Subject selection response testing method and device and storage medium

Abstract

The invention relates to the technical field of subject cognition testing, and discloses a subject selection response testing method and device and a storage medium, the testing is divided into at least two stages, multi-dimensional biological information of a subject in the testing process is obtained, the multi-dimensional biological information can reflect the comprehensive performance of the subject in the testing process, and the comprehensive performance of the subject in the testing process can be reflected by the multi-dimensional biological information. And the performance grade of the subject can be determined through the multi-dimensional biological information, so that a reliable basis is provided for generation of a customized test scheme in the next step. And finally, a target display strategy, a plurality of target selection objects and a plurality of target interference objects of the next stage are generated in a customized manner by integrating historical test results and subject performance levels corresponding to the historical test results. The test of the next stage is generated based on historical test and comprehensive performance, so that the pertinence is higher, the obtained test result is more reliable, and finally the reliability of the subject selection reaction test is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of subject cognitive testing, and particularly relates to a subject choice reaction testing method and device and a storage medium. BACKGROUND

[0002] Choice reaction time (CRT) is a key indicator in cognitive psychology, used to assess the time from stimulus recognition to decision-making to reaction when facing multiple options. It reflects attention allocation, decision-making speed and executive control ability, and is usually measured through experimental tasks (such as two-choice or multiple-choice button reaction).

[0003] In the prior art, the choice reaction test is usually prepared in advance, and then the subject is tested based on the corresponding hardware, for example, the tester wears earphones in front of a clickable screen, and the test content is output through the screen and the earphones, and then the test result is obtained based on the user's clicks, and finally the test score is obtained. However, the reliability of the method of the prior art depends on the formulation of the test scheme, but in reality, a set of scheme may not be suitable for everyone, therefore, it is necessary to propose a customized choice reaction test method for subjects to improve the reliability of the subject choice reaction test. SUMMARY

[0004] The present application provides a subject choice reaction testing method and device and a storage medium, which can improve the reliability of the subject choice reaction test.

[0005] The first aspect of the present application discloses a subject choice reaction testing method, the method comprising: obtaining a historical test result of a subject, wherein the historical test result is obtained by detecting feedback information of the subject after a plurality of selection objects are displayed to the subject according to a preset display strategy; obtaining multi-dimensional biological information of the subject during the historical test, wherein the multi-dimensional biological information comprises one or more of eye contact information, expression information, screen dwell time information, body movement information and heart rate information; determining a subject performance level corresponding to the historical test according to the multi-dimensional biological information corresponding to the historical test, wherein the subject performance level is used to measure the difficulty of the subject in completing the test; determining a target display strategy, a plurality of target selection objects and a plurality of target interference objects for a next stage according to the historical test result and the subject performance level corresponding to the historical test; performing a next stage test, comprising: displaying the plurality of target selection objects and the plurality of target interference objects to the subject based on the target display strategy, and determining a choice reaction test result of the subject after detecting the feedback information of the subject.

[0006] As an optional implementation, in a first aspect of the present invention, the method further includes: Obtain the multidimensional biometrics of the subjects during the next stage of testing, and determine the subject's performance level for the next stage of testing based on the multidimensional biometrics of the next stage of testing. Based on the results of the selection response test and the subject's performance level corresponding to the next stage test, the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage are redefined, and the execution of the next stage test is retried. The operation of obtaining the subject's multi-dimensional biological information during the next stage test is also triggered, and the subject's performance level corresponding to the next stage test is determined based on the multi-dimensional biological information corresponding to the next stage test. Obtain the selection response test results corresponding to each next stage test, and determine whether the subject performance level corresponding to the next stage test for a consecutive preset number of times is a preset high difficulty level; if so, obtain the selection response test results corresponding to multiple subject performance levels at a preset adaptation difficulty level as reliable selection response test results.

[0007] As an optional implementation, in a first aspect of the present invention, determining the subject performance level corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test includes: Input the multi-dimensional biological information corresponding to the historical test into the pre-trained subject performance analysis model to obtain the analysis results output by the subject performance analysis model, and determine the subject performance level corresponding to the historical test based on the analysis results; The subject performance analysis model is obtained by training a pre-set training dataset, which includes training multidimensional biological information and subject performance level labels corresponding to the training multidimensional biological information.

[0008] As an optional implementation, in a first aspect of the present invention, the method further includes: Based on the preset display strategy corresponding to the historical test, multiple selection objects, and the multi-dimensional biometric information corresponding to the historical test, the subject's interest matrix is ​​determined. The interest matrix is ​​used to represent the subject's degree of interest in different test contents in the historical test. And, the step of determining the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage based on the historical test results and the subject performance level corresponding to the historical test includes: Based on the interest matrix, multiple target selection objects and multiple target interference objects are determined for the next stage, including image objects and / or sound objects; Based on the historical test results and the subject performance level corresponding to the historical test results, a target display strategy for the next stage is determined. The target display strategy is used to control the dynamic changes of the target selection object and the target interference object during the display.

[0009] As an optional implementation, in a first aspect of the present invention, determining the subject's interest matrix based on a preset display strategy corresponding to historical tests, multiple selection objects, and multi-dimensional biometric information corresponding to the historical tests includes: The test content matrix is ​​determined based on the preset display strategy corresponding to the historical test and multiple selection objects. The elements in the test content matrix include one or more of the following: shape objects, color objects, size objects, and sound objects. Based on the multi-dimensional biological information, the weight of each element in the test content matrix is ​​calculated to obtain the weight value corresponding to each element; The subject's interest matrix is ​​determined based on the test content matrix and the weight value corresponding to each element in the test content matrix.

[0010] As an optional implementation, in a first aspect of the present invention, determining the target display strategy for the next stage based on the historical test results and the subject performance level corresponding to the historical test results includes: Based on the historical test results, determine the corresponding position of the historical test results in the pre-stored test result database, which is a database established after analyzing the distribution patterns of the population selection response test results; Based on the subject's performance level corresponding to the historical test results, determine the performance level for the next stage and the level difference. Based on the grade difference and the corresponding position of the historical test results in the pre-stored test result database, determine the target position of the next stage test plan in the test result database. Based on the target location, determine the target display strategy for the next stage.

[0011] As an optional implementation, in a first aspect of the present invention, the step of calculating the weight of each element in the test content matrix based on the multi-dimensional biological information to obtain the weight value corresponding to each element includes: The historical tests are divided into different test nodes, and the node elements corresponding to each node are determined. The node elements include one or more of the following: shape objects, color objects, size objects, and sound objects. Based on the multi-dimensional biological information, determine the node multi-dimensional biological information corresponding to each test node; For each node, the sub-weights of each node element are determined based on the multi-dimensional biological information of the node. Based on the sub-weights of each node element corresponding to all nodes, the weight of each element in the test content matrix is ​​calculated to obtain the weight value corresponding to each element.

[0012] A second aspect of the present invention discloses a subject selection response testing device, the device comprising: The first acquisition module is used to acquire the subject's historical test results, wherein the historical test results are obtained by displaying multiple selection objects to the subject through a preset display strategy and then detecting the subject's feedback information. The second acquisition module is used to acquire multi-dimensional biometric information of the subject during historical tests. The multi-dimensional biometric information includes one or more of the following: eye contact information, facial expression information, screen dwell time information, body movement information, and heart rate information. The rating determination module is used to determine the subject performance rating corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test. The subject performance rating is used to measure the difficulty of the subject completing the test. The analysis and determination module is used to determine the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage based on the historical test results and the subject performance level corresponding to the historical test. The test execution module is used to execute the next stage of testing, including: presenting the subject with multiple target selection objects and multiple target interference objects based on the target display strategy, and determining the subject's selection response test results after detecting the subject's feedback information.

[0013] As an optional implementation, in a second aspect of the invention, the apparatus further includes a cycle test module, the cycle test module being configured to perform the following operations: Obtain the multidimensional biometrics of the subjects during the next stage of testing, and determine the subject's performance level for the next stage of testing based on the multidimensional biometrics of the next stage of testing. Based on the results of the selection response test and the subject's performance level corresponding to the next stage test, the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage are redefined. The test execution module is then triggered to perform the operation of the next stage test, as well as to trigger the operation of obtaining the subject's multi-dimensional biological information during the next stage test and determining the subject's performance level corresponding to the next stage test based on the multi-dimensional biological information corresponding to the next stage test. Obtain the selection response test results corresponding to each next stage test, and determine whether the subject performance level corresponding to the next stage test for a consecutive preset number of times is a preset high difficulty level; if so, obtain the selection response test results corresponding to multiple subject performance levels at a preset adaptation difficulty level as reliable selection response test results.

[0014] As an optional implementation, in a second aspect of the present invention, the specific operation method by which the level determination module determines the subject performance level corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test includes: Input the multi-dimensional biological information corresponding to the historical test into the pre-trained subject performance analysis model to obtain the analysis results output by the subject performance analysis model, and determine the subject performance level corresponding to the historical test based on the analysis results; The subject performance analysis model is obtained by training a pre-set training dataset, which includes training multidimensional biological information and subject performance level labels corresponding to the training multidimensional biological information.

[0015] As an optional implementation, in a second aspect of the invention, the apparatus further includes: The interest analysis module is used to determine the subject's interest matrix based on the preset display strategy corresponding to the historical test, multiple selection objects, and multi-dimensional biometric information corresponding to the historical test. The interest matrix is ​​used to represent the subject's degree of interest in different test content in the historical test. Furthermore, the analysis and determination module, based on the historical test results and the subject performance level corresponding to the historical test, determines the specific operational methods for the next stage's target display strategy, multiple target selection objects, and multiple target interference objects, including: Based on the interest matrix, multiple target selection objects and multiple target interference objects are determined for the next stage, including image objects and / or sound objects; Based on the historical test results and the subject performance level corresponding to the historical test results, a target display strategy for the next stage is determined. The target display strategy is used to control the dynamic changes of the target selection object and the target interference object during the display.

[0016] As an optional implementation, in a second aspect of the invention, the interest analysis module determines the specific operation method of the subject's interest matrix based on a preset display strategy corresponding to historical tests, multiple selection objects, and multi-dimensional biometric information corresponding to the historical tests, including: The test content matrix is ​​determined based on the preset display strategy corresponding to the historical test and multiple selection objects. The elements in the test content matrix include one or more of the following: shape objects, color objects, size objects, and sound objects. Based on the multi-dimensional biological information, the weight of each element in the test content matrix is ​​calculated to obtain the weight value corresponding to each element; The subject's interest matrix is ​​determined based on the test content matrix and the weight value corresponding to each element in the test content matrix.

[0017] As an optional implementation, in a second aspect of the invention, the analysis and determination module determines the specific operation method of the target display strategy for the next stage based on the historical test results and the subject performance level corresponding to the historical test results, including: Based on the historical test results, determine the corresponding position of the historical test results in the pre-stored test result database, which is a database established after analyzing the distribution patterns of the population selection response test results; Based on the subject's performance level corresponding to the historical test results, determine the performance level for the next stage and the level difference. Based on the grade difference and the corresponding position of the historical test results in the pre-stored test result database, determine the target position of the next stage test plan in the test result database. Based on the target location, determine the target display strategy for the next stage.

[0018] As an optional implementation, in a second aspect of the present invention, the specific operation method by which the interest analysis module calculates the weight of each element in the test content matrix based on the multi-dimensional biological information to obtain the weight value corresponding to each element includes: The historical tests are divided into different test nodes, and the node elements corresponding to each node are determined. The node elements include one or more of the following: shape objects, color objects, size objects, and sound objects. Based on the multi-dimensional biological information, determine the node multi-dimensional biological information corresponding to each test node; For each node, the sub-weights of each node element are determined based on the multi-dimensional biological information of the node. Based on the sub-weights of each node element corresponding to all nodes, the weight of each element in the test content matrix is ​​calculated to obtain the weight value corresponding to each element.

[0019] A third aspect of the present invention discloses a subject selection response testing system, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the subject selection response test method according to any of the first aspects of the present invention.

[0020] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when executed by a processor, implement some or all of the steps in the subject selection response test method described in any of the first aspects of the present invention.

[0021] Compared with the prior art, the present invention has the following beneficial effects: In this invention, the subject's choice response test protocol is not a one-time, unchanging plan. Instead, the test is divided into at least two phases, using historical test results as the basis for customizing the test protocol for the next phase. Simultaneously, this invention acquires multi-dimensional biometric information from the subject during the test. This information reflects the subject's overall performance, allowing for the determination of the subject's performance level corresponding to historical test results, thus providing a reliable basis for generating the next customized test protocol. Finally, this invention integrates historical test results and their corresponding performance levels to generate a customized test protocol for the next phase. Because the next phase's test protocol is based on the subject's historical test results and overall performance, it is more targeted, yielding more reliable test results and ultimately improving the reliability of the subject's choice response test. Attached Figure Description

[0022] 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.

[0023] Figure 1 This is a schematic flowchart of a subject selection response test method disclosed in an embodiment of the present invention; Figure 2 This is a schematic flowchart of another subject selection response test method disclosed in an embodiment of the present invention; Figure 3 This is a schematic flowchart of another subject selection response test method disclosed in an embodiment of the present invention; Figure 4 This is a histogram of male CRT distribution disclosed in an embodiment of the present invention; Figure 5 This is a histogram of female CRT distribution disclosed in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of a subject selection response testing device disclosed in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of a subject selection response testing system disclosed in an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0026] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0027] This invention discloses a method, apparatus, and system for testing subject selection responses, which can improve the reliability of subject selection response testing. These will be described in detail below.

[0028] Example 1 Please see Figure 1 , Figure 1 This is a schematic flowchart of a subject selection response test method disclosed in an embodiment of the present invention. Figure 1 The described subject selection response testing method can be integrated into a subject selection response testing device, which can be integrated into a cloud server or a local server. For example... Figure 1As shown, the subject's choice of response test method may include the following steps: Step 101: Obtain the subject's historical test results.

[0029] In this embodiment of the invention, historical test results refer to the test results generated by the subject based on historical tests up to the current time. These historical test results are obtained by displaying multiple selection objects to the subject using a preset display strategy and then detecting the subject's feedback. For example, in a selection response test, a target pattern is randomly generated on the screen, and the subject is required to quickly select the correct information corresponding to the target pattern to measure their selection response time.

[0030] Step 102: Obtain multi-dimensional biometric information of the subjects during historical testing.

[0031] In this embodiment of the invention, multidimensional biometric information may include one or more of the following: eye contact information, facial expression information, screen dwell time information, body movement information, and heart rate information. This multidimensional biometric information reflects the subject's overall performance during the test and provides a reliable basis for generating customized test plans in the next step. This embodiment of the invention addresses the problem in existing technologies where test plans are formulated only once and cannot be personalized for each subject. It divides the selection response test into historical tests and the next stage of testing, utilizing the results of historical tests and multidimensional biometric information to provide data support for the customized generation of the next stage of test plans.

[0032] Step 103: Determine the subject performance level corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test.

[0033] In this embodiment of the invention, the subject performance level is used to measure the difficulty of the subject completing the test; the performance level can show the subject's performance in relation to historical tests, which is helpful for analyzing the subject's performance and its fit with historical tests.

[0034] In an optional embodiment, determining the subject performance level corresponding to the historical test based on multi-dimensional biometric information may include: Input the multi-dimensional biometric information corresponding to the historical test into the pre-trained subject performance analysis model, obtain the analysis results output by the subject performance analysis model, and determine the subject performance level corresponding to the historical test based on the analysis results; The subject performance analysis model is obtained by training a pre-set training dataset, which may include multi-dimensional biological information for training and subject performance level labels corresponding to the multi-dimensional biological information for training.

[0035] Step 104: Based on the historical test results and the corresponding subject performance level, determine the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage.

[0036] In this embodiment of the invention, the next-stage target display strategy, multiple target selection objects, and multiple target interference objects constitute the test scheme for the next-stage selection response test. The target selection object is the core of detecting the subject's selection response ability; it is the object that the subject needs to select, presenting specific information requiring selection to the subject, who then makes a choice based on that information. The target interference objects serve to interfere with the subject's selection process. In some optional implementations, the target interference objects may not be required, and only the target selection objects are provided. Furthermore, the objects in the target selection objects and target interference objects may include image objects and / or sound objects. The target display strategy controls the dynamic changes of the target selection objects and target interference objects during display. Thus, by controlling the dynamic changes of the target selection objects and target interference objects during display through the target display strategy, a test scheme for the next stage of selection response is provided to the subject. Optionally, multiple combinations of target selection objects and target interference objects can be set in advance, along with multiple display strategies. Then, based on historical test results and the subject's performance level, multiple target selection objects and multiple target interference objects for the next stage can be determined from the multiple combinations of target selection objects and target interference objects; and the target display strategy for the next stage can be determined from the multiple display strategies set in advance.

[0037] Step 105: Perform the next stage test, which may include: presenting the subject with multiple target selection objects and multiple target interference objects based on the target presentation strategy, detecting the subject's feedback information, and determining the subject's selection response test results.

[0038] In this embodiment of the invention, the subject's choice response test plan is not a one-time, unchanging design. Instead, the test is divided into at least two stages, using historical test results as the basis for customizing the test plan for the next stage. Simultaneously, this embodiment acquires multi-dimensional biometric information of the subject during the test. This information reflects the subject's overall performance, allowing for the determination of the subject's performance level corresponding to historical test results, thus providing a reliable basis for generating the next customized test plan. Finally, this embodiment integrates historical test results and the corresponding subject performance levels to generate a customized test plan for the next stage. Because the next stage test plan is generated based on the subject's historical test results and overall performance, it is more targeted, yielding more reliable test results and ultimately improving the reliability of the subject's choice response test.

[0039] In an optional embodiment, the method in steps 101 to 104 is illustrated as follows: An adaptive subject selection response testing method. The invention concept of this method lies in utilizing multi-dimensional bio-information from the subject's historical tests to dynamically assess their cognitive load and task difficulty (performance level), and based on this, intelligently adjust the stimulus presentation strategy, objectives, and distractors of subsequent tests, thereby achieving personalized adaptation of test difficulty and more accurately measuring the subject's selection response capability boundary.

[0040] The system corresponding to this method mainly consists of four core modules: 1. Data Acquisition Module: Responsible for synchronously collecting the test results and biometric information of the subjects during the testing process.

[0041] 2. Data Analysis and Evaluation Module: Responsible for processing bioinformation and calculating the subject's performance level.

[0042] 3. Adaptive Strategy Engine: This is the core algorithm module that determines the test parameters for the next stage based on historical data.

[0043] 4. Test Presentation and Execution Module: Responsible for executing tests according to the instructions of the strategy engine and recording the results.

[0044] The implementation steps of this method are as follows: S1. Preset initial display strategy and object library, which may include: Display strategy: Set initial parameters, such as stimulus (selected object) presentation duration (e.g., 500ms), stimulus interval (ISI), screen layout (e.g., 4×4 grid), and the sequence of target appearance positions. This strategy should be of medium difficulty.

[0045] Select object library: Build a rich database of stimuli, such as graphics, symbols, numbers, words, pictures, etc., and pre-label their basic attributes, such as complexity and similarity.

[0046] Distractor Object Database: Similarly, a database of distractors is established. Distractors and target items have quantifiable similarity gradients, for example, from "completely different" to "highly similar".

[0047] S2. Perform the initial test and collect data, which may include: A test trial is formed by randomly selecting a set of target objects (e.g., 2) and a set of interference objects (e.g., 14) from the object library.

[0048] These objects are shown to the subjects using an initial pre-set strategy.

[0049] Collect feedback information: Record the subject's choice (click or touch), reaction time (RT), and whether it is correct or not.

[0050] Simultaneous collection of multi-dimensional biological information: Eye gaze information: The eye tracker collects the fixation point, fixation trajectory, and changes in pupil diameter.

[0051] Facial expression information: Micro-expressions are analyzed using computer vision algorithms (such as the FER2013 model) via camera to identify emotional states such as confusion, focus, and fatigue.

[0052] Screen dwell time: The total time from stimulus presentation to the subject's response.

[0053] Body motion information: Analyzes the frequency and amplitude of body movements such as swaying, leaning forward, and leaning backward using cameras or posture sensors.

[0054] Heart rate information: Heart rate and its variability (HRV) are acquired via a wrist-worn heart rate strap or camera-based photoplethysmography (rPPG).

[0055] S3. Data processing and performance rating steps, including: S31. Data Preprocessing: Biometric data is cleaned, denoised, and standardized. For example, heart rate data is filtered and smoothed, and eye-tracking data is calibrated and interpolated.

[0056] S32. Calculate performance level: Construct a performance rating model. The model takes multi-dimensional biological information as input and outputs a comprehensive "performance rating" score (e.g., 1-10, where 1 represents very difficult / cognitive overload and 10 represents very easy / effortless).

[0057] Model features may include: Cognitive load indicators: pupil dilation rate (positively correlated with cognitive load), decreased heart rate variability (positively correlated with stress / load).

[0058] Confusion and distraction indicators: the number of times the gaze point rapidly jumps between the target and non-target, the frequency and duration of confused expressions, and the increase in unconventional body movements.

[0059] Attention metrics: percentage of time spent gazing at the target object, and focused facial expressions.

[0060] Model building methods: Weighted scoring or machine learning models (such as Support Vector Machine (SVM) or Random Forest) can be used. Initially, expert rules can be used to define weights, and later, after accumulating sufficient data, supervised learning can be used for training (using the "difficulty" labeled by experts as labels).

[0061] The optional performance level determination method in this embodiment of the invention is as follows: Performance rating = 10 - (W1 × normalized pupillary change rate + W2 × normalized confused expression score + W3 × normalized body sway amplitude - W4 × normalized target fixation time percentage) W1, W2, W3, and W4 are the weights of each indicator, determined through experiments or data analysis.

[0062] S4. Adaptive policy generation steps, including: S41. Input: Historical test results and calculated performance level from the previous test phase.

[0063] S42. Strategy adjustment rules are determined, and the following options are available: (1) If the performance level is less than the preset first threshold and the accuracy is low: the test is deemed too difficult. In this case, the difficulty needs to be reduced. The target display strategy, multiple target selection objects, and multiple target interference objects are determined as follows: Target presentation strategies: extend stimulus presentation time and increase stimulus intervals.

[0064] Multiple target selection objects and multiple target interference objects: Select interference objects with lower similarity to the target, so that the difference is more obvious, or reduce the number of interference objects.

[0065] (2) Performance level is greater than the preset second threshold and accuracy is high with short reaction time: At this time, the difficulty needs to be increased, and the target display strategy, multiple target selection objects, and multiple target interference objects are determined as follows: Target presentation strategies: shorten stimulus presentation time, reduce stimulus intervals, and change the location of the target to make it less likely to be expected.

[0066] Multiple target selection objects and multiple target distractor objects: Select distractors with higher similarity to the target (more deceptive), or increase the number of distractors. More complex new target objects can even be introduced.

[0067] (3) Performance level between the first and second thresholds: The difficulty level is moderate. At this time, the difficulty level should be maintained but the stimulus should be changed. Only the target and non-target objects should be changed, while the policy parameters remain unchanged to avoid learning effects.

[0068] S43. Output: Determine the target display strategy, multiple target selection objects, and specific parameters of multiple target interference objects for the next stage of testing.

[0069] S5. Perform the next phase of testing, which may include: S51. The test presentation module receives instructions from the adaptive strategy engine.

[0070] S52. Following the new target presentation strategy, present the newly selected target selection object and target interference object to the subject on the screen.

[0071] S53. Repeat the data collection process in the first stage, detect the subject's feedback information, and simultaneously record multi-dimensional biological information.

[0072] S54. Determine the selection response test result (correctness or incorrectness and response time) for this test.

[0073] In an optional embodiment, the above method may further include: S6. Iteration and termination operations may include: The above steps S1-S5 form a closed loop and are continuously iterated.

[0074] The results and biometric information from each test are added to the subject's historical database, making the adaptive model increasingly accurate. If a subject's performance level remains stable over N consecutive rounds, it indicates that a stable capability boundary has been found, where N is a pre-defined number of stable tests, which is a positive integer.

[0075] In yet another optional embodiment, the selection response test results in the above method further include a selection response curve, which is used to: show the changes in the subject's performance at different difficulty levels.

[0076] In an optional embodiment, to further improve the reliability of the selected reaction test, such as Figure 2 As shown, the iteration and termination operations in step S6 may include: Obtain multidimensional biometrics of the subjects for the next stage of testing, and determine the subject's performance level for the next stage of testing based on the multidimensional biometrics of the subjects for the next stage of testing. Based on the results of the response test and the subject's performance level corresponding to the next stage test, the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage are redefined, and the execution of the next stage test is retried. The process of obtaining the subject's multi-dimensional biological information during the next stage test is also triggered, and the subject's performance level for the next stage test is determined based on the multi-dimensional biological information corresponding to the next stage test. Obtain the selection response test results for each subsequent stage test, and determine whether the subject's performance level for the next stage test for a consecutive preset number of times is the preset high difficulty level; if so, obtain the selection response test results corresponding to multiple subject performance levels at the preset adaptation difficulty level as reliable selection response test results.

[0077] In this optional embodiment, an iterative loop operation is constructed, where each test is an optimized version of the previous test. The customization method is the same as steps 101 to 105 of the embodiment of the present invention; that is, after each test, a test result and multi-dimensional biological information are obtained, and then a test plan for the next test is generated. This process is repeated continuously to obtain richer test data through multiple tests. The preset high difficulty level indicates that the subject's performance in the test is strenuous and difficult to complete; while the preset adaptive difficulty level indicates that the subject's performance in the test is adapted to their abilities, allowing the subject to maximize their choice and response capabilities. Specifically, the high difficulty level and adaptive difficulty level can be determined based on the preset performance levels.

[0078] During the testing process, the test results for each subsequent stage are obtained. If the subject's performance level for a consecutive preset number of test results is consistently at a preset high difficulty level, it indicates that the test has reached the subject's difficulty limit, and further testing will no longer yield data of reference value. Furthermore, the test results obtained at multiple adaptive difficulty levels are used as the final test result. This result, obtained at the adaptive difficulty level, reflects the subject's maximized choice response ability and is therefore called a reliable choice response test result. This reliable choice response test result has higher accuracy and reliability.

[0079] As can be seen, in this optional embodiment, through multiple tests, and with each test plan determined based on the test results of the previous test and multi-dimensional biometric information, the most suitable test plan for the subject can be found step by step, and the most matching test plan can be customized for them, which is conducive to improving the reliability of the test results. In addition, the test results obtained under multiple adaptation difficulty levels are used as the final test results. The test results obtained under these adaptation difficulty levels are made by the subject when their selection response ability is maximized, so their accuracy and reliability are higher.

[0080] Optionally, the difficulty of the next test generated after each test can be increased. When the subject's performance level in a test reaches the preset adaptive difficulty level, it indicates that the test plan matches the subject's selection and response ability well. In this case, the difficulty level of the subsequent preset number of tests remains unchanged, but the target selection object and the interference selection object change, thus obtaining several more test results with the subject's performance level at the adaptive difficulty level. The difficulty is then increased until the subject's performance level is consistently at the preset high difficulty level multiple times, indicating that the subject's testing limit has been reached and further testing is unnecessary.

[0081] Example 2 Please see Figure 3 , Figure 3 This is a schematic flowchart of another subject selection response testing method disclosed in an embodiment of the present invention. Figure 3 The described subject selection response testing method can be integrated into a subject selection response testing device, which can be integrated into a cloud server or a local server. For example... Figure 3 As shown, the subject's choice of response test method may include the following steps: Step 201: Obtain the subject's historical test results.

[0082] Step 202: Obtain multi-dimensional biometric information of the subjects during historical testing.

[0083] Step 203: Determine the subject performance level corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test.

[0084] In this embodiment of the invention, the specific implementation of steps 201-203 can be found in steps 101-103 of embodiment one of the invention, and will not be repeated here.

[0085] Step 204: Determine the subject's interest matrix based on the preset display strategy corresponding to the historical test, multiple selection objects, and multi-dimensional biometric information corresponding to the historical test.

[0086] In this embodiment of the invention, the interest matrix is ​​used to represent the degree of interest a subject has in different test contents in historical tests. To further provide customized testing plans, ensuring that test results are obtained when the subject's responsiveness is maximized, this application also considers the subject's interests when generating the next stage of the testing plan. By incorporating as many subjects' interests as possible into the testing plan, a more personalized testing plan can be obtained, ensuring that test results are obtained when the subject's responsiveness is maximized.

[0087] Step 205: Determine multiple target selection objects and multiple target interference objects for the next stage based on the interest matrix.

[0088] In this embodiment of the invention, the objects among the target selection object and multiple target interference objects may include image objects and / or sound objects. Specifically, they may include one or more of shape objects, color objects, size objects, and sound objects. For example, in a selection response test involving screen-displayed image information and audio-played sound information, the subject needs to click on the selection result based on the display of the target selection object and multiple target interference objects.

[0089] Step 206: Based on the historical test results and the corresponding subject performance levels, determine the target presentation strategy for the next stage.

[0090] In this embodiment of the invention, the target display strategy is used to control the dynamic changes of the target selection object and the target interference object during display. For example, it controls the appearance time, appearance form, duration, displacement direction, and color changes of the target selection object and the target interference object. The combination of the display strategy and the target selection object and the target interference object constitutes a complete testing scheme.

[0091] Step 207: Perform the next stage test, which may include: presenting the subject with multiple target selection objects and multiple target interference objects based on the target presentation strategy, detecting the subject's feedback information, and determining the subject's selection response test results.

[0092] As can be seen, in this embodiment of the invention, the subject's selection test plan is not a one-time, unchanging solution. Instead, the test is divided into at least two stages, using the results of previous tests as the basis for customizing the test plan for the next stage. Specifically, based on the test plan corresponding to the historical test results and the multi-dimensional biometric information corresponding to those results, an interest matrix for the subject is determined. Based on this interest matrix, multiple target selection objects and multiple target interference objects for the next stage are determined. Based on the historical test results and the subject's performance level corresponding to those results, a target display strategy for the next stage is determined. In this embodiment of the invention, the test plan for the next stage not only considers the subject's historical performance but also their interests. For example, multiple target selection objects and multiple target interference objects are closely matched with the subject's interests, which is beneficial for the subject to demonstrate their selection response ability. Therefore, this embodiment of the invention utilizes multi-dimensional biometric information to determine the subject's performance level and interest matrix, analyzing the subject's comprehensive historical test performance from multiple perspectives to obtain a more reasonable test plan for the next stage, ultimately resulting in more reliable and accurate selection response test results.

[0093] In an optional embodiment, determining the subject's interest matrix based on a preset display strategy corresponding to historical tests, multiple selection objects, and multi-dimensional biometric information corresponding to historical tests may include: Based on the preset display strategy corresponding to historical tests and multiple selectable objects, a test content matrix is ​​determined. Elements within the test content matrix can include one or more of the following: shape objects, color objects, size objects, and sound objects. Specifically, the multiple selectable objects include various image and sound elements. Elements can be automatically extracted from the test plan using a corresponding artificial intelligence model, or they can be manually labeled. For example, the test content matrix could be: {Portrait image, gray background, area 20-40 square centimeters, singing voice, 20-60 decibels, uniform pattern, brown hair, blue tie, double eyelids, single eyelids} The weight of each element in the test content matrix is ​​calculated based on multi-dimensional biometric information to obtain the weight value corresponding to each element. In this optional embodiment, the multi-dimensional biometric information can reflect the subject's interest in different elements. Optionally, multiple element objects can be varied in historical tests. Then, based on the subject's multi-dimensional biometric information (such as facial expressions, eye movements, heart rate, etc.), the elements that the subject is more interested in are determined, and different elements are assigned certain weight values. The larger the weight value, the more interested the subject is.

[0094] The subject's interest matrix is ​​determined based on the test content matrix and the weight value corresponding to each element in the test content matrix.

[0095] In this optional embodiment, further optionally, weighting each element in the test content matrix based on multi-dimensional biometric information to obtain a weight value corresponding to each element may include: The historical test is divided into different test nodes, and the node elements corresponding to each node are determined. The node elements may include one or more of the following: shape objects, color objects, size objects, and sound objects. Specifically, the historical test process is a flow of a set time period, which includes: video information played by the display device and / or sound information that affects the device's playback. Therefore, in order to obtain the subject's interest, the preset time can be divided into different time nodes, that is, test nodes. For example, every 10 seconds of testing is a test node. In this way, by analyzing each node, a better analysis of the subject's interest can be achieved.

[0096] Based on multidimensional biological information, determine the node multidimensional biological information corresponding to each test node; specifically, the multidimensional biological information of the subject during the time period between each test node and the next test node can be used as the node multidimensional biological information corresponding to that test node.

[0097] For each node, the sub-weights of each node element are determined based on the multi-dimensional biological information of the node.

[0098] Based on the sub-weights of each node element corresponding to all nodes, the weight of each element in the test content matrix is ​​calculated to obtain the weight value corresponding to each element.

[0099] As can be seen, the above operation divides the historical test into multiple test nodes. By analyzing each test node, the sub-weights of the node elements on each test node are obtained, which is the interest of the subjects in the node elements. Finally, by combining all test nodes, a more accurate weight value corresponding to each element is determined.

[0100] In another optional embodiment, determining the target presentation strategy for the next stage based on historical test results and the corresponding subject performance levels may include: Based on historical test results, the corresponding positions of the historical test results in the pre-stored test result database are determined. The test result database is a database established after analyzing the distribution patterns of the population's selection response test results. This database is built based on a large amount of data and can reflect the selection response patterns of the population. Therefore, it also provides a reference for the construction of the next stage test plan of this optional embodiment.

[0101] Based on the subject's performance level corresponding to the historical test results, the performance level for the next stage is determined, and the level difference is established. For example, the test difficulty can be increased based on historical test results to find the subject's testing limits. If the subject's performance level corresponding to the historical test results is a preset easy level, the next stage can be adjusted to an appropriate level; if the subject's performance level corresponding to the historical test results is a preset appropriate level, the next stage can be adjusted to a more difficult level. Optionally, a pre-defined correspondence between the performance level corresponding to the next stage test plan and the performance level corresponding to the historical test results can be established. Based on this correspondence, the performance level corresponding to the next stage test plan can be directly determined according to the subject's performance level corresponding to the historical test results.

[0102] Based on the grade difference and the corresponding position of historical test results in the pre-stored test result database, the target position of the next stage test plan in the test result database is determined; in this optional embodiment, the grade difference is converted into the next position in the database, that is, the change of the subject's performance level is reflected by its distribution pattern in the database, so as to determine a more reasonable target display strategy based on the target position.

[0103] Based on the target location, determine the target display strategy for the next stage.

[0104] As can be seen, this optional embodiment prepares a database in advance that can reflect the distribution pattern of the population's choice response data, and then maps the changes in performance level to different locations in the database, thereby more reasonably determining the target display strategy.

[0105] Examples of optional embodiments are illustrated below: The "Choice Reaction Time" (CRT) of participants to visual stimuli (person icons) was measured using a mobile application. A "two-choice" task was employed: if a male image appeared, the participant chose the male option below; if a female image appeared, the participant chose the female option below. Ten test results were included. In this task, a person image (male or female) appeared at random intervals 10 times, and participants were asked to choose the correct gender as quickly as possible. After each participant clicked on the previous image, the next image appeared randomly (at random times). This design aimed to prevent participants from perceiving any underlying rhythm or pattern in the image presentation, thus more accurately assessing their responses. The program recorded the time interval between the image appearance and the user's click, recording it as the CRT. A population CRT database was constructed by collecting multiple population CRT data. The Kolmogorov-Smirnov method and histograms were used to determine that the data originated from a normal distribution. Figure 4 Histogram of male CRT distribution and Figure 5 The histogram of CRT distribution in women is shown in Table 1. The distribution of CRT values ​​in different gender groups is shown in Table 1. Table 1. Distribution of CRT values ​​in different gender groups

[0106] Optionally, the population can then be further subdivided into different genders and age groups (17, 18, 19, 20, 21, 22-30), and a normal distribution probability density function can be constructed for each group. Matching the test results of the subjects with the aforementioned database can determine the corresponding position of historical test results in the pre-stored test result database. Subsequently, the target position is determined based on the level difference (e.g., advancing 2 levels or retreating 1 level). This target position is an important and distribution-compliant basis for generating test parameters. Therefore, determining the test parameters corresponding to the test scenario based on the target position allows for a more reasonable determination of the test parameters. The distribution data of male CRT values ​​in different age groups are shown in Table 2. Table 2. Distribution of CRT values ​​in men across different age groups

[0107] The distribution of CRT values ​​in women across different age groups is shown in Table 3: Table 3. Distribution of CRT values ​​in women across different age groups

[0108] The embodiments of this invention ultimately obtain a database that records the selection response data of the population, and after data pattern analysis, a data distribution probability database is established. When the historical test results of the subjects are obtained, the test results are matched with the above database to determine the corresponding position of the historical test results in the pre-stored test result database. Subsequently, the target position is determined according to the level difference (e.g., moving forward 2 levels or backward 1 level). The target position is an important and distribution-compliant basis for the generation of the target display strategy. Therefore, the target display strategy can be determined more reasonably based on the target position.

[0109] Example 3 This invention discloses a subject selection response testing device, such as... Figure 6 As shown, the device may include: The first acquisition module 301 is used to acquire the subject's historical test results, wherein the historical test results are obtained by displaying multiple selection objects to the subject through a preset display strategy and then detecting the subject's feedback information. The second acquisition module 302 is used to acquire multi-dimensional biometric information of the subject during historical tests. The multi-dimensional biometric information may include one or more of the following: eye contact information, facial expression information, screen dwell time information, body movement information, and heart rate information. The rating determination module 303 is used to determine the subject performance rating corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test. The subject performance rating is used to measure the difficulty of the subject completing the test. The analysis and determination module 304 is used to determine the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage based on the historical test results and the subject performance level corresponding to the historical test. The test execution module 305 is used to execute the next stage of the test, and may include: displaying multiple target selection objects and multiple target interference objects to the subject based on the target display strategy, and determining the subject's selection response test results after detecting the subject's feedback information.

[0110] In an optional embodiment, the device may further include a loop test module, which is used to perform the following operations: Obtain multidimensional biometrics of the subjects for the next stage of testing, and determine the subject's performance level for the next stage of testing based on the multidimensional biometrics of the subjects for the next stage of testing. Based on the results of the response test and the subject's performance level corresponding to the next stage test, the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage are redefined. The test execution module 305 is then triggered to execute the operation of the next stage test, as well as to trigger the operation of obtaining the subject's multi-dimensional biological information during the next stage test and determining the subject's performance level corresponding to the next stage test based on the multi-dimensional biological information corresponding to the next stage test. Obtain the selection response test results for each subsequent stage test, and determine whether the subject's performance level for the next stage test for a consecutive preset number of times is the preset high difficulty level; if so, obtain the selection response test results corresponding to multiple subject performance levels at the preset adaptation difficulty level as reliable selection response test results.

[0111] In another optional embodiment, the specific operation method by which the grade determination module 303 determines the subject performance grade corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test may include: Input the multi-dimensional biometric information corresponding to the historical test into the pre-trained subject performance analysis model, obtain the analysis results output by the subject performance analysis model, and determine the subject performance level corresponding to the historical test based on the analysis results; The subject performance analysis model is obtained by training a pre-set training dataset, which may include multi-dimensional biological information for training and subject performance level labels corresponding to the multi-dimensional biological information for training.

[0112] In yet another alternative embodiment, the device may further include: The interest analysis module (not shown in the attached diagram) is used to determine the subject's interest matrix based on the preset display strategy corresponding to the historical test, multiple selection objects, and multi-dimensional biometric information corresponding to the historical test. The interest matrix is ​​used to represent the subject's degree of interest in different test content in the historical test. Furthermore, the analysis and determination module 304, based on historical test results and the corresponding subject performance levels, determines the specific operational methods for the next stage's target display strategy, multiple target selection objects, and multiple target interference objects, which may include: Based on the interest matrix, determine multiple target selection objects and multiple target interference objects for the next stage. The objects may include image objects and / or sound objects. Based on historical test results and the corresponding subject performance levels, the target presentation strategy for the next stage is determined. The target presentation strategy is used to control the dynamic changes of the target selection object and the target interference object during presentation.

[0113] In another optional embodiment, the interest analysis module determines the specific operation method of the subject's interest matrix based on the preset display strategy corresponding to the historical test, multiple selection objects, and multi-dimensional biometric information corresponding to the historical test, which may include: The test content matrix is ​​determined based on the preset display strategy corresponding to the historical test and multiple selection objects. The elements in the test content matrix may include one or more of the following: shape objects, color objects, size objects, and sound objects. The weight of each element in the test content matrix is ​​calculated based on multi-dimensional biological information to obtain the weight value of each element. The subject's interest matrix is ​​determined based on the test content matrix and the weight value corresponding to each element in the test content matrix.

[0114] In another optional embodiment, the analysis and determination module 304 determines the specific operation method of the target display strategy for the next stage based on historical test results and the subject performance level corresponding to those historical test results, which may include: Based on historical test results, determine the corresponding position of the historical test results in the pre-stored test result database. The test result database is a database established after analyzing the distribution patterns of the population selection response test results. Based on the subject's performance level corresponding to the historical test results, determine the performance level for the next stage and the level difference. Based on the grade difference and the corresponding position of historical test results in the pre-stored test result database, determine the target position of the next stage test plan in the test result database. Based on the target location, determine the target display strategy for the next stage.

[0115] In another optional embodiment, the interest analysis module calculates the weight of each element in the test content matrix based on multi-dimensional biological information to obtain the weight value corresponding to each element. The specific operation may include: The historical tests are divided into different test nodes, and the node elements corresponding to each node are determined. The node elements may include one or more of the following: shape objects, color objects, size objects, and sound objects. Based on multi-dimensional biological information, determine the multi-dimensional biological information of each test node; For each node, the sub-weights of each node element are determined based on the multi-dimensional biological information of the node. Based on the sub-weights of each node element corresponding to all nodes, the weight of each element in the test content matrix is ​​calculated to obtain the weight value corresponding to each element.

[0116] Example 4 Please see Figure 7 , Figure 7 This is a schematic diagram of a subject selection response testing system disclosed in an embodiment of the present invention. The subject selection response testing system may include: Memory 401 storing executable program code; Processor 402 coupled to memory 401; The processor 402 calls the executable program code stored in the memory 401 to execute some or all of the steps in any of the subject selection response test methods in Embodiment 1 or Embodiment 2 of the present invention.

[0117] Example 5 This invention discloses a computer storage medium storing computer instructions. When executed by a processor, these computer instructions implement some or all of the steps in any of the subject selection response test methods in Embodiment 1 or Embodiment 2 of this invention.

[0118] Example 6 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to perform some or all of the steps in any of the subject selection response test methods in Embodiment 1 or Embodiment 2 of this invention.

[0119] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0120] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0121] Finally, it should be noted that the above embodiments are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for testing subject selection response, characterized in that, The method includes: Obtain the subject's historical test results, wherein the historical test results are obtained by displaying multiple selection objects to the subject through a preset display strategy and then detecting the subject's feedback information; The subject's multidimensional biometric information during historical testing is obtained, including one or more of the following: eye contact information, facial expression information, screen dwell time information, body movement information, and heart rate information. Based on the multi-dimensional biometric information corresponding to the historical tests, the subject performance level corresponding to the historical tests is determined, and the subject performance level is used to measure the difficulty of the subject completing the test; Based on the historical test results and the subject performance level corresponding to the historical test, determine the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage; The next stage of testing includes: presenting the subject with multiple target selection objects and multiple target interference objects based on the target presentation strategy, detecting the subject's feedback information, and determining the subject's selection response test results.

2. The subject selection response test method according to claim 1, characterized in that, The method further includes: Obtain the multidimensional biometrics of the subjects during the next stage of testing, and determine the subject's performance level for the next stage of testing based on the multidimensional biometrics of the next stage of testing. Based on the results of the selection response test and the subject's performance level corresponding to the next stage test, the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage are redefined, and the execution of the next stage test is retried. The operation of obtaining the subject's multi-dimensional biological information during the next stage test is also triggered, and the subject's performance level corresponding to the next stage test is determined based on the multi-dimensional biological information corresponding to the next stage test. Obtain the selection response test results corresponding to each next stage test, and determine whether the subject performance level corresponding to the next stage test for a consecutive preset number of times is a preset high difficulty level; if so, obtain the selection response test results corresponding to multiple subject performance levels at a preset adaptation difficulty level as reliable selection response test results.

3. The subject selection response test method according to claim 1, characterized in that, The step of determining the subject performance level corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test includes: Input the multi-dimensional biological information corresponding to the historical test into the pre-trained subject performance analysis model to obtain the analysis results output by the subject performance analysis model, and determine the subject performance level corresponding to the historical test based on the analysis results; The subject performance analysis model is obtained by training a pre-set training dataset, which includes training multidimensional biological information and subject performance level labels corresponding to the training multidimensional biological information.

4. The subject selection response test method according to any one of claims 1-3, characterized in that, The method further includes: Based on the preset display strategy corresponding to the historical test, multiple selection objects, and the multi-dimensional biometric information corresponding to the historical test, the subject's interest matrix is ​​determined. The interest matrix is ​​used to represent the subject's degree of interest in different test contents in the historical test. And, the step of determining the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage based on the historical test results and the subject performance level corresponding to the historical test includes: Based on the interest matrix, multiple target selection objects and multiple target interference objects are determined for the next stage, including image objects and / or sound objects; Based on the historical test results and the subject performance level corresponding to the historical test results, a target display strategy for the next stage is determined. The target display strategy is used to control the dynamic changes of the target selection object and the target interference object during the display.

5. The subject selection response test method according to claim 4, characterized in that, The step of determining the subject's interest matrix based on the preset display strategy corresponding to the historical test, multiple selection objects, and the multi-dimensional biometric information corresponding to the historical test includes: The test content matrix is ​​determined based on the preset display strategy corresponding to the historical test and multiple selection objects. The elements in the test content matrix include one or more of the following: shape objects, color objects, size objects, and sound objects. Based on the multi-dimensional biological information, the weight of each element in the test content matrix is ​​calculated to obtain the weight value corresponding to each element; The subject's interest matrix is ​​determined based on the test content matrix and the weight value corresponding to each element in the test content matrix.

6. The subject selection response test method according to claim 5, characterized in that, The step of determining the target presentation strategy for the next stage based on the historical test results and the corresponding subject performance levels includes: Based on the historical test results, determine the corresponding position of the historical test results in the pre-stored test result database, which is a database established after analyzing the distribution patterns of the population selection response test results; Based on the subject's performance level corresponding to the historical test results, determine the performance level for the next stage and the level difference. Based on the grade difference and the corresponding position of the historical test results in the pre-stored test result database, determine the target position of the next stage test plan in the test result database. Based on the target location, determine the target display strategy for the next stage.

7. The subject selection response test method according to claim 5, characterized in that, The step of calculating the weight of each element in the test content matrix based on the multi-dimensional biological information to obtain the weight value corresponding to each element includes: The historical tests are divided into different test nodes, and the node elements corresponding to each node are determined. The node elements include one or more of the following: shape objects, color objects, size objects, and sound objects. Based on the multi-dimensional biological information, determine the node multi-dimensional biological information corresponding to each test node; For each node, the sub-weights of each node element are determined based on the multi-dimensional biological information of the node. Based on the sub-weights of each node element corresponding to all nodes, the weight of each element in the test content matrix is ​​calculated to obtain the weight value corresponding to each element.

8. A subject selection response testing device, characterized in that, The device includes: The first acquisition module is used to acquire the subject's historical test results, wherein the historical test results are obtained by displaying multiple selection objects to the subject through a preset display strategy and then detecting the subject's feedback information. The second acquisition module is used to acquire multi-dimensional biometric information of the subject during historical tests. The multi-dimensional biometric information includes one or more of the following: eye contact information, facial expression information, screen dwell time information, body movement information, and heart rate information. The rating determination module is used to determine the subject performance rating corresponding to the historical test based on the multi-dimensional biometric information corresponding to the historical test. The subject performance rating is used to measure the difficulty of the subject completing the test. The analysis and determination module is used to determine the target display strategy, multiple target selection objects, and multiple target interference objects for the next stage based on the historical test results and the subject performance level corresponding to the historical test. The test execution module is used to execute the next stage of testing, including: presenting the subject with multiple target selection objects and multiple target interference objects based on the target display strategy, and determining the subject's selection response test results after detecting the subject's feedback information.

9. A subject selection response testing system, characterized in that, The system includes: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the subject selection response test method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which, when executed by a processor, implement the subject selection response test method as described in any one of claims 1-7.

Images