Data Processing Method and System for Interruption Response Capability Assessment

Abstract

The present invention relates to the technical field of human factors engineering and intelligent evaluation, and specifically provides a method and system for processing evaluation data of interruption response capabilities. The method includes constructing an experimental process scheduling structure that includes a primary task and an interruption task, collecting and constructing a complete behavior data stream, extracting time features during task switching and recovery, performing standardization and perturbation annotation, conducting factor analysis in combination with task labels, and generating a set of ability factor parameters. Subsequently, a scoring template is matched to calculate the individual interruption response ability score, a grade label is generated based on the score, and task ability adaptation and recommendation are completed. This method realizes the structuring, quantification, and closed-loop feedback of ability evaluation, and improves the evaluation accuracy and the intelligent level of task matching.

Description

Technical Field

[0001] The present invention relates to the cross - field of human factors engineering, cognitive psychology and artificial intelligence, and particularly to a method and system for processing evaluation data of interruption coping ability. Background Art

[0002] In complex operation scenarios, personnel often face situations of multi - task concurrency and high - frequency interruptions. An individual's coping ability with interruption information directly affects operation safety and system stability. Existing evaluation methods for interruption coping ability mainly rely on static questionnaire scales or single - task completion duration indicators, and it is difficult to truly reflect the response efficiency, recovery ability, and behavioral fluctuation characteristics during the dynamic task switching process.

[0003] In recent years, with the development of human - computer interaction and behavior data acquisition technologies, researchers have begun to attempt to model interruption coping ability through experimental task simulation and behavioral data stream analysis. However, traditional methods still have the following deficiencies in task structure design, standardized index extraction, ability dimension construction, and personalized recommendation mechanisms:

[0004] (1) Lack of a data modeling system for the whole process of main task - interruption - recovery task;

[0005] (2) Lack of a quantitative mapping path between behavioral data and ability labels;

[0006] (3) The evaluation results cannot be closed - loop feedback to subsequent task configurations, lacking the system's adaptive optimization ability. Summary of the Invention

[0007] The present invention provides a method and system for processing evaluation data of interruption coping ability to solve the problem of how to construct reaction - time characteristic indicators based on the behavioral data stream during the task response process, perform factor analysis modeling in combination with task labels, and then achieve quantitative scoring of an individual's interruption coping ability and task - matching recommendation.

[0008] To solve the above - mentioned technical problems, the present invention provides a method for processing evaluation data of interruption coping ability, including:

[0009] Construct a task structure, configure task switching logic and time control, and generate an experimental process scheduling structure;

[0010] Present task content according to the experimental process scheduling structure, record user responses and mark stages, and construct a behavioral data stream;

[0011] Calculate time indicators based on the behavioral data stream, perform data standardization processing, and generate perturbation annotation information and a set of characteristic indicators;

[0012] Construct a mapping relationship by combining the set of characteristic indicators and experimental task labels, perform factor analysis processing, and generate a set of ability factor parameters;

[0013] Match the scoring template, calculate the score for the ability to handle interruptions, generate labels based on the level boundaries, and output the scoring recommendation result data. The expression for the scoring recommendation result data is:

[0014]

[0015] where is the scoring recommendation result data; is the mapping structure function; is the label representing the interruption handling ability level; is the individual's interruption handling ability score; is the user's unique identifier; is the evaluation timestamp; is the experimental task number; is the summary of the ability dimension; is the ability-task adaptation identifier;

[0016] Based on the scoring recommendation result data, complete the discrimination of task ability adaptation, generate the matching task vector, and feedback it to the task modeling process.

[0017] Furthermore, the steps for constructing the task structure include:

[0018] Obtain the task template sets of the main task and the interruption task, construct the cross-task structure, and generate the task parameter configuration table;

[0019] Based on the task parameter configuration table, set the interruption trigger timing and the task switching logic, and generate the experimental process control table;

[0020] Combine the experimental process control table to configure the task display order and the time control logic, and output the experimental process scheduling structure.

[0021] Furthermore, the steps for constructing the behavior data stream include:

[0022] Obtain the experimental process scheduling structure, execute the alternating presentation of the main task and the interruption task, and collect the user interaction response data;

[0023] Mark the task phases and record the timestamps for the user interaction response data to generate the response time segmented data;

[0024] Based on the response time segmented data, construct the behavior data streams of the main task, the interruption task, and the recovery task.

[0025] Furthermore, the steps for calculating the time metrics include:

[0026] Obtain the behavior data stream, and calculate the time metrics of task switching time, task recovery time, and reaction delay time;

[0027] Clean and standardize the data for the task switching time, task recovery time, and reaction latency time metrics;

[0028] Based on the results of the standardization process, identify the behavioral fluctuation range and generate the perturbation annotation information and the set of feature metrics.

[0029] Furthermore, the steps for constructing the mapping relationship include:

[0030] Obtain the set of feature metrics and the perturbation annotation information, and construct the ability evidence structure and the ability mapping relationship table;

[0031] Combine the ability evidence structure with the experimental task labels to establish the ability mapping relationship table between the ability dimension and the task performance.

[0032] Furthermore, the steps for generating the set of ability factor parameters include:

[0033] Perform factor analysis on the ability mapping relationship table to generate the set of ability factor parameters.

[0034] Furthermore, the steps for calculating the interruption coping ability score include:

[0035] Obtain the set of ability factor parameters, match the scoring template library, and calculate the individual interruption coping ability score, where the individual interruption coping ability score is:

[0036]

[0037] where, is the individual interruption coping ability score; is the total number of ability factor dimensions; is the ability factor loading; is the standardized ability feature metric; is the response function of the th ability metric; is the weighted factor for the corresponding time series factor; is the total task cycle time;[[ID=4)]]

[0038] Furthermore, the steps for generating the scoring recommendation result data include:

[0039] Based on the interruption coping ability score, match the scoring grade boundary rules to generate the ability grade label, where the grade label is:

[0040]

[0041] where, represents the interruption coping ability grade label; is the individual interruption coping ability score; , is the grading score boundary threshold;

[0042] Structurally bind the interruption response ability score and the ability level label to generate the scoring recommendation result data.

[0043] Furthermore, the steps for task ability adaptation discrimination include:

[0044] Obtain the scoring recommendation result data, combine it with the task scenario label, and perform the task ability adaptation discrimination operation;

[0045] According to the result of the task ability adaptation discrimination operation, select the set of adapted task templates and generate the matching task vector;

[0046] Use the matching task vector as the input parameter for the new round of task modeling and feedback it to the task modeling process.

[0047] Furthermore, an interruption response ability evaluation data processing system includes:

[0048] Task modeling and process control module, used to construct the task structure, configure the task switching logic and time control, and generate the experimental process scheduling structure;

[0049] Behavior collection and data construction module, used to present the task content according to the experimental process scheduling structure, record the user response, and construct the behavior data stream;

[0050] Index extraction and feature construction module, used to calculate the time index based on the behavior data stream, perform data standardization processing, and generate the set of feature indicators;

[0051] Ability modeling module, used to construct the mapping relationship by combining the set of feature indicators and the experimental task label, perform factor analysis, and generate the set of ability factor parameters;

[0052] Scoring and grading module, used to match the scoring template, calculate the ability score and generate the ability level label, and output the scoring recommendation result data;

[0053] Adaptation recommendation module, used to complete the task ability adaptation discrimination according to the scoring recommendation result data, generate the matching task vector and feedback it to the task modeling process.

[0054] The key innovation points of the present invention include:

[0055] (1) Propose a method for constructing an interruption response evaluation model based on the behavior data stream, systematically integrating the task switching response time and stage markers, and supporting the whole-process evaluation modeling.

[0056] (2) Design a dynamic adaptation mechanism for the scoring result and task template, and realize the adaptive closed-loop process of evaluation - recommendation - training based on the label mapping and feedback mechanism.

[0057] The following are its main beneficial effects:

[0058] (1) Improve the timeliness and accuracy of interrupt response evaluation. This invention automatically controls the presentation order and time logic of the main task and interrupt task by constructing an experimental process scheduling structure, and records user response data in real time. It combines behavioral data streams to calculate time indicators such as task switching time, recovery time, and response delay. Compared with traditional methods that rely on manual recording and subjective judgment, the system can achieve high-precision, standardized data collection and timing management, significantly improving evaluation efficiency and accuracy.

[0059] (2) Forming a closed-loop feedback mechanism for task modeling and capability assessment. After binding the scoring result structure, the present invention performs capability adaptation and discrimination operations based on the scoring recommendation results and task scenario labels, generates matching task vectors, and feeds them back to the interrupted task modeling process, thus achieving automatic linkage between task generation and capability assessment. This closed-loop structure effectively solves the problem of disconnection between evaluation and recommendation in traditional systems and supports the design of continuous personalized training tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A flowchart of a method for processing interrupt response capability assessment data provided in an embodiment of the present application;

[0061] Figure 2 This is a structural block diagram of the interrupt response capability evaluation data processing system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] Example 1: Reference Figure 1 , is a flow chart of a method for processing interruption response capability evaluation data provided by an embodiment of the present invention. The flow chart may include at least steps S100-S600:

[0063] S100, building a task structure based on a set of task templates, configuring task switching logic and time control, and generating an experimental process scheduling structure;

[0064] S200: Present the task content according to the experimental process scheduling structure, record user responses and mark the stages, and build a complete behavioral data flow;

[0065] S300, calculating the time index based on the behavior data stream, completing data standardization processing, and generating disturbance annotation information and a set of feature indicators;

[0066] S400, constructing a mapping relationship by combining the characteristic indicator set and the experimental task label, performing factor analysis to generate a capability factor parameter set;

[0067] S500. Calculate the ability score for coping with interruption of the matching score template, generate labels based on the grade boundaries, and output the recommended score result data.

[0068] S600. Based on the recommended score result data, complete the discrimination of task ability adaptation, generate a matching task vector, and feedback it to the task modeling process.

[0069] Step S100 includes at least steps S110 - S130:

[0070] S110. Obtain the task template sets of the main task and the interrupted task, construct four types of cross - task structures, and generate a task parameter configuration table.

[0071] Specifically, in this step, the pre - constructed main task template and interrupted task template are called from the task library. The task template set includes two types of tasks: operation - type tasks and memory - type tasks. Attribute parameters such as cognitive load level, duration, and task feedback mechanism are set for each type of task.

[0072] After obtaining the task template set, the system constructs the following four types of cross - task structures: operation - type main task and operation - type interrupted task, operation - type main task and memory - type interrupted task, memory - type main task and operation - type interrupted task, memory - type main task and memory - type interrupted task. The cross - task structure is used to simulate the multi - type task switching behavior in the real - world work scenario, covering different combinations of cognitive resource conflicts.

[0073] Furthermore, the system extracts task attribute parameters according to task type, content length, task trigger method, and interruption insertion form, and generates a task parameter configuration table. The task parameter configuration table contains fields such as task identifier, task classification label, execution duration, task interval time, prompt mechanism, and feedback mode, which are used as the input basis for the subsequent experimental process control rules.

[0074] S120. Based on the task parameter configuration table, set the interruption trigger timing and task switching logic, and generate an experimental process control table.

[0075] Specifically, the system loads the task parameter configuration table into the task logic engine, configures the task switching points according to the task duration field, and inserts the interrupted task into the main task timeline. The interruption trigger timing includes three forms: fixed - time - point trigger, random - period trigger, and task - condition trigger. The interruption trigger point position of each main task is set through logical decision rules, the task conversion status is marked, and the interrupted task entry is embedded.

[0076] During the construction of the task switching logic, the system defines the transfer paths for three types of stages: the main task, the interrupt task, and the recovery task, and configures the switching identification and behavior marking rules for each stage. The system synchronizes with the trigger condition and time process through judgment, performs the jump from the main task to the interrupt task during operation, and then executes the recovery logic to return to the original task process.

[0077] Furthermore, after completing the above configuration, the system organizes and outputs the interrupt trigger point, stage transfer identification, task jump path, condition node list, etc., to generate an experimental process control table. The experimental process control table will be used as the input content for the subsequent task scheduling control module, providing a basis for the specific scheduling of the task display order.

[0078] S130. Configure the task display order and time control logic in combination with the experimental process control table, and output the experimental process scheduling structure.

[0079] Specifically, the system reads the task stage identification, task switching node, interrupt trigger time, task category order, etc. in the experimental process control table to establish a task display sequence. The task display sequence arranges the main task segment, interrupt task segment, and task recovery segment in chronological order, and defines the display duration, start and end timestamps, and time difference between adjacent task switches for each segment.

[0080] Furthermore, the system sets the time control logic to restrict the task presentation rhythm. The time control logic includes mechanisms such as the minimum interval time between tasks, the response time acquisition time window, the interrupt duration limit, and the non-response timeout mark, ensuring that the user behavior responses are comparable and segmentable.

[0081] The system synchronously generates a task presentation control structure and a time axis structure based on the task display sequence and time control logic, and numbers and archives them. Finally, an experimental process scheduling structure is generated, which includes a task stage sequence, display time configuration, response synchronization identification, and interrupt processing rhythm, and is used to drive the subsequent user interaction operation and response behavior acquisition process.

[0082] Through the task structure modeling and process control steps from S110 to S130, the standardized configuration of the task dimension design, parameter regulation, and behavior driving mechanism is realized, supporting the technical closed-loop of the subsequent multi-stage response behavior acquisition, index construction, and ability analysis. The constructed cross-task structure and interrupt logic control strategy improve the accuracy and generality of the interrupt response ability evaluation method, while ensuring controllable experimental scheduling, stable response characteristics, and unified behavior data structure, providing a traceable data basis and task label basis for the system scoring and feedback recommendation module.

[0083] Step S200 includes at least steps S210 - S230:

[0084] S210. Obtain the experimental process scheduling structure, execute the alternating presentation of the main task and the interrupt task, and collect user interaction response data.

[0085] Specifically, in this step, the information of the main task segment, the interrupt task segment, and the recovery task segment recorded in the experimental process scheduling structure is first read, and the task content is presented to the user under test in a visual or auditory form on the interaction platform. The task content is displayed sequentially in a sequence control manner, and each task segment is bound with a unique identifier, content encoding, and corresponding timestamp interval.

[0086] During the task presentation process, the system control logic alternately switches the main task and the interrupt task according to the timing and rhythm set in the scheduling structure, including but not limited to the alternation of operation tasks and memory tasks, and the switching of different task intensities. The tasks guide the user state change through explicit prompts or instantaneous jumps. During the task execution process, the user interacts with the system by means of mouse clicks, keyboard inputs, touch behaviors, or voice responses.

[0087] The system synchronously collects the interaction response data generated by the user in each task segment. The user interaction response data includes fields such as operation type, operation location, response time, task feedback information, and behavior sequence number. This data will be used to analyze the task execution rhythm and interrupt reaction characteristics in the subsequent steps.

[0088] S220. Perform task stage marking and timestamp recording on the user interaction response data to generate response time segmented data.

[0089] Specifically, the system first extracts the timestamp of each response event from the user interaction response data, and divides all interaction behaviors into three categories: main task segment response, interrupt task segment response, and recovery task segment response with reference to the start and end times of the tasks set in the experimental process scheduling structure.

[0090] During the response time segmentation process, the system uses the task display order in the scheduling structure as the segmentation node, logically attributes the user interaction events in chronological order, and binds the stage label. The task stage marking includes parameters such as task segment name, task number, task type, and task duration to achieve the structural consistency of the data segmentation label.

[0091] Furthermore, the system calculates the first response time, average response interval, response quantity, and response distribution trend under each task segment, and the results constitute the response time segmented data. The response time segmented data will be used to construct a complete behavior data stream in step S230.

[0092] During this process, the system filters out missing responses, duplicate responses, or non-task responses, and generates a response data quality report, providing a clean data source for subsequent task switch analysis and feature metric extraction.

[0093] S230. Based on the segmented response time data, construct the behavioral data stream throughout the entire process of the main task - interruption task - recovery task.

[0094] Specifically, the system reads the task segment classification, response event sequence, time interval, and behavioral tags in the segmented response time data, concatenates and combines the data for all task execution phases, and generates a behavioral data stream composed of the main task segment, interruption task segment, and recovery task segment in chronological order.

[0095] The behavioral data stream has a complete behavioral event sequence structure, including fields such as stage number, task type, response time interval, switching point time mark, and stage start and end identifiers. Each stage data block contains a response behavior event chain, and the stages are connected through task switching nodes to form a complete user behavior execution trajectory.

[0096] Furthermore, the system constructs a task transition record between behavioral segments, including structures such as the jump path from the main task to the interruption task and the regression path from the interruption task to the recovery task, and embeds a task switching flag in the behavioral data stream. This structure will be used in S310 to calculate metrics such as switching time consumption and recovery time.

[0097] Finally, the system outputs the behavioral data stream throughout the entire process of the main task - interruption task - recovery task, as the basic data set for constructing metrics in the S300 stage, and as evidence of behavioral performance in the S400 stage ability modeling.

[0098] By implementing the steps of S210, S220, and S230, the system realizes a full-process closed loop from experimental task control to user behavior response collection, then to response behavior segmentation and behavioral data stream construction, forming a continuous path structure of task-driven - behavior mapping - metric generation. The constructed segmented response time data and behavioral data stream provide a clean, structured, and traceable data basis for subsequent metric calculations, improving the accuracy and robustness of response feature extraction and ability modeling in interruption response ability evaluation.

[0099] Step S300 at least includes steps S310 - S330:

[0100] S310. Obtain the behavioral data stream and calculate metrics such as task switching time consumption, task recovery time consumption, and reaction delay time.

[0101] Specifically, the behavior data stream is constructed in step S230, which has completed the complete division of the main task segment, the interrupt task segment, and the recovery task segment, and marked the task type, response time, task switching node, and phase identifier. The system first extracts the task switching flags between each segment of tasks from the behavior data stream, confirms the first switching event and recovery event between the main task and the interrupt task, and identifies the timestamps of the task switching point and the recovery point.

[0102] After identifying the task switching structure, the system calculates three types of time-related metrics based on the timestamps: task switching time consumption, task recovery time consumption, and reaction delay time metric. Among them, the task switching time consumption refers to the interval time between the last effective response of the main task and the first response of the interrupt task, and the task recovery time consumption refers to the interval time between the last response of the interrupt task and the first response after the main task is restored; the reaction delay time metric refers to the delay time of the user's first behavior response relative to the start time of the task display within each task segment.

[0103] The above three metrics are all based on behavior events, obtained through the time series difference method, and appended to the behavior data stream structure, providing structured input for the subsequent data cleaning and standardization processing module.

[0104] S320. Perform data cleaning and standardization processing on the task switching time consumption, task recovery time consumption, and reaction delay time metric.

[0105] After receiving the three types of time-related metrics calculated in step S310 in this step, data quality filtering, error handling, and structural standardization conversion are performed to ensure the analysis stability, sample consistency, and statistical applicability of the metrics.

[0106] Specifically, the system first filters out the missing values, out-of-limit values, and duplicate values in the task switching time consumption, task recovery time consumption, and reaction delay time metric. Among them, the missing values adopt the interpolation completion strategy, the out-of-limit values are removed according to the set threshold, and the duplicate records are merged by the task structure mapping rule.

[0107] The cleaned time-related metrics are re-archived in the form of a data sequence and standardized according to the task type and task segment marker. The standardization processing method adopts interval scaling and distribution alignment, so that the time consumption metrics under different task types can be compared on a unified scale. The standardization processing also includes steps such as data centering, variance normalization, in-task sequence sorting, and behavior state identifier embedding.

[0108] The processed task switching time consumption, task recovery time consumption, and reaction delay time metric will retain the task number, paragraph marker, and user identifier, and output a structured metric sequence table, providing basic support for the identification of the behavior fluctuation interval and the construction of the feature metric set in S330.

[0109] S330. Based on the standardized processing results, identify the behavior fluctuation intervals, and generate perturbation annotation information and a set of characteristic indicators.

[0110] In this step, after receiving the task switching time, task resumption time, and reaction delay time indicators that have been standardized, through behavior change trend analysis and abnormal event recognition, determine the behavior fluctuation intervals, and output structured perturbation annotation information and a set of characteristic indicators.

[0111] Specifically, the system performs internal task behavior stability detection based on the change curves of each response time in the standardized indicator sequence. The system conducts trend clustering and sliding window analysis on the upper and lower fluctuation intervals of consecutive response time intervals, and marks them as behavior fluctuation intervals in scenarios such as a significant increase in response time, a decrease in frequency, or response loss.

[0112] After identifying the behavior fluctuation intervals, the system combines the task stage identifier and user marks to assign each behavior fluctuation interval to the main task segment, interrupted task segment, or resumed task segment, and marks the behavior perturbation sources, including behavior feature labels such as device interference, a sharp increase in task difficulty, and loss of attention.

[0113] The system constructs a set of characteristic indicators based on the perturbation annotation information. The set includes dimensions such as task switching time statistical features, recovery time trend slope, interval variance of reaction delay, perturbation duration distribution, and perturbation response fluctuation amplitude. The structure of the set of characteristic indicators contains indicator numbers, indicator types, associated task segments, and numerical fields for use by the subsequent S400 module for ability modeling.

[0114] By implementing steps S310, S320, and S330, the system completes the process of layer-by-layer extraction from behavior response events to time-based indicators, and then to stability features and perturbation labels. The formed task switching time, task resumption time, and reaction delay time indicators construct the quantitative expression basis for individual interruption response behaviors, while the behavior fluctuation intervals and perturbation annotation information further achieve the structured feature capture of cognitive stability and adjustment efficiency, providing a solid data support and behavior interpretation basis for the construction of the ability assessment model and the scoring strategy.

[0115] Step S400 includes at least steps S410 - S430:

[0116] S410. Obtain the set of characteristic indicators and the perturbation annotation information, and construct an ability evidence structure and an ability mapping relationship table.

[0117] The characteristic indicator set and the disturbance annotation information were generated in the previous step S330. The characteristic indicator set includes standardized statistical indicators for task switching time, task recovery time, and reaction delay time, as well as behavioral fluctuation characteristics such as disturbance duration, response variance, and response stability. The disturbance annotation information is the abnormal response marker identified during the behavioral fluctuation period, including but not limited to identification fields such as loss of attention, high time-consuming sudden change, and frequency decrease.

[0118] This step first acquires the aforementioned structured data set, establishes a capability mapping reference structure, and constructs a capability evidence structure. This capability evidence structure is used to express the parameter link from the behavior layer to the capability layer, specifically including: behavior indicator number, source task stage, behavior event characteristics, disturbance identification label, response trend category, and numerical expression.

[0119] During the construction process, the system categorizes and labels each indicator's behavior segment information within the task flow, integrating it with the corresponding disturbance annotation information. For each indicator set, the system establishes behavior segment relationships, disturbance interaction relationships, and assessment role identifiers (e.g., switching ability, recovery efficiency, cognitive load tolerance, etc.).

[0120] Furthermore, the system maps the fused capability evidence structure to behavioral data records and generates a capability mapping table. This table uses behavioral indicators as source nodes and capability labels as target nodes, establishing a one-to-many or many-to-one mapping relationship. Each mapping record includes the source indicator ID, target capability name, weight factor reference range, perturbation intervention impact, and task source tag.

[0121] S420: Combine the capability evidence structure and the experimental task labels to establish a capability mapping relationship table between capability dimensions and task performance.

[0122] After the capability mapping relationship table is constructed in S410, this step further combines the structure with the experimental task label to complete the capability dimension construction and improve the capability mapping description of the task presentation layer.

[0123] Specifically, this step first obtains the experimental task label, which is generated during the task structure construction process of S110-S130, including structural fields such as task type (operation type, memory type), task segment attributes (main task, interrupt task, recovery task), task difficulty coefficient, and information interference category.

[0124] The system performs joint structure modeling on the experimental task labels and the ability mapping relationship table, and constructs a hierarchical ability mapping table based on the task dimension. This ability mapping table consists of three parts: the ability dimension layer, the task label layer, and the behavior index layer. The system classifies the ability indicators showing consistent behavior patterns under the same task label into the same ability dimension, such as "cognitive flexibility", "attention switching ability", and "interruption recovery ability".

[0125] During the modeling process, the system further classifies the nodes in the ability mapping relationship table and establishes a task mapping path. In the path, the source node is the feature index, the first-hop connection is the perturbation label, the second-hop is the task label, and the final hop is the ability dimension node. The system performs path integrity check and label consistency verification on this path, and eliminates the invalid nodes caused by task switching failure or incomplete data.

[0126] The final output is the ability dimension mapping structure table, which contains information such as the set of feature indicators associated with each ability dimension, the corresponding task segment number, the mapping path diagram structure, and the number of nodes. This structure provides an input framework for the subsequent factor analysis model.

[0127] S430. Perform confirmatory factor analysis processing on the ability mapping relationship table to generate an ability factor parameter set.

[0128] After completing the mapping of the ability dimension and task performance, this step inputs the structured ability mapping relationship table into the modeling engine, performs confirmatory factor analysis processing, and outputs a quantifiable ability factor parameter set for individual ability difference modeling and scoring strategy matching.

[0129] Specifically, the system calls the confirmatory factor modeling module and imports the ability mapping relationship table and the experimental sample set. The system first performs dimension initialization processing, specifies the behavior index set, task label structure, and perturbation label status for each ability dimension, and performs parameter nesting processing.

[0130] The system aggregates the indicators under the ability dimension according to the structural consistency of the task label layer and the behavior index layer to form a factor observation matrix. The observation matrix records the behavior performance scores of the user under each ability dimension, and combines the previous standardization processing results to form a unified data scale.

[0131] Subsequently, the system performs model fitting and confirmatory factor analysis operations, confirms the factor contribution degree of each indicator through the load coefficient of the behavior indicator under multiple ability dimensions, and adjusts the model structure and path coefficient. The obtained ability factor parameter set includes structural fields such as the ability dimension name, the set of core observation indicators, the average weight of the indicators, the load intensity, the factor variance interpretation rate, and the factor correlation coefficient matrix.

[0132] The generated set of ability factor parameters is saved in the form of a standardized vector and serves as the sole basis for input to the S510 scoring model, which is used to match the scoring template library and calculate the interruption response ability score.

[0133] By executing steps S410, S420, and S430, the system has completed the complete transformation from the set of feature indicators and perturbation annotation information to the ability dimension modeling, and established an ability mapping network among multiple tasks, multiple indicators, and multiple labels. The set of ability factor parameters extracted based on confirmatory factor analysis provides a structurally rigorous and numerically quantifiable evaluation basis for subsequent ability scoring, effectively improving the accuracy, interpretability, and generalization ability of the interruption response ability modeling.

[0134] Step 500 includes at least steps S510 - S530:

[0135] S510. Obtain the set of ability factor parameters, match the scoring template library, and calculate the individual interruption response ability score.

[0136] In this step, the standardized ability indicators and their corresponding time - change response functions are obtained from the set of ability factor parameters, and an ability comprehensive evaluation model including the functional integral of the time derivative is designed.

[0137] The system first extracts the following input variables from the set of ability factor parameters output in the previous steps:

[0138] Ability factor load

[0139] Standardized feature indicators , such as from the standardized sequence of task - switching time, task - resumption time, and reaction delay time

[0140] Dynamic response function , representing the response change of the th indicator during the evaluation period

[0141] Functional integral weighting coefficient

[0142] Based on the above data, the following original score function is constructed:

[0143] ①

[0144] ①

[0145] Where:

[0146] : Individual interruption response ability score;

[0147] : Total number of ability factor dimensions; ​

[0148] : Ability factor loading, derived from the factor analysis model;

[0149] : Standardized ability characteristic index, derived from the feature aggregation of behavioral data streams;

[0150] : The th response function of the ability index, representing the change curve of the task switching response at different times;

[0151] : Weighting factor corresponding to the time series factor;

[0152] : Total task cycle time, in seconds (e.g., the experiment duration is 120 seconds);

[0153] : Reflect the dynamic change trend of the index within the task cycle.

[0154] Formula ① introduces the change rate of behavioral characteristics in the time domain, enabling the index score to reflect the user's dynamic response ability during task interruption - recovery, and making up for the time series blind spot of static scoring. The weight values of each factor are as follows: , , derived from the maximum likelihood estimation of historical samples.

[0155] S520. Based on the interruption coping ability score, match the scoring grade boundary rule to generate an ability grade label.

[0156] To achieve the labeling process of the ability grade, the system matches the scoring grade boundary rule composed of a multi-level piecewise function according to the score generated in step S510 to generate three types of grade labels.

[0157] ②

[0158] ②

[0159] Among them:

[0160] : Represents the interruption coping ability grade label;

[0161] , : Are the grade scoring boundary thresholds, and the recommended values are , , which can be dynamically adjusted according to the task complexity;

[0162] If the task template difficulty is marked as "high", then can be increased to 70 to adapt to higher scoring accuracy requirements.

[0163] The mapping function can be automatically generated according to the label distribution in the training set. Its purpose is to map continuous scores to discrete levels for subsequent task recommendation matching and visualization display.

[0164] S530. Structurally bind the interruption response ability score and the ability level label to generate score recommendation result data.

[0165] The system constructs the following mapping structure function , and binds the score and the level label to generate a complete score recommendation result structure:

[0166] ③

[0167] ③

[0168] Where:

[0169] : Score recommendation result data;

[0170] : User unique identifier;

[0171] : Evaluation timestamp;

[0172] : Experimental task number;

[0173] : Ability dimension summary, such as "Reaction stability: 89, Switching agility: 82";

[0174] : Ability-task adaptation identifier, used to judge the matching degree in S600.

[0175] The system also performs the following normalization operations on the output results:

[0176] Compress the factor summary in into a dimension structure table;

[0177] Round to 1 decimal place;

[0178] Add a field verification mechanism to ensure that each score result structure has complete fields.

[0179] This structure will be used as the input source in the subsequent task adaptation discrimination module (S600) to drive the logic engine for task template pushing.

[0180] Explanation of the connection with the previous and subsequent steps

[0181] Connection with the previous step:

[0182] The ability factor parameter set output by S430 is used as the basic input for Formula ①;

[0183] The output of Formula ① is the input for Formula ②;

[0184] The output of Formula ② and are simultaneously referenced by ③ to complete the structure binding.

[0185] Subsequent step transfer:

[0186] The scoring recommendation result data is used as the input for S610 for task ability matching and vector generation;

[0187] The field will participate in the similarity calculation process and be compared with the task scenario label for comparison;

[0188] The field is used for the visual rendering of the personalized ability growth path.

[0189] By introducing an original mathematical model that combines functional analysis, high-order derivative integration, and set mapping structure, S510–S530 successfully constructs a high-dimensional conversion path from ability factors to scores, scores to labels, and labels to structures. The formula not only retains the quantitative differences of the original indicators but also reflects their time-domain dynamic characteristics during the task execution process, realizing a static–dynamic combined ability evaluation system. This mechanism improves the evaluation accuracy, enhances the sensitivity to behavior fluctuations and ability responses, is significantly superior to the traditional average weighted score model, and has outstanding innovation and practical value.

[0190] Step S600 includes at least steps S610 - S630:

[0191] S610. Obtain the scoring recommendation result data, combine it with the task scenario label, and perform a task ability adaptation discrimination operation.

[0192] In this step, an ability adaptation discrimination operation is performed based on the scoring recommendation result data and the task scenario label to achieve a closed-loop conversion from score output to task recommendation structure.

[0193] Specifically, the system first calls the scoring recommendation result data output by the S530 structure binding module, which includes fields: individual interruption response ability score, ability level label, ability dimension summary, and task matching identifier. This scoring recommendation result data has been structured and encapsulated in the system, with a unique identifier and traceability.

[0194] Further, the system calls the preset task scenario tag set in the task tag database and compares this set with the task matching identification field in the scoring recommendation result data. The task scenario tags include a task complexity tag, a switching frequency tag, an attention allocation requirement tag, and a response accuracy requirement tag, which respectively correspond to the structural parameter sets of the main task and the interrupt task templates.

[0195] The system performs the mapping discrimination of ability-scenario tags through a structural comparison method, specifically including: performing a matching discrimination logic on each ability dimension summary field in the scoring recommendation result data to determine whether the ability score structure of the current individual meets the threshold criteria set in the candidate task scenario tags. For example, when the "recovery efficiency" is lower than the set threshold and the task scenario tag requires "high-intensity continuous recovery performance", it is determined that this task template is not suitable.

[0196] Finally, the system outputs a set of task ability adaptation discrimination operation results, which includes an adapted task tag list, a non-adapted tag list, and a task recommendation confidence weight field, providing a decision basis for generating the subsequent matching task template set.

[0197] S620. Select an adapted task template set according to the task ability adaptation discrimination operation result and generate a matching task vector.

[0198] This step is based on the task ability adaptation discrimination operation result, screens an adapted task template set from the task template library, and generates a matching task vector accordingly.

[0199] Specifically, the system extracts all task template sets with complete structure identifiers from the task template library. This set includes the main task template structure and the interrupt task template structure. Each task template contains five-dimensional fields: a structure encoding, a task requirement tag, an interaction process, a switching logic, and a coping ability requirement tag.

[0200] The system performs a structural mapping of the adapted tag list in the task ability adaptation discrimination operation result and the task requirement tags in the template library, screens out the task template set with a matching rate higher than the threshold, and forms the current individual ability-task adaptation set.

[0201] On this basis, the system performs parameter vectorization processing on each screened task template, extracts its core parameters such as the task structure encoding, switching complexity parameter, recovery rhythm intensity factor, and interaction requirement intensity factor, and performs sequence encoding according to a unified rule to form a matching task vector.

[0202] Each dimension in the matching task vector corresponds to a first-level structural variable in the task modeling parameters, which will be referenced in subsequent task structure generation and display scheduling. The generated matching task vector will serve as the core input item for the interrupted task modeling parameter set, implementing the model-driven ability - task reconstruction logic.

[0203] S630. Use the matching task vector as the input parameter for the new round of interrupted task modeling, and feedback it in a closed loop to the interrupted scenario task modeling and experimental process control.

[0204] In this step, use the matching task vector as the input parameter for the new round of interrupted task modeling to achieve the closed-loop construction of the experimental process.

[0205] Specifically, the system first calls the interrupted task modeling parameter generator set in the task modeling module and injects the matching task vector into the task modeling parameter configuration interface. The field structure of the matching task vector is consistent with the task template set structure in S110, and the fields include task identification, switching trigger conditions, interaction response requirements, and timing rhythm control factors.

[0206] After the system inputs the task vector, according to the parameter processing logic in the original modeling process, it reconstructs the experimental task structure, including: automatically constructing a task parameter configuration table, resetting the interruption trigger timing and switching rhythm rules, updating the experimental process control table, and generating a new experimental process scheduling structure.

[0207] At the same time, the system performs parameter integrity verification and task template compatibility verification to ensure the deployability and data consistency of the new round of task structure.

[0208] Finally, the closed-loop formed experimental process scheduling structure will enter the task execution path again, driving subsequent task display, response collection, data calculation, ability modeling, and adaptation update to form a continuously evolving intelligent adaptation evaluation loop.

[0209] By implementing sub-steps S610 - S630, the system realizes the transformation logic from the interruption response ability structure scoring result to the individualized task recommendation structure, and completes the closed-loop adaptation of the ability - task structure body. This module constructs a dynamically updatable task matching mechanism, and based on the scoring result and task tags, realizes the adaptive ability modeling logic, with high adaptability, high responsiveness, and iterative optimization ability, providing the system with continuous evolution ability and task reconstruction ability, and significantly enhancing the application value of the interruption response ability evaluation result in actual task scheduling.

[0210] Embodiment 2: Figure 2 Show a structural block diagram of an interruption response ability evaluation data processing system according to an embodiment of the present invention. As Figure 2 shown, the structure may include:

[0211] The task modeling and process control module 10 is used to construct a task structure based on a set of task templates, configure task switching logic and time control, and generate an experimental process scheduling structure. Specifically, this module obtains the template sets of the main task and the interrupt task from the task template database, constructs a cross-task structure and generates a task parameter configuration table; further, according to the task parameter configuration table, sets the interrupt trigger timing and switching logic of the task, and generates an experimental process control table; finally, combines the experimental process control table to configure the task display sequence and time control logic, and outputs a complete and executable experimental process scheduling structure, providing structural guidance for the execution of subsequent experimental tasks and the collection of user interaction response data.

[0212] The behavior collection and data construction module 20 is used to present task content according to the experimental process scheduling structure, record user responses and mark phases, and construct a complete behavior data stream. Specifically, this module alternately presents the main task and the interrupt task in sequence according to the generated experimental process scheduling structure, and real-time collects the user's interaction response data, including reaction duration, response method, and task phase completion status; then performs task phase marking and timestamp recording processing on the collected user interaction response data to form response time segmented data; finally, based on the response time segmented data, constructs a continuous behavior data stream covering the whole process of the main task, the interrupt task, and the recovery task, providing a complete data basis for subsequent data analysis.

[0213] The index extraction and feature construction module 30 is used to calculate time indexes based on the behavior data stream, complete data standardization processing, and generate perturbation annotation information and a set of feature indexes. Specifically, this module extracts key time indexes such as task switching time consumption, task recovery time consumption, and reaction delay time from the behavior data stream; further performs data cleaning and standardization processing on the extracted time indexes to eliminate abnormal data and scale differences; then identifies the individual's behavior fluctuation range according to the standardized data, and generates accurate perturbation annotation information and the corresponding set of feature indexes, providing data input for subsequent ability dimension modeling.

[0214] The ability modeling module 40 is used to construct a mapping relationship by combining the set of feature indexes and the experimental task labels, perform factor analysis processing and generate a set of ability factor parameters. Specifically, this module uses the set of feature indexes and the perturbation annotation information to construct an ability evidence structure and an ability mapping relationship table, and further combines the experimental task labels to clarify the corresponding relationship between the ability dimension and the task performance; then performs confirmatory factor analysis processing on the ability mapping relationship table to obtain a clear, definite, and stable set of ability factor parameters, providing a reliable factorized data basis for subsequent ability score calculation and label generation.

[0215] The scoring and grading module 50 is used to match the scoring template library, calculate the individual's interruption coping ability score, generate an ability level label based on the grade boundary, and output the scoring recommendation result data. Specifically, this module matches the preset scoring template library according to the set of ability factor parameters, and calculates the score of the individual's interruption coping ability; further, according to the calculated ability score value, it calls the built-in scoring grade boundary rule to generate a structured ability level label; finally, it structurally binds the individual ability score and the corresponding level label to form unified scoring recommendation result data, providing a scoring basis for subsequent task ability adaptation decisions.

[0216] The adaptation recommendation module 60 is used to complete the discrimination of task ability adaptation based on the scoring recommendation result data, generate a matching task vector and feedback it to the task modeling process. Specifically, this module first obtains the scoring recommendation result data, combines it with the task scenario label, and performs the adaptability discrimination operation of ability and task scenario to determine the task characteristics suitable for the individual to execute; subsequently, according to the result of the adaptation discrimination, it accurately selects the set of adapted task templates from the preset task template library, and generates a structured matching task vector based on the selected templates; finally, it closes the loop and feeds back the matching task vector to the task modeling and process control module to drive the re-modeling of the new round of interruption task structure and the control of the experimental process, forming a continuously optimized evaluation feedback loop.

[0217] The beneficial effects of the above embodiments are as follows:

[0218] The interruption coping ability evaluation data processing system provided by the present invention completely covers the whole process from the construction of the experimental task structure to the individual ability evaluation and task adaptation recommendation, significantly improving the structured level of the evaluation data and the accuracy of analysis; the system effectively improves the recognition accuracy and reliability of the interruption coping ability through the accurate collection of task interaction response data, the accurate extraction of characteristic indicators and factor analysis modeling; further, through the closed-loop feedback mechanism, it realizes the dynamic update of the individual task adaptation ability and the real-time reconstruction of the task structure, forming a continuously evolving evaluation and training closed-loop, ensuring the sustainable optimization and long-term stable operation of the system; at the same time, the intuitive user interface and the perfect real-time monitoring and guarantee mechanism improve the user experience and decision-making efficiency, ensuring the practicality and reliability of the system in actual applications, and having significant technical advantages and promotion value.

Claims

1. A method for processing evaluation data of interruption response capabilities, characterized in that It includes the following steps: Construct a task structure, configure task switching logic and time control, and generate an experimental process scheduling structure; Present task content according to the experimental process scheduling structure, record user responses and mark phases, and construct a behavioral data stream; Calculate time metrics based on the behavioral data stream, perform data standardization processing, and generate perturbation annotation information and a set of feature metrics; Construct a mapping relationship by combining the set of feature metrics and experimental task labels, perform factor analysis processing, and generate a set of ability factor parameters; According to the set of ability factor parameters, match the scoring template library, and calculate the individual's ability score for coping with interruptions. The individual's ability score for coping with interruptions is: ； Among them, is the individual's interruption coping ability score; is the total number of ability factor dimensions; is the ability factor loading, which is derived from the factor analysis model, and the input framework of the factor analysis model is the mapping relationship constructed by the feature index set and the experimental task label; is the standardized ability feature index, and the standardized ability feature index represents the standardized sequence of the task switching time, task recovery time, and reaction delay time included in the feature index set; is the response function of the i-th ability index, and the response function represents the response change of the i-th ability index in the evaluation period ; is the weighting factor corresponding to the time series factor; is the total task cycle time; reflects the dynamic change trend of the index within the task cycle; According to the individual's ability score for coping with interruptions, call the grade boundary to generate a label, and output the scoring recommendation result data. The expression of the scoring recommendation result data is: ； Among them, is the scoring recommendation result data; is the mapping structure function; is the label representing the level of interruption response ability; is the individual interruption response ability score; is the unique user identifier; is the evaluation timestamp; is the experimental task number; is the ability dimension summary; is the ability-task adaptation identifier; Based on the scoring recommendation result data, complete the discrimination of task ability adaptation, generate a matching task vector, and feedback it to the task modeling process.

2. The method according to claim 1, characterized in that, The steps for constructing the task structure include: Obtain the task template sets of the main task and the interrupt task, construct a cross-task structure, and generate a task parameter configuration table; Set the interruption trigger timing and task switching logic based on the task parameter configuration table, and generate an experimental process control table; Combine the experimental process control table to configure the task display order and time control logic, and output the experimental process scheduling structure.

3. The method according to claim 1, wherein The steps for constructing the behavioral data stream include: Obtain the experimental process scheduling structure, alternately present the main task and the interrupt task, and collect user interaction response data; Perform task phase marking and timestamp recording on the user interaction response data to generate response time segmented data; Construct the behavioral data streams of the main task, the interrupt task, and the recovery task based on the response time segmented data.

4. The method according to claim 1, characterized in that The steps for calculating time metrics include: Obtain the behavioral data stream, and calculate the task switching time consumption, task recovery time consumption, and reaction delay time metrics; Perform data cleaning and standardization processing on the task switching time consumption, task recovery time consumption, and reaction delay time metrics; Based on the results of the standardization processing, identify the behavioral fluctuation interval, and generate perturbation annotation information and a set of feature metrics.

5. The method according to claim 1, wherein The steps for constructing the mapping relationship include: Obtain the set of feature metrics and perturbation annotation information, and construct an ability evidence structure and an ability mapping relationship table; Combine the ability evidence structure and the experimental task labels to establish an ability mapping relationship table between the ability dimension and task performance.

6. The method according to claim 1, wherein The steps for generating the set of ability factor parameters include: Perform factor analysis processing on the ability mapping relationship table to generate the set of ability factor parameters.

7. The method according to claim 1, wherein The steps for generating the scoring recommendation result data include: Based on the score for coping with interruptions, match the scoring grade boundary rules to generate an ability grade label. The grade label is: Among them, represents the interruption response ability level label; is the individual interruption response ability score; , are the level scoring boundary thresholds; Perform structural binding on the score for coping with interruptions and the ability grade label to generate the scoring recommendation result data.

8. The method according to claim 1, wherein The steps for completing the discrimination of task ability adaptation include: Obtain the scoring recommendation result data, combine the task scenario label, and perform the discrimination operation of task ability adaptation; According to the results of the task ability adaptation discrimination operation, select the set of adapted task templates, and generate a matching task vector; Use the matching task vector as the input parameter for the new round of task modeling, and feedback it to the task modeling process.

9. A data processing system for evaluating the interrupt handling ability, characterized in that, It includes: The task modeling and process control module is used to construct the task structure, configure the task switching logic and time control, and generate the experimental process scheduling structure; The behavior acquisition and data construction module is used to present the task content according to the experimental process scheduling structure, record the user responses, and construct the behavior data stream; The metric extraction and feature construction module is used to calculate the time metrics based on the behavior data stream, perform data normalization processing, and generate the feature metric set; The ability modeling module is used to construct the mapping relationship by combining the feature metric set and the experimental task labels, perform factor analysis, and generate the ability factor parameter set; A scoring and grading module, which is used to match a scoring template library according to the set of ability factor parameters, calculate an individual's ability score for interrupt handling, and the individual's ability score for interrupt handling is as follows: ; where is the individual's ability score for interrupt handling; is the total number of ability factor dimensions; is the ability factor loading, which is derived from a factor analysis model, and the input framework of the factor analysis model is the mapping relationship constructed by the set of feature indicators and the experimental task labels; is the standardized ability feature indicator, and the standardized ability feature indicator represents a standardized sequence of task switching time, task recovery time, and reaction delay time included in the set of feature indicators; is the th response function of the ability indicator, and the response function represents the response change of the th ability indicator during the evaluation period; is the weighting factor for the corresponding time series factor; is the total task cycle time; reflects the dynamic change trend of the indicator during the task cycle; according to the individual's ability score for interrupt handling, call the level boundary to generate a label, and output the scoring recommendation result data. The expression of the scoring recommendation result data is: ; where is the scoring recommendation result data; is the mapping structure function; is the label representing the interrupt handling ability level; is the individual's ability score for interrupt handling; is the user's unique identifier; is the evaluation timestamp; is the experimental task number; is the ability dimension summary; is the ability-task adaptation identifier; The adaptation recommendation module is used to complete the task ability adaptation discrimination according to the scoring recommendation result data, generate the matching task vector and feedback it to the task modeling process.

Images