76 results about "Real time classification" patented technology

A system for real-time detection and mitigation of morphing malware in high-density edge networks, consisting of: a data acquisition unit configured to receive, normalize, and encode multimodal telemetry data streams originating from at least one of the following domains: network traffic, process behavior, system call sequences, binary instruction traces, and control flow graphs; the data acquisition unit is further configured to compute feature embeddings over sliding time windows and apply privacy-preserving redactions prior to storage; a generative neural processor that is operationally coupled to the data acquisition unit and configured to generate synthetic morphing malware variants by learning probabilistic transformations of previously observed malicious data representations, maintaining semantic functionality while varying structural and behavioral features; a discriminative neural processor trained adversarially with the generative neural processor, wherein the discriminative neural processor is configured to detect morphing malware by evaluating a probability distribution over multimodal telemetry embeddings and classifying anomalous process and flow behaviors in real time; a coordination processor that is communicatively connected to both the generative neural processor and the discriminative neural processor and is configured to orchestrate adversarial co-training, regulate detection thresholds, calculate reinforcement-based penalties for false negative results, and trigger countermeasures as soon as a detection confidence level exceeds a predefined adaptive threshold; a secure, system-integrated inference and enforcement unit configured to perform low-latency countermeasures at the network edge, including selective packet filtering, flow isolation, process interruption, or system microsegmentation, based on instructions from the coordinating processor; and a hardware-embedded security enclave that is embedded in the system and configured to store cryptographic keys, neural model parameters, and integrity affirmation data to ensure the confidentiality, authenticity, and immutability of model artifacts and policy configurations.

The disclosure includes a digital twin system. The digital twin allows for real time classification and ranking of data received from a distributed learning knowledge acquirer. The digital twin system ranks the data while the distributed learning knowledge acquirer is performing a drift evaluation. The distributed learning knowledge acquirer uses the ranked data as training data for discriminative AI models. The digital twin system offers more flexibility and precision in ranking the data. The digital twin system is a digital twin providing contextual active dynamic learning to the distributed learning knowledge acquirer's physical system. Digital twin system causes a model driven approach to allow for superior predictive capabilities by being able to examine large state spaces.

The invention belongs to the technical field of machining and intelligent manufacturing, and particularly relates to an intelligent regulation and control system and method for discharge energy of a spark machine. Comprising a multi-mode gap state sensing module, a high-throughput data synchronous acquisition and preprocessing module, a discharge pulse real-time classification and feature extraction module, an LSTM-based gap state trajectory prediction module, a multi-target model prediction control module and a high-frequency pulse power supply execution module. By fusing the electrical parameters and the in-situ optical turbidity signal, multi-dimensional perception of the discharge state is realized, the future discharge trend is predicted by using an LSTM network, and an optimal pulse parameter combination is solved online by combining an MPC controller. By the adoption of the technical scheme, dynamic optimal balance of the material corrosion rate, the surface quality and the stability in the machining process can be achieved, and the overall machining benefit is improved.

The application relates to the fields of artificial intelligence and digital medicine, and proposes a deep learning model self-adaptive testing method based on artificial intelligence and related equipment.The method comprises the following steps: obtaining a deep learning model and test data, the deep learning model can obtain feature representation and classification results of any test data; a first data set for storing the feature representation and the classification results is created; real-time test batches are input into the deep learning model to obtain real-time feature representation and real-time classification results of the test data; the first data set is queried based on the real-time feature representation to construct a feature consistency loss; proxy feature representation of each category in the first data set is calculated to construct a feature uniformity loss; the deep learning model and the first data set are updated based on the feature consistency loss and the feature uniformity loss; and the self-adaptive testing of the deep learning model is completed until a preset condition is met. The application can improve the precision of the deep learning model applied to the field of digital medicine on medical test data.

The invention discloses an electronic nose gas classification model construction method and system, and relates to the technical field of gas sensing detection and artificial intelligence crossing. The method comprises the steps of performing fine adjustment on a pre-trained Transform encoder based on drift-free source domain data, constructing a source domain reference model and initializing an online updating component; in the real-time classification stage, after preprocessing and feature textualization conversion are carried out on target domain data, the drift mode type of the target domain data is judged by calculating feature distribution similarity, and representative samples are screened from current data; aiming at the new drift mode, training a new LoRA adapter; for a known drift mode, loading an existing LoRA adapter and carrying out lightweight fine tuning; and finally, obtaining a model for gas classification. According to the method, self-adaptive and lightweight online learning of sensor drift is realized, the calculation overhead and the storage requirement are reduced while the classification precision is ensured, and the long-term stability of an electronic nose system in a dynamic environment is improved.

This invention provides a real-time radio signal identification and classification system and method based on artificial intelligence, relating to the field of radio signal identification technology. The system includes: a signal preprocessing module for filtering, denoising, and normalizing received radio signals to generate a standardized signal dataset; a Hilbert space mapping module for mapping each signal sample in the standardized signal dataset to a complex vector in Hilbert space; a quantum gate operation module for performing quantum state evolution on the complex vector using single-qubit and two-qubit gates to generate superposition and entangled states containing signal characteristics; an amplitude compression module for compressing the signal dataset into a quantum state of n qubits using an exponential compression strategy; and an artificial intelligence classification module for real-time classification of signals using deep neural networks or support vector machines based on quantum state measurement results, outputting classification labels.

This invention discloses a real-time detection method and system for abnormal behavior based on micro-execution state sequences, relating to the field of computer-related technologies. The method includes: offline analysis of the binary code of embedded firmware to generate a legitimate fingerprint database of micro-execution state sequences; non-intrusive sniffing of the CPU's instruction bus and real-time classification of executed instructions via a hardware monitoring unit; calculation of real-time fingerprints based on instruction type sequences; extraction of legitimate fingerprints from the legitimate fingerprint database; synchronization with a fingerprint comparator for comparison; and generation of fingerprint comparison results; and triggering an abnormal response unit based on the fingerprint comparison results. This invention solves the technical problems in existing technologies where low-overhead, fine-grained, and broad-spectrum defense capabilities for embedded firmware runtime behavior monitoring cannot be achieved in resource-constrained environments, resulting in poor real-time detection performance, sensitivity, and protection coverage. It achieves the technical effect of improving the real-time performance and sensitivity of embedded firmware runtime integrity detection, as well as the protection coverage and system energy efficiency.

The application provides a kind of shipboard aviation equipment composite material damage D-S evidence theory nondestructive evaluation method, belongs to the field of shipboard aviation equipment nondestructive evaluation, it includes the following steps: at time, the triaxial damage area characteristics and triaxial vibration frequency characteristics of the composite material structure of shipboard aviation equipment are synchronously acquired and stored;The triaxial damage area characteristics and triaxial vibration frequency characteristics at time are compared respectively, and the corresponding triaxial damage area change degree and triaxial vibration frequency change degree are obtained;The identification framework of D-S evidence theory is established, and the triaxial mass function of the composite material structure is calculated respectively;According to the created D-S damage judgment model, the classification judgment and early warning of the composite material damage of shipboard aviation equipment are carried out.The application can realize the real-time classification evaluation of the dynamic damage of the composite material component of shipboard aviation equipment, and provide data support for the condition-based maintenance of shipboard aviation equipment.

The application discloses a DAS signal cross-scene multi-category classification method, system, device and medium, belongs to signal recognition classification in the field of optical fiber sensing technology, and aims to solve the technical problems that the DAS signal can only recognize single scene events in the prior art, and the DAS signal cannot be recognized and classified in a complex scene. The application comprises the following steps: acquiring samples and labels; constructing a signal recognition classification model comprising a feature extraction network and an identification classification network; the identification classification network comprises a tree classifier, each non-leaf node of the tree classifier comprises a node classification sub-network and an output layer, the node classification sub-network comprises a one-dimensional convolution layer, a batch normalization layer, a ReLU layer, a one-dimensional maximum pooling layer, a one-dimensional convolution layer, a batch normalization layer, a ReLU layer and a one-dimensional maximum pooling layer, and the output layer comprises a transformation layer, a full connection layer, a ReLU layer, a full connection layer, a ReLU layer and a Softmax layer arranged in sequence; training the signal recognition classification model; and classifying signals in real time.

The invention discloses a generative artificial intelligence cerebral artery lesion detection method based on plain-scan brain CT. The method comprises the steps that 1, a plain-scan brain CT image to be processed is acquired; 2, converting the plain scanning brain CT image into a CTA image through an adaptive noise elimination network; and 3, carrying out multi-modal lesion detection on the basis of the CTA image generated in the step 2. According to the method, a CTA image is generated through an adaptive noise elimination network (ANE-NET), and a real-time lesion feature analysis engine (RTAL-FE) is embedded in the generation process, so that real-time classification prediction of lesion types is realized. And furthermore, a detection result is output through a dynamic weight decision model (DWD-M), so that the generation quality and the detection efficiency are remarkably improved. The problems that a traditional method is low in generation quality and lags behind detection are solved, and the method is particularly suitable for low-dose and non-invasive cerebrovascular disease screening scenes and has important clinical application value.

The application discloses an agent model routing method and related device, and relates to the technical field of artificial intelligence, which comprises the following steps: receiving a user request; judging the complexity category of the user request from the dimensions of experience reuse, real-time classification and on-demand arbitration based on a three-layer cooperative complexity discrimination mechanism to obtain a complexity category discrimination result; selecting a target model from multiple candidate models according to the complexity category discrimination result, wherein the selection process comprises health filtering, constraint filtering of the candidate models, and comprehensive evaluation of the quality and cost of the filtered models; and executing the user request by using the target model. The application can improve the accuracy and stability of complexity discrimination, and reduce the model calling cost as much as possible under the premise of ensuring the task processing quality.

The invention provides a real-time classification method and system for working condition data, a storage medium and a computer. The method comprises the following steps: preprocessing sampling data obtained by continuously sampling an oil well to obtain an operation cycle of the oil well; the sampling frequency is adjusted according to the operation cycle of the oil well, secondary sampling is conducted on the oil well through the adjusted sampling frequency, and obtained secondary sampling data is compressed; performing indicator diagram classification coding based on the past indicator diagram classification data to obtain a coding table, and training and simulating a neural network by using the past indicator diagram classification data to obtain a neural network model; and carrying out data processing on the secondary sampling data by utilizing a neural network model so as to realize real-time classification of the working condition data of the oil well. The machine learning based on the neural network algorithm can be used for analyzing and identifying the wellhead working condition, data acquisition is quantized, a simplified neural network is constructed, and a foundation is laid for improvement of an oil extraction working condition identification technology.

The invention discloses a method, a system, equipment and a medium for classifying crack faults of a planetary gearbox, belongs to the classification of the crack faults of the planetary gearbox, and aims to solve the problems that a large number of complete source domain samples are difficult to obtain and the model classification accuracy is low. The method comprises the following steps: S1, acquiring a planetary gearbox crack fault acoustic signal sample data set and hard tag data; s2, constructing a crack fault classification model; s3, pre-training the crack fault classification model by using the sample data set and the hard tag data; s4, inputting sample data in the sample data set into the pre-trained crack fault classification model and obtaining a category probability; aggregating the category probabilities of all sample data belonging to the same crack fault type, and weighting to generate soft label data; using the sample data set and the soft label data to update and retrain the crack fault classification model; and S5, the updated crack fault classification model is used for real-time classification of crack faults.

A system for labelling and classification of encrypted network traffic is disclosed. The system employs a Labeler, having a semi-supervised machine learning module for semi-automated labeling of encrypted network traffic, with an initial involvement of a human-in-the-loop intelligence for rapid training of the Labeler. The Labeler produces a labeled training set of encrypted network traffic flows. The system further includes a Modeler having a genetic algorithm module, for automatically selecting a list of network traffic features for further use in real-time classification of the encrypted network traffic, and outputting a corresponding classification model. The system further includes a Classifier for real-time classification of the encrypted network traffic using the classification model. Corresponding methods for labeling and classifying the encrypted network traffic are also provided.

The application discloses a fabric classification method based on an intelligent near-infrared spectrum system and a neural network, which is applied to an intelligent near-infrared spectrum system composed of a near-infrared spectrometer, a capacitive touch serial port screen, a ZYNQ processing platform and a control bottom plate, wherein the near-infrared spectrometer is used for collecting near-infrared spectrum reflection data of the fabric and transmitting the data to the control bottom plate through a UART interface; an STM32 module is built in the control bottom plate and is used for controlling the spectrometer to collect data, completing preliminary processing, and transmitting the processed spectrum reflection data to the ZYNQ processing platform through the UART interface; a Zy-Net classification module in the ZYNQ processing platform calculates the spectrum data based on the neural network and utilizes the hardware acceleration capability of an FPGA built in the ZYNQ processing platform to realize efficient and low-delay real-time classification, and finally, the classification result is displayed in real time through the capacitive touch serial port screen. The application fully utilizes the software and hardware collaborative advantages of the ZYNQ processing platform to realize the real-time display of the classification of different fabrics in a fast and efficient manner.

The invention discloses a hyperspectral image edge intelligent classification technology based on an RK3588 platform, and the technology comprises the steps: constructing a high-precision and light-weight Transform hyperspectral image classification teacher model on a high-performance server, carrying out the compression of the teacher model through the comprehensive utilization of knowledge distillation, model quantification, pruning and other technologies, and carrying out the classification of the edge of a hyperspectral image. Generating a lightweight student model suitable for edge deployment; secondly, carrying out operator-level optimization and adaptation according to the NPU (Network Processing Unit) hardware characteristics of the RK3588 chip; and finally, deploying the optimized lightweight model on an RK3588 edge computing platform to realize real-time and low-power-consumption classification of the hyperspectral image. By means of model compression and hardware collaborative optimization, the problem that a high-precision model is transplanted and deployed to a domestic edge platform is solved, the execution efficiency of classification tasks is remarkably improved, the method has the advantages of being low in delay and high in energy efficiency, and real-time classification of hyperspectral images can be achieved.

Aspects of the present disclosure are operable to protect against malicious objects, such as JavaScript code, which may be encountered, downloaded, or otherwise accessed from a content source by a computing system. In an example, antivirus software implementing aspects disclosed herein may be capable of detecting malicious objects in real-time. Aspects of the present disclosure aim to reduce the amount of time used to detect malicious code while maintaining detection accuracy, as detection delays and / or a high false positive rate may result in a negative user experience. Among other benefits, the systems and methods disclosed herein are operable to identify malicious objects encountered by a computing system while maintaining a high detection rate, a low false positive rate, and a high scanning speed.

The application discloses a kind of based on image recognition's road surface state intelligent perception method and system.The system includes: image pre-processing module, fusion ESCA attention mechanism and LCAhead's road surface state intelligent perception module, model training module, image classification identification module and risk classification and driving guide module.The method includes the following steps: data enhancement is carried out to data image;Based on EfficientNetB0 model, fusion ESCA attention mechanism and LCAhead module;Configuration training hyperparameter and based on road environment perception dataset updates model weight;Data are input into ESCA-LCA Net road environment perception model training, realize the real-time classification identification of road environment state, and obtain corresponding risk classification and driving guide according to identification result.The application can improve the identification ability of multi-dimensional fine-grained road surface features, realize the accurate distinction and comprehensive judgment of dry and wet state, snow, water, unevenness and other types of road surface features.

The invention discloses a spam short message quasi-real-time classification method and system based on a large language model workflow, and relates to the technical field of artificial intelligence and mobile communication big data, and the method comprises the steps: extracting to-be-classified suspected spam short message data in a previous time period from a database; grouping identifiers are constructed for the suspected junk short message data, data compression is carried out, and a data pair combination of the suspected junk short messages and the corresponding grouping identifiers is constructed; pre-arranging a junk short message classification workflow based on load limitation of a large language model application development platform, and inputting the data pair combination into the junk short message classification workflow to generate reply information; extracting a classification result according to the reply information; and mapping all suspected junk short messages in the suspected junk short message data in the last time period to corresponding classification results according to the grouping identifiers, and returning the classification results to the database. According to the invention, efficient, accurate and automatic classification of massive suspected junk short messages can be realized.

The application discloses a strip plate shape intelligent regulation and control method based on an adaptive fusion model, which comprises the following steps: step 1, collecting historical rolling production process data and performing pretreatment; step 2, constructing a rolling production process data set based on the pretreated data; step 3, classifying plate shape quality according to the ratio of strip crown and target thickness and setting a category label; step 4, establishing an adaptive strip outlet plate shape diagnosis model containing multiple classifiers based on a DS theory, and training the diagnosis model through the rolling production process data set; step 5, inputting rolling production process data under a new rolling schedule into the classifier of the trained adaptive strip outlet plate shape diagnosis model to obtain a real-time classification prediction result of the strip, and if the prediction classification is under-crown or over-crown, step 6 is executed; otherwise, the process parameters are not adjusted; and step 6, dynamically adjusting and optimizing the process parameters based on an inverse linear quadratic control (ILQ) according to the prediction result of step 5.

The invention provides a heterogeneous driving behavior feature extraction and online identification method in a man-machine cooperation scene, and the method comprises the steps: obtaining traffic data in multiple man-machine cooperation driving scenes, and carrying out the research based on a data set; carrying out preprocessing methods such as target detection, multi-target tracking and acceleration smoothing on the data set, and extracting characteristic parameters in a car following process; a clustering index is calculated from the characteristic parameters, clustering analysis is carried out on the car following behaviors based on a K-Means clustering algorithm, and the car following behaviors are divided into three types according to driving behavior differences; on the basis of a factor analysis method, common factors are extracted from the characteristic parameters, and heterogeneous driving behavior car-following characteristic parameter extraction is achieved; according to the extracted common factors, an online identification model is constructed through an artificial neural network (ANN), three types of heterogeneous driving behaviors are classified in real time, and the problem that ACC cannot accurately identify the car following characteristics of the heterogeneous driving behaviors under man-machine cooperative driving can be solved.

The application provides a kind of motion recognition and intestinal gas detection method and equipment based on convolutional neural network, it is related to motion recognition and intestinal gas detection technical field.Detection device includes display screen, upper shell, battery, circuit board, gas sensitive element, lower shell, wire, buckle, host computer;Specific implementation includes motion gesture recognition and intestinal gas detection;Motion gesture recognition is carried out data acquisition by six-axis inertial navigation element, feature extraction and dimensionality reduction fusion, six classification identification model is calculated by forward propagation and outputs the probability value of 6 kinds of gestures, the class with the maximum probability is taken as the recognition result of current motion gesture, realizes real-time classification;Intestinal gas detection adopts gas sensitive element to detect gas concentration, according to gas concentration, threshold method is used to realize the judgment of intestinal gas health condition, combined with clinical data and individual physiological characteristics, multi-level alarm mechanism is set.

A physiological state monitoring system includes an implantable multi-analyte sensor probe including a first working electrode configured to generate a first electrical signal indicating concentration of a first analyte and a second working electrode configured to generate a second electrical signal indicating a concentration of a second analyte. Monitor system control circuitry is configured to generate a feature vector that includes one or more of a baseline-subtracted analyte value, a first-order temporal derivative, a second-order temporal derivative, or an inter-analyte ratio based on the digital sensor data, access parameters of a machine-learning classification model trained on historical multi-analyte sensor logs and associated ground-truth physiological states, and use the machine-learning classification model to generate, based on the feature vector, a real-time classification label and an associated confidence value identifying a physiological state.

The invention discloses an automatic driving emergency processing method and system based on a brain-computer interface. The method comprises the steps that a dry electrode electroencephalogram cap is adopted to collect resting state electroencephalogram signals of multiple users in a normal driving scene and braking state electroencephalogram signals of the multiple users in various emergency scenes; performing time-frequency domain processing on the resting state electroencephalogram signal and the braking state electroencephalogram signal of each user, constructing a time-frequency domain feature data set, and performing classification training on the hybrid classification model to obtain a hybrid classifier; a dry electrode electroencephalogram cap is adopted to collect electroencephalogram signals of a user in the vehicle driving process in real time, time-frequency domain processing is conducted, electroencephalogram monitoring data are obtained, and a hybrid classifier is adopted to conduct real-time classification on the electroencephalogram monitoring data; and in response to the fact that the real-time classification result is expected braking, a braking instruction is sent to an automatic driving system of the vehicle, so that the vehicle is braked. Through dry electrode electroencephalogram collection and multi-emergency intention recognition, the safety and reliability of automatic driving are remarkably improved.

The application discloses a kind of low signal-to-noise ratio ultra-short time signal classification method and system, and classification method includes the following process: the input sub-sample obtained is extracted, and the feature vector of multiple double-point pairs is obtained, the feature vector is composed of the feature amplitude of multiple double-point pairs;Utilize the feature vector of multiple double-point pairs to classify the low signal-to-noise ratio ultra-short time signal;The acquisition process of the input sub-sample includes: the double-point pair of the narrowband signal of low signal-to-noise ratio ultra-short time signal is sampled, and input sub-sample is obtained;The double-point pair is any two sampling points of low signal-to-noise ratio ultra-short time signal.The application can classify low signal-to-noise ratio ultra-short time signal in real time.

The application discloses an anti-interference enhancement method for high-speed Wi-Fi transmission of a motion camera, and comprises the following steps: acquiring inertial motion data collected by a built-in inertial measurement unit of the motion camera and direction reference information of a receiving end; extracting multi-dimensional motion features based on the inertial motion data; performing real-time classification of a motion mode based on the multi-dimensional motion features, outputting a current motion mode identifier, and at least including a rotation dominant mode, a periodic swing mode and a shock precursor mode and corresponding mode feature parameters; generating a transmission parameter adjustment instruction according to the mode identifier, combining the mode feature parameters and the direction reference information of the receiving end; and performing corresponding transmission parameter feedforward adjustment based on the instruction. The application adopts a response lag limitation which is different from a post-radio frequency feedback, avoids loss and frequent oscillation of a throughput in a high dynamic scene, and improves the wireless link robustness and the real-time performance of video stream transmission in a limit motion environment.

An intelligent camera system with integrated artificial intelligence for real-time object classification and adaptive function control, consisting of: an image sensor unit configured to capture successive image sequences of an observed environment; an optical assembly operationally coupled to the image sensor unit to project incident light onto a sensor surface; at least one processing unit that is arranged in a camera housing and electrically connected to the image sensor unit; a non-volatile memory that is operationally connected to the processing unit and configured to store executable instructions, trained object classification parameters, and control decision data; an image preprocessing unit, which is executed by the processing unit and is configured to normalize, filter, and align successive image frames in time; an artificial intelligence inference unit executed by the processing unit, configured to perform object classification in real time directly on the preprocessed image sequences using the stored trained parameters; a decision control unit executed by the processing unit, configured to generate adaptive control outputs based on classified object attributes such as object category, spatial position, motion properties, and confidence level; and A control interface unit electrically coupled to the decision control unit and configured to transmit adaptive control outputs to one or more functional components of a machine or structure, wherein all image acquisition, classification, decision making and control signal generation takes place locally within the camera housing, wherein the image sensor unit comprises a solid-state image sensor configured to operate at a variable frame rate, which is dynamically adjusted by the processing unit based on the detected scene complexity and object motion characteristics to maintain classification accuracy in real time while reducing the computational load.

The application relates to the technical field of intelligent management and energy consumption prediction of new energy automobile batteries, in particular to an electric vehicle driving range prediction method based on energy consumption decoupling and double-dimension scene matching, which comprises the following steps: acquiring real-time feature vectors of vehicle operation in a low-temperature domain state and preprocessing, adopting a sliding window method based on power gradient to recombine features; defining the boundary of a scene and calibrating a label based on unsupervised clustering, and determining the scene label of a real-time feature vector based on supervised classification; adopting a regression model to perform heterogeneous model prediction scheduling to obtain a predicted driving range; the application logically recombines discrete fragmented data according to power loss gradient, introduces multi-dimensional energy loss features to construct a regression prediction system, defines the boundary of a scene by adopting an unsupervised clustering algorithm, and combines a supervised real-time classification logic to solve the problem of low prediction accuracy of the driving range of an electric vehicle in a low-temperature environment in the prior art.

The present application relates to the technical field of network security, and proposes a three-stage cascaded IPv6 DDOS attack detection and protection method based on deep learning, which acquires a multi-source fusion data set, carries out filtering detection and protection processing based on dynamic rules, inputs a packet-level data set in the multi-source fusion data set into a lightweight packet-level pre-detection model to carry out real-time classification inference and acquire a primary classification result, carries out scheduling decision according to the primary classification result, inputs a flow-level data set in the multi-source fusion data set into a flow-level deep detection model to carry out deep detection processing and acquire a final prediction result, and carries out closed-loop feedback according to the final prediction result. The present application avoids the influence of easy-to-mix categories and decision limitations, and improves detection accuracy and efficiency.

Technologies are described herein for classifying personalized interactions at an application. A method can include receiving and storing user inputs associated with interactions between users of the application, building historical models based on the user inputs to classify the interactions, wherein building a historical model for a particular user comprises aggregating particular user inputs associated with a set of previous interactions between a particular user and other users, in association with a pending interaction for the particular user and during the pending transaction associating a current user input with the historical model for the particular user and based on analyzing the historical model for the particular user, determining that the pending interaction satisfies a condition, and interrupting the pending interaction based on determining that the pending interaction satisfies the condition.