16 results about "Dialog management" patented technology

A method in a contact center for generating an action classifier model and use thereof in selectively initiating turn set queries of a knowledge base to assist agents in real time during ongoing conversations with customers. The method includes: generating an action classifier model; receiving classification data that classifies a first plurality of the customer actions found in training samples as belonging to a first action category for which a knowledge base search is deemed needed, and a second plurality of the customer actions as belonging to a second action category for which a knowledge base search is deemed not needed; and using the action classifier model and the received classification data to perform a query filtering routine for selectively initiating a turn set query for a present turn set occurring in an ongoing conversation between an agent and customer.

The invention discloses an online interview system and method based on an AI large model and a digital human, and mainly relates to the technical field of online interview. Comprising a user interaction layer, a service layer, a model layer and a data layer. Wherein the user interaction layer comprises a video interview interface module, a digital human display module and a candidate motion capture module; the service layer comprises an interview dialogue management module, a candidate scoring module, a test question management module and a digital person management module; the model layer comprises a resume analysis model, an interview dialogue generation model and a scoring model; the data layer comprises a user data storage module, an interview record storage module, a score data module and an interview question bank; according to the method, the AI large model is combined with the digital human, so that the accuracy of the information obtained by online interview is improved, the interview experience of candidates is improved, the interview efficiency in a large number of interview scenes is improved, and the manpower consumption of recruiters is effectively reduced.

A method in a contact center for generating an action classifier model and use thereof in selectively initiating turn set queries of a knowledge base to assist agents in real time during ongoing conversations with customers. The method includes: generating an action classifier model; receiving classification data that classifies a first plurality of the customer actions found in training samples as belonging to a first action category for which a knowledge base search is deemed needed, and a second plurality of the customer actions as belonging to a second action category for which a knowledge base search is deemed not needed; and using the action classifier model and the received classification data to perform a query filtering routine for selectively initiating a turn set query for a present turn set occurring in an ongoing conversation between an agent and customer.

The dialog management method comprises: performing semantic analysis on current input content of a user to obtain corresponding current user semantic information; obtaining current dialog state information of the user from stored state information of the user according to the current user semantic information; determining a current node in which the current dialog is located from a stored dialog resource architecture by querying, and jumping to a corresponding destination node when a jump condition of the current node is triggered, and obtaining output content of the destination node from the dialog resource architecture; the dialog resource architecture is a multi-level finite state machine structure, comprising a plurality of dialog nodes, and the dialog nodes jump based on a preset jump condition; and generating reply content corresponding to the current input content of the user according to the current dialog state information of the user and the output content of the destination node. The above scheme can effectively control the entire dialog process.

A dialog management system that coordinates system dialog responses based on natural language guidelines which provide non-deterministic ways for the system to properly respond to a dialog input based on the dialog history / context. For each input, an appropriate guideline is selected by a machine learning component based on the dialog history. The guideline is then sent, along with the dialog history, to a downstream machine learning component to determine an appropriate dialog system response.

Methods and systems are disclosed for improving dialog management for task-oriented dialog systems. The disclosed dialog builder leverages machine teaching processing to improve development of dialog managers. In this way, the dialog builder combines the strengths of both rule-based and machine-learned approaches to allow dialog authors to: (1) import a dialog graph developed using popular dialog composers, (2) convert the dialog graph to text-based training dialogs, (3) continuously improve the trained dialogs based on log dialogs, and (4) generate a corrected dialog for retraining the machine learning.

Implementations relate to dialog management of a large language model (LLM) utilized in generating natural language (NL) output during an ongoing dialog. Processor(s) of a system can: receive NL based input as part of the ongoing dialog, generate NL based output utilizing the LLM, and cause the NL based output to be rendered. Further, the processor(s) can receive subsequent NL based input as part of the ongoing dialog. In some implementations, the processor(s) can determine whether to modify a corresponding dialog context in generating subsequent NL based output, and modify the corresponding dialog context accordingly. For example, the processor(s) can restrict the corresponding dialog context, or supplant the corresponding dialog context with a corresponding curated dialog context. In additional or alternative implementations, the processor(s) can modify a corresponding NL based output threshold utilized in generating the subsequent NL based response to ensure the resulting NL based output is desirable.

Systems and methods for automatically and continuously processing communications exchanged among users and automated agents and corresponding user behaviors are provided to dynamically generate topical communications sessions from ongoing communications sessions. The topical communications sessions are implemented to reduce the cognitive effort of conversation management within existing communications sessions where topical drift may occur. The framework allows users to submit multimedia inputs that are classified by the systems and methods and automatically routed to appropriate communications containers.

An object of a system according to an embodiment is to reduce child's repulsion to homework and to effectively manage progress.SOLUTION: A system includes a homework progress confirmation unit, an interaction unit, a progress management unit, and a reminder unit. The homework progress check unit checks the progress of the homework using the generated AI. The interaction unit performs an interaction to reduce the child's repulsion based on the homework progress confirmed by the homework progress confirmation unit. A progress management part manages the progress of homework on the basis of the interaction performed by the interaction part. The reminder unit sends a reminder at an appropriate timing based on the homework progress managed by the progress management unit.SELECTED DRAWING: Figure 1

A dialog management system that coordinates system dialog responses based on natural language guidelines which provide non-deterministic ways for the system to properly respond to a dialog input based on the dialog history / context. For each input, an appropriate guideline is selected by a machine learning component based on the dialog history. The guideline is then sent, along with the dialog history, to a downstream machine learning component to determine an appropriate dialog system response.

Techniques for selecting an application to perform an action based on a user satisfaction with a current exchange are described. A user speaks an utterance and the system generates dialog state data corresponding to various information associated with a current exchange between the user and the system, including input audio data, speech processing results, context data, personal graph data, etc. The system may estimate a user satisfaction value associated with the current exchange and update the dialog state data to include the estimated user satisfaction value. The system processes the updated dialog state to generate candidate actions corresponding to actions to be performed by an application in response to the utterance. The system may process to select a single action from the candidate actions and generate a request for the application to perform the action.

Systems and methods for automatically and continuously processing communications exchanged among users and automated agents and corresponding user behaviors are provided to dynamically generate topical communications sessions from ongoing communications sessions. The topical communications sessions are implemented to reduce the cognitive effort of conversation management within existing communications sessions where topical drift may occur. The framework allows users to submit multimedia inputs that are classified by the systems and methods and automatically routed to appropriate communications containers.

A computer-implemented method dynamically routes and processes user queries in a bot-builder system. The method involves receiving a user query and routing the user query to a Personal Info Retrieval Module, a Document Retrieval Module, and a Tool Manager. The Personal Info Retrieval Module retrieves and updates personal information in real time through API calls. The Document Retrieval Module and Tool Manager retrieve document and tool embeddings from corresponding vector stores. An AI model processes the user query to generate query embeddings, performing similarity searches against the document and tool embeddings. The retrieved information is combined with the user query and chat history to form a comprehensive input, which the AI model processes to determine an appropriate response. The response is generated using existing knowledge or by invoking an external tool. The system includes real-time updates, leveraging historical interaction records and external services and integration of external tools.

A system for processing user utterances and / or text based queries that tracks entities and other context data of a current dialog between the system and the user and can fill slots for new intents of the dialog by performing statistical processing on previously mentioned entities with respect to current slots to be filled. The system may compare a previously mentioned entity to a current slot to be filled using vector representations, such as word embeddings, of the current utterance, dialog history, current intent, name of an entity under consideration, category of the current slot to be filled, distance between the current dialog turn and the dialog turn that mentioned the entity, and other considerations. The individual vectors may be weighted according to an attention operation and processed by a trained decoder to output a score indicating whether the entity in consideration is relevant to the particular slot. In this manner, slots may be filled using entities from previous dialog turns, thus performing statistical anaphora resolution and leading to improved system performance.

Systems and methods provide real-time, non-turn-based, dialog management. An example method includes receiving an initial or next block in a stream of blocks; generating a first candidate response based on receiving the block; updating a ranked list of candidate responses with at least one of the first candidate responses, the candidate responses accepted or pending at the time of receiving the block, the updated ranked list of candidate responses including one or more backend requests and one or more system responses; performing backend requests to two or more dialog modes based on the updated ranked list; and after performing the backend requests: generating backend responses based on information obtained for the two or more dialog modes in response to the backend requests; deriving a composite candidate response from the two or more dialog modes based on the generated backend responses; further updating the updated ranked list based on the composite candidate response; and pruning the further updated ranked list based on an updated ranking of candidate responses of the further updated ranked list.