such as concept classes and process classes, into a similar knowledgebase-compatible format.

The invention discloses a robot control method, device and system based on a cloud platform, and relates to the field of communication and information. The method comprises the steps that the solid robot cloud control platform receives a man-machine interaction event, related to voice, transmitted by a solid robot; according to the man-machine interaction event related to voice, the solid robot cloud control platform obtains a corresponding service process used for controlling the robot to interact with a user; the solid robot cloud control platform executes the service process, so that an execution result is obtained; and the solid robot cloud control platform sends the execution result to the solid robot, so that the solid robot performs corresponding operations. According to the embodiment, the cloud platform and the ASR technology are utilized to realize natural language interaction between the solid robot and the user, and the problems that in the existing solid robot voice interaction technology, the requirement of an ASR engine for the hardware capability of the solid robot is high, the semantic recognition management difficulty is large and the service lacks flexibility aresolved.

Techniques are disclosed to provide guided natural language interactions with a connected data system, such as a graph database. In various embodiments, natural language input associated with a graph database query associated with a graph data set is received. The natural language input is processed to generate a set of candidate strings. At least a subset of the candidate strings is mapped to an entity in the graph data set. The entity and data comprising the graph data are used set to determine a candidate graph pattern associated with the graph database query. The candidate graph pattern is used to guide a user associated with the natural language input to refine the graph database query.

The invention provides a watch robot intelligent autonomous operation system. The watch robot intelligent autonomous operation system comprises a microprocessor, a wireless communication module, a GPS positioning device, an electronic guardrail, a Wetalker, a dialogue learning engine, an emotional instant feedback engine and a battery; the wireless communication module and the GPS positioning device are electrically connected with the microprocessor; the microprocessor is loaded with the electronic guardrail, the Wetalker, the dialogue learning engine and the emotional instant feedback engine; and the battery supplies electricity for the microprocessor, the wireless communication module and the GPS positioning device. The watch robot intelligent autonomous operation system is a child intelligent wearable intelligent product, contact between patients and children is facilitated, voice relative and friend outbound, triple zero-second positioning, emergent people searching, habit developing, course managing, natural language interaction and knowledge interactive questioning and answering are achieved, and the learning content of the dialogue learning engine comprises 100000 ancient poetry, all available knowledge covered by geographical astronomy, 10000000 music, 100000 idiom stories, 500 idiom videos, 1000000 nursery rhyme fairy tales, synonyms, antonyms, Chinese and English.