Team training assessment method and device based on novel team building and collaborative tasks

Abstract

This invention discloses a team training assessment method and apparatus based on novel team building and cooperation tasks, belonging to the field of team building and cooperation training assessment technology. The method includes: assessing team members' personality traits based on an adult attachment scale; assessing team members' dominance based on the Big Five personality traits scale and a logical dominance quantification formula; conditionally grouping team members according to test score sequences, attachment type label sequences, and logical dominance intention score sequences based on a dual psychological compatibility constraint grouping strategy; conducting ability tests on team cooperation groups based on a forced dependency cooperation training task, and collecting multimodal physiological signals using LSL technology; synchronously collecting LSL signals after progressively challenging training; and evaluating team training results based on a team cooperation ability assessment model. This invention is a team training assessment method that transforms individual ability and personality characteristic assessment results into specific team building strategies.

Description

Technical Field

[0001] This invention relates to the field of team building and collaborative training assessment technology, and in particular to a team training assessment method and apparatus based on novel team building and collaborative tasks. Background Technology

[0002] With the rapid development of information technology and artificial intelligence, the production and task patterns of modern society are undergoing profound changes. In key areas such as education, business management, medical surgery, and emergency rescue, work patterns have gradually shifted from individual operations to highly collaborative teamwork models involving multiple people. Faced with increasingly complex, dynamic, and uncertain task environments, the cognitive and execution capabilities of a single individual are often insufficient to meet various challenges. High-quality teamwork, through information sharing and complementary strengths among members, can significantly improve task completion efficiency and decision-making quality. Therefore, teamwork has become a core competency for solving complex problems in modern society.

[0003] Given the importance of teamwork, how to improve team effectiveness through effective team grouping, designing scientific training methods, and objectively and accurately evaluating training results has high scientific research value and practical significance. Effective training and evaluation can not only identify weaknesses in team collaboration and optimize personnel allocation and division of labor strategies, but also provide a scientific basis for selecting high-performing teams.

[0004] However, despite the consensus on the importance of teamwork, current methods for assessing the effectiveness of team training still have significant limitations. Existing assessment systems mainly rely on traditional psychological tests and behavioral observations. These methods are mostly post-hoc assessments and heavily depend on participants' self-reports or observers' subjective judgments, making them highly susceptible to social desirability effects or observational biases. They struggle to objectively and in real-time reflect the rapidly changing psychological states and cognitive loads among team members during collaboration. At the physiological level, although neuroscience research has confirmed that inter-brain synchronization (IBS) is an important indicator of teamwork levels, and electroencephalography (EEG) hyperscanning technology offers the possibility of observing inter-brain communication, current team training assessments still lack the systematic application of objective physiological signals such as EEG. The few existing studies mostly remain at the stage of simple statistical analysis based on correlation analysis, lacking technical solutions that can integrate multimodal physiological characteristics and utilize neural network models to objectively and quantitatively assess the effectiveness of team training.

[0005] In the existing technology, there is a lack of a team training assessment method that can transform the assessment results of individual abilities and personality traits into specific team building strategies. Summary of the Invention

[0006] To address the technical problems of existing technologies, such as the lack of psychological consideration in team formation strategies leading to high internal friction in cooperation, the difficulty in designing cooperative tasks to induce deep collaboration, and the reliance on subjective reports and the inability of single-modal data to comprehensively reflect the cooperation mechanism, this invention provides a team training and evaluation method and apparatus based on novel team formation and cooperative tasks. The technical solution is as follows: On the one hand, a team training and evaluation method based on novel team building and collaborative tasks is provided. This method is implemented by a team training and evaluation device and includes: Based on a mandatory dependency-based collaborative training task, the team members' abilities were tested, and the test score sequence was recorded. Based on the adult attachment scale, the personality traits of team members were assessed to obtain the attachment type label sequence of team members; Based on the Big Five personality scale and the logical dominance quantification formula, the dominance of team members is evaluated to obtain the logical dominance intention score sequence of team members; Based on a dual psychological compatibility constraint grouping strategy, team members are conditionally grouped according to the test score sequence, attachment type label sequence, and logical dominance intention score sequence to obtain team cooperation groups; Based on a mandatory dependency-based cooperative training task, the team cooperation group was tested for ability, and LSL technology was used to collect multimodal physiological signals to obtain baseline task score sequences and baseline task physiological data. Based on a mandatory dependency-based collaborative training task, progressively challenging training was conducted on the team collaboration group. After training, the group was tested and LSL data was collected simultaneously to obtain the final evaluation score sequence and final evaluation physiological data. Based on the team collaboration ability assessment model, team training is evaluated according to baseline task scores, baseline task physiological data, final evaluation scores, and final evaluation physiological data to obtain training evaluation results.

[0007] On the other hand, a team training evaluation device based on novel team building and cooperation tasks is provided. This device is applied to a team training evaluation method based on novel team building and cooperation tasks. The device includes: The initial competency assessment module is used to test the competencies of team members based on a mandatory dependency-based collaborative training task and record the test score sequence. The attachment assessment module is used to assess the personality traits of team members based on an adult attachment scale and obtain the attachment type label sequence of team members. The dominance assessment module is used to assess the dominance of team members based on the Big Five personality traits scale and the logical dominance quantification formula, and to obtain the logical dominance intention score sequence of team members. The team member grouping module is used to group team members based on a dual psychological compatibility constraint grouping strategy, according to the test score sequence, attachment type label sequence, and logical dominance intention score sequence, to obtain team cooperation groups; The first information acquisition module is used to test the ability of team cooperation groups based on the mandatory dependency cooperative training task, and to use LSL technology to acquire multimodal physiological signals, obtain baseline task score sequences and baseline task physiological data. The second information acquisition module is used to implement progressive difficulty training for team cooperation groups based on mandatory dependency cooperative training tasks, test after training and collect LSL data simultaneously to obtain the final evaluation score sequence and final evaluation physiological data. The training comprehensive evaluation module is used to evaluate team training based on the team collaboration ability evaluation model, using baseline task scores, baseline task physiological data, final evaluation scores, and final evaluation physiological data to obtain training evaluation results.

[0008] On the other hand, a team training and evaluation device is provided, the team training and evaluation device comprising: a processor; a memory storing computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, any one of the methods described above in the team training and evaluation method based on novel team building and cooperation tasks is implemented.

[0009] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored therein, the at least one instruction being loaded and executed by a processor to implement any of the above-described methods for team training and evaluation based on novel team building and collaboration tasks.

[0010] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following: This invention proposes a team training assessment method based on novel team building and collaborative tasks. Through the proposed scientific team formation strategy based on psychological attachment safety complementarity and ability stratification, the subjects are divided according to their ability scores. In the random sampling process based on constraint satisfaction problems, a grouping strategy based on dual psychological compatibility constraints is adopted, including emotional compatibility constraints and attachment safety complementarity constraints, to ensure psychological attachment safety complementarity and ability stratification complementarity. Based on the mandatory dependency cooperative task architecture, two types of mandatory dependency cooperative tasks are designed, including cooperative task A and cooperative task B. The complete control freedom is decomposed and distributed to different members to build a mandatory cooperative environment that must rely on high-frequency interaction to complete. This invention utilizes LSL technology to temporally align three types of physiological signals—EEG, EOG, and EMG—and calculate various feature values. A team collaboration ability assessment model constructed using a Transformer model is trained to perform binary classification on the physiological characteristics of subjects' baseline and final assessment states. Classification accuracy is used as an objective indicator of changes in neural plasticity, establishing a validation model linking physiological pattern changes with improved behavioral performance. This invention is a team training and assessment method that transforms individual ability and personality characteristic assessment results into specific team-building strategies. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a team training and evaluation method based on a novel team building and collaboration task provided by an embodiment of the present invention; Figure 2 This is a block diagram of a team training and evaluation device based on a novel team building and cooperation task provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a team training and assessment device provided in an embodiment of the present invention. Detailed Implementation

[0013] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0014] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0015] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0016] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0017] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0018] This invention provides a team training and evaluation method based on novel team building and collaborative tasks. This method can be implemented using a team training and evaluation device, which can be a terminal or a server. Figure 1 The flowchart shown is for a team training and evaluation method based on novel team building and collaborative tasks. The processing flow of this method may include the following steps: S1. Based on a mandatory dependency-based collaborative training task, conduct ability tests on team members and record the test score sequence; Among them, the mandatory dependency-based cooperative training tasks include team cooperation task A and team cooperation task B; Teamwork Task A is a team-based distributed collaborative flight control task; Teamwork Task A is a team training task. Teamwork Task B is a teamwork dynamic balance control task; Teamwork Task B is a team testing task.

[0019] In one feasible implementation, the present invention addresses the problem that existing collaborative task designs struggle to induce deep cooperation by designing a mandatory dependency-based task architecture. This architecture forces members to engage in deep interaction through permission separation, thus resolving the pain point that traditional tasks struggle to accurately stimulate collaborative behavior.

[0020] Forced dependency-based collaborative training tasks include team collaboration task A and team collaboration task B; Task A is designed as a team-based distributed collaborative flight control task, aiming to control a virtual aircraft to move in three-dimensional space to capture target objects (coins). In team cooperation mode, the specific control dimensions are allocated as follows: the first member controls the aircraft's vertical ascent and descent, the second member controls its horizontal offset, and the third member controls its longitudinal acceleration and deceleration. In single-person operation mode, one operator independently controls the aircraft's movement in all the above dimensions. The scoring rule for this task is 1 point for each coin successfully captured, with the final cumulative score (0-100) serving as the performance indicator. The environmental parameters for the task are set as follows: the total task execution time (200s) is fixed, the total number of coins generated (100) and the generation time interval (2s) remain constant, and the spatial coordinates of the coins are randomly generated in a two-dimensional cross-section perpendicular to the flight direction at each generation time point along the flight path. This task is divided into three difficulty levels, with the total display cross-section size set to... Given the following premise: Difficulty 1: Concentrate the coins in the center The area is defined, and the radius of the gold coin is set to [value]. Difficulty 2: Expand the gold coins to a global distribution and set the gold coin radius to [value missing]. Difficulty 3: Expand the gold coins to a global distribution and set the gold coin radius to [value missing]. .

[0021] The core innovation of this task lies in decomposing three-dimensional spatial motion into three mutually exclusive control channels: vertical, horizontal, and velocity. Any deviation in any single dimension cannot be compensated for by other members, thus fundamentally eliminating individual negligence in team tasks. This more effectively accelerates the training and improvement of brain-to-brain synchronization capabilities within the team.

[0022] In this invention, team collaboration task A is used as a team training task. After successful team formation, the team needs to complete the team training according to the following settings: Week 1 training difficulty is 1, Weeks 2-3 training difficulty is 2, and Week 4 training difficulty is 3. During the training execution of team task A, no physiological signals need to be collected; only the training score for each session needs to be output. This score serves as feedback for the team to independently evaluate the effectiveness of the execution strategy and allows the team to dynamically adjust the execution strategy for subsequent training based on this score.

[0023] Task B is a team-based dynamic balance control task designed to control a virtual equilateral triangle (120mm side length) to prevent a loaded sphere (10mm radius) from falling. In team mode, the control dimensions are allocated as follows: three operators are each responsible for the vertical drive of one vertex of the triangle, adjusting the plane's tilt angle by changing the Z-axis height of their respective vertices. The larger the tilt angle, the greater the sphere's falling speed. In single-operation mode, one operator centrally controls the three vertices or the overall posture of the triangle. The scoring rule is 1 point for every 2 seconds the sphere remains on the triangle; if the sphere falls, it cools down for 1 second, resets, and no points are awarded during the reset period. The final cumulative score (0-100) serves as the performance indicator. The environmental parameters are set as follows: the total task execution time (200s) is fixed, and the task introduces instability constraints, meaning the triangle cannot remain perfectly level under any control combination; the sphere is constantly moving, requiring team members to continuously cooperate to adjust the plane's level.

[0024] Unlike traditional methods that directly control the plane's tilt angle, this task decomposes the balance control of the plane into three independent vertex height controls. This means that no single member can independently determine the plane's orientation, forcing the team to collaboratively synthesize balancing forces through a high degree of geometric intuition. More importantly, the designed "never-unsteady" characteristic eliminates an absolute static equilibrium point, ensuring the sphere is always in motion. This design forces team members to move beyond reactive control based solely on observing the ball's movement, requiring them to establish high-frequency predictive coordination. This involves continuous, subtle, anticipatory compensation to counteract the system's instability, effectively enhancing brain-to-brain synchronization during training.

[0025] Team collaboration task B serves two purposes. First, it assesses individual team member abilities. Before team formation, each candidate completes the game individually and earns a score, which is then used as part of their individual ability score. No physiological signals need to be collected during this individual ability test. Second, this task serves as a core tool for team collaboration assessment, applied in pre- and post-training phases. After team formation (before training) and after the training period (after training), three members work together on task B. At both key assessment points, the system synchronously records team performance scores and collects multimodal physiological signals from all members, including EEG, EOG, and EMG signals.

[0026] For those participating in the training for the first time, an individual ability test will be conducted. Participants will complete a three-person team cooperative task B individually and obtain a test score sequence. (0-100).

[0027] S2. Based on the adult attachment scale, assess the personality traits of team members and obtain the attachment type label sequence of team members; Optionally, based on an adult attachment scale, personality traits of team members are assessed to obtain a sequence of attachment type labels for each team member, including: Based on the Adult Attachment Scale, the team members' attachment styles were assessed to obtain a sequence of attachment dimension scores. The composite mean score is calculated based on the attachment dimension score sequence to obtain the closeness dependence composite mean score sequence and the anxiety mean score sequence. Based on a preset scoring threshold, the team members' attachment styles are determined according to the closeness-dependence composite average score sequence and the anxiety average score sequence, and an attachment style label sequence is obtained.

[0028] In one feasible implementation, the present invention combines assessments of both test score sequences and personality trait scale levels to determine the scales used for personality trait assessment, including the Adult Attachment Scale (AAS) and the Big Five Personality Inventory (BFI).

[0029] The Adult Attachment Scale was used to assess the personality traits of all participants. Based on the Adult Attachment Scale, data was extracted from the participants. The three subscale scores: affinity score (1-5 points), Dependency score (1-5 points), anxiety score (1-5 points). Calculate the "average score of closeness dependency". Compared to "equal distribution of anxiety" The calculation formulas are as follows: (1) and (2): (1); (2); Using 3 as the dividing line, the following types of people are identified: secure (average closeness dependency score > 3, average anxiety score < 3), preemptive (average closeness dependency score > 3, average anxiety score > 3), rejecting (average closeness dependency score < 3, average anxiety score < 3), and fearful (average closeness dependency score < 3, average anxiety score > 3).

[0030] Based on the results of the Adult Attachment Scale, secure attachment, characterized by high closeness dependence and low anxiety, is most conducive to teamwork. Considering that both possessive and fearful attachments tend to have high anxiety, while both rejecting and fearful attachments exhibit low closeness dependence, this method innovatively reorganizes the four personality types into two dimensions: secure attachment (containing only "secure") and insecure attachment (covering "possessive," "rejecting," and "fearful").

[0031] S3. Based on the Big Five personality scale and the logical dominance quantification formula, the dominance of team members is evaluated to obtain the logical dominance intention score sequence of team members. Optionally, based on the Big Five personality traits scale and the logical dominance quantification formula, a dominance assessment is conducted on team members to obtain a sequence of logical dominance intention scores for each team member, including: Based on the Big Five personality traits scale, the personality traits of team members were assessed to obtain a sequence of personality trait scores. The mean score sequence of the Big Five personality traits is obtained by calculating the mean score of the cooperative dimension based on the personality trait score sequence. Based on the logic-dominant quantitative formula, the logic-dominant intention score sequence is obtained by calculating the average score sequence of the Big Five personality traits.

[0032] In one feasible implementation, the Big Five Personality Inventory is used to score the personality traits of all subjects. The original Big Five Personality Inventory used in this invention includes five higher-order domain scales, namely extraversion (…). ), due diligence ( ), openness ( ), affinity ( ) and negative emotions ( Each domain encompasses three sub-scales. Extraversion covers sociality, dominance, and energy levels; Affinity covers empathy, respect for others, and trust; Conscientiousness covers organization, productivity, and responsibility; Negative Emotions cover anxiety, depression, and mood swings; and Openness covers aesthetic sensitivity, intellectual curiosity, and creative imagination.

[0033] Members with higher Logical Dominance Score (LDS) are more likely to play the role of "decision outputter" in the team; that is, members with an LDS score greater than 2.5 are more likely to play the role of "decision outputter".

[0034] To maximize decision-making efficiency, this invention retains only one member with a high LDS score in the three-person team configuration to act as the "decision outputter." This "single-core driven" configuration effectively avoids the clash of viewpoints caused by multiple decision centers, reducing unnecessary internal friction and disputes from a mechanism perspective.

[0035] Among them, the formula for quantifying logical dominance is as follows (3): (3); in, Score for dominant intention; Extraversion score in the Big Five personality traits average score sequence; The conscientiousness score in the Big Five personality traits average score sequence; The openness score is the average score in the Big Five personality traits sequence. Affinity score in the Big Five personality traits average score sequence; The negative emotion score is represented in the Big Five personality traits average score sequence.

[0036] In one feasible implementation, a novel formula for calculating the logical dominance score is designed based on the scores of the above five higher-order domain scales, as shown in equation (3). The formula regards extroversion as the core driving force for leading the team (accounting for 50%), which determines a team member's willingness to lead the team; it introduces conscientiousness and openness as positive modifiers to ensure that the dominant behavior is both stable and flexible; and it guarantees the leader's cooperative attitude through the addition of affinity. The model uses the "subtraction" logic to reverse the negative emotions, thereby accurately obtaining the subject's true "dominance willingness" score in the team.

[0037] S4. Based on the dual psychological compatibility constraint grouping strategy, team members are conditionally grouped according to the test score sequence, attachment type label sequence, and logical dominance intention score sequence to obtain the team cooperation group. Optionally, based on a dual psychological compatibility constraint grouping strategy, team members are conditionally grouped according to the test score sequence, attachment type label sequence, and logical dominance intention score sequence to obtain team cooperation groups, including: Based on preset capability classification thresholds, team members are classified into capability levels according to the test score sequence, and high-capability member pool, medium-capability member pool and low-capability member pool are constructed. Based on the emotional compatibility constraint, and according to the attachment type label sequence and the logical dominance intention score sequence, team leaders are selected from the high-energy member pool and the medium-energy member pool to obtain the team leader set and the corresponding team leader member pool. Based on the captain member pool, the pools are divided into high-energy member pool, medium-energy member pool, and low-energy member pool to obtain the non-captain member pool. Based on the attachment security complementarity constraint, matching team members are selected from the non-captain member pool according to the attachment type label sequence and the logical dominance intention score sequence to obtain the team member set corresponding to the captain set. Team collaboration groups are formed based on the team leader and team member groups.

[0038] In one feasible implementation, in a group training scenario, participants inevitably exhibit differences in ability, typically categorized into three levels: High (H), Medium (M), and Low (L). Without imposing specific grouping constraints, existing randomized grouping models face two significant problems: On the one hand, homogeneous grouping limits the potential for improvement in interbrain synchronization. However, improved interbrain synchronization can enhance team training effectiveness. The high-ability group (HHH), due to the highly similar cognitive patterns among its members, is prone to "homogeneous cognitive redundancy," leading to training gain saturation (ceiling effect). Conversely, the low-ability group (LLL), lacking effective cognitive guidance, struggles to establish stable neural coupling (floor effect). In contrast, the balanced group (HML), with a significant ability gradient, utilizes "cognitive potential difference" to drive neural traction, gradually inducing higher-intensity interbrain synchronization as training progresses.

[0039] On the other hand, completely randomized grouping lacks control over socio-psychological factors. This can easily lead to a lack of a clear logical leader within the team, or interpersonal friction caused by incompatible personality traits among members (such as a cluster of low-dependency, high-anxiety personality traits), thereby inhibiting the realization of brain synchronization and severely suppressing the effectiveness of teamwork training.

[0040] In view of this, the present invention proposes a grouping strategy based on dual psychological compatibility constraints, which aims to construct an optimal team model from two dimensions: individual ability gradient and personality trait matching, in order to solve the above-mentioned problems of homogeneity inefficiency and psychological friction, thereby maximizing the benefits of brain-to-brain synchronous improvement in team training.

[0041] To address the lack of scientific team-building strategies in existing team training, or the high internal friction and low brain synchronization rate caused by single-dimensional considerations (such as simply stacking abilities or focusing only on psychological compatibility), this invention proposes a multi-dimensional hierarchical intelligent team-building mechanism based on the Constraint Satisfaction Problem (CSP). This mechanism innovatively introduces "Hyper-Level Liaison (HML) configuration" as a hard constraint, aiming to promote brain synchronization among team members through differentiated combinations of high, medium, and low abilities to improve training effectiveness. By combining the dual psychological verification logic of "secure attachment constraint" and "dominant personality constraint," it resolves the risk of psychological rejection during the team-building process, thereby achieving optimal team configuration in terms of both neurocognitive training effectiveness and psychological safety compatibility.

[0042] This invention employs a dual psychological compatibility constraint grouping strategy, modeling the team formation process as a constraint satisfaction problem. Team formation is not completely random, but must satisfy three types of hard constraints: a preset gradient of individual ability levels, a difference in dominant willingness scores, and a safety type restriction.

[0043] Each group's three members must come from three different pools of individual skill levels.

[0044] Condition 2: The team leader must come from a high-energy pool or medium-energy pool and have a secure personality; their LDS score must be greater than 2.5 and at least 1.5 points higher than any team member.

[0045] Condition 3: The team must include at most one non-safe subject.

[0046] Gather all team members according to Sort in descending order. Set two threshold quantiles. and The subjects were divided into three tiers: a high-energy member pool ( ): Zhongneng member pool ( ): and low-energy member pool ( ): .

[0047] Based on the participants' secure personality type and LDS scores, members with a secure personality type and an LDS score > 2.5 were selected from the high-energy and medium-energy pools to serve as team leaders. A team leader pool was then constructed. The mathematical expression for the captain member pool is as follows (4): (4); in, This represents the set of members in the captain member pool; Represents any single test member, and is a basic element in the high-energy member pool and the medium-energy member pool; , These respectively characterize the high-energy member pool and the medium-energy member pool; The attachment style type determination function. Here, a value of 1 is set as the identifier for secure attachment. Characterizing the participants The Logical Dominance Score.

[0048] Excluding the team leader's ability pool, select members from the other two pools whose LDS rating is more than 1.5 points lower than the team leader's as candidates. Randomly select two members from these pools. If both members are non-safe, return one of them and select a safe member from the pool to replace them.

[0049] The three players were removed from their respective resource pools.

[0050] S5. Based on the mandatory dependency cooperative training task, the team cooperation group is tested for ability, and LSL technology is used to collect multimodal physiological signals to obtain the baseline task score sequence and baseline task physiological data. In one feasible implementation, after the group is formed (before training), three members work together to perform task B. The system needs to synchronously record the team performance score and collect multimodal physiological signals from all members, including EEG (electroencephalogram), EOG (electroophthalmicogram), and EMG (electromyographic signal), to construct quantitative comparative data on training effects.

[0051] Data acquisition was uniformly performed using the same model Neuroscan 32-lead system. The EEG electrode layout strictly followed the international 10-20 standard; EOG (electroophthalmic) and EMG (electromyographic) were captured using the external electrodes provided with the device, with the former electrodes placed on the left and right eyelids and the latter attached to the left and right cheekbone areas.

[0052] To ensure strict data synchronization in collaborative group tasks, this invention constructs an EEG ultrasound data acquisition architecture based on the LabStreaming Layer (LSL) protocol. Through LSL's unified timestamp broadcasting and drift correction mechanism, the system can guarantee that the start and end times of the recordings of the three members are completely consistent, and the sampling frequencies of the three types of physiological signals remain highly uniform, thereby achieving millisecond-level precision in fully synchronized group-level data recording.

[0053] Multimodal physiological signals were acquired primarily during the execution of team-based collaborative task B in a mandatory dependency-based training exercise. EEG, EMG, and EOG data were collected from the subjects. LSL technology was used to add millisecond-level high-precision timestamps to individual data streams, effectively eliminating timing errors caused by device transmission delays. This unified timing benchmark ensured that the physiological data of each individual subject could be strictly aligned on the timeline, enabling offline synchronous analysis of team signals. A high-density electrode array (32 electrodes) was used to acquire EEG data, ensuring coverage of all important brain regions. Bandpass filtering was performed on the acquired multimodal physiological signals to remove interference signals and artifacts. Bandpass filtering was applied to the acquired EEG data, with a filtering range set from 0.5Hz to 40Hz, removing low-frequency drift and high-frequency noise while retaining effective brain activity information. Electromyographic signals from the zygomaticus major muscle were acquired using electrode patches. Bandpass filtering was applied to the acquired EMG data, with a filtering range set from 20Hz to 450Hz, removing low-frequency baseline drift and high-frequency noise while retaining effective signals generated by muscle contraction. Horizontal electrooculogram (EOG) signals were acquired at the outer corners of both eyes using electrode patches. The acquired EOG signals were bandpass filtered from 0.5 Hz to 40 Hz to remove low-frequency drift and high-frequency noise, while retaining effective electrooculogram information.

[0054] S6. Based on the mandatory dependency cooperative training task, the team cooperation group is trained with progressive difficulty. After training, the group is tested and LSL is collected simultaneously to obtain the final evaluation score sequence and the final evaluation physiological data. In one feasible implementation, team collaboration groups undergo training on team collaboration task A for at least four weeks, with at least three sessions per week. The training difficulty level is 1 in week 1, 2-3 in weeks 2, and 3 in week 4. All team collaboration tasks A are performed in the same manner throughout the four weeks of training. The specific steps are as follows: a team of three first completes one round of team collaboration task A, followed by a three-minute rest. This constitutes one complete round of team collaboration training. A total of three rounds of team collaboration training tasks need to be completed, and the score for team collaboration task A in each round is recorded.

[0055] After the training cycle ends (post-training), three members will work together to perform Task B. The system needs to simultaneously record the team's performance score and collect multimodal physiological signals from all members, including EEG (electroencephalogram), EOG (electroophthalmogram), and EMG (electromyography), to construct quantitative comparative data on training effectiveness. The method for collecting multimodal physiological data after training is the same as the method for collecting data before training.

[0056] S7. Based on the team collaboration ability assessment model, team training is evaluated according to baseline task scores, baseline task physiological data, final evaluation scores, and final evaluation physiological data to obtain training evaluation results.

[0057] Optionally, based on the team collaboration ability assessment model, team training is evaluated according to baseline task scores, baseline task physiological data, final evaluation scores, and final evaluation physiological data to obtain training evaluation results, including: Based on a preset sliding window, the baseline physiological data and the final evaluation physiological data are segmented to obtain the baseline physiological dataset and the final evaluation physiological dataset. Physiological features were extracted based on the baseline physiological dataset and the final evaluation physiological dataset to obtain baseline EEG features, baseline EMG features, baseline EOG features, final EEG features, final EMG features, and final EOG features. The baseline EEG features, baseline EMG features, and baseline EOG features are spliced ​​together in time series to obtain the baseline time series feature sequence. The final EEG features, final EMG features, and final EOG features are spliced ​​together in time series to obtain the final time series feature sequence. Based on the baseline and final time series feature sequences, a team collaboration ability assessment model is used for classification prediction to obtain the baseline classification accuracy and the final classification accuracy. The team collaboration ability assessment model is constructed by combining a convolutional neural network with a Transformer model. The behavioral assessment results are calculated based on the baseline task score and the final assessment score. The physiological assessment results are calculated based on the baseline classification accuracy and the final classification accuracy. Training assessment results are obtained based on behavioral and physiological assessment results.

[0058] In one feasible implementation, evaluation is based on team multimodal physiological signals. Multimodal physiological signals (EEG, EMG, and EOG) collected during the baseline assessment (before training) and final assessment (after training) phases of team collaboration task B are selected and preprocessed and feature extracted using the following procedure: All physiological signal data of team members were strictly aligned on the timeline to ensure that the start and end times were consistent; the data of the three team members were vertically stacked in the channel dimension in the order of EEG, EMG, and EOG. The aligned and stacked multimodal time series were segmented using a sliding window with a length of 4 seconds and an overlap rate of 50%. For each sliding window, the statistical characteristics (mean, standard deviation, peak value, minimum value, and median) of each type of signal were calculated.

[0059] The feature data of each window are spliced ​​together in chronological order to form a time-series feature sequence.

[0060] The constructed feature data is input into the team collaboration ability assessment model, and local features are extracted and feature maps are generated using a convolutional neural network (CNN). The feature maps are converted into vector sequences and input into a Transformer Encoder to fuse global temporal features. The classification results are output through a fully connected layer to identify the physiological state before and after training.

[0061] Evaluation based on physiological data showed that a high classification accuracy indicated a significant change in the team's brain and physiological synchronization during training. Evaluation based on behavioral data also included comparing pre-test (before training) and post-test (after training) scores for Team Collaboration Task B. A significantly higher post-test score compared to the pre-test score indicated a significant effectiveness of the training intervention.

[0062] Combining the aforementioned behavioral data with the dual assessment results of multimodal physiological characteristics, this study not only validated the improvement in collaborative efficiency at the explicit performance level but also provided objective physiological evidence of enhanced interbrain synchronization at the implicit neural mechanism level. This mutually reinforcing logic of "behavior-physiology" strongly confirms the significance of the training effect and its inherent enhancement of interbrain synchronization.

[0063] This invention proposes a team training assessment method based on novel team building and collaborative tasks. Through the proposed scientific team formation strategy based on psychological attachment safety complementarity and ability stratification, the subjects are divided according to their ability scores. In the random sampling process based on constraint satisfaction problems, a grouping strategy based on dual psychological compatibility constraints is adopted, including emotional compatibility constraints and attachment safety complementarity constraints, to ensure psychological attachment safety complementarity and ability stratification complementarity. Based on the mandatory dependency cooperative task architecture, two types of mandatory dependency cooperative tasks are designed, including cooperative task A and cooperative task B. The complete control freedom is decomposed and distributed to different members to build a mandatory cooperative environment that must rely on high-frequency interaction to complete. This invention utilizes LSL technology to temporally align three types of physiological signals—EEG, EOG, and EMG—and calculate various feature values. A team collaboration ability assessment model constructed using a Transformer model is trained to perform binary classification on the physiological characteristics of subjects' baseline and final assessment states. Classification accuracy is used as an objective indicator of changes in neural plasticity, establishing a validation model linking physiological pattern changes with improved behavioral performance. This invention is a team training and assessment method that transforms individual ability and personality characteristic assessment results into specific team-building strategies.

[0064] Figure 2 This is a block diagram of a team training and evaluation device based on a novel team building and cooperation task, provided by an embodiment of the present invention. This device is used for a team training and evaluation method based on a novel team building and cooperation task. (Refer to...) Figure 2 The device includes an initial ability assessment module 210, an attachment assessment module 220, a dominance assessment module 230, a team member grouping module 240, a first information collection module 250, a second information collection module 260, and a comprehensive training assessment module 270. Among them: The initial competency assessment module 210 is used to test the competency of team members based on a mandatory dependency cooperative training task and record the test score sequence. The attachment assessment module 220 is used to assess the personality traits of team members based on an adult attachment scale and obtain the attachment type label sequence of team members. The dominance assessment module 230 is used to assess the dominance of team members based on the Big Five personality scale and the logical dominance quantification formula, and to obtain the logical dominance intention score sequence of team members. The team member grouping module 240 is used to group team members based on a dual psychological compatibility constraint grouping strategy, according to the test score sequence, attachment type label sequence, and logical dominance intention score sequence, to obtain team cooperation groups; The first information acquisition module 250 is used to test the ability of team cooperation groups based on the forced dependency cooperative training task, and to use LSL technology to acquire multimodal physiological signals to obtain baseline task score sequences and baseline task physiological data. The second information acquisition module 260 is used to implement progressive difficulty training for team cooperation groups based on a forced dependency cooperative training task, test after training and collect LSL data simultaneously to obtain the final evaluation score sequence and final evaluation physiological data. The training comprehensive evaluation module 270 is used to evaluate team training based on the team cooperation ability evaluation model, according to the baseline task score, baseline task physiological data, final evaluation score and final evaluation physiological data, and to obtain training evaluation results.

[0065] Among them, the mandatory dependency-based cooperative training tasks include team cooperation task A and team cooperation task B; Teamwork Task A is a team-based distributed collaborative flight control task; Teamwork Task A is a team training task. Teamwork Task B is a teamwork dynamic balance control task; Teamwork Task B is a team testing task.

[0066] Optionally, the attachment assessment module 220 is further used for: Based on the Adult Attachment Scale, the team members' attachment styles were assessed to obtain a sequence of attachment dimension scores. The composite mean score is calculated based on the attachment dimension score sequence to obtain the closeness dependence composite mean score sequence and the anxiety mean score sequence. Based on a preset scoring threshold, the team members' attachment styles are determined according to the closeness-dependence composite average score sequence and the anxiety average score sequence, and an attachment style label sequence is obtained.

[0067] Optionally, the dominance assessment module 230 is further used for: Based on the Big Five personality traits scale, the personality traits of team members were assessed to obtain a sequence of personality trait scores. The mean score sequence of the Big Five personality traits is obtained by calculating the mean score of the cooperative dimension based on the personality trait score sequence. Based on the logic-dominant quantitative formula, the logic-dominant intention score sequence is obtained by calculating the average score sequence of the Big Five personality traits.

[0068] The formula for quantifying logical dominance is as follows (1): (1); in, Score for dominant intention; Extraversion score in the Big Five personality traits average score sequence; The conscientiousness score in the Big Five personality traits average score sequence; The openness score is the average score in the Big Five personality traits sequence. Affinity score in the Big Five personality traits average score sequence; The negative emotion score is represented in the Big Five personality traits average score sequence.

[0069] Optionally, the team member grouping module 240 is further used for: Based on preset capability classification thresholds, team members are classified into capability levels according to the test score sequence, and high-capability member pool, medium-capability member pool and low-capability member pool are constructed. Based on the emotional compatibility constraint, and according to the attachment type label sequence and the logical dominance intention score sequence, team leaders are selected from the high-energy member pool and the medium-energy member pool to obtain the team leader set and the corresponding team leader member pool. Based on the captain member pool, the pools are divided into high-energy member pool, medium-energy member pool, and low-energy member pool to obtain the non-captain member pool. Based on the attachment security complementarity constraint, matching team members are selected from the non-captain member pool according to the attachment type label sequence and the logical dominance intention score sequence to obtain the team member set corresponding to the captain set. Team collaboration groups are formed based on the team leader and team member groups.

[0070] Optionally, training the comprehensive evaluation module 270 is further used for: Based on a preset sliding window, the baseline physiological data and the final evaluation physiological data are segmented to obtain the baseline physiological dataset and the final evaluation physiological dataset. Physiological features were extracted based on the baseline physiological dataset and the final evaluation physiological dataset to obtain baseline EEG features, baseline EMG features, baseline EOG features, final EEG features, final EMG features, and final EOG features. The baseline EEG features, baseline EMG features, and baseline EOG features are spliced ​​together in time series to obtain the baseline time series feature sequence. The final EEG features, final EMG features, and final EOG features are spliced ​​together in time series to obtain the final time series feature sequence. Based on the baseline and final time series feature sequences, a team collaboration ability assessment model is used for classification prediction to obtain the baseline classification accuracy and the final classification accuracy. The team collaboration ability assessment model is constructed by combining a convolutional neural network with a Transformer model. The behavioral assessment results are calculated based on the baseline task score and the final assessment score. The physiological assessment results are calculated based on the baseline classification accuracy and the final classification accuracy. Training assessment results are obtained based on behavioral and physiological assessment results.

[0071] This invention proposes a team training assessment method based on novel team building and collaborative tasks. Through the proposed scientific team formation strategy based on psychological attachment safety complementarity and ability stratification, the subjects are divided according to their ability scores. In the random sampling process based on constraint satisfaction problems, a grouping strategy based on dual psychological compatibility constraints is adopted, including emotional compatibility constraints and attachment safety complementarity constraints, to ensure psychological attachment safety complementarity and ability stratification complementarity. Based on the mandatory dependency cooperative task architecture, two types of mandatory dependency cooperative tasks are designed, including cooperative task A and cooperative task B. The complete control freedom is decomposed and distributed to different members to build a mandatory cooperative environment that must rely on high-frequency interaction to complete. This invention utilizes LSL technology to temporally align three types of physiological signals—EEG, EOG, and EMG—and calculate various feature values. A team collaboration ability assessment model constructed using a Transformer model is trained to perform binary classification on the physiological characteristics of subjects' baseline and final assessment states. Classification accuracy is used as an objective indicator of changes in neural plasticity, establishing a validation model linking physiological pattern changes with improved behavioral performance. This invention is a team training and assessment method that transforms individual ability and personality characteristic assessment results into specific team-building strategies.

[0072] Figure 3 This is a schematic diagram of the structure of a team training and assessment device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the team training assessment equipment may include the above-mentioned Figure 2 The illustrated team training and evaluation device is based on a novel team building and collaboration task. Optionally, the team training and evaluation device 310 may include a first processor 2001.

[0073] Optionally, the team training evaluation device 310 may also include a memory 2002 and a transceiver 2003.

[0074] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0075] The following is combined with Figure 3 A detailed introduction to each component of the team training and assessment device 310: The first processor 2001 is the control center of the team training and evaluation device 310. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0076] Optionally, the first processor 2001 can perform various functions of the team training and evaluation device 310 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0077] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 3 CPU0 and CPU1 are shown in the diagram.

[0078] In a specific implementation, as one example, the team training and evaluation device 310 may also include multiple processors, for example... Figure 3 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0079] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0080] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently and be connected to the interface circuit of the team training evaluation device 310. Figure 3 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0081] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0082] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 3 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0083] Alternatively, the transceiver 2003 can be integrated with the first processor 2001, or it can exist independently and be used in conjunction with the interface circuit of the team training evaluation device 310. Figure 3 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0084] It should be noted that, Figure 3 The structure of the team training evaluation device 310 shown does not constitute a limitation on the router. Actual team training evaluation devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0085] Furthermore, the technical effect of the team training assessment device 310 can be referred to the technical effect of the team training assessment method based on the novel team building and cooperation task described in the above method embodiments, and will not be repeated here.

[0086] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or it may be any conventional processor, etc.

[0087] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0088] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0089] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0090] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0091] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0092] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0093] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0094] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0095] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0097] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A team training and evaluation method based on novel team building and collaborative tasks, characterized in that, The method includes: Based on a mandatory dependency-based collaborative training task, the team members' abilities were tested, and the test score sequence was recorded. Based on the adult attachment scale, the personality traits of team members were assessed to obtain the attachment type label sequence of team members; Based on the Big Five personality scale and the logical dominance quantification formula, the dominance of team members is evaluated to obtain the logical dominance intention score sequence of team members; Based on a dual psychological compatibility constraint grouping strategy, team members are conditionally grouped according to the test score sequence, attachment type label sequence, and logical dominance intention score sequence to obtain team cooperation groups; Based on a mandatory dependency-based cooperative training task, the team cooperation group was tested for ability, and LSL technology was used to collect multimodal physiological signals to obtain baseline task score sequences and baseline task physiological data. Based on a mandatory dependency-based collaborative training task, progressively challenging training was conducted on the team collaboration group. After training, the group was tested and LSL data was collected simultaneously to obtain the final evaluation score sequence and final evaluation physiological data. Based on the team collaboration ability assessment model, team training is evaluated according to baseline task scores, baseline task physiological data, final evaluation scores, and final evaluation physiological data to obtain training evaluation results.

2. The team training and evaluation method based on novel team building and collaborative tasks according to claim 1, characterized in that, The mandatory dependency-based cooperative training tasks include team cooperation task A and team cooperation task B; The team cooperation task A is a team distributed collaborative flight control task; the team cooperation task A is a team training task; Team collaboration task B is a team collaboration dynamic balance control task; team collaboration task B is a team testing task.

3. The team training and evaluation method based on novel team building and collaborative tasks according to claim 1, characterized in that, The assessment of team members' personality traits based on an adult attachment scale yields a sequence of attachment type labels for each member, including: Based on the Adult Attachment Scale, the team members' attachment styles were assessed to obtain a sequence of attachment dimension scores. The composite mean score is calculated based on the attachment dimension score sequence to obtain the closeness dependence composite mean score sequence and the anxiety mean score sequence. Based on a preset scoring threshold, the team members' attachment styles are determined according to the closeness-dependence composite average score sequence and the anxiety average score sequence, and an attachment style label sequence is obtained.

4. The team training and evaluation method based on novel team building and collaborative tasks according to claim 1, characterized in that, The team members' dominance was assessed based on the Big Five personality traits scale and the logical dominance quantification formula, resulting in a sequence of logical dominance intention scores for each member, including: Based on the Big Five personality traits scale, the personality traits of team members were assessed to obtain a sequence of personality trait scores. The mean score sequence of the Big Five personality traits is obtained by calculating the mean score of the cooperative dimension based on the personality trait score sequence. Based on the logic-dominant quantitative formula, the logic-dominant intention score sequence is obtained by calculating the average score sequence of the Big Five personality traits.

5. The team training and evaluation method based on novel team building and collaborative tasks according to claim 4, characterized in that, The logic-dominant quantification formula is as follows (1): （1）； in, Score for dominant intention; Extraversion score in the Big Five personality traits average score sequence; The conscientiousness score in the Big Five personality traits average score sequence; The openness score is the average score in the Big Five personality traits sequence. Affinity score in the Big Five personality traits average score sequence; The negative emotion score is represented in the Big Five personality traits average score sequence.

6. The team training and evaluation method based on novel team building and collaborative tasks according to claim 1, characterized in that, The grouping strategy based on dual psychological compatibility constraints groups team members according to test score sequences, attachment type label sequences, and logical dominance intention score sequences to obtain team cooperation groups, including: Based on preset capability classification thresholds, team members are classified into capability levels according to the test score sequence, and high-capability member pool, medium-capability member pool and low-capability member pool are constructed. Based on the emotional compatibility constraint, and according to the attachment type label sequence and the logical dominance intention score sequence, team leaders are selected from the high-energy member pool and the medium-energy member pool to obtain the team leader set and the corresponding team leader member pool. Based on the captain member pool, the pools are divided into high-energy member pool, medium-energy member pool, and low-energy member pool to obtain the non-captain member pool. Based on the attachment security complementarity constraint, matching team members are selected from the non-captain member pool according to the attachment type label sequence and the logical dominance intention score sequence to obtain the team member set corresponding to the captain set. Team collaboration groups are formed based on the team leader group and the team member group.

7. The team training and evaluation method based on novel team building and collaborative tasks according to claim 1, characterized in that, The team collaboration ability assessment model evaluates team training based on baseline task scores, baseline task physiological data, final assessment scores, and final assessment physiological data to obtain training assessment results, including: Based on a preset sliding window, the baseline physiological data and the final evaluation physiological data are segmented to obtain the baseline physiological dataset and the final evaluation physiological dataset. Physiological features were extracted based on the baseline physiological dataset and the final evaluation physiological dataset to obtain baseline EEG features, baseline EMG features, baseline EOG features, final EEG features, final EMG features, and final EOG features. The baseline EEG features, baseline EMG features, and baseline EOG features are spliced ​​together in time series to obtain the baseline time series feature sequence. The final EEG features, final EMG features, and final EOG features are spliced ​​together in time series to obtain the final time series feature sequence. Based on the baseline and final time-series feature sequences, a team collaboration ability assessment model is used for classification prediction to obtain the baseline classification accuracy and the final classification accuracy. The team collaboration ability assessment model is constructed by combining a convolutional neural network with a Transformer model. The behavioral assessment results are calculated based on the baseline task score and the final assessment score. The physiological assessment results are calculated based on the baseline classification accuracy and the final classification accuracy. Training assessment results are obtained based on behavioral and physiological assessment results.

8. A team training and evaluation device based on novel team building and cooperation tasks, wherein the device is used to implement the team training and evaluation method based on novel team building and cooperation tasks as described in any one of claims 1-7, characterized in that, The device includes: The initial competency assessment module is used to test the competencies of team members based on a mandatory dependency-based collaborative training task and record the test score sequence. The attachment assessment module is used to assess the personality traits of team members based on an adult attachment scale and obtain the attachment type label sequence of team members. The dominance assessment module is used to assess the dominance of team members based on the Big Five personality traits scale and the logical dominance quantification formula, and to obtain the logical dominance intention score sequence of team members. The team member grouping module is used to group team members based on a dual psychological compatibility constraint grouping strategy, according to the test score sequence, attachment type label sequence, and logical dominance intention score sequence, to obtain team cooperation groups; The first information acquisition module is used to test the ability of team cooperation groups based on the mandatory dependency cooperative training task, and to use LSL technology to acquire multimodal physiological signals, obtain baseline task score sequences and baseline task physiological data. The second information acquisition module is used to implement progressive difficulty training for team cooperation groups based on mandatory dependency cooperative training tasks, test after training and collect LSL data simultaneously to obtain the final evaluation score sequence and final evaluation physiological data. The training comprehensive evaluation module is used to evaluate team training based on the team collaboration ability evaluation model, using baseline task scores, baseline task physiological data, final evaluation scores, and final evaluation physiological data to obtain training evaluation results.

9. A team training assessment device, characterized in that, The team training assessment equipment includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 7.

Images