19 results about "Work memory" patented technology

Mechanisms are disclosed for detecting one or more defects in a system In-system and externally observable events are received. Active state information is derived from the in- system and externally observable events. If a memory update is required based on facts from the semantic memory, an episodic memory and a working memory are updated. Actions required from a procedural memory are extracted based on the updated episodic memory and the updated working memory. A prompt is executed on a generative language model to produce a model reasoning output. Reproduction steps are derived from the episodic memory, based on a determination that a defect is present from the model reasoning output. A defect signal is generated and provided to a testing user.

A system and method are disclosed for securely transferring or storing protected working memory outside an owner thread while maintaining full encryption throughout its lifecycle. The protected working memory has an encrypted data component and a keystream component containing dynamically updated encryption information used for per-cycle decryption and re-encryption. A hardened cryptographic subsystem, such as a Trusted Execution Environment (TEE), Secure Element (SE), TPM, or HSM, performs authenticated encryption using device-bound key material to wrap either (i) the keystream component alone or (ii) the entire protected working memory blob. The wrapped object is suitable for storage or transfer across threads or in external memory, without exposing plaintext or keystream material. When restoring, an authorized owner thread supplies a key handle to the hardened subsystem to securely decrypt and reconstruct the protected working memory only within a guarded heap. At no point are plaintext contents or keystreams available to the operating system or user-accessible memory.

The application relates to the cross field of biomedical engineering and artificial intelligence, and discloses a personalized brain power development training method based on electroencephalogram signals. The method comprises the following steps: collecting resting state and task state multi-channel electroencephalogram signals of a subject, constructing a functional connection matrix after pretreatment, identifying individualized weak connection target points through difference operation and cluster analysis; matching a neural feedback training protocol from a preset paradigm library based on the target points, and generating a feedback signal by extracting a target point synchronicity feature in real time during training to guide the subject to actively enhance the weak connection; updating the model after each training and dynamically optimizing subsequent parameters to form a closed-loop regulation. The application improves working memory and attention through individualized targeted training, induces neural plasticity, and realizes efficient and accurate brain power development.

This invention discloses an embodied intelligent agent and a method for ensuring its operational security. The method includes: constructing a hybrid long-short-term security memory for the embodied intelligent agent, comprising a long-term security memory storing cross-task security experiences and a short-term working memory recording the current task's temporal trajectory; performing forward predictive reasoning based on the long-term security memory to retrieve security experiences relevant to the current context and perform contextual verification on candidate actions output by the embodied intelligent agent; triggering an interception mechanism to prohibit the execution of candidate actions when a contextual risk is detected; and performing backward reflective reasoning based on the short-term working memory to infer temporal security constraints during task execution by analyzing global task instructions and verifying temporal risks by tracing back historical trajectories; triggering a replanning mechanism and generating a corrective action sequence when a temporal risk is detected. Thus, by designing bidirectional security reasoning, the security of the embodied intelligent agent's task execution is effectively improved.

System for diagnosing a battery cell (204) of a vehicle (100), comprising: a processor (302) and a working memory (304) or data storage (308) comprising an algorithm or computer instructions which, when executed by the processor (302), perform an operation comprising: Determine that a current flows through a current collector (206, 214) of the accumulator cell (204), Generating a mechanical excitation of the current collector (206, 214), Determining the amplitude of a voltage across the accumulator cell (204) based on mechanical excitation, and Determining the presence of a crack or separation of a foil of the current collector (206, 214) on the basis of the amplitude of the voltage across the accumulator cell (204).

This application proposes a robot handling method, device, electronic device, and storage medium based on knowledge-enhanced fusion memory. The method includes: retrieving historical working memory and fusing it with the current state, enabling the robot to refer to past experience and extract global motion patterns and contextual relationships from historical operation data; constructing a structured layout to enhance the robot's perception dimension from simple object recognition to understanding the dynamic spatiotemporal relationships between objects, so that the robot's actions are no longer isolated point-to-point movements; and generating control commands by fusing memory-enhanced feature vectors with the structured layout to achieve precise and compliant control, thereby comprehensively improving the success rate and safety of robot handling.

The application discloses an optoelectromechanical system for enhancing working memory, which comprises a transcranial support module, a light therapy module, a blood oxygen and heart rate detection module and a main control module, wherein the light therapy module is used for emitting therapeutic light waves to the head of a user; the blood oxygen and heart rate detection module is used for detecting the blood oxygen and heart rate of the user, and comprises the following steps: collecting PPG signals of the user, calculating a signal quality score, when the signal quality score is less than a score threshold value, if the absolute value of the light intensity amplitude difference between the current sampling point and the previous sampling point of the PPG signal exceeds a first threshold value, it is judged that the current sampling point is an abnormal point, the current sampling point is repaired, otherwise, the PPG signal is subjected to adaptive Kalman filtering; the blood oxygen value, heart rate value and standard deviation of the interval of the user are calculated according to the filtered PPG signal; and the main control module is used for adjusting the light intensity, duty cycle and treatment time of the therapeutic light waves output by the light therapy module according to the blood oxygen value, heart rate value and standard deviation of the interval of the user. RR RR ​​

This invention discloses a digital identity verification method and system based on layered truth verification, belonging to the fields of information security and discrete logic technology, and is particularly suitable for dynamic identity status management in financial anti-fraud scenarios. Existing technologies employ a "static snapshot + probability judgment" architecture, which cannot address the verification requirements of dynamically changing identity status over time. This invention, based on the underlying theory of Discrete Spatiotemporal Scaling Law (T-DS), layers identity-related propositions into a first type of proposition (structural propositions, permanently locked, corresponding to the T-DS anchor layer) and a second type of proposition (factual propositions, dynamically falsifiable, corresponding to the Working Memory layer). Through modules such as parent quarantine, clone verification, dual-track memory management, and chain auditing, it achieves a unity between the unforgeability of identity anchors and the dynamic updability of identity status. The system includes a proposition layering module, a first-type verification module, an evidence structure module, a contradiction detection module, a weight comparison module, a truth database module, an audit chain module, a parent quarantine module, a clone verification module, and a memory management module.

This disclosure relates to a query processing method, apparatus, device, and medium based on a self-evolving memory agent, belonging to the technical field of data processing. The method includes: responding to a current query request output by a first user, invoking a data processing model under a target configuration node within a set memory configuration period, and extracting a target memory feature set matching the current query request; wherein the feature elements of the target memory feature set are associated with the target configuration node; invoking a preset data detection model, using the target configuration node and the memory features as input conditions, to obtain a current working memory sequence; wherein the current working memory sequence is used to characterize the solution result of the current query request.

The invention discloses an FPGA resource scheduling method for automatic driving perception decision decoupling, and relates to the technical field of automatic driving. The method specifically comprises the following steps of: receiving multi-source heterogeneous sensor data by utilizing a reconfigurable sensory memory interface module of a dynamic logic area at the front end of an FPGA (Field Programmable Gate Array), executing time-space synchronization, and performing normalized projection to obtain a driving situation dynamic map data frame; a dual-port cache region is constructed by utilizing a cognitive fusion and working memory module of FPGA on-chip high-speed storage resources, and a multi-channel layered space-time tensor serving as an on-chip data exchange medium is maintained and refreshed in real time; a cognitive decision module of a rear-end static logic area is used for reading the dynamic map, reasoning is conducted in combination with priori knowledge called by a long-term memory interface, and a control instruction is generated; the dynamic map is defined as a standardized boundary of software and hardware interaction, and only a logic circuit of the sensory memory interface module is refreshed when the configuration of the sensor is changed. The objective of the invention is to realize perception and decision decoupling through a standardized architecture of a hardware bottom layer and improve the real-time performance and robustness of a system.

The invention discloses a work memory training method, system and device based on a brain-computer interface, and a storage medium, and belongs to the technical field of brain-computer interfaces. The attention method is carried out on the basis of electroencephalogram signal data, measured in real time through a brain-computer interface, of a trainee, movement of a training role is controlled on the basis of an attention numerical value by providing the training role, at least two target objects are further displayed in an observable scene at intervals, and the target objects are different. The sequence of the target objects is firstly displayed for a period of time in the observable scene, then the target objects are randomly displayed one or more times, the target objects displayed in sequence are sequential objects, and the target objects not displayed in sequence are non-sequential objects. When the method, the system, the equipment and the medium are used for training, a trainee needs to remember the target objects and the sequence of the target objects by means of working memory. In addition, the trainee needs to send a second instruction at a proper time for sequential objects, and the trainee needs to control not to send the second instruction for non-sequential objects and non-target objects, so that the attention of the trainee is further improved.

This invention discloses a cognitive fatigue grading assessment method based on multidimensional performance characteristics, belonging to the field of cognitive fatigue assessment technology. The invention pre-collects multiple training samples to construct a feature dimensionality reduction model, including variable standardization and screening templates, as well as principal component and comprehensive performance index calculation templates. This model is used for variable screening and extraction of four principal components and comprehensive performance indicators. Baseline data is obtained through the feature dimensionality reduction model. During monitoring, a sliding window captures interactive data in real time and obtains real-time data through the feature dimensionality reduction model. A priority-based ladder-style judgment logic is executed to judge the cognitive fatigue state of the test subjects in reverse order, thereby identifying different fatigue states. This invention is used to solve the problem of detecting cognitive fatigue under continuous working memory tasks, determining whether subjects or staff are experiencing different degrees of fatigue and issuing early warnings. It is also applied to the determination of cognitive fatigue in radar monitoring work.

This application discloses a method, application method, and apparatus for determining a cognitive load prediction model, relating to the field of human-computer interaction technology. The method includes acquiring EEG signals, task difficulty of the main task, working memory capacity of the subjects, and performance data of secondary tasks from several subjects; preprocessing the EEG signals and extracting multi-dimensional EEG features; combining the secondary task performance data with task difficulty and working memory capacity, using a residual-mixed effects model to generate a comprehensive cognitive load score, and mapping it to a comprehensive cognitive load score level using a percentage method; constructing a time-series dataset based on the multi-dimensional EEG features and corresponding levels; using the multi-dimensional EEG features as input and the corresponding levels as labels, training a CNN-Bi-LSTM-Attention network using a cross-entropy loss function to obtain a trained cognitive load prediction model. This application can use this model to predict cognitive load levels.

The present application belongs to the field of human-computer interaction and computer vision technology, aiming at the problem of existing fatigue data collection method that behavior representation is lagging and label confidence is low, a task-driven fatigue data collection method in intelligent interaction scene is disclosed. First, set multi-period collection plan to obtain sleep quality, and collect subjective scale score, heart rate characteristics and facial video under baseline state; then, perform progressive active fatigue induction containing visual, working memory and eye movement search load, and collect the same data in the control stage again; then, carry out triple cross-validation on subjective score, heart rate characteristics and eye movement characteristics; finally, assign wakefulness / fatigue label to facial video sequence verified. The present application overcomes the lagging behavior representation by progressive task-driven regulation, filters out subjective pseudo-label noise by multi-modal strict cross-validation, and constructs a pure visual modal fatigue detection data set with objective physiological benchmark support.

The application provides a working memory quantitative prediction method based on respiratory-electroencephalogram coupling characteristics and adaptive causal inference, and belongs to the technical field of biomedical signal processing and artificial intelligence. In order to solve the problems that the prior art cannot capture the nonlinear causal dependence between respiration and electroencephalogram and the deep learning model lacks task-specific design, the application synchronously collects sleep period electroencephalogram, nasal airflow, chest and abdominal respiratory movement and snoring vibration signal; extracts the snoring spectrum centroid frequency and calculates the slow wave suppression time constant through the exclusive index mapping; adopts the directional transfer entropy of the dynamic threshold to perform nonlinear causal inference; deeply embeds the physiological parameters and causal indicators into the coupling architecture composed of the snoring modulation graph convolution, the causal gated Transformer and the snoring perception multilayer perception machine, and designs the dynamic gated multi-task output and the ablation perception loss function. The application can realize quantitative prediction of reaction time, accuracy and comprehensive cognitive score, and has the characteristics of high precision and adaptability.

Method for operating a control device (CD), in particular a control device (CD) for detecting living beings or objects in an area, wherein the control device (CD) has a processor (1) and a working memory (3), a first interface (7) for receiving measured values ​​(x_i) and a second interface (9) for outputting a result (E), wherein the method comprises the following steps: - providing a respective measured value (x_i) and a decision value (β_i) to the working memory (3), wherein, based on the respective decision value (β_i) and the measured value (x_i), a partial result (p_i) is calculated using the processor and the partial result (p_i) is provided to the working memory (3), wherein the working memory (3) is configured to receive the respective decision value (β_i), the respective partial result (p_i) and the respective measured value (x_i);Whereby for i=1 to i=N the following step is performed:- Calculating a further partial result (p_i+1) from a further measured value (x_i+1), the further decision value (β_i+1) and the partial result (p_i) from the respective preceding step (i), Whereby after i=N steps the partial result (p_N) is provided as the result (E) to the second interface (9).;

The application belongs to the technical field of image processing, and provides a brain function magnetic resonance imaging head motion correction method, device, equipment and medium, wherein the method comprises: acquiring a brain function magnetic resonance image, processing the brain function magnetic resonance image through a head motion correction model to obtain a head motion correction result; wherein the head motion correction model generates a target deformation image through a smoothing deformation field, and then performs sampling and time sequence enhancement processing to obtain a training sample, adopts a visual cortex-like topological feature space information distribution mechanism and a prefrontal cortex-like working memory characteristic time sequence information coherence mechanism to perform spatial perception logic and time sequence context association on the training sample, and adopts a bidirectional optical flow network and a back-like attention network to select a characteristic weight adaptive distribution mechanism, and performs self-supervised fine-tuning on real data. Through the above scheme, the precision and robustness of brain function magnetic resonance imaging head motion correction are improved.