60 results about "Interaction history" patented technology

The invention provides a digital human interaction control method and device fusing emotion semantics and logical reasoning and a storage medium. The method comprises the following steps: analyzing multi-modal input data of a user, constructing emotion-semantics joint representation, and generating a logic decision path; and through a cognitive fusion module, emotion-semantic representation and a logic decision path are fused, and an interaction response adapting to emotion and logic consistency is generated. The system optimizes an emotion semantic model and a logical reasoning rule on line according to user feedback and interaction history, and real-time interaction of emotion dynamic and logical rules is achieved. The system can dynamically adjust the logic decision path based on the multi-mode emotional state of the user, and improves the naturalness and situation adaptability of interaction. A dynamic time warping algorithm and a factorization machine are introduced to process a multi-modal feature fusion problem, and the accuracy and robustness of emotional state recognition are improved. The online optimization mechanism enables the model and the rule to be evolved continuously, and reasoning errors are corrected automatically through user feedback, so that error circulation is avoided.

Embodiments of the present invention provide computer-implemented methods, computer program product, and computer systems. One or more processors analyze user prompts using one or more natural language understanding techniques. One or more processors then enrich the user prompts by integrating contextual data from user interaction history and adapt the enriched user prompts to align with characteristics of Large Language Models (LLMs) and Application Programming Interfaces (API) requirements of the LLMs.

Techniques for ASR processing using language model (LM)-generated context are described. A LM is prompted to generate words that are relevant for / may be included in a future user input. The prompt to the LM can include words from user interaction history, dialog history, dialog topic, user preferences, etc. The information included in the prompt may focus on rare or unique words rather than words that the ASR model is already confident in recognizing. The techniques can be plugged into an existing / pretrained ASR model and can be used with any existing / pretrained LM, thus saving resources needed to implement and maintain the components.

The invention discloses a psychological health analysis method and apparatus, an electronic device and a storage medium, through the application, dynamic psychological assessment is generated through multi-modal data fusion analysis, and personalized scenarized dynamic interaction content is generated based on an assessment result and an interaction history, so that the psychological health analysis efficiency is improved. Meanwhile, continuous learning and correlation analysis are carried out on the psychological state of the user by utilizing a multi-dimensional memory architecture, so that the system can understand the change of the user state and adjust an interaction strategy like a human consultant, and therefore, the technical problems of insufficient emotional distraction and credibility of the user due to the adoption of a standardized reply mode in the prior art can be solved, and the user experience is improved. The technical effects of enhancing the emotion affinity of the system, establishing a continuous and credible interaction relationship and improving the durability of the psychological intervention effect are achieved.

The present technology, roughly described, generates grammars, such as context free grammars, dynamically and by induction, that can specify constraints for a decoding system. The grammar can be created to support an automated agent involved in an interaction (e.g., a conversation) with a client. In some instances, grammars can be generated dynamically based on copying portions of an interaction history and based on business logic rules. Grammars can also be induced automatically from API specifications and collections of strings. The newly generated context free grammars can be used by a language model to perform constrained decoding.

The invention discloses an interactive entertainment dialogue method and device based on a dialogue model, a medium and a product, and relates to the field of data processing. The method comprises the following steps: receiving current dialogue information input by a user in interactive entertainment content; user interaction behavior data and factual data related to the current dialogue information are retrieved from a preset interaction historical record storage module, and a historical record retrieval result is obtained; according to the retrieval result and the timestamp of the current dialogue information, determining a weight coefficient of the retrieval result and the dialogue information; generating weighted data based on the retrieval result, the current dialogue information and the weight coefficient; inputting the weighted data into a preset dialogue model to obtain reply information output by the dialogue model; and sending the reply information to the user. According to the method and the device, the quality and the efficiency of interactive entertainment dialogues can be improved, the problem that the dialogue model enquires unexperienced story plots when the user does not experience all story lines of a certain role is relieved, and better interactive entertainment experience is brought to the user.

The invention provides a multi-modal recommendation method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: determining a project description picture and a project description text, and carrying out the weighted fusion of the project description picture and the project description text, and obtaining an overall modal feature expression; determining interaction historical data of the user and the project, and obtaining a user preference score based on the overall modal feature expression and the interaction historical data; inputting the user preference score into a pre-trained multi-modal preference optimization recommendation model to obtain an optimized user preference score; and obtaining a recommendation result based on the optimized user preference score. According to the method and the device, the multi-modal information fusion efficiency can be improved, and the preference of the user can be more accurately captured and modeled.

The invention belongs to the field of digital human interaction management, relates to a data analysis technology, is used for solving the problem that the multi-round interaction state of a digital human cannot be monitored and analyzed in the prior art, and particularly relates to a digital human interaction management system based on big data analysis. Comprising a voice interaction support module, a multi-round dialogue supervision module and an effectiveness optimization analysis module which are connected in sequence, the voice interaction support module is used for identifying voice information received by the digital human, converting the voice information into text information, inputting the text information into the general large model, calling a corresponding output instruction and sending the output instruction to the execution module; according to the method, reasonable logic extension and supplementary answering can be performed according to the questions of the user, the interaction history and intention information of the user in multiple rounds of dialogues can be effectively memorized, the dialogue context association model is established, and it is ensured that the platform can accurately understand the evolution and progression of the intention of the user in the multiple rounds of dialogues.

The invention discloses a recommendation method and device combining a language model and a collaborative architecture, a medium and equipment. According to the method, information input by a user is obtained, and the information comprises interaction historical information of the user and natural language description of an item; inputting the information into a trained mixed recommendation model, so that the mixed recommendation model outputs recommendation of the information based on a mask evaluation mechanism; wherein the mixed recommendation model is obtained by training a preset mask language model according to a Bert4Rec architecture, an mT5 model and a contrast learning technology. According to the method combining the multi-modal data and the advanced model architecture, the performance of a recommendation system can be remarkably improved, a more accurate and satisfactory recommendation result is provided for the user, and the problem that accurate recommendation cannot be provided for the problem of the user in the prior art is solved.

A system and method for generating personalized wellness recommendations in real time, based on a user's emotional state, contextual situation, and interaction history. The system leverages a large language model (LLM) integrated with an emotion ontology based on the Wheel of Emotion to analyze both user-submitted input and historical behavior. In some embodiments, the system extracts emotional and situational cues from natural language input and recommends wellness practices that match specified preferences including emotional impact, guidance level, and duration. A fallback prioritization logic is applied to ensure relevant results even when exact matches are unavailable. The system may also generate a compassionate message aligned with the user's inferred emotional state and return structured output. In automated embodiments, the system selects a weighted mix of familiar and exploratory content. The architecture includes preference drift tracking, confidence-based filtering, and memory-optimized re-ranking to improve emotional targeting and user engagement.

We provide the system. [Solution] A data collection method for collecting customer interaction history, A data analysis means that analyzes the aforementioned dialogue history using natural language processing technology to extract customer interests and needs, A proposal generation means that generates personalized follow-up proposals based on the extracted customer interests and needs, A notification means for notifying the terminal of the generated follow-up proposal, A follow-up execution means that executes a follow-up proposal using the aforementioned terminal and records the results, A system including a learning means to improve the proposal generation means using the execution results.

In one embodiment, a method includes detecting activity of one or more agents that modifies a processing state of a first of multiple invoices, each invoice requesting approval. The activity is conducted by the one or more agents through interacting with the procurement processing system. The method includes updating, based on the detected activity, an invoice interaction history record associated with the first invoice in an invoice interaction history datastore communicatively coupled to the procurement processing system. The method includes generating one or more metrics regarding activity of the agents affecting a processing state of the invoices based on the updated invoice interaction history datastore. The method includes providing the one or more metrics for presentation to the procurement processing system.

The application provides a frozen base model personalized reply method and device based on dynamic activation guidance, acquires current user query information and interaction history state information; inputs the current user query information and the interaction history state information into a bypass network for personalized dynamic activation guidance, obtains a dynamic guidance vector output by the bypass network; inputs the current user query information and the dynamic guidance vector into a frozen base model, and obtains a personalized reply corresponding to the current user query information output by the frozen base model. The technical scheme of the application is based on the collaborative reasoning architecture of the lightweight bypass network and the frozen base model, inputs the current user query information and the dynamic guidance vector obtained by the bypass network into the frozen base model, injects an activation state based on the frozen base model, obtains the personalized reply corresponding to the current user query information, and improves the accuracy of the personalized reply.

The invention is applicable to the technical field of interactive video processing and information updating scheduling, and provides a real-time interactive enhancement system for electronic publications, which comprises a data acquisition module used for acquiring a user interactive historical record of a target unmanned vending machine and an initial updating period value of a target interactive video. Aiming at the interactive video updating problem in the unmanned vending scene, the method does not depend on an updating mode purely based on a commodity data change period in the prior art, but introduces user interaction feedback as a core decision basis. A correction factor is dynamically generated to adjust an initial updating period value by obtaining and analyzing user interaction historical records, recognizing wrong clicks, repeated switching of branch paths or interruption after interaction steps are not completed, and combining the occurrence frequency in a newest preset time window, so that the updating rhythm can truly reflect understanding and trust requirements of users.

The invention belongs to the technical field of natural language processing, and particularly relates to a method for relieving a robot session failure by utilizing explanatory interaction, which comprises the following steps of: monitoring a session process between a robot and a user in real time by utilizing a natural language processing technology and an emotion analysis algorithm; generating corresponding explanatory interaction content; personalized explanatory interaction content is provided for each user by analyzing the interaction history and preference setting information of the user; and feedback suggestions of the user on the explanatory interaction are collected, system optimization is carried out according to feedback information, and the quality and effect of the explanatory interaction are continuously improved. According to the method, an explanatory interaction mechanism is introduced, so that the robot can provide detailed explanation and description for the user when the session failure occurs, and the user is helped to better understand the behavior and state of the robot. Meanwhile, by continuously optimizing the content and form of the explanatory interaction, the satisfaction degree and credibility of the user can be improved, and effective man-machine communication is promoted.

The present application relates to the field of group portrait, disclose a kind of user portrait generation method, device, computer equipment and storage medium, its method includes: obtaining user interaction history record;According to user interaction history record generates user intent data, user intent data includes each user's flow node and node intent, a flow node corresponds to a node intent;According to user intent data constructs g×c two-dimensional matrix, wherein, g is total number of users, c is total number of node intent;Two-dimensional matrix is decomposed into first matrix and second matrix by non-negative matrix decomposition algorithm, first matrix is g×p matrix, second matrix is p×c matrix, and p is self-defined dimension;According to first matrix and second matrix, construct a number of group user portraits.The user portrait generated by the present application is highly matched with the intelligent customer service system, and the reply satisfaction of the intelligent customer service system can be improved.

[Problem] To provide an information processing device that can carry out interaction by using information obtained by compressing interaction history. [Solution] An information processing device according to the present invention is connected to: an external device that uses a first graph document in which a document structure is graphed; and a large-scale language model that generates the first graph document. The information processing device is characterized by having a control means that creates a first prompt on the basis of information including the first graph document, transmits the first prompt to the large-scale language model, acquires, from the large-scale language model, the first graph document that was updated on the basis of the first prompt, and transmits the acquired first graph document to the external device.

The embodiment of the invention provides a data processing method and device, equipment and a readable medium. The method comprises the steps of determining attribute information of a user in response to a return behavior of the user for a specified function of an application, and the attribute information of the user is determined based on interaction historical data of the user. And based on the attribute information, determining interaction content corresponding to the attribute information. And displaying the interactive content on an interactive interface of the application. According to the scheme, the interaction content is determined based on the attribute information of the user to execute display, the interaction content can better fit the requirements and habits of the user, and therefore the interaction quality of interaction with the user can be improved.

The invention discloses a new problem scene-oriented multi-modal large model knowledge tracking method, which is characterized in that modal level fusion is realized by adopting a perception coordination module, vision, text and context input are aligned, and rich problem characterization is constructed; problem-level fusion is realized through a cognitive integration module, multi-modal clues and learner interaction history are dynamically integrated, and a potential knowledge state is deduced under the condition of not depending on a question ID; and through an adaptive generalization module, representation is dynamically generated for unseen problems based on semantic similarity, and zero sample migration is realized. Compared with the prior art, the method has the advantages that zero sample knowledge without problems is tracked, so that the MKT-LLM can truly realize zero sample generalization to open and real world education content, and the limitation that an existing knowledge tracking method cannot be generalized to a new problem is effectively solved; the method can be widely applied to an intelligent education system, a self-adaptive learning platform and an interactive tutoring system, and provides technical support for personalized education in an open learning environment.

The invention provides an intention-driven NPC behavior and dialogue generation method. The method comprises the following steps: receiving an NPC behavior and dialogue generation request to trigger an NPC behavior and dialogue generation process; determining the current action intention of the NPC by analyzing the internal state of the NPC, the external environment perception information and the interaction historical data; judging whether the next purpose of the NPC is to generate a behavior or a conversation according to the current action intention of the NPC; if the next purpose of the NPC is to generate a behavior, generating an action generation field of the NPC, and if the next purpose of the NPC is to generate a dialogue, generating a dialogue generation field of the NPC; matching the action generation field or the dialogue generation field with a preset action data list, and if an unmatched field exists, correcting the unmatched field to obtain a final action generation field or a final dialogue generation field; generating an action instruction according to the final action generation field, and generating dialogue content according to the final dialogue generation field; and repeating the above steps until the NPC stops interaction.

To provide methods, systems, and computer program products for detecting online contextual evolution of linguistic terms.SOLUTION: A computer-implemented method disclosed herein comprises: detecting an increase in use of a linguistic term at a messaging source; determining that a plurality of linguistic terms related to the linguistic term are disproportionally related to the increase in use of the linguistic term at the messaging source; identifying a possible evolution of the linguistic term based on user reactions to the linguistic term at the messaging source in consideration of an interaction history; and classifying one or more messages as including an evolved use of the linguistic term.SELECTED DRAWING: Figure 4

A computing system is provided, including processing circuitry configured to cause an interaction interface for a trained generative model to be presented, in which the interaction interface is configured to communicate a portion of a user interaction history. The processing circuitry is further configured to receive, via the interaction interface, an input for the trained generative model to generate an output. The processing circuitry is further configured to send a command to create, via the trained generative model or another trained generative model, a whiteboard based on the user interaction history and receive the created whiteboard. The processing circuitry is further configured to generate a prompt based on the whiteboard and the instruction from the user and provide the prompt to the trained generative model. The processing circuitry is further configured to receive a response from the trained generative model and output the response via the interaction interface.

The invention discloses a knowledge perception recommendation method based on preference personalized aggregation, and the method comprises the steps: 1, inputting a user set, an article set, a user and article interaction history, and a knowledge graph, and defining a super node representing the preference of each user for each user; step 2, constructing a collaborative attribute graph based on the input; step 3, obtaining preference representation of each aspect of each user on the collaborative attribute graph through graph aggregation; step 4, on the knowledge graph, obtaining a final embedding representation of the article through graph aggregation; step 5, on the user-article interaction diagram, combining the selector and the preference representation of each user to obtain the final embedded representation of the user; and step 6, obtaining a preference prediction score of each user about each article through the user embedding representation and the article embedding representation.

A computing system (10) is provided that includes processing circuitry (14) configured to render an interactive interface (84) for a trained generative model (80), where the interactive interface (84) is configured to communicate a portion of a user interaction history (40). The processing circuitry (14) is further configured to receive an input (92) via the interactive interface (84) for the trained generative model (80) to generate an output (94). The processing circuitry (14) is further configured to send a command to create a whiteboard (60) based on the user interaction history (40) via the trained generative model (80) or another trained generative model (81), and to receive the created whiteboard (60). The processing circuitry (14) is further configured to generate prompts (70) based on the whiteboard (60) and instructions from the user, and provide the prompts (70) to the trained generative model (80). The processing circuitry (14) is further configured to receive a response from the trained generative model (80) and output (94) the response via the interactive interface (84).

We provide the system. [Solution] A means of saving the basic information entered by the user, A means for generating a virtual partner based on user selection using a generated artificial intelligence model, A means for generating individual responses based on the user's interaction history, A means of performing functions to support daily life in conjunction with external services, A means for users to interact with a virtual partner while on a mobile device and receive life support, A system that includes this.

A computing system is provided, including processing circuitry configured to cause an interaction interface for a trained generative model to be presented, in which the interaction interface is configured to communicate a portion of a user interaction history. The processing circuitry is further configured to receive, via the interaction interface, an input for the trained generative model to generate an output. The processing circuitry is further configured to send a command to create, via the trained generative model or another trained generative model, a whiteboard based on the user interaction history and receive the created whiteboard. The processing circuitry is further configured to generate a prompt based on the whiteboard and the instruction from the user and provide the prompt to the trained generative model. The processing circuitry is further configured to receive a response from the trained generative model and output the response via the interaction interface.

This system provides an educational assessment method that efficiently evaluates children's intellectual abilities and developmental status based on their interaction history with AI, and then provides feedback on the results to parents and educators. [Solution] The system comprises a storage means for saving dialogue history, a summary generation means for generating a summary of the dialogue history after a predetermined period of time has elapsed, an analysis means for integrating and analyzing new dialogue history with the saved summaries, and an evaluation generation means for generating an educational evaluation based on the analysis results. The analysis means performs the analysis based on rubrics related to language patterns, knowledge, and interests. Rubrics can be set by parents or teachers. This makes it possible to efficiently conduct long-term learning evaluations and realize multifaceted educational evaluations.

A content recommendation method, which can effectively improve the accuracy of a model for predicting a feedback action of a user, thereby improving the accuracy of content recommendation. In the method, interaction histories between a user and a recommendation system and a feature of content to be recommended are extracted by means of one feature extraction network, a feature of content in which the user is interested is extracted from the interaction histories by means of another feature extraction network, and a feedback action of the user for the content to be recommended is then predicted on the basis of the two extracted features. In the present solution, a feature of content in which a user is interested is additionally extracted from interaction histories, i.e., priori knowledge is additionally provided during content recommendation, and the content in which the user is interested is highlighted in the interaction histories, such that when predicting a feedback action of the user, a model can focus on the content in which the user is interested, thereby effectively improving the accuracy of the model for predicting the feedback action of the user.