Attention state detection device

Abstract

The invention discloses an attention state detection device, and relates to the technical field of computer vision. In the device, eye movement characteristics are acquired through a first acquisition module, then behavior characteristics are determined based on the eye movement characteristics in a first determination module, and finally, the attention state is determined based on a pre-established attention stage, a pre-established mapping relation between the behavior characteristics and a threshold value and the current behavior characteristics in a second determination module. In the attention detection device, the attention is divided into a plurality of stages in advance, such as a visual search characterization stage, a sight orientation characterization stage, an attention maintenance characterization stage and an attention concentration characterization stage, and a mapping relationship among the attention stages, behavior characteristics and threshold values is pre-established, so that the attention detection accuracy is improved. According to the invention, the existing attention stage and the missing attention stage can be determined based on the mapping relation and the current behavior characteristics, so that the user can know the specific stage where the attention is missing, and the accurate judgment of the attention state is realized.

Description

Technical Field

[0001] This invention relates to the field of computer vision technology, and in particular to an attention state detection device. Background Technology

[0002] Eye movement patterns can directly reflect a person's visual focus area and fixation patterns, thus attention detection can be conducted based on eye movement data. However, related attention detection methods based on eye movement data often only use fixation time, reaction time, or error rate to provide an overall score, and then use this score to comprehensively evaluate and judge the level of attention. Relying solely on the overall score can easily lead to biased and inaccurate assessment results, failing to truly reflect the state of attention.

[0003] Therefore, how to accurately detect attentional states is a technical problem that urgently needs to be solved by those in this field. Summary of the Invention

[0004] The purpose of this invention is to provide an attention state detection device to solve the technical problem that relying solely on overall scores for judgment can easily lead to biased and inaccurate evaluation results, making it difficult to truly reflect the attention state.

[0005] To solve the above-mentioned technical problems, the present invention provides an attention state detection device, comprising:

[0006] The first acquisition module is used to acquire eye movement features; wherein, the eye movement features include at least the fixation duration, scan start and end time, and saccade amplitude;

[0007] The first determining module is used to determine the current behavioral features based on the eye movement features; wherein the behavioral features include at least features characterizing visual search, features characterizing gaze orientation, features characterizing attention maintenance, and features characterizing attention concentration;

[0008] The second determining module is used to determine the attention state based on a pre-established mapping relationship between attention stages, behavioral features and thresholds, and the current behavioral features; wherein the attention stages include at least a visual search stage, a gaze orientation stage, an attention maintenance stage and an attention concentration stage; and the attention state includes at least an attention presence stage and an attention absence stage.

[0009] For example, the first acquisition module specifically includes:

[0010] The acquisition module is used to acquire the gaze point coordinate sequence to determine the eye movement position;

[0011] The third determining module is used to determine the eye movement features based on the eye movement position.

[0012] For example, the attention state detection device further includes:

[0013] A module is established to create a two-dimensional rectangular coordinate system with the reference gaze point on the screen as the origin, and to use the raw data collected by the eye tracker when the eyes gaze at the reference gaze point as the reference value.

[0014] The second acquisition module is used to acquire the current data collected by the eye tracker when the eyes are focused on the target point on the screen;

[0015] The third acquisition module is used to acquire the current eye movement deviation between the current data and the benchmark value;

[0016] The fourth determining module is used to determine the current pixel offset based on the pre-established correspondence between eye movement deviation and pixel offset, and the current eye movement deviation.

[0017] The fourth acquisition module is used to acquire the coordinates of the target point based on the current pixel offset and the coordinate origin.

[0018] For example, the features representing visual search include at least scan rate and gaze point spatial entropy;

[0019] The features characterizing gaze orientation include at least the scan rate, target area hit rate, and target area fixation ratio;

[0020] The features characterizing attention maintenance include at least the average duration of continuous fixation and the number of fixation interruptions;

[0021] The features characterizing attention concentration include at least the long-term gaze retention rate.

[0022] For example, the first determining module specifically includes:

[0023] The first acquisition submodule is used to acquire the number of scans that occur per unit time, and use the number of scans as the scan rate.

[0024] The second acquisition submodule is used to divide the visual space into multiple uniform grid units; count the number of gaze points falling in each grid unit; determine the proportion of each gaze point in the total gaze points based on the number of gaze points in each grid unit; and calculate the information entropy based on the proportion to obtain the gaze point spatial entropy.

[0025] The third acquisition submodule is used to acquire the proportion of the number of times the gaze point falls into the target area within a preset time period to the total number of gazes, so as to determine the target area hit rate.

[0026] The fourth acquisition submodule is used to obtain the proportion of fixation time in the target area to the total fixation time in order to determine the fixation proportion in the target area;

[0027] The fifth acquisition submodule is used to acquire the average duration of a single continuous fixation of the target area in order to determine the average duration of continuous fixation.

[0028] The sixth acquisition submodule is used to acquire the number of times the gaze is interrupted and shifted from the target area within the preset time period, so as to determine the number of gaze interruptions;

[0029] The seventh acquisition submodule is used to acquire the percentage of events with continuous gaze exceeding a preset threshold duration in order to determine the long-term gaze retention rate.

[0030] For example, the attention state detection device further includes: an establishment module for establishing a mapping relationship between attention stages, behavioral features and thresholds;

[0031] The mapping relationship is as follows:

[0032] If the scanning rate is greater than the frequency threshold, the spatial entropy of the fixation point is greater than the spatial entropy threshold, and the fixation ratio of the target area is less than the fixation ratio threshold, then the corresponding attention stage is the representational visual search stage.

[0033] If the target area hit rate is greater than the hit threshold, the corresponding attention stage is the characterization of gaze orientation stage;

[0034] If the average duration of continuous fixation is greater than the fixation duration threshold and the number of fixation interruptions is less than the number threshold, then the corresponding attention stage is the attention maintenance stage.

[0035] If the long-term fixation retention rate is greater than the retention rate threshold, then the corresponding attention stage is the stage that represents attention concentration.

[0036] For example, the attention state detection device further includes: a fifth determining module; the fifth determining module is used to acquire behavioral features of multiple sample objects, acquire the mean of the same behavioral feature of the multiple sample objects, and use the mean as a threshold corresponding to the behavioral feature.

[0037] For example, the attention stages sequentially include a visual search stage, a gaze orientation stage, an attention maintenance stage, and an attention concentration stage; the attention state includes at least an attention presence stage and an attention absence stage.

[0038] The attention state detection device further includes:

[0039] The fifth acquisition module is used to acquire the missing type when an attention-deficient stage is detected in the attention state; wherein the missing type includes at least a single missing type, a consecutive missing type, and a non-adjacent stage missing type.

[0040] For example, the attention state detection device further includes:

[0041] The sixth acquisition module is used to acquire the current difference between the behavioral features corresponding to the attention deficit stage and the corresponding threshold when an attention deficit stage is detected.

[0042] The sixth determination module is used to determine the missing level corresponding to the current difference based on the mapping relationship between the difference between the behavioral characteristics of the attention stage and the corresponding threshold and the missing level.

[0043] For example, the attention state detection device further includes:

[0044] The training module is used to train the attention deficit stage according to the degree of attention deficit level; after the training is completed, it returns to trigger the first acquisition module.

[0045] The attention state detection device provided by this invention first acquires eye movement features through a first acquisition module, then determines behavioral features based on the eye movement features in a first determination module, and finally determines the attention state based on a pre-established mapping relationship between attention stages, behavioral features, and thresholds, and the current behavioral features in a second determination module. Because this attention detection device pre-divides attention into multiple stages, such as representing a visual search stage, a gaze orientation stage, an attention maintenance stage, and an attention concentration stage, and pre-establishes a mapping relationship between attention stages, behavioral features, and thresholds, it can determine the existing and missing attention stages based on this mapping relationship and the current behavioral features. This allows the user to understand the specific stage where attention is missing, achieving accurate judgment of the attention state. Attached Figure Description

[0046] To more clearly illustrate the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the 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.

[0047] Figure 1 This is a schematic diagram of an attention state detection device provided in an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram of a cognitive attention detection system based on an eye tracker, provided as an embodiment of the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 of ordinary skill in the art without creative effort are within the protection scope of the present invention.

[0050] The core of this invention is to provide an attention state detection device to solve the technical problem that relying solely on overall scores for judgment can easily lead to biased and inaccurate evaluation results, making it difficult to truly reflect the attention state.

[0051] To enable those skilled in the art to better understand the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Figure 1 This is a schematic diagram of an attention state detection device provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the attention detection device includes:

[0052] The first acquisition module 1 is used to acquire eye movement features; wherein, the eye movement features include at least the fixation duration, scan start and end time, and saccade amplitude;

[0053] The first determining module 2 is used to determine the current behavioral features based on eye movement features; wherein, the behavioral features include at least features representing visual search (referred to as search features), features representing gaze orientation (referred to as orientation features), features representing attention maintenance (referred to as stable attention features), and features representing attention concentration (referred to as focus features).

[0054] The second determining module 3 is used to determine the attention state based on the pre-established mapping relationship between attention stages, behavioral features and thresholds, and the current behavioral features; wherein, the attention stages include at least the visual search stage (referred to as the search stage), the gaze orientation stage (referred to as the orientation stage), the attention maintenance stage (referred to as the stable attention stage), and the attention concentration stage (referred to as the focus stage); the attention state includes at least the attention presence stage and the attention absence stage.

[0055] In one possible implementation, the first acquisition module specifically includes: a collection module for collecting a sequence of gaze coordinates to determine the eye movement position; and a third determination module for determining eye movement features based on the eye movement position. That is, the gaze coordinates need to be acquired first.

[0056] To obtain the gaze coordinates, the attention state detection device also includes:

[0057] The module is used to establish a two-dimensional rectangular coordinate system with the reference gaze point on the screen as the origin, and to use the raw data collected by the eye tracker when the eyes gaze at the reference gaze point as the reference value.

[0058] The second acquisition module is used to acquire the current data collected by the eye tracker when the eyes are focused on the target point on the screen;

[0059] The third acquisition module is used to acquire the current eye movement deviation between the current data and the baseline value;

[0060] The fourth determining module is used to determine the current pixel offset based on the pre-established correspondence between eye movement deviation and pixel offset, and the current eye movement deviation.

[0061] The fourth acquisition module is used to obtain the coordinates of the target point based on the current pixel offset and the origin.

[0062] This method yields the coordinates of the fixation point, thus determining the eye movement location. After obtaining the eye movement location, eye movement features are determined based on that location.

[0063] In practice, the user's eye movement position data is first acquired using an eye tracker. Based on the patterns of change in this data, fixation and saccade states are distinguished, and the corresponding eye movement features are then determined. Specifically, the fixation duration is determined based on the time period during which the eye movement position remains stable; the scan start and end times are determined based on the start and end times of the eye movement scan; and the saccade amplitude is determined based on the amount of displacement of the eye movement position during the saccade process. The extracted eye movement features include at least the fixation duration, scan start and end times, and saccade amplitude, providing feature support for subsequent attention assessment.

[0064] After obtaining the eye movement features, the current behavioral features are determined based on these features. These behavioral features include at least the features representing visual search, the features representing gaze orientation, the features representing attention maintenance, and the features representing attention concentration.

[0065] In one possible implementation, the features characterizing visual search include at least scan rate and gaze spatial entropy; the features characterizing gaze orientation include at least scan rate, target area hit rate and target area gaze ratio; the features characterizing attention maintenance include at least the mean continuous gaze duration and the number of gaze interruptions; and the features characterizing attention concentration include at least the long-term gaze retention rate.

[0066] To determine these behavioral characteristics, the first determination module specifically includes:

[0067] The first acquisition submodule is used to acquire the number of scans that occur per unit time, and use the number of scans as the scan rate.

[0068] The second acquisition submodule is used to divide the visual space into multiple uniform grid units; count the number of gaze points falling in each grid unit; determine the proportion of each gaze point in the total gaze points based on the number of gaze points in each grid unit; calculate the information entropy based on the proportion to obtain the gaze point spatial entropy.

[0069] The third acquisition submodule is used to acquire the proportion of the number of times the gaze point falls into the target area within a preset time period to the total number of gazes, so as to determine the target area hit rate.

[0070] The fourth acquisition submodule is used to obtain the proportion of fixation time in the target area to the total fixation time in order to determine the fixation proportion in the target area;

[0071] The fifth acquisition submodule is used to acquire the average duration of a single continuous fixation of the target area in order to determine the average duration of continuous fixation.

[0072] The sixth acquisition submodule is used to acquire the number of times the gaze is interrupted and shifted from the target area within a preset time period, so as to determine the number of gaze interruptions;

[0073] The seventh acquisition submodule is used to acquire the percentage of events with continuous gaze exceeding a preset threshold duration in order to determine the long-term gaze retention rate.

[0074] There are no restrictions on the preset duration and preset threshold; they are determined based on the actual situation. After identifying the behavioral characteristics, the attention state is determined based on the pre-established attention stages, the mapping relationship between behavioral characteristics and thresholds, and the current behavioral characteristics.

[0075] Specifically, the attention state detection device further includes: an establishment module, used to establish a mapping relationship between attention stages, behavioral features, and thresholds; wherein the mapping relationship is:

[0076] If the scanning rate is greater than the frequency threshold, the spatial entropy of the fixation point is greater than the spatial entropy threshold, and the fixation ratio of the target area is less than the fixation ratio threshold, then the corresponding attention stage is the representational visual search stage.

[0077] If the target area hit rate is greater than the hit threshold, the corresponding attention stage is the characterization of gaze orientation stage;

[0078] If the average duration of continuous fixation is greater than the fixation duration threshold and the number of fixation interruptions is less than the number threshold, then the corresponding attention stage is the attention maintenance stage.

[0079] If the long-term fixation retention rate is greater than the retention rate threshold, then the corresponding attention stage is the stage that represents attention concentration.

[0080] The thresholds mentioned (such as frequency threshold, spatial entropy threshold, fixation ratio threshold, hit threshold, fixation duration threshold, number of fixations threshold, and retention rate threshold) are not limited and are determined based on the actual situation. To improve the accuracy of the selected thresholds, the attention state detection device also includes a fifth determination module in implementation. This fifth determination module is used to acquire the behavioral characteristics of multiple sample objects, obtain the mean of the same behavioral characteristic of multiple sample objects, and use the mean as the threshold corresponding to the behavioral characteristic. The sample objects are users with normal attention.

[0081] After establishing the mapping relationship, and obtaining the current behavioral characteristics, the attention state can be determined based on the mapping relationship.

[0082] In addition to the attention presence stage and attention absence stage described above, to understand attention states in detail, in practice, attention stages include, in turn, the visual search stage, the gaze orientation stage, the attention maintenance stage, and the attention concentration stage; attention states include at least the attention presence stage and the attention absence stage.

[0083] The attention state detection device further includes: a fifth acquisition module, used to acquire the missing type when an attention missing stage is detected; wherein the missing type includes at least a single missing type, a continuous missing type, and a non-adjacent stage missing type.

[0084] In this embodiment, the location and duration of attention abnormalities can be more accurately located, enabling fine-grained detection of attention deficits.

[0085] In addition, to understand the degree of attention deficit, the attention state detection device also includes: a sixth acquisition module, used to acquire the current difference between the behavioral features corresponding to the attention deficit stage and the corresponding threshold when an attention deficit stage is detected; and a sixth determination module, used to determine the degree of deficit corresponding to the current difference based on a pre-set mapping relationship between the difference between the behavioral features of the attention stage and the corresponding threshold and the degree of deficit.

[0086] The degree of deficiency is categorized as mild, moderate, and severe. To intervene in attentional stage deficits, the attentional state detection device also includes, in practice:

[0087] The training module is used to train the attention deficit stage according to the degree of attention deficit level; after training is completed, it returns to trigger the first acquisition module.

[0088] The attention state detection device provided in this embodiment of the invention first acquires eye movement features through a first acquisition module, then determines behavioral features based on the eye movement features in a first determination module, and finally determines the attention state based on a pre-established mapping relationship between attention stages, behavioral features, and thresholds, and the current behavioral features in a second determination module. In this attention detection device, because attention is pre-divided into multiple stages, such as representing a visual search stage, a gaze orientation stage, an attention maintenance stage, and an attention concentration stage, and a pre-established mapping relationship between attention stages, behavioral features, and thresholds, existing and missing attention stages can be determined based on this mapping relationship and the current behavioral features. This allows the user to understand the specific stage where attention is missing, achieving accurate judgment of the attention state.

[0089] To enable those skilled in the art to better understand the attention state detection device described above, the process will be further explained below with reference to the accompanying drawings and specific embodiments. Figure 2 This is a schematic diagram of a cognitive attention detection system based on an eye tracker provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the system comprises a data acquisition layer (4), an analysis and judgment layer (5), and an intervention execution layer (6). The data acquisition layer (4) includes an eye-tracking data acquisition module and a behavioral feature calculation module. The analysis and judgment layer (5) includes an attention phase model construction module, an attention phase determination module, and a phase missing identification module. The intervention execution layer (6) includes a phased training generation module and a training feedback and phase update module. After the training feedback and phase update module, the system returns to trigger the behavioral feature calculation module. The following describes each module in the system.

[0090] ① Eye-tracking data acquisition module: The eye tracker has a sampling frequency of 100Hz and a spatial resolution of ≤0.5° visual angle. It acquires the gaze point coordinate sequence (xt, yt), gaze duration, saccade start and end time, amplitude, and velocity.

[0091] ② Behavioral Feature Calculation Module: Eye movement features are extracted during an assessment, and search features, orientation features, stable attention features, and focus features are derived based on these features. Search features include: (Saccade Rate Fs: Number of saccades per unit time, reflecting the frequency of visual search; Average Saccasion Amplitude As: Average angular amplitude of fixation point displacement during saccades, reflecting the size of the search range; Fixation Point Spatial Entropy Hfix: Distribution entropy value of the fixation point in the stimulus space, describing the dispersion of the fixation distribution); Orientation features include: (Saccade Rate Fs: Number of saccades per unit time, reflecting the frequency of visual search; Target Area Hit Rate Rtarget: The proportion of fixations that fall into the target area within the assessment time window out of the total number of fixations; Target Area Fixation Ratio Ptarget: ...). The proportion of fixation time in the target area to the total fixation time); stable attention characteristics (mean duration of continuous fixation Dfix: the average duration of a single continuous fixation on the target area; number of fixation interruptions Nbreak: the number of times fixation is interrupted and shifted from the target area within the evaluation window; standard deviation of fixation point drift σdrift: the standard deviation of fixation point position fluctuation during continuous fixation, used to describe fixation stability); focus characteristics (long-term fixation retention rate Rsustain: the proportion of events where continuous fixation exceeds a preset threshold; microsacrifice rate Rmicro: the proportion of microsacrifice events to total sacrifice events, used to reflect the level of fine visual control).

[0092] ③ Attention stage model construction modules: S1 (search stage), S2 (orientation stage), S3 (stable attention stage), S4 (focus stage). Normal evolution path (S1→S2→S3→S4); allowed backtracking: S(i)→S(i-1) (indicating attention interruption); prohibited skipping: S(i)↛S(i+2) (requires stage-by-stage evolution).

[0093] ④ Attention Stage Determination Module: The attention stage is determined based on the eye movement features calculated by the behavioral feature calculation module. Behavioral features are mapped to the stage determination space, using a multi-index threshold + rule fusion model. When the following conditions are met: the scan rate Fs is high, the fixation point spatial entropy Hfix is ​​high, and the target area fixation ratio Ptarget is lower than the preset threshold θ1, the current attention stage is determined to be the S1 search stage.

[0094] When the following conditions are met: the target area hit rate Rtarget is higher than the preset threshold θ2, the current attention phase is determined to be the S2 orientation phase.

[0095] When the following conditions are met: the average duration of continuous fixation, Dfix, is higher than the preset threshold θ3, and the number of fixation interruptions, Nbreak, is lower than the preset threshold θ4, the current attention stage is determined to be the S3 stable attention stage.

[0096] When the following conditions are met: the long-term fixation rate Rsustain is higher than the preset threshold θ5, the current attention stage is determined to be the S4 focus stage.

[0097] The threshold is the average of the data from multiple (e.g., 50) normal individuals after evaluation.

[0098] ⑤ Stage Missing Module: This module diagnoses abnormal patterns in the attention evolution process by identifying the specific missing stage based on missing stage type judgment rules. Missing stages include single missing, consecutive missing, and non-adjacent stage anomalies. Specifically, a single missing stage refers to a significant anomaly in only one stage; consecutive missing stages refer to anomalies in multiple adjacent stages (e.g., S2+S3 missing); and discontinuous missing stages refer to anomalies in non-adjacent stages (e.g., S1+S4 missing). The module categorizes the severity based on threshold levels and trains accordingly for different stages. Thresholds are divided into three levels: mild, moderate, and severe.

[0099] ⑥ Stage-based Training Generation Module: This module generates targeted training plans based on stage-specific missing stage diagnosis, and adaptively adjusts the difficulty algorithm according to the missing stage and degree of missing information. For example, if the search stage S1 is missing, the search strategy is improved for search training; if the orientation stage S2 is missing, target locking is improved for orientation training; if the stable attention stage S3 is missing, attention stability is improved for attention stability training; and if the focus stage S4 is missing, sustained focus is improved for focus training. Difficulty parameters include: number of stimuli, interference intensity, target salience, and task duration. In practice, these parameters can be dynamically adjusted based on the degree of missing information.

[0100] ⑦ Training Feedback and Phase Update Module: After training, return to the trigger behavior feature calculation module to start the next evaluation and perform cyclical evaluation training.

[0101] Compared to methods that rely solely on fixation time, reaction time, or error rate for overall scoring and comprehensive evaluation of attention levels and states, the attention state detection device provided in this invention explicitly models attention as a multi-stage evolutionary process; it uses eye-tracking behavior to calculably determine the current stage of attention; it identifies the specific stage corresponding to attention deficit; and it generates phased and targeted training intervention programs based on the stage deficit, thereby achieving more interpretable and targeted attention detection.

[0102] The attention state detection device provided by the present invention has been described in detail above. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. It should be noted that those skilled in the art can make various improvements and modifications to the present invention without departing from its principles, and these improvements and modifications also fall within the protection scope of the present invention.

[0103] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. An attention state detection device, characterized in that, include: The first acquisition module is used to acquire eye movement features; wherein, the eye movement features include at least the fixation duration, scan start and end time, and saccade amplitude; The first determining module is used to determine the current behavioral features based on the eye movement features; wherein the behavioral features include at least features characterizing visual search, features characterizing gaze orientation, features characterizing attention maintenance, and features characterizing attention concentration; The second determining module is used to determine the attention state based on a pre-established mapping relationship between attention stages, behavioral features and thresholds, and the current behavioral features; wherein the attention stages include at least a visual search stage, a gaze orientation stage, an attention maintenance stage and an attention concentration stage; and the attention state includes at least an attention presence stage and an attention absence stage.

2. The attention state detection device according to claim 1, characterized in that, The first acquisition module specifically includes: The acquisition module is used to acquire the gaze point coordinate sequence to determine the eye movement position; The third determining module is used to determine the eye movement features based on the eye movement position.

3. The attention state detection device according to claim 1, characterized in that, Also includes: A module is established to create a two-dimensional rectangular coordinate system with the reference gaze point on the screen as the origin, and to use the raw data collected by the eye tracker when the eyes gaze at the reference gaze point as the reference value. The second acquisition module is used to acquire the current data collected by the eye tracker when the eyes are focused on the target point on the screen; The third acquisition module is used to acquire the current eye movement deviation between the current data and the benchmark value; The fourth determining module is used to determine the current pixel offset based on the pre-established correspondence between eye movement deviation and pixel offset, and the current eye movement deviation. The fourth acquisition module is used to acquire the coordinates of the target point based on the current pixel offset and the coordinate origin.

4. The attention state detection device according to any one of claims 1 to 3, characterized in that, The features representing visual search include at least scan rate and gaze point spatial entropy; The features characterizing gaze orientation include at least the scan rate, target area hit rate, and target area fixation ratio; The features characterizing attention maintenance include at least the average duration of continuous fixation and the number of fixation interruptions; The features characterizing attention concentration include at least the long-term gaze retention rate.

5. The attention state detection device according to claim 4, characterized in that, The first determining module specifically includes: The first acquisition submodule is used to acquire the number of scans that occur per unit time, and use the number of scans as the scan rate. The second acquisition submodule is used to divide the visual space into multiple uniform grid units; count the number of gaze points falling in each grid unit; determine the proportion of each gaze point in the total gaze points based on the number of gaze points in each grid unit; and calculate the information entropy based on the proportion to obtain the gaze point spatial entropy. The third acquisition submodule is used to acquire the proportion of the number of times the gaze point falls into the target area within a preset time period to the total number of gazes, so as to determine the target area hit rate. The fourth acquisition submodule is used to obtain the proportion of fixation time in the target area to the total fixation time in order to determine the fixation proportion in the target area; The fifth acquisition submodule is used to acquire the average duration of a single continuous fixation of the target area in order to determine the average duration of continuous fixation. The sixth acquisition submodule is used to acquire the number of times the gaze is interrupted and shifted from the target area within the preset time period, so as to determine the number of gaze interruptions; The seventh acquisition submodule is used to acquire the percentage of events with continuous gaze exceeding a preset threshold duration in order to determine the long-term gaze retention rate.

6. The attention state detection device according to claim 5, characterized in that, Also includes: A module is created to establish the mapping relationship between attention stages, behavioral characteristics, and thresholds; The mapping relationship is as follows: If the scanning rate is greater than the frequency threshold, the spatial entropy of the fixation point is greater than the spatial entropy threshold, and the fixation ratio of the target area is less than the fixation ratio threshold, then the corresponding attention stage is the representational visual search stage. If the target area hit rate is greater than the hit threshold, the corresponding attention stage is the characterization of gaze orientation stage; If the average duration of continuous fixation is greater than the fixation duration threshold and the number of fixation interruptions is less than the number threshold, then the corresponding attention stage is the attention maintenance stage. If the long-term fixation retention rate is greater than the retention rate threshold, then the corresponding attention stage is the stage that represents attention concentration.

7. The attention state detection device according to claim 6, characterized in that, Also includes: The fifth module is determined; The fifth determining module is used to obtain behavioral features of multiple sample objects, obtain the mean of the same behavioral feature of the multiple sample objects, and use the mean as a threshold corresponding to the behavioral feature.

8. The attention state detection device according to claim 6, characterized in that, The attention phases sequentially include the visual search phase, the gaze orientation phase, the attention maintenance phase, and the attention concentration phase; The attention state includes at least a phase of attention presence and a phase of attention absence; The attention state detection device further includes: The fifth acquisition module is used to acquire the missing type when an attention-deficient stage is detected in the attention state; wherein the missing type includes at least a single missing type, a consecutive missing type, and a non-adjacent stage missing type.

9. The attention state detection device according to claim 6, characterized in that, Also includes: The sixth acquisition module is used to acquire the current difference between the behavioral features corresponding to the attention deficit stage and the corresponding threshold when an attention deficit stage is detected. The sixth determination module is used to determine the missing level corresponding to the current difference based on the mapping relationship between the difference between the behavioral characteristics of the attention stage and the corresponding threshold and the missing level.

10. The attention state detection device according to claim 9, characterized in that, Also includes: The training module is used to train the attention deficit stage according to the degree of attention deficit level. After training is complete, return to trigger the first acquisition module.

Images