Abstract: Provide are a method for evaluating a human-machine interaction of a vehicle, a system, an edge computing device, and a medium. The method includes: acquiring, in a target driving test scenario, human-factor interaction data and external data, in which the human-factor interaction data is generated based on an interaction between a tester and a human-machine interaction system of the vehicle, and the external data is associated with driving of the vehicle; and evaluating an interaction element in the human-machine interaction system based on the human-factor interaction data and the external data to obtain evaluation data for the interaction element.

Abstract: Provided is an electroencephalogram (EEG) signal preprocessing method, system and terminal device. The method includes: receiving original EEG signals collected by an EEG collection device, data structure of the original EEG signals corresponds to pre-positioned EEG signal channel locations; performing artifact removal and noise removal operations on the collected original EEG signals to obtain pure EEG signals; obtaining event marks of the original EEG signals, dividing the pure EEG signals into multiple segments each containing EEG signals within preset length of time range before and after an event occurs; obtaining, for the segments, the preset analysis indicators to be extracted, performing time-domain analysis to extract time-domain analysis indicators, and performing frequency-domain analysis to extract frequency-domain analysis indicators. The technical solution can improve the processing efficiency of removing noise and artifacts from the original EEG data, thereby improving the quality of EEG data.

Abstract: A method for controlling a signal acquisition electrode, an electroencephalogram, EEG, signal acquisition apparatus, and a medium are provided. The signal acquisition electrode is movably connected to a wearable component of the EEG signal acquisition apparatus. The wearable component is adapted to be worn on a head of a user, and the EEG signal acquisition apparatus further includes a pushing component. The method includes: controlling, when a contact impedance between the signal acquisition electrode and the head is greater than or equal to a first impedance threshold, the pushing component to push the signal acquisition electrode to move towards the head to acquire an EEG signal by using the signal acquisition electrode.

Abstract: Provided are a method and an apparatus for feedbacking a human-machine collaboration state based on virtual-real integration, and an electronic device. Ergonomic data of an operation subject in a human-machine collaboration process for a current operation task and an operation scene image that is obtained by shooting the human-machine collaboration process and at least includes an operation device and a setting parameter of an operation environment are acquired. A human-machine collaboration state recognition is performed based on the operation scene image to obtain target collaboration state data corresponding to the current operation task, and a personnel state recognition is performed based on the ergonomic data to obtain personnel state data of the operation subject. Based on the target collaboration state data and the personnel state data, a state of the human-machine collaboration process is feedbacked.

Abstract: Provided is a personnel on-duty status early-warning method, apparatus, device, system and medium. The method includes: continuously collecting human body data of personnel in an actual working environment; determining on-duty status of the personnel corresponding to the collected human body data based on the obtained human body data by using a state detection model, the state detection model is obtained by pre-training a preset model based on a training dataset, and the training dataset includes human body data and corresponding on-duty status annotation information; performing on-duty status monitoring on the personnel based on the on-duty status determined for the personnel; and outputting early-warning prompt information in response to the on-duty status of the personnel during the on-duty status monitoring meeting a preset early-warning condition. The method can improve the detection accuracy of the personnel on-duty status.

Abstract: An eye movement analysis method comprises: acquiring a first scene video seen by a target user in a preset environment, and simultaneously acquiring eye movement gaze data of the target user in the environment; performing semantic segmentation on the first scene video based on a deep learning algorithm to obtain a second scene video, wherein the second scene video is divided to have eye movement area of interest; superposing the eye movement gaze data with the second scene video to obtain a gaze pixel point corresponding to the eye movement gaze data in the second scene video; and determining the gaze pixel point corresponding to each frame image in the second scene video and outputting eye movement data index of the target user gazing at the eye movement area of interest in combination with time sequence.

Abstract: A method for evaluating and optimizing user experience in human-computer interaction includes: acquiring a multimodal biological signal of a user during human-computer interaction, and preprocessing the multimodal biological signal to extract a fixation position and index parameters of multiple dimensions; standardizing the index parameters, and performing, based on each index parameter and a weight for each index parameter, weighted average to calculate a user experience evaluation score of each dimension; acquiring a weight for the user experience evaluation score, and performing weighted average to calculate an overall user experience evaluation result; visually presenting, based on the overall user experience evaluation result, user experience situation data of the user for a current fixation position; and acquiring a correction parameter of the user, and optimizing, based on the correction parameter, the weights using a machine learning optimization algorithm.

Abstract: A finger interaction trajectory acquisition method and system, and a storage medium are provided. The method includes: acquiring, in response to an individual hand interacting with a target object through a finger, motion posture information continuously collected by a three-dimensional motion capture system to obtain three-dimensional position coordinates of a to-be-measured joint or bone of the individual hand; sequentially determining whether a finger position at each timestamp is located on the target object in a predetermined coordinate system, and storing, in response to determining that a finger interaction occurs, the position coordinates of the distal phalanx as an interaction position point and storing the corresponding timestamp; and drawing a finger trajectory and a finger interaction trajectory.

Abstract: An intelligent drawing method for human machine interaction HMI design prototype includes: importing an HMI design prototype to be tested; obtaining an HTML script of the imported HMI design prototype page, and displaying the prototype page including content blocks on a display interface; automatically recognizing the content blocks on the prototype page by reading codes of the HMI design prototype page in the automatic recognition drawing mode, monitoring block selection operations of experimenter on the display interface, recognizing the corresponding content block as an interaction area based on a position of the block selection operation, automatically marking the recognized content block as the interaction area, and adding the recognized content area in a drawing area list; and automatically detecting interaction operations of a subject in a process of the subject testing the HMI design prototype, automatically associating the interaction operation with the corresponding content block.

Abstract: Disclosed are a sensor data transmission method and a device. The method includes: a periodic signal acquisition apparatus receiving a message requesting for data packet description information from a data receiving end and reporting the data packet description information to the data receiving end, wherein the data packet description information includes: signal type information, the acquisition rate for each type of signal, and the sending rate of a data packet; receiving a data reporting request from the receiving end, and sending a data packet to the data receiving end according to the sending rate of the data packet in the data packet description information, wherein the data packet sent to the data receiving end contains a packet header portion and a load portion, the packet header portion includes a frame header field, a load length field, and a check field.

Abstract: The present disclosure provides an evaluation method, device, and storage medium for intelligent human-machine cooperation system, the method comprises the following steps: recording a real-time objective data of subject during an execution of the intelligent human-machine cooperation system test; inputting the objective data into a pre-trained fitting model to predict and obtain a subjective evaluation of a prediction, the pre-trained fitting model is based on a recorded objective data and subjective evaluation fitting, and the subjective evaluation is obtained based on a first subjective evaluation result of the subject after executing the intelligent human-machine cooperation system test for pre-training; obtaining a real-time human-machine cooperation score based on a predicted subjective evaluation.

Abstract: Provided are a human-machine interaction collection method, apparatus, and system for a wearable extended reality device. Human body state information is obtained by analyzing human body perception data collected. A three-dimensional environment scene corresponding to environmental perception data collected is obtained by modeling the environmental perception data collected. The human body state information and the three-dimensional environment scene are displayed in an integrated manner using an extended reality device. The human body state information and the three-dimensional environment scene that are obtained are transmitted to a cloud center.

Abstract: A system, an electronic device and an optical signal processing method including receiving optical signals by a spectrum analyzer, which outputs a first wavelength range of the optical signals, primary filtering the first wavelength range based on a pre-set wavelength threshold of red light to obtain a second wavelength range, accessing wavelength ranges of ambient light acquired, respectively accessing upper limit values and lower limit values of the wavelength ranges of the ambient light, obtaining a filtering upper and lower limit value respectively based on the upper limit values and the lower limit values, and setting a filtering wavelength range based on the filtering upper limit value and the filtering lower limit value, re-filtering the second wavelength range based on the filtering wavelength range to obtain a target filtering range, filtering the optical signals with the target filtering range to filter out ambient light from the optical signals.

Abstract: The present application provides a method, device, and storage medium for visualizing eye movement data based on gaze trajectories. The method obtains the gaze point position, gaze point sequence, and gaze point trajectory of a subject through collected eye movement data. Based on the angle of the line connecting two adjacent gaze points, the line connecting the two adjacent gaze points is mapped to a visualization graph, and the vertices of the corresponding line connecting individual angles in the visualization graph are connected to form a visualization graph of the frequency of eye movement scanning direction. The present application provides an eye gaze trajectory algorithm through visualization graphs of eye movement scanning direction frequency, which can intuitively and accurately reflect individual eye movement and gaze characteristics.

Abstract: A bioelectrical signal abnormality monitoring method comprises: generating a noise signal having a preset constant frequency; superposing the noise signal onto a right leg drive electrode; using a front-end circuit to preprocess analog signals from a reference electrode and a collecting electrode, and outputting the analog signals to an analog-to-digital converter; using the analog-to-digital converter to convert into digital signals, and transmitting the digital signals to an operation analysis unit; the operation analysis, unit performing band-stop filtering on the digital signals, performing a subtraction operation on the digital signals before and after the band-stop filtering processing to obtain a difference value, storing the difference value in a queue, periodically solving for the RMS of the data in the queue, and based on the RMS and a fitting formula, calculating the impedance of the human body; and judging an electrode connection state according to the impedance of the human body.

Abstract: Disclosed is a multi-light source heart rate measurement apparatus. The measurement apparatus includes: a first optical receiving group, a second optical receiving group, a first light source and a second light source. Distances between the first light source and the first optical receiving group and the second optical receiving group respectively are both a preset resting and first dynamic heart rate measurement interval; the distance between the second light source and the first optical receiving group is a preset resting heart rate measurement interval, and the resting heart rate measurement interval is less than or equal to the resting and first dynamic heart rate measurement interval; the distance between the second light source and the second optical receiving group is a preset second dynamic heart rate measurement interval, and the second dynamic heart rate measurement interval is greater than the resting and first dynamic heart rate measurement interval.

Abstract: Disclosed are a human-computer interaction movement track detection method, device, apparatus, and computer-readable storage medium. The method comprises: segmenting a movement path of a movement target to obtain one or more sub paths; monitoring and recording movement of the movement target in each of the sub paths to obtain a human-computer interaction movement track of the movement target in each of the sub paths; identifying the human-computer interaction movement track of the movement target in each of the sub paths with a determination model corresponding to each of the sub paths; and detecting a human-computer interaction movement track of the movement target based on identification of the human-computer interaction movement track in each of the sub paths.

Abstract: The present application relates to a method, apparatus, device, system and storage medium for collecting spatiotemporal behaviors and generating a spatiotemporal behavior track. The method includes: obtaining a first time series containing a plurality of sampling points; taking one sampling point as a current sampling point; setting a window time, and finding a first sampling point and a last sampling point within the window time; taking a first position as a center of a circle, which is a center point of the reality display device corresponding to the current sampling point, and calculating an angular speed between the first sampling point and the last sampling point; if the angular speed is greater than a preset angular speed threshold, taking the current sampling point as a displacement point; processing the plurality of sampling points as described above to obtain a second time series; drawing a moving track map.

Abstract: The present application relates to a clock quartz oscillator synchronization method, system and apparatus, in which the method includes, when a calculation unit is in network connection, calculating a first deviation between a calculation unit time and a network clock time; updating a fundamental deviation according to the first deviation; updating the calculation unit time and calculating an actual refresh frequency of the calculation unit according to the fundamental deviation; calculating a second deviation between the calculation unit time and a sensor time; and according to the second deviation, updating the sensor time and calculating an actual interruption frequency of the sensor. The present application provides a synchronization method for calculation, estimation, correction, compensation of time deviation caused by the clock quartz oscillator, which has a benefit of time deviation reduction when one or more sensors are in data exchange with one or more calculation units.

Abstract: A method for extracting a black-odorous water body based on a CART classification model includes: selecting a research region, designing sampling points within the region; monitoring relevant chemical indicators of the water body at various sampling points, extracting remote sensing reflectance data of the water body, determining a type of the water body according to a classification standard of relevant chemical indicators for an urban black-odorous water body; comparing and analyzing the remote sensing reflectance data to obtain spectral change features of the black-odorous water body and a general water body; constructing each node of a decision tree according to the spectral change features and based on Gini index, constructing a decision tree classification model to obtain classification results of the black-odorous water body and the general water body, calculating a classification accuracy; analyzing the classification results to obtain spatiotemporal distribution changes of black-odorous water bodies