5713results about "Special service for subscribers" patented technology

Systems and methods for recording and transcribing conversations in real-time. Sentiment analysis is performed on each utterance to determine both an intent of the conversation along with sentiment. Annotated transcripts are provided. A machine learning model may be used to augment sentiment analysis.

The present disclosure generally relates to systems, software, and computer-implemented methods for using generative artificial intelligence to improve user interactions. One example method includes identifying, in a contact center application of an agent, a start of an assisted leg of an interaction of a user with a system. A user interaction summary is retrieved that summarizes events that have previously occurred in the interaction. A generative large language model (LLM) artificial intelligence (AI) context prompt is extracted based on the user interaction summary. The context prompt is provided to a generative LLM AI engine to set a context for the generative LLM AI engine. Event information is received that includes a query for the generative LLM AI engine. The query is provided to and a query response is received from the generative LLM AI engine. The contact center application is updated in response to the query response.

An example operation may include one or more of displaying a report on a user interface of a software application on a user device, listening to a call between a user on the user device and a different user on a second user device that is connected to the user device via a network, executing a generative artificial intelligence (GenAI) model based on content that is heard during the call and content within the report displayed on the user interface to identify content within the displayed report that is discussed during the call, and modifying the displayed report to emphasize the identified content within the displayed report on the user interface.

Disclosed are systems and methods that ingest substantial volumes of data from a variety of sources associated with a computing system network to create integrated, intuitive, efficient, and coherent adaptive workspace display interfaces. The ingestion includes event data generated by event source software applications running on end user computing devices as well as call and end user attribute data that is used to determine state, presence, and performance data for the end user computing devices that is formatted for display on the adaptive workspace interfaces and used during performance monitoring and collaboration between system end users. The adaptive workspace interfaces provide functions that facilitate real time collaboration between end users that enhances shared experiences between system end users and customers.

A communications session with a user may be automated using a language model. The language model may be instructed to select a next action to be performed where the next action may include transmitting a responsive communication to the user or performing an API call. The prompt used to query the language model may include one or more of the following: a representation of text of the communications session, a list of available API calls, instructions to select a next action, a representation of API calls performed, or a representation of API call responses received. The language model may be sequentially queried to continue the communications session by transmitting responsive communications or performing API calls. In some implementations, a prompt template may be used to generate the prompt and a prompt template may be selected using text of the communications session.

The method and systems for automatically identified currently viewing website domain name or a uniform resource locator (URL), receiving, by the server, said automatically identified website domain name or the uniform resource locator (URL), a request or an invitation for initiating a communication including live chat, puts the request for initiating a communication including live chat from the first user and the second user in a communication including live chat queue of the website or the uniform resource locator (URL) associated account, for available or identified or relevant agents to pick up, routing request or invitation for initiating a communication including live chat from the first user and the second user according to a pre-set rules and start a communication including live chat by available agent by selecting particular request for initiating a communication including live chat from the queued communication including live chats.

A disclosed method includes monitoring a plurality of emergency event queues at an emergency network entity; determining that an emergency event in one of the emergency event queues corresponds to an emergency type that can be responded to using an unmanned aerial vehicle; determining that an unmanned aerial vehicle is available that has capabilities corresponding to the emergency type; establishing an unmanned aerial vehicle control link between the unmanned aerial vehicle and the emergency network entity; and deploying the unmanned aerial vehicle to the emergency event location and providing data from the unmanned aerial vehicle on a display of the emergency network entity.

System and methods for simultaneous voice and data content driven commercial data platform are disclosed herein. One disclosed system comprises a plurality of peer nodes, a first interaction manager stored on the dialer device and programmed to transmit interaction data to a database during a call with a receiver device, and a second interaction manager stored on the receiver device and programmed to distribute interaction data to the database during the call. The plurality of peer nodes is programmed to obtain receiver content data from the database using the receiver identifier, distribute the receiver content data to the dialer device, obtain dialer content data from the database, distribute the dialer content data to the receiver device, and interaction data in the database. In specific embodiments, the receiver device is programmed to access data from an external platform. In specific embodiments, the system uses a chatbot with artificial intelligence.

The invention discloses a dynamic scheduling method and device for mass call requests and a medium, and relates to the technical field of information management, and the method comprises the steps: receiving mass call request information through an information sending device, carrying out the language processing to generate an analysis data set, and obtaining the request types through deep learning classification; performing multi-objective optimization on the analysis data set to generate a dynamic call queue; constructing a time sequence prediction model based on historical records, predicting a call peak, carrying out resource scheduling analysis, and formulating a scheduling strategy; and generating a feedback result after executing the scheduling strategy, synchronizing the feedback result to the call center, and updating the strategy according to response information to realize intelligent dynamic scheduling. The technical problem that in the prior art, the resource scheduling efficiency of the call center in the mass request processing process is low is solved, and the technical effect of optimizing the resource scheduling efficiency of the call center is achieved.

A method of prioritizing incoming emergency calls, comprising receiving one or more emergency calls originating from one or more client devices used to report one or more emergency events, computing an event zone for each emergency event based on one or more event attributes of the emergency event retrieved according to data extracted from the emergency call, receiving one or more subsequent emergency calls originating from one or more another client devices, computing a location of each another client devices with respect to the event zone of one or more of the emergency events, responding to the subsequent emergency calls with one or more queries generated automatically according to the relative location of each another client device with respect to one or more of the event zones, and prioritizing the subsequent emergency calls according to a response to the to the query(s) via the another client devices.

A method for agent interaction analysis using artificial intelligence according to an embodiment includes receiving a transcript for a real-time agent interaction between a contact center agent and client, processing the interaction using at least one artificial intelligence model to determine a call adherence score, an agent positivity score, a client sentiment, an agent sentiment, and a plurality of agent skill levels associated with respective agent skills, determining a combined agent performance score based on the call adherence score and the agent positivity score, transmitting the combined agent performance score to an agent device for display on a gamification dashboard, retrieving agent-specific content of the contact center agent in response to determining that the agent sentiment is negative, and transmitting the agent-specific content to the agent device for display in conjunction with the real-time agent interaction to improve the agent sentiment.

The invention relates to a distributed outbound system optimization method based on cloud computing. The method comprises the following steps: disassembling an outbound task into fine-grained subtasks including dialing, recording, interaction and recording; generating a unique identifier for each subtask; based on a distributed task scheduler; according to node real-time performance and network delay, dynamically distributing tasks, and introducing a task priority rule; monitoring a task execution state in real time through a distributed tracking system; recovering and redistributing abnormal and failed tasks; fragmenting the call-out data according to regions or customer groups, and distributing the call-out data to different nodes; processing the call record and the client feedback by using a stream processing framework comprising Apache Flink; adding a call task including Kafka into a distributed task queue; setting a dynamic priority queue, and adjusting the priority according to the task timeliness; setting an overtime threshold value for the call task, and monitoring a task state in real time; and when the task is overtime or failed, triggering a retry strategy including adjusting the call period and switching the node.

An emergency response assistant system may generate emergency response insights and provide the insights to an emergency responder application for an emergency communications center (ECC), an operations center, or a first responder. The emergency response assistant system may include a data retrieval system and an augmentation and generation system. The data retrieval system may be configured to transform emergency response procedures into vectors that are stored in a vector database. The augmentation and generation system may be configured to perform a vector search of the vector database with an AI model using context from call (e.g., a 911 call) characteristics and external data sources and may be configured to display the results on a user interface of an emergency management application to provide emergency response procedure suggestions to a user of an ECC computing system, an operations center computing system, or a first responder computing device.

Apparatuses, systems, and techniques to selectively suppress noise in a conference call. In at least one embodiment, one or more neural networks may be used to identify a source of a noise component and cause a notification to be sent, informing a user of the noise source to confirm or decline suppression of the noise component.

The invention discloses a call center outbound call completing rate improving method, system and device and a storage medium, and relates to the technical field of call center management, and the method comprises the steps: collecting historical outbound call data of a call center; analyzing historical outbound data by using a machine learning algorithm, and establishing an outbound connection prediction model; based on an outbound call connection prediction model, calculating an optimal outbound call time window and an expected connection probability for each number to be called; formulating an outbound strategy according to the optimal outbound time window and the expected connection probability, and generating an outbound task queue according to the outbound strategy; executing an outbound task according to the outbound task queue, and generating an outbound task record; and updating the outbound call connection prediction model and the outbound call strategy by using the outbound call task record, dynamically optimizing the outbound call process, and completing the improvement of the outbound call connection rate of the call center. According to the method, the historical outbound data are analyzed through the machine learning algorithm, the outbound call connection prediction model is established, the prediction accuracy of the outbound call connection rate is improved, and the resource utilization efficiency is also greatly improved.

The invention discloses an AI-based telephone answering system, and relates to the technical field of telephone answering. Comprising a real-time voice acquisition and preprocessing module, a voice speed detection and prediction module, a self-adaptive ASR dynamic regulation and control module, a refined voice slicing and decoding module, a keyword detection and voice recognition module, a semantic understanding and intention analysis module and an emergency response and scheduling module. And the real-time voice acquisition and preprocessing module is used for acquiring user voice data of the emergency call in real time, establishing a real-time audio stream transmission channel and quickly preprocessing the acquired audio signal. According to the method, the voice features of the user at the high speed are quickly and accurately captured, and the voice segmentation length of the ASR engine is dynamically adjusted, so that each voice segment is clearer and more accurate, cross-segmentation vocabulary segmentation and recognition errors caused by too high speed are avoided, and the user experience is improved. Therefore, omission and misjudgment risks of the emergency information of the user are effectively avoided in an emergency help-seeking scene.

The invention discloses a traffic domain service voice adaptive generation method and system based on a thinking chain fine-tuning large model, and the method comprises the steps: converting an input voice signal into a high-dimensional voice feature signal through a voice encoder, and generating a text output signal according to the high-dimensional voice feature signal through a text decoder and a pinyin decoder; according to the invention, a variational de-quantization joint data enhancement mechanism, a dual-channel multi-mode discriminator architecture and a layered composite loss function are adopted to carry out high-fidelity emotional speech generation and robustness synthesis in a complex noise environment, and semantic-driven dynamic rhythm optimization and professional term precise pronunciation are synchronously supported; in an application scene in the traffic field, a multi-task speech recognition method can be adopted to realize efficient linkage of character-level recognition, audio-to-pinyin conversion and sentence-level accent classification modules, so that complex accent, more noise and traffic term polyphone challenges are effectively handled, and the method is suitable for being widely popularized and used.

Systems and methods to cause an intent discovery system to identify new user intents without additional training. The system may comprise of two neural networks. The first neural network generates a prompt tailored to a particular domain (e.g., travel), and may include known intents pertinent to the domain selected examples from a training dataset to provide context to the prompt. The second neural network may use this prompt to identify intents from new utterances in the prompt. The identified intents that are not in the list of known intents are then used to update the database.

The present invention discloses a method for intelligently generating meeting minutes files, comprising the following steps: step one, collecting and uploading the audio data of the meeting to a cloud server through a recording device; step two, using a voiceprint recognition large model to identify different speakers in the audio after receiving the audio data uploaded in step one; step three, converting the voice segments segmented in step two into text content, and improving the accuracy of the text through an error correction model; step four, based on vectorization technology and cosine similarity algorithm; step five, summarizing and extracting the topics, key points, and decision summaries corresponding to each set; step six, summarizing the meeting summary; step seven, forming meeting minutes; step eight, extracting various information of the meeting minutes from a database. The method for intelligently generating meeting minutes files of the present invention, by automatically processing the content of the meeting, the system can not only identify different speakers, but also automatically distinguish topics, summarize discussion points, and refine decision content.

A method of leveraging machine learning to predict empathy for improved contact center interactions according to an embodiment includes receiving, by a computing system, at least one user message from a real-time contact center interaction with a user, generating, by an artificial intelligence system of the computing system, at least one empathy score based on the at least one message using the machine learning, wherein each of the at least one empathy score is indicative of a real-time empathy of the user, generating, by the artificial intelligence system of the computing system, an empathetic text response to the at least one user message based on the at least one empathy score, and responding to the at least one user message in the real-time contact center interaction based on the empathetic text response generated by the artificial intelligence system of the computing system.

A conferencing system includes a plurality of microphones and an audio processing system that generates and evaluates machine-learning / artificial intelligence models to optimize acoustics of meeting rooms.

An automated support process implemented with a language model may be improved by allowing a human agent to provide input to the language model to fix mistakes or otherwise improve the automated support process. In some implementations, a language model prompt may be used to instruct a language model to be able to provide a response that includes requesting assistance from a human agent. The request for assistance may then be sent to the human agent and a response from the human agent may then be processed by the language model to allow the language model to provide better responses for the support process. In some implementations, a human agent may monitor automated support sessions and provide unrequested input into a support session where needed to improve the quality of the support session.

Systems and methods develop and apply one or more extractive summarization models for locating contact center conversation details in a transcript, extracting pertinent verbiage, and, in a transformation of the communication details, automatically generating summaries at one or more levels of abstraction, the summaries in full sentences, in a manner that a contact center agent understands. The models are trained using machine learning algorithms.

The system obtains network information by creating an index of network websites and obtains UE contextual information including: cell tower ID serving the UE, technical capability of the UE, UE performance information, updates to the UE, UE browsing history, and site deployment information. The system obtains from the UE a natural language query and provides the query, the network information, and the UE contextual information to an AI. The system obtains from the AI an answer to the natural language query, where the answer is a summary of a relevant website. Based on the UE contextual information, the system determines whether a user of the UE is technologically savvy or not technologically savvy. If the user is technologically savvy, the system presents the answer and a link to the relevant website; otherwise, the system offers to connect the user to an operator of the network.

The invention discloses an intelligent customer service response method and system based on a large model, and the method comprises the steps: obtaining user input and a historical dialogue of a user, splicing the user input and the historical dialogue with a preset first prompt, inputting a large model, and outputting query rewriting and intention recognition; responding to the intention recognition, splicing the intention recognition with a preset second prompt, and inputting the large model to output a calling instruction; and responding to the calling instruction, and generating content output. By obtaining the content input by the user and combining the historical dialogue corresponding to the user, the processing content for the user can be automatically completed, the large model can effectively rewrite and identify the intention of the processing content through the prompt generated by the processing content, the requirement for the content input by the user is greatly reduced through the mode, the processing process is more flexible, and the user experience is improved. Meanwhile, after accurate intention recognition is obtained, next-step processing can be carried out more accurately, so that accurate content output is obtained, and the efficiency and accuracy of processing user problems are higher.

Embodiments of the disclosure provide a method of processing messages received in an asynchronous communication system. In some embodiments, the method includes analyzing interactions on a digital communication channel, determining that the interactions have paused for an amount of time, analyzing content of the interactions to determine an estimate of the amount of time, updating a state of the agent to release the agent for the estimated amount of time, and setting a timer that will automatically change the state of the agent back to an occupied state for the interactions at a future time that aligns with an expiration of the timer.

An emergency management system (EMS) captures alarm reports that are called into an emergency call center (ECC) and converts the audio data of the alarm report into actionable alert data that may be displayed in and dispatched from an emergency response application that is operated at the ECC. The alert system includes a central station system, an ECC system, and an emergency management system (EMS). The ECC system has call handling equipment (CHE) to receive calls for an emergency call telephone number and an alarm reporting telephone number. The emergency response application can display a queue of alerts, and each of the alerts includes alert data that can be displayed. The EMS includes an automated interview system that can at least partially use an AI model to transform the audio data into alert data that is used to populate the queue of alerts.