CN-119745319-B - Cognitive state evaluation method in closed environment

CN119745319BCN 119745319 BCN119745319 BCN 119745319BCN-119745319-B

Abstract

The disclosure relates to a cognitive state evaluation method, a device, an electronic device and a storage medium in a closed environment. The method comprises the steps of collecting emotion cognition characteristics and attention cognition characteristics based on a preset emotion cognition model and a preset attention cognition model respectively, performing dimension reduction processing on the emotion cognition characteristics and the attention cognition characteristics, and evaluating the cognition state based on a support vector machine SVM classifier learning cognition characteristic model by taking the emotion cognition characteristics and the attention cognition characteristics subjected to the dimension reduction processing as input to generate an evaluation result. The brain cognitive state is evaluated from subjective and objective angles by adopting a self-evaluation scale, the measured brain electrical characteristics and the measured behavioral characteristics, and is identified and classified by using a machine learning method, so that the brain evaluation state is evaluated, and a method basis is provided for the detection of the brain cognitive state under the condition of long-term closed operation.

Inventors

CHANG QI
ZHANG LIJIAN
WU JINTAO
YI WEIBO
CHEN YUANFANG
LIU HAO
GE XIAOFEI

Assignees

北京机械设备研究所

Dates

Publication Date: 20260512
Application Date: 20241122

Claims (5)

1. A method of cognitive state assessment in a closed environment, the method comprising: Based on the preset emotion cognition model and the preset attention cognition model respectively, collecting emotion cognition characteristics and attention cognition characteristics, wherein the collecting emotion cognition characteristics based on the preset emotion cognition model further comprises: Performing quantitative measurement based on the anxiety self-evaluation SAS, the depression self-evaluation SDS, the psychological stress self-evaluation PSET and the symptom self-evaluation SCL-90 to obtain a SAS score, an SDS score, a PSET score and a somatic, compulsive, interpersonal relationship sensitive, depression, anxiety, hostility, horror, paranoid and psychotropic factor score in the SCL-90; Performing behavioral characteristics and electroencephalogram characteristics ERP extraction based on emotion stroop electroencephalogram experiments to obtain the preset number of emotional behavioral characteristics and the amplitudes of ERP components; the acquisition of the attention deficit characteristics based on the preset attention deficit model further includes: Designing an attention network ANT electroencephalogram experiment, and acquiring behavioral characteristics of attention oriented network efficiency, attention alert network efficiency and attention execution control network efficiency and corresponding electroencephalogram characteristics based on the attention network ANT experiment after a simulated driving task with preset duration is tested; Performing dimension reduction treatment on the emotion cognition characteristics and the attention cognition characteristics based on a factor analysis method to obtain dimension reduced emotion cognition characteristics and attention cognition characteristics; Respectively learning the emotion cognition characteristics and the attention cognition characteristics after dimension reduction by using a multi-core learning support vector machine, and establishing an emotion state and attention level classification model to realize evaluation of the emotion state and the attention level; calculating a combined kernel vector based on a kernel function vector and a weight vector thereof obtained by EasyMKL algorithm, inputting the combined kernel vector into a Support Vector Machine (SVM) classifier, and completing a classification experiment by combining a testing set to obtain an emotion state evaluation result and an attention level evaluation result; And according to the emotion state evaluation result and the attention level evaluation result, evaluating the cognitive state of the tested in the closed environment, and generating an evaluation result.
2. The method of claim 1, wherein the method further comprises: recruiting a preset number of experimenters to participate in emotion experiments and attention experiments; In emotion induction experiments, using movie fragments in a preset emotion video database to induce specific positive, neutral and negative emotions of a tested person for emotion induction, and completing training sample collection; in the attention experiment, based on an attention network ANT brain electrical experiment, after one hour of simulated driving task, the fatigue self-evaluation result and ANT brain electrical data of a tested are collected, and the training sample collection is completed.
3. A cognitive state assessment device in a closed environment based on the method of claim 1 or 2, characterized in that the device comprises: The feature acquisition module is used for acquiring emotion cognition features and attention cognition features based on a preset emotion cognition model and a preset attention cognition model respectively; the dimension reduction processing module is used for carrying out dimension reduction processing on the emotion cognition characteristics and the attention cognition characteristics; The cognitive state evaluation module is used for taking the emotion cognitive characteristics and the attention cognitive characteristics which are subjected to the dimension reduction processing as input, evaluating the cognitive state based on a Support Vector Machine (SVM) classifier learning cognitive characteristic model, and generating an evaluation result.
4. An electronic device, comprising Processor, and A memory having stored thereon computer readable instructions which, when executed by the processor, implement the method according to claim 1 or 2.
5. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, implements the method according to claim 1 or 2.

Description

Cognitive state evaluation method in closed environment Technical Field The disclosure relates to the field of electroencephalogram application, in particular to a cognitive state evaluation method, a device, electronic equipment and a computer readable storage medium in a closed environment. Background In many work processes, an operator or staff is required to work and live in a particular closed environment. Researches show that the closed isolation environment is different from the conventional environment of human life, the conditions of social isolation and spatial sealing exist, and abnormal reactions such as brain cognitive functions can occur for people in the closed isolation environment. Electroencephalograms have recently been used in two studies of closed environments (space), exploring how closed environments affect the physiological and emotional states of the brain. One study found that three months of isolation resulted in a general decrease in brain activity, as well as a decrease in physical state and aggressiveness. Another study investigated the effect of the closed environment on stress. This study evaluates the brain activity of the participants in 6 different countries living in a simulated spacecraft for 520 days with complete isolation, and the study found that the global cerebral cortex's alpha and beta activity was significantly reduced from the start to the end of the mission. A recent research on the mental health of resident training officers and soldiers in a fully-enclosed environment of a plateau discovers that the fully-enclosed environment has a certain influence on the mental health of resident training officers and soldiers, and is mainly expressed in aspects of emotional agitation, anxiety, depression and the like. A good level of attention of the operator in the task is an important condition for completing the job. Posner et al (2002,2014) first subdivided the attention network into three sub-networks, alert (Alerting), directional (Orienting) and perform control (executive control). Note that these three networks represent the ability of an individual to obtain and maintain alertness to a certain type of information or goal, to selectively pay attention to externally useful information, and to handle conflicting information. The three components of attention may be measured by an attention network efficiency test (AttentionNetwork Test, ANT) developed by Fan et al. ANT is used by a large number of researchers and has proven to be an effective tool for measuring the efficiency of various attention networks (Macleod et al 2010). Note that the network experimental paradigm has been demonstrated by a relatively adequate theoretical demonstration of yield and experimental study, demonstrating that it is widely used in psychology, neuroscience and medicine due to its high operability and short testing time. ANTs rely on performance measurements of the stimulus under different conditions, such as response time and accuracy, and calculation of differential scores for target alertness, orientation, and performance control. Accordingly, there is a need for one or more approaches to address the above-described problems. It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art. Disclosure of Invention It is an object of the present disclosure to provide a cognitive state assessment method, apparatus, electronic device, and computer-readable storage medium in a closed environment, which overcome, at least in part, one or more of the problems due to the limitations and disadvantages of the related art. According to one aspect of the present disclosure, there is provided a cognitive state assessment method in a closed environment, including: Based on a preset emotion cognition model and a preset attention cognition model respectively, acquiring emotion cognition characteristics and attention cognition characteristics; performing dimension reduction treatment on the emotion cognition characteristics and the attention cognition characteristics; and taking the emotion cognition characteristics and the attention cognition characteristics which are subjected to the dimension reduction treatment as input, and evaluating the cognition state based on a Support Vector Machine (SVM) classifier learning cognition characteristic model to generate an evaluation result. In an exemplary embodiment of the present disclosure, the method for acquiring emotional cognitive characteristics based on a preset emotional cognitive model further includes: Performing quantitative measurement based on the anxiety self-evaluation SAS, the depression self-evaluation SDS, the psychological stress self-evaluation PSET and the symptom self-evaluation SCL-90 to obtain a SAS score, an SDS score, a PSET