36 results about "Human agent" patented technology

Techniques for triggering a transfer of a chat conversation with a user from a chatbot to a human agent based on detection of transfer criteria are disclosed. The chatbot uses natural language processing and a generative model to collect and organize information from the chat conversation to present to the human agent in a report when the chat conversation is transferred to the human agent. The chat conversation is transferred to the human agent by presenting the report and a graphical chat interface to the human agent. The graphical chat interface displays messages from chat conversation between the human agent and the user and displays messages from chat conversations between the human agent and multiple other users. Transferring the chat conversation from the chatbot to the human agent includes presenting interface elements to the human agent for receiving user input from the human agent for transmission to the user.

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.

The invention discloses a flow feature confusion method based on an AI virtual human, and the method comprises the steps: S1, configuring the basic attributes of the virtual human and a preset behavior strategy, and automatically obtaining the fingerprints of Internet access equipment of a user; s2, virtual human environment fingerprint camouflage is carried out by configuring a containerized operation environment and adjusting browser fingerprints; s3, dynamically generating behavior parameters for determining a virtual human online task based on LLM drive of preset parameters; and S4, the virtual human calls a local browser driver on line based on the behavior parameters obtained in the S3, simulates human to access the target site and generates feature traffic. According to the method, the virtual human Agent is driven by the AI, the mixed flow is generated by autonomously acting on the network, the user identification and tracking technology of the network access target based on the flow signal characteristics is effectively interfered, the signal statistics characteristics of the user internet surfing flow can be effectively mixed, and the method is suitable for the network privacy protection requirements in various scenes.

Systems and methods for an artificial intelligence (AI) agent to perform self-learning, self-evaluation based on a rubric and then perform self-correction as needed is described. The methods generate a rubric. The rubric includes the AI agent's performance data and evaluations of the data and related feedback by a separate LLM and a human agent. Once a level of confidence is achieved that the AI agent is performing at a threshold confidence level of the human agent, or that the separate LLM is evaluating the AI agent's performance within a threshold confidence of the human agent's evaluation of the same, the rubric in which the AI agent's performance and evaluation data is inputted is determined to be complete for use in a self-evaluation. The AI agent may then use the rubric to self-evaluate and self-correct its performance without a need for human evaluation.

A system includes a processing circuit configured to receive a first input during a conversation. The processing circuit is further configured generate a first message parameter associated with the first input. The first message parameter corresponds with a first task that the processing circuit is authorized to autonomously perform. The processing circuit is further configured to autonomously perform the first task. The processing circuit is further configured to receive a second input from during the conversation. The processing circuit is further configured to generate a second message parameter associated with the second input. The second message parameter corresponds with a second task that the processing circuit is unauthorized to autonomously perform. The processing circuit is further configured to add a human agent device associated with a human agent to the conversation to provide a second response based on the second input and to perform the second task.

To allow the human customer service agents to specialize in the instances where human service is preferred, but to scale to the volume of large call centers, systems and methods are provided in which human agents and intelligent virtual assistants (IVAs) co-handle a conversation with a customer. IVAs handle simple or moderate tasks, and human agents are used for those tasks that require or would benefit from human compassion or special handling. Instead of starting the conversation with an IVA and then escalating or passing control of the conversation to a human to complete, the IVAs and human agents work together on a conversation.

Systems and methods are provided to assess a communication conducted over a network. The systems monitor the communication and submit a survey to the customer and agent. The agent may be a human agent or an artificially intelligent (AI) agent. The survey is selected or generated, such as in response to communication content, and presented to the customer and agent. If the scoring is significantly different, an automated agent initiates a remediation action, such as to coach a human agent or to provide feedback or a corrective prompt to an AI agent.

The present invention provides a robust and effective solution to an entity or an organization by enabling them to implement a system for automatic switching between visual responses, audio responses and textual responses in an omni-channel single view experience. Particularly, the system and method may empower a user to choose between any mode of interaction, the modes being provision of a visual interaction, audio interaction or a textual based interaction and a combination thereof based on a machine learning architecture and also provide seamless human agent handover. Thus, the system and method of the present disclosure may be beneficial for both entities and users.

Techniques for executing system actions during conversations between a human user and an autonomous conversational system are disclosed. A first generative language model processes user messages to determine user intent, while a dialog management model analyzes the intent and conversation context to identify required system actions. The system executes actions by retrieving parameters from context, performing database queries or API calls to obtain response data, and storing results in conversation context variables. A second generative language model generates natural language responses using the action results. The system maintains conversation context including message history, action results, and state information, validates action execution, and initiates human agent handoff when needed. The system improves over time by detecting poor performance, gathering problematic conversations, and retraining using updated configurations.

Method and media for an interface for a context-aware conversational assistant. A hybrid system is disclosed that can take advantage of both a human agent's facility at interacting with the user and an automated system's speed and accuracy at information retrieval to quickly and accurately provide the user with the needed information. In response to a user query, the conversational assistant determines one or more responses that may be relevant and presents them in the chat window to the agent. If the conversational assistant correctly interpreted the question, the agent can quickly respond to the query using the pregenerated response. Otherwise, the agent can edit a pregenerated response or compose a new response from scratch.

A human and a first AI agent are connected in a conversation which may be spoken (via telephone call) or via text (such as in a mobile or other messaging application). Keywords or phrases identified from the conversation are then compared to entries in an intent database to identify (a) an intent of the human indicating why they joined the conversation. (b) a necessity for involving a second agent in the conversation; and / or (c) based on the intent, which of several other agents are an appropriate match for the second agent. The second agent is then gracefully involved in the conversation by ensuring the human is continuously engaged until the second agent is available.

User interfaces for identifying communication sessions requiring human supervision are disclosed. According to an aspect, a system includes a communication session manager configured to define a supervising human agent. The communication session manager is configured to identify a virtual entity communication sessions assigned to the supervising human agent, thus defining a plurality of monitored virtual entity communication sessions. Further, the communication session manager is configured to render a user interface that presents the monitored virtual entity communication sessions. The communication session manager is also configured to receive selection, by the supervising human agent, of one of the plurality of monitored virtual entity communication sessions, thus defining a selected virtual entity communication session. Further, the communication session manager is configured to involve the supervising human agent in the selected virtual entity communication session.

A system is provided.SOLUTION: A system comprising: means for receiving a query; means for analyzing the received query to identify query content; means for accessing an in-house system to obtain relevant information based on the identified query content; means for generating an answer to the query using a generative AI model based on the obtained information; means for evaluating the reliability of the generated answer; means for determining whether the answer is appropriate based on the evaluation results and escalating to a human representative if not appropriate; means for sending a final answer to the user; and means for storing the query and answer in a log.SELECTED DRAWING: Figure 1

This application provides an AI-powered call transfer method, apparatus, electronic device, and medium, comprising: responding to a detected call transfer to human agent, extracting session parameters from the current AI interaction process and querying full metadata parameters associated with the currently interacting user; fusing the session parameters and full metadata parameters to obtain a complete transfer parameter package; generating a transfer work order based on the transfer parameter package using a large language model; and sending the generated transfer work order to the target human agent's port. This invention achieves seamless integration from AI interaction to human service, significantly improves the integrity of context transmission, greatly reduces the number of times users repeatedly describe their problems, and effectively improves customer satisfaction and service efficiency.

An architecture including a human and a human AI agent designed to understand and interact with the human, a system and a system AI agent designed to understand and interact with the system. The human AI agent and the system AI agent are configured to communicate with each other so that the human AI agent learns about the system and the system AI agent learns about the human, optimizing the interaction between the human and the system. The human AI agent and the system AI agent are configured so that the human AI agent learns about the system and the system AI agent learns about the human during a configuration process before the architecture is operational and while the architecture is operating.

The invention discloses a flow feature confusion method based on an AI virtual human, and the method comprises the steps: S1, configuring the basic attributes of the virtual human and a preset behavior strategy, and automatically obtaining the fingerprints of Internet access equipment of a user; s2, virtual human environment fingerprint camouflage is carried out by configuring a containerized operation environment and adjusting browser fingerprints; s3, dynamically generating behavior parameters for determining a virtual human online task based on LLM drive of preset parameters; and S4, the virtual human calls a local browser driver on line based on the behavior parameters obtained in the S3, simulates human to access the target site and generates feature traffic. According to the method, the virtual human Agent is driven by the AI, the mixed flow is generated by autonomously acting on the network, the user identification and tracking technology of the network access target based on the flow signal characteristics is effectively interfered, the signal statistics characteristics of the user internet surfing flow can be effectively mixed, and the method is suitable for the network privacy protection requirements in various scenes.

A method for generating an optimal set of parameters for a design project of a product, in which subject matter experts, working with an artificial intelligence module, select a number of fundamental measurement factors that are related to a group of fundamental prime measurements, all of which in the aggregate comprise a product profile matrix. The fundamental measurement factors are weighted and scored so that the resulting matrix reflects the various aspect of the proposed design. Through an iterative process, the fundamental measurement factors are modified until the product profile matrix provides a set of satisfactory scores that yields an acceptably low risk in proceeding with the selected design.

Contact centers that handle real-time interactions with customers commonly utilize automated agents to handle one set of work items while human agents handle the work items that are more complicated, rare, or otherwise unable to be successfully resolved by an automated agent. Customers may erroneously select a human agent when an automated agent would suffice and, similarly, may be forced to wade through automated options when a human agent is required. Systems and methods disclosed herein provide for the determination of a reason, or a prioritized list of reasons, for a call and present resolution options to a specific customer for that specific reason(s). As a result, the resources of the contact center are better utilized and the customer experience improved.

The present application discloses a call center message distribution method, comprising: generating a notification message in response to receiving vehicle data information; obtaining the status of a human agent in response to the generated notification message, and displaying the vehicle data information on a pop-up screen at the first idle human agent among the human agents; receiving a voice call request from the vehicle; and, in response to the voice call request, invoking the interface information of the human agent to distribute the corresponding human agent to conduct a voice call with the vehicle. The call center message distribution method of the present application can distribute messages to an agent as soon as they are received, reducing waiting time and improving processing efficiency. Furthermore, the method includes an instant message notification and refresh solution, which improves performance.

The application discloses a kind of human in loop multi-agent microservice system AgentInn design and construction method, including human in loop control module, multi-agent cooperation module, dynamic capability expansion module and task arrangement module.Human in loop control module realizes the control, participation and observation of human to agent by starting confirmation, running intervention, abnormal recovery, human agent registration, cooperation routing and experience feedback;Multi-agent cooperation module realizes cooperation arrangement and load balancing by cooperation space, role load balancing and agent discovery;Dynamic capability expansion module supports on-demand creation and hierarchical exposure of tool service and intelligent service;Task arrangement module manages progress using Cycle-Sprint-Phase three-layer time abstraction, and realizes task flow by combining flow decision and context transmission.The application solves the problems of lack of human participation in multi-agent cooperation, high complexity of cooperation arrangement and limited capability expansion, and realizes multi-agent microservice cooperation.

Disclosed are systems and methods for enabling collaborative AI-human voice interactions in an outbound call environment. An AI voice engine synthesizes real-time speech responses, optionally using a voice model representing a specific human agent. A sentiment analysis engine monitors user speech to classify emotional state, and an emotion modulation engine dynamically adjusts tone, pitch, and prosody of AI output based on inferred sentiment or operator commands. An operator console allows live human oversight, including editing AI-generated text, selecting emotional tone presets, or overriding responses entirely. The system supports real-time disclosure of AI identity and records call metadata for compliance. Training modules log operator interventions, sentiment patterns, and interaction outcomes to improve future AI behavior, enabling a scalable voice platform that balances automation with human empathy.

The application relates to the technical field of natural language processing, in particular to an intelligent assistance method and system suitable for call center human agents, which comprises the following steps: obtaining target dialogue text; taking the segmented words after removing stop words in the target dialogue text as target segmented words; obtaining all co-occurrence words of each target segmented word according to the stop word features and emotional intensity of the sentence where the target segmented word is located; obtaining the associated words of each target segmented word according to the co-occurrence frequency of each target segmented word and its co-occurrence words and the appearance frequency of each co-occurrence word; dividing all target segmented words into multiple entity sets according to the similarity of associated words and the similarity of pinyin between target segmented words, then obtaining the entity vocabulary of each entity set, and finally replacing all target segmented words with the entity vocabulary corresponding to the entity set where the target segmented word is located. The application accurately obtains the co-occurrence words of each target segmented word, thereby accurately obtaining the entity vocabulary corresponding to each target segmented word, and improving the error correction accuracy of the dialogue text.

A software agent, comprising a machine learning algorithm trained to engage in a conversation with a customer to take an order, receives an utterance from a customer. The utterance is converted to text and an analysis of the text performed. If the software agent determines, based on the analysis, that the software agent is untrained to respond to the text, the software agent establishes a connection to a point-of-sale device associated with a human agent. The human agent may perform a modification (e.g., an edit to the text, a modification to a cart, or provide input) to a modifiable portion displayed by the point-of-sale device. The software agent, based at least in part on the modification, resumes the conversation with the customer. The human agent does not directly interact with the customer during the conversation between the software agent and the customer.

A human and a first AI agent are connected in a conversation which may be spoken (via telephone call) or via text (such as in a mobile or other messaging application). Keywords or phrases identified from the conversation are then compared to entries in an intent database to identify (a) an intent of the human indicating why they joined the conversation. (b) a necessity for involving a second agent in the conversation; and / or (c) based on the intent, which of several other agents are an appropriate match for the second agent. The second agent is then gracefully involved in the conversation by ensuring the human is continuously engaged until the second agent is available.

This invention relates to a knowledge graph-based intelligent customer service question-and-answer precision recommendation and processing method, belonging to the field of electronic digital data technology. The method includes: constructing a conversation prediction knowledge graph based on the historical conversation counts from multiple channels; predicting the future conversation counts from multiple channels based on the conversation prediction knowledge graph and the current conversation counts from multiple channels; setting the number of robot agents and human agents based on the future conversation counts from multiple channels; accessing conversations from multiple channels, using robot agents to perform semantic understanding of user questions in the conversation, constructing a user demand profile, and determining whether to assign a human agent; if so, assigning the optimal human agent based on the status data of the human agent; if not, generating answers based on the user demand profile, conducting a dialogue, and generating recommended questions based on a question association graph. The question association graph records the relationships between multiple questions, which has the advantage of improving the quality and efficiency of customer service.

A system includes a processing circuit configured to receive a first input from a user device. The processing circuit is further configured to determine a first task that the processing circuit is authorized to autonomously perform based on the first input. The processing circuit is further configured to autonomously perform the first task based on determining the processing circuit is authorized to autonomously perform the first task. The processing circuit is further configured to receive a second input from the user device. The processing circuit is further configured to determine a second task that the processing circuit is unauthorized to autonomously perform based on the second input. The processing circuit is further configured to provide the second input to a human agent device associated with a human agent based on determining the processing circuit is unauthorized to autonomously perform the second task.

The invention belongs to the technical field of customer service seat service, particularly relates to a novel customer service queuing method based on joint participation of AI and manpower, and aims to solve the problems that the existing AI can only process simple problems and complex problems and needs to transfer human seats, and the number of AI seats can be adjusted in real time based on system load (such as elastic expansion of cloud resources). In order to solve the problems that in the prior art, the number of human seats is relatively fixed, the following scheme is proposed and comprises the following steps: S1, preparing a queuing system and receiving a request; s2, classifying incoming requests, and identifying problem complexity; s3, distributing the requests to queues with different priorities according to a classification result, and determining a routing strategy; s4, processing the request according to the strategy; s5, the system state is monitored in real time, and the number of the AI seats is adjusted in real time, the waiting time can be shortened during peak load (dynamic AI capacity expansion), and the cost can be reduced during low peak load (dynamic capacity reduction).

An automated interactive voice dialogue system using a human-in-the-loop design may enable human-supported interventions, where the automated system still conducts most of the interaction but enables a human agent to assume control of the dialogue and assist, if deemed necessary, so that the user may continue the interaction with little interruption or frustration. In some examples, the user of the dialogue system of this disclosure may not realize that there was a problem, and that the interaction is being or has switched from an automated dialogue system to a human. In some examples, the automated dialogue system of this disclosure may also automatically switch back to machine interaction when the human agent has resolved the situation.

The invention relates to the technical field of natural language processing, in particular to an intelligent assistance method and system suitable for a call center manual service agent, and the method comprises the steps: obtaining a target dialogue text; recording the segmented words in the target dialogue text after the stop words are removed as target segmented words; obtaining all co-occurrence words of each target segmented word according to stop word features and emotion intensity degrees of statements where each target segmented word is located; according to the co-occurrence frequency of each target segmented word and each co-occurrence word and the occurrence frequency of each co-occurrence word, obtaining an associated word of each target segmented word; according to the associated word similarity degree and the pinyin similarity degree between the target segmented words, dividing all the target segmented words into a plurality of entity sets, then obtaining entity vocabularies of each entity set, and then replacing all the target segmented words with the entity vocabularies corresponding to the entity sets where the target segmented words are located. According to the method, the co-occurrence word of each target segmented word is accurately obtained, so that the entity vocabulary corresponding to each target segmented word is accurately obtained, and the error correction accuracy of the dialogue text is improved.

A computer-implemented method for analyzing whether a phone call is answered by a human agent. The computer-implemented method receives phone call audio data of the phone call and separates the phone call audio data into caller stream data and agent stream data that each includes a plurality of frames and calculates decibel level for each frame. In response to measuring alternating groups of frames in the caller stream data and agent stream data that exceed a dialog decibel threshold, the computer-implemented method further identifies a dialog in the phone call audio data. In response to measuring decibel levels that exceed the dialog decibel threshold in corresponding frames in both the caller stream data and agent stream data, the computer-implemented method further identifies talkover in the phone call audio data. Furthermore, in response to identifying the dialog and if a level of talkover in the phone call audio data does not exceed a talkover threshold, the computer-implemented method determines the call is answered by the human agent.