10 results about "Mental load" patented technology

The invention relates to a brain load identification method based on electroencephalogram signals, and belongs to the technical field of man-machine interaction. Comprising the steps of obtaining electroencephalogram signals in different mental load states and preprocessing the electroencephalogram signals, constructing a feature map, constructing a mental load recognition model, training a network model, inputting a test set and outputting a test result. According to the method, electroencephalogram data representing brain load are extracted by using electroencephalogram signal equipment and are put into a brain load identification model for brain load classification, and feature dependence of time-frequency-space three-dimensional features of electroencephalogram signals can be extracted simultaneously by a three-dimensional wavelet convolution branch of the brain load identification model; due to the fact that the three-dimensional wavelet convolution and the spectrogram convolution are embedded into the double-branch parallel structure of the gating neural network, the brain load model can extract global features and local features at the same time, the problem that in a traditional neural network, the single-dimensional feature recognition rate is low is solved, meanwhile, the calculation complexity of brain load recognition is reduced through a single channel, and the brain load recognition efficiency is improved. And the operation cost is reduced.

The invention discloses a cognitive impairment risk intelligent matching intervention system based on multi-modal data, and belongs to the technical field of cognitive impairment, and the cognitive impairment risk intelligent matching intervention system specifically comprises the following steps: collecting a tactile interaction sequence and a face video data stream when a user executes a cognitive intervention task, and constructing an original multi-modal data set; extracting tactile operation track features and reconstructing a heart rate variability sequence, and generating a synchronous multi-mode feature set; identifying a difference interval of state fluctuation and extracting behavior and physiological features in the interval to form an instant physical and mental load parameter set; in combination with an interaction efficiency index in the task execution record, generating a joint state feature vector, and outputting a personalized adaptation instruction through a pre-trained sub-state-parameter association model; and constructing an adaptive strategy model by using the multi-modal features and an adaptive instruction to realize millisecond-level dynamic adjustment from the real-time multi-modal features to task parameters. According to the method, real-time perception and accurate matching of the cognitive emotion load of the user are realized, and the individuation degree and instantaneity of intervention are improved.

The invention belongs to the technical field of pilot mental load assessment design, and particularly relates to a pilot mental load assessment model construction method based on multi-physiological parameter fusion, which comprises the following steps: step 1, collecting physiological parameters of a pilot under different mental load levels, and establishing a corresponding relationship between the physiological parameters of the pilot and the mental load levels; the mental workload levels comprise high, medium and low levels; the physiological parameters comprise eye movement, electrocardio and electroencephalogram characteristics; step 2, based on the established corresponding relation between the physiological parameters of the pilot and the mental load level, using a Transform model to construct a pilot mental load assessment model, using a convolutional neural network (CNN) method to optimize the pilot mental load assessment model, obtaining a Transform + CNN pilot mental load assessment model, and establishing a pilot mental load assessment model; and the Transform + CNN pilot mental load evaluation model is further optimized through a feature level fusion optimization method, and a feature level fusion Transform + CNN pilot mental load evaluation model is obtained.

The invention discloses a method for measuring a brain load forward effect threshold based on beta high-frequency band time specificity, which is characterized by comprising the following steps of: setting a plurality of test tasks with different brain load levels from low to high, and collecting original electroencephalogram data of a tested person under the different brain load levels; preprocessing the original electroencephalogram data, and calculating an average waveband power index value of the tested person in a beta high-frequency waveband under different mental load levels according to the preprocessed electroencephalogram data; the minimum time segment sequence number ti with the statistical significance difference between the two conditions of different mental load levels and the time segment sequence number difference Adjti between the adjacent mental levels are calculated, the mental load level i * corresponding to the minimum Adjti is obtained, and i * is the mental load forward effect level threshold value of the tested person; the method has the advantage of objectively and accurately evaluating the mental load positive effect threshold value of the tested person by analyzing the beta high-frequency band time specificity change in the electroencephalogram signal data.

The embodiment of the invention provides a mental load threshold determination method and system based on manager risk preference, and relates to the technical field of human factor engineering, system design and human resource management, and the method comprises the steps: collecting not less than 30 task samples in the same task scene in a target field, obtaining mental load intensity data and a corresponding task error rate, wherein mental load intensity is calculated based on a multi-resource theoretical model; establishing a monotonically increasing mental load intensity-error rate linear regression model in a set interval by adopting a least square method, and verifying the significance of the model through F test or t test; the acceptable maximum error rate input by the manager is substituted into the mental load intensity-error rate linear regression model, and an analytical method is used for inverse solution to obtain a mental load threshold value; and outputting a mental load threshold value for personnel post compilation, task process design or man-machine function distribution. And a scientific and quantitative decision basis is provided for man-machine function distribution, post compilation and process optimization in a system design stage.

The invention belongs to the technical field of health monitoring, and particularly relates to a brain load real-time evaluation method and system based on wrist temperature change characteristics, and the method comprises the steps: obtaining the wrist skin temperature; analyzing the obtained temperature to obtain a temperature change characteristic; according to the obtained temperature change characteristics, brain work duration is considered, and a brain load real-time evaluation model is constructed; calculating a mental load score according to the constructed mental load real-time evaluation model; and judging the current mental load state based on the obtained mental load score, and completing mental load real-time evaluation based on the wrist temperature change characteristics.

The invention relates to the technical field of man-machine interaction, and discloses a multi-modal physiological feature-based cross-individual mental load personalized recognition system and method, and the system comprises a data processing module, a first model construction module, a second model construction module and a model evaluation module. The data processing module is used for acquiring a multi-modal physiological signal and subjective mental load of an operator in the process of executing long-time continuous complex multiple tasks, and extracting a multi-modal data set with consistent time sequence; the first model construction module and the second model construction module construct a cross-individual mental load recognition model for the physiological features output by the feature extraction module based on domain adversarial mechanism alignment inter-domain feature distribution and dual-classifier adversarial mechanism alignment inter-category feature distribution, and the model evaluation module recognizes a result according to the mental load. According to the method, individual difference adaptation and category semantic unification are realized, the cross-individual and cross-scene generalization ability is improved, and targeted identification of individuals is realized, so that the identification accuracy is improved.

The invention discloses chewing gum based on composite stimulation as well as a preparation method and application of the chewing gum. Comprising the following raw material components in parts by weight: 0.09 to 0.105 part of 1, 8-cineole, 40 to 45 parts of gum base, 25 to 35 parts of D-mannitol, 8 to 15 parts of erythritol, 12 to 18 parts of purified water, 1 to 2 parts of caprylic / capric triglyceride, 0.3 to 0.8 part of soya bean lecithin, 0.2 to 0.4 part of Arabic gum and 0.05 to 0.1 part of carnauba wax. By organically combining composite stimulation with computerized task training, the limitation that a traditional nerve stimulation technology needs professionals and equipment is avoided, and work memory training is safe, effective and easy and convenient to operate. The device is especially suitable for daily training of people needing cognition improvement, such as people with high mental load and people with hypomnesis.

One or more example embodiments of the present invention describes a method for monitoring a person in an environment, including integrating the person into the environment, wherein the person has a task to solve in the environment, measuring with a sensor system a number of physical conditions of the person while the person interacts with the environment, the sensor system providing a sensor-dataset including measured physical values about the person from which mental conditions of the person can be inferred, generating assessment-data from the sensor-dataset, the assessment-data reflecting at least one of an ability of the person to accomplish the task or the mental load of the person while solving the task, repeating the measuring and the generating a plurality of times and outputting the generated assessment-data or data based on the generated assessment-data.

The invention discloses an electroencephalogram monitoring method based on mental load prediction. The method comprises the following core steps: constructing a mental load prediction model; historical time domain data, frequency domain data and historical behavior feedback data of a monitored person in different mental load scenes collected by electroencephalogram monitoring equipment are obtained, key features are extracted from the data, and a model capable of predicting the current mental load level in real time is obtained through training; secondly, collecting an initial electroencephalogram signal of a monitored person in real time through electroencephalogram monitoring equipment, and inputting the initial electroencephalogram signal into the mental load prediction model to predict the mental load level; finally, parameters of the electroencephalogram monitoring equipment are adjusted in a self-adaptive mode according to the predicted load level, and accurate collection and analysis early warning of electroencephalogram signals of the monitored person are completed based on the adjusted parameters. According to the method, the brain state is pre-judged in advance and the monitoring parameters are dynamically adapted through the cooperation of brain load prediction and electroencephalogram monitoring, so that the interference of different brain fluctuations on the electroencephalogram monitoring precision is effectively reduced.