Method and device for determining user concentration and electronic equipment

Abstract

The invention discloses a method and device for determining user concentration and electronic equipment. The method comprises the steps of obtaining to-be-processed data of a target user within a preset duration; performing data extraction on the to-be-processed data according to the plurality of feature dimensions to obtain to-be-used data under the feature dimensions; inputting the to-be-used data into the concentration degree evaluation model for concentration degree evaluation to obtain concentration degree evaluation attributes of the target user; when the concentration degree evaluation attribute meets an interference mode evaluation condition, inputting the to-be-used data into the interference classification model to obtain an interference mode corresponding to the concentration degree evaluation attribute; wherein the interference mode is used for representing an interference type influencing the concentration degree of the target user. According to the method and the device, the cost of evaluating the concentration degree of the user is reduced, the concentration degree of the target user is evaluated and the interference mode influencing the concentration degree is determined under the condition that the target user is not influenced, the target user is conveniently reminded according to the concentration degree of the user, and the purpose of improving the working efficiency of the user is achieved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, and electronic device for determining user concentration. Background Art

[0002] Since the working environment of staff is usually open, they are often disturbed by various interruptions during the work process. Under the influence of various interruptions, the staff's concentration will be scattered, which will affect their work status.

[0003] Currently, existing technologies mainly rely on wearing or wearing specific devices to detect user concentration. However, this approach can disrupt normal office work processes, resulting in a poor user experience. Furthermore, these specific devices are expensive and lack widespread adoption. Summary of the Invention

[0004] The present invention provides a method, device and electronic device for determining user concentration, which reduces the cost of user concentration assessment. Without affecting the target user, the target user's concentration is assessed and the interference pattern that affects the concentration is determined, making it convenient to remind the target user according to the user's concentration, so as to achieve the purpose of improving the user's work efficiency.

[0005] According to one aspect of the present invention, a method for determining user concentration is provided, the method comprising:

[0006] Obtaining data to be processed from the target user within a preset time period, wherein the data to be processed includes eye data and cursor movement data of the target user;

[0007] Extracting data from the data to be processed based on a plurality of predetermined feature dimensions to obtain data to be used corresponding to the feature dimensions, wherein the feature dimensions are determined based on processing first sample data corresponding to a first sample user under a plurality of interference modes, and the feature dimensions are positively correlated with an assessment of the user's concentration;

[0008] Input the data to be used into the pre-trained focus assessment model to perform focus assessment and obtain the focus assessment attributes of the target user;

[0009] When the concentration evaluation attribute satisfies the interference pattern evaluation condition, the data to be used is input into the pre-trained interference classification model to obtain the interference pattern corresponding to the concentration evaluation attribute;

[0010] The interference pattern is used to characterize the type of interference that affects the target user's concentration. The interference pattern includes any one or more of internal and external noise interference patterns, memory interference patterns, and pop-up window prompt interference patterns of terminal devices.

[0011] According to another aspect of the present invention, there is provided an apparatus for determining a user's concentration, the apparatus comprising:

[0012] A data acquisition module is used to acquire the target user's data to be processed within a preset time period, wherein the data to be processed includes the target user's eye data and cursor movement data;

[0013] a feature extraction module, configured to extract data from the data to be processed based on a plurality of predetermined feature dimensions to obtain data to be used corresponding to the feature dimensions, wherein the feature dimensions are determined based on processing first sample data corresponding to a first sample user under a plurality of interference modes, and the feature dimensions are positively correlated with an assessment of the user's concentration;

[0014] A focus assessment module is used to input the data to be used into a pre-trained focus assessment model to perform focus assessment and obtain the focus assessment attributes of the target user;

[0015] An interference pattern determination module is configured to input the to-be-used data into a pre-trained interference classification model to obtain an interference pattern corresponding to the concentration evaluation attribute when the concentration evaluation attribute satisfies the interference pattern evaluation condition;

[0016] The interference pattern is used to characterize the type of interference that affects the target user's concentration. The interference pattern includes any one or more of internal and external noise interference patterns, memory interference patterns, and pop-up window prompt interference patterns of terminal devices.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining user concentration according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining user concentration according to any embodiment of the present invention when executed.

[0022] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for determining user concentration according to any embodiment of the present invention.

[0023] The technical solution of the embodiment of the present invention obtains the target user's data to be processed within a preset time period, and extracts features from the data to be processed through multiple feature dimensions to determine the data to be used under multiple feature dimensions. Based on this, data support is provided for the subsequent concentration evaluation of the target user. The data to be used is input into the pre-trained concentration evaluation model for concentration evaluation, and the concentration evaluation attribute of the target user is obtained, thereby realizing the concentration evaluation of the target user. When the concentration evaluation attribute meets the interference pattern evaluation condition, the data to be used is input into the interference classification model to obtain the interference pattern corresponding to the concentration evaluation attribute. Based on this, the factors affecting the target user's concentration are determined, which facilitates the subsequent reminder of the target user based on the factors affecting the target user's concentration, so as to achieve the purpose of improving the target user's work efficiency. The present invention solves the problems in the prior art of relying on external devices to evaluate user concentration, which affects the user's normal work, has a poor user experience, and has a high evaluation cost. The present invention evaluates and analyzes the target user's eye data and cursor movement data through a concentration evaluation model and an interference classification model, thereby reducing the cost of user concentration evaluation. Without affecting the target user, the target user's concentration is evaluated and the interference pattern that affects the concentration is determined, which facilitates reminding the target user according to the user's concentration, so as to achieve the purpose of improving user work efficiency.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 is a flow chart of a method for determining user concentration provided by an embodiment of the present invention;

[0027] Figure 2 is a flowchart illustrating a method for determining user concentration provided by an embodiment of the present invention;

[0028] Figure 3is an example diagram of a reminder text provided by an embodiment of the present invention;

[0029] Figure 4 This is a flow chart of a model training method provided by an embodiment of the present invention;

[0030] Figure 5 2 is a structural example diagram of a model training system provided by an embodiment of the present invention;

[0031] Figure 6 This is an example diagram of a Schulte experiment webpage provided by an embodiment of the present invention;

[0032] Figure 7 This is an example diagram of a pop-up window in the pop-up window prompt interference mode provided by an embodiment of the present invention;

[0033] Figure 8 is a structural diagram of a device for determining user concentration provided by an embodiment of the present invention;

[0034] Figure 9 3 is a schematic structural diagram of an electronic device for implementing the method for determining user concentration according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] Example 1

[0038] Figure 1This is a flow chart of a method for determining user concentration provided by the first embodiment of the present invention. This embodiment is applicable to situations where the target user's concentration is evaluated and interference patterns that affect the concentration are determined without affecting the target user. The method can be performed by a device for determining user concentration. The device for determining user concentration can be implemented in the form of hardware and / or software. The device for determining user concentration can be configured in electronic devices such as mobile phones, computers, or servers. Figure 1 As shown, the method includes:

[0039] S110 : Acquire data to be processed of the target user within a preset time period, wherein the data to be processed includes eye data and cursor movement data of the target user.

[0040] The target user is the user who currently needs to undergo concentration detection. The preset duration may be a pre-set period of time during which the target user is in a working state. Optionally, the device for determining user concentration corresponding to an embodiment of the present invention may be deployed in an electronic device where the target user is working, and when it is detected that the electronic device corresponding to the target user is in a working state, the data to be processed within the preset duration is obtained. The data to be processed may include eye data and cursor movement data of the target user.

[0041] Eye data can be understood as the eye movement trajectory data of the target user looking at the corresponding electronic device within a preset time period, as well as the hand-eye accompanying data between the eye movement trajectory data and the cursor movement data. Optionally, the eye movement trajectory data may include the average eye movement speed of the target user between two mouse click events. The hand-eye accompanying data may include eye movement trajectory data that changes with the cursor movement trajectory. For example, the hand-eye accompanying data may include the average similarity data of the hand-eye data in the horizontal direction between two mouse click events. Optionally, the eye data can be obtained by an eye tracker deployed on the target user's corresponding electronic device.

[0042] The cursor motion data can be understood as the cursor movement trajectory data of the electronic device corresponding to the target user within a preset time period. Optionally, the cursor movement trajectory data can include the total duration of the cursor movement within the preset time period, the average mouse movement speed between two mouse click events, and other data.

[0043] Specifically, upon detecting that the target user's electronic device is in operation, raw eye data and raw cursor motion data of the target user are obtained over a preset duration. Data preprocessing, such as missing value detection and outlier detection, is performed on the raw eye data and raw cursor motion data to fill in missing values ​​and remove outliers, resulting in preprocessed eye data and cursor motion data. This preprocessed eye data and cursor motion data are then used as pending data for the target user over the preset duration, allowing the target user's concentration to be assessed based on the pending data.

[0044] For example, see Figure 2 , Figure 2 A flowchart illustrating an example of a detection method for determining a user's concentration. Figure 2 The user's concentration is evaluated and determined through the detection platform. The detection platform is implemented in Python. Figure 2 The hand-eye data corresponds to the eye data and cursor motion data mentioned in the above embodiment. The hand-eye data preprocessing corresponds to the process of obtaining the data to be processed in S110 of the embodiment of the present invention.

[0045] Specifically, after acquiring the target user's hand-eye data for a preset duration, the data is tested for missing values ​​and outliers. Based on the test results, missing values ​​in the hand-eye data are then filled in. Optionally, to avoid affecting the overall distribution of the hand-eye data, adjacent hand-eye data can be used for filling, i.e., filling in data using the upstream and downstream data of the missing value. Furthermore, outliers in the hand-eye data are deleted. For example, eye data outside the preset screen range of the target user's corresponding electronic device is deleted. This results in preprocessed hand-eye data, i.e., the data to be processed.

[0046] S120 , extracting data from the data to be processed according to a plurality of predetermined feature dimensions to obtain data to be used corresponding to the feature dimensions.

[0047] The characteristic dimension is determined based on processing the first sample data corresponding to the first sample user under multiple interference modes, and the characteristic dimension is positively correlated with the user's concentration evaluation.

[0048] The first sample user may be a user used to obtain training sample data during the training process of the concentration assessment model and the interference classification model. The multiple interference modes may include: at least one or more of: internal and external noise interference modes, memory interference modes, and pop-up window prompt interference modes of the terminal device. The first sample data may include eye data and cursor movement data collected by the first sample user under each interference mode. The feature dimension may be a feature dimension associated with the user concentration assessment determined after feature analysis of the first sample data under multiple interference modes. The data to be used may be feature data obtained after feature extraction of the processed data based on each feature dimension. Optionally, the data to be used under the feature dimension may include: the average eye movement speed of the target user between two mouse click events, the average similarity data of the hand-eye data in the horizontal direction between the two mouse click events, the total duration of the cursor movement within a preset duration, the average mouse movement speed between two mouse click events, etc.

[0049] Specifically, data extraction processing is performed on the data to be processed according to a plurality of predetermined feature dimensions, and the data to be used under each feature dimension is determined, so as to evaluate the concentration of the target user based on the data to be used.

[0050] For example, in combination with the above examples, Figure 2 The calculation of the hand-eye data features in corresponds to the process of determining the data to be used in S120 of the embodiment of the present invention.

[0051] After obtaining the hand-eye data after data preprocessing, data extraction processing of multiple feature dimensions is performed on the hand-eye data according to multiple feature dimensions determined in advance to obtain the hand-eye data features under each feature dimension, that is, the data to be used.

[0052] S130: Input the data to be used into a pre-trained concentration evaluation model to perform concentration evaluation, and obtain the concentration evaluation attribute of the target user.

[0053] Among them, the concentration evaluation model can be a pre-trained machine learning model for evaluating the concentration of the target user. Optionally, the concentration evaluation model can be a machine learning model corresponding to the Gradient Boosting Decision Tree (GBDT) algorithm. It should be noted that the Gradient Boosting Decision Tree algorithm achieves better learning goals by forming multiple machine learning machines (individual learners). For the GBDT algorithm, there is a close connection between individual learners, and except for the first individual learner, the remaining learners need to be formed serially.

[0054] The focus assessment attribute can be used to characterize the target user's level of focus. The focus assessment attribute can be used to determine whether the target user is focused. Optionally, a preset focus assessment standard attribute can be set. If the focus assessment attribute is consistent with the preset focus assessment standard attribute, the target user is determined to be focused. If the focus assessment attribute is inconsistent with the preset focus assessment standard attribute, the target user is determined to be distracted.

[0055] Specifically, the data to be used under multiple feature dimensions are input into a pre-trained concentration evaluation model to perform concentration evaluation processing, and determine the concentration evaluation attributes corresponding to the target user within a preset time period.

[0056] For example, in conjunction with the above example, the GBDT classifier is used as an example for the focus assessment model. The hand-eye data features under multiple feature dimensions are input into the GBDT classifier for focus assessment processing to determine whether the target user's attention is focused, that is, to obtain the target user's focus assessment attribute.

[0057] S140: When the concentration evaluation attribute satisfies the interference pattern evaluation condition, the data to be used is input into a pre-trained interference classification model to obtain an interference pattern corresponding to the concentration evaluation attribute.

[0058] The interference pattern evaluation condition may be a pre-set condition that the concentration evaluation attribute needs to meet. Optionally, a preset concentration evaluation standard attribute may be set. If the concentration evaluation attribute is inconsistent with the preset concentration evaluation standard attribute, it is determined that the concentration evaluation attribute meets the interference pattern evaluation condition. In other words, when it is detected that the target user has low concentration, the interference pattern that causes the target user's low concentration may be evaluated. The preset concentration evaluation standard attribute may be used to characterize the target user's high concentration.

[0059] The interference mode is used to characterize the type of interference that affects the concentration of the target user. The interference mode includes any one or more of the internal and external noise interference mode, the memory interference mode, and the pop-up prompt interference mode of the terminal device. The internal and external noise interference mode can be used to characterize the external environmental noise interference and / or the device noise interference of the electronic device. The memory interference mode can be used to characterize the memory interference that is not related to work and affects normal work. For example, if the target user makes or receives a call within the preset time, the concentration evaluation attribute may be inconsistent with the preset concentration evaluation standard attribute, that is, the target user is not focused.

[0060] The interference classification model can be a pre-set model for determining the interference pattern corresponding to the target user. Optionally, the interference classification model can be a model corresponding to the Support Vector Machine (SVM) algorithm. It should be noted that the SVM algorithm is based on a linear classifier and uses kernel technique transformation to project the data to be used from the initial space to a linearly separable high-dimensional space to enable it to have nonlinear classification capabilities. The advantage of using the model corresponding to the SVM algorithm is that under the condition of a limited number of samples, the model classification accuracy and model generalization ability are high.

[0061] Specifically, if the focus assessment attribute is inconsistent with the preset focus assessment standard attribute, the focus assessment attribute is determined to meet the interference pattern assessment condition. The data to be used is input into a pre-trained interference classification model, which outputs the interference pattern corresponding to the focus assessment attribute based on the interference classification model. Based on this, the interference pattern that affects the target user's focus is determined, facilitating subsequent reminders to the target user based on the interference pattern affecting their focus, thereby achieving the goal of improving the target user's work efficiency.

[0062] For example, in conjunction with the above example, the interference classification model is described as an SVM classifier. When the GBDT classifier outputs the result that the target user has low concentration or is not paying attention, the hand-eye data features are input into the SVM classifier to determine the type of interference that affects the target user's attention, that is, the interference pattern.

[0063] Optionally, after obtaining the interference pattern, a reminder text corresponding to the interference pattern is displayed in the interface.

[0064] The interface may be a display interface of an electronic device corresponding to the target user. The reminder text may be used to remind the target user of low concentration and interference patterns that cause low concentration of the target user. For example, the feedback reminder text may be as follows: Figure 3 The prompt text is displayed to the target user in the form of a pop-up window.

[0065] Specifically, after determining the interference pattern that causes the target user's concentration evaluation attribute to be inconsistent with the preset concentration evaluation standard attribute, a reminder text is generated based on the interference pattern and the concentration evaluation attribute, and the reminder text is displayed in the interface of the electronic device corresponding to the target user.

[0066] The technical solution of this embodiment obtains the target user's data to be processed within a preset time period, and extracts features from the data to be processed through multiple feature dimensions to determine the data to be used under multiple feature dimensions. Based on this, data support is provided for the subsequent evaluation of the target user's concentration. The data to be used is input into the pre-trained concentration evaluation model for concentration evaluation, and the target user's concentration evaluation attribute is obtained, thereby realizing the evaluation of the target user's concentration. When the concentration evaluation attribute meets the interference pattern evaluation condition, the data to be used is input into the interference classification model to obtain the interference pattern corresponding to the concentration evaluation attribute. Based on this, the factors affecting the target user's concentration are determined, which facilitates the subsequent reminder of the target user based on the factors affecting the target user's concentration, so as to achieve the purpose of improving the target user's work efficiency. The present invention solves the problems in the prior art of relying on external devices to evaluate user concentration, which affects the user's normal work, has a poor user experience, and has a high evaluation cost. The present invention evaluates and analyzes the target user's eye data and cursor movement data through a concentration evaluation model and an interference classification model, thereby reducing the cost of user concentration evaluation. Without affecting the target user, the target user's concentration is evaluated and the interference pattern that affects the concentration is determined, which facilitates reminding the target user according to the user's concentration, so as to achieve the purpose of improving user work efficiency.

[0067] Example 2

[0068] Figure 4 This is a flow chart of a model training method provided by the second embodiment of the present invention. This embodiment is based on the above embodiment. Before evaluating the concentration of the target user and determining the interference pattern that affects the concentration based on the concentration evaluation model and interference classification model obtained in advance, the concentration evaluation model and the interference classification model can be trained to obtain the trained concentration evaluation model and interference classification model. The specific implementation method can be found in the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the above embodiments are not repeated here. Figure 4 As shown, the method includes:

[0069] S210 , obtaining a plurality of first sample data in different interference modes and non-interference modes, wherein the first sample data is eye data and cursor movement data generated by a first sample user after simulating a preset experiment.

[0070] Among them, different interference modes may include: any one or more of internal and external noise interference mode, memory interference mode, and pop-up prompt interference mode. The first sample data corresponding to the internal and external noise interference mode is the eye data and cursor movement data generated when the first sample user completes the preset experiment within the third preset duration of noise interference. The third preset duration can be the preset duration of internal noise and / or external noise. The internal noise can be the noise emitted by the electronic device corresponding to the first sample user. The external noise can be the external environmental noise.

[0071] The first sample data corresponding to the memory interference mode is the eye data and cursor movement data generated by the first sample user performing a preset experiment while repeating preset content. The preset content can be pre-set content that the first sample user needs to repeat. For example, the first sample user can be asked to repeat the four numbers "x,x,x,x" during the preset experiment.

[0072] The first sample data corresponding to the pop-up prompt interference mode is the eye data and cursor movement data generated by executing a preset experiment in which the first sample user is constantly disturbed by pop-up prompt information. The pop-up prompt information can be used to simulate the advertising pop-up information or message pop-up information in actual work scenarios.

[0073] The preset experiment can be an experiment designed to simulate eye and cursor movement data generated by a user during normal work. Alternatively, the preset experiment can be a Schulte grid experiment. The Schulte grid experiment, a computerized TMT experiment, involves sequentially searching for numbers from 1 to 25 and using the mouse to click within the corresponding number squares.

[0074] Specifically, eye data and cursor movement data generated by a first sample user after simulating a preset experiment in at least one interference mode or a non-interference mode are obtained.

[0075] For example, the preset experiment is the Schulte grid experiment. Figure 5 The system shown in implements the training of the concentration assessment model and the distraction classification model. Figure 5 First, the first sample data of the first sample user is obtained through the Schulte experiment webpage in the data collection platform. The Schulte experiment webpage is a webpage developed based on JavaScript.

[0076] That is, a Schulte experiment webpage is created in the data collection platform, and three different interference modes are built into the data collection platform, so that the first sample user is required to complete the preset experiment under each interference mode in the data collection platform, and the first sample data is obtained using the hand-eye data collector. Figure 6 shown.

[0077] The first sample user simulated the process of a pre-set experiment. Specifically, the first sample user sequentially searched for and clicked on the numbers 1 to 25 in the Schulte grid. It should be noted that the numbers presented in each Schulte grid experiment were randomly arranged. Each Schulte grid experiment could be broken down into at least 25 mouse click events.

[0078] To improve the recognition of interference patterns, during the first sample user's simulation of the Schulte grid experiment, one or more interference processing methods including internal and external noise interference patterns, memory interference patterns, and pop-up window prompt interference patterns were added to obtain the first sample data of the first sample user under different interference patterns. The specific processing methods for the above three interference patterns are as follows:

[0079] Internal and External Noise Interference Mode: Select a noise segment with a third preset duration of 183 seconds and play it continuously in a loop while the first sample user completes the Schulte grid test. The noise can be selected from TV snow noise. To ensure the noise interference effect, use external speakers with the media volume set to maximum. Ensure that the first sample user has no hearing impairments and obtain the first sample data for the internal and external noise interference mode.

[0080] Memory Interference Mode: While the first sample user is performing the Schulte Grid experiment, they are asked to repeat pre-set content unrelated to the experiment. For example, the pre-set content could be four numbers, which would occupy the first sample user's working memory and act as a memory distractor. Specifically, the first sample user searches and clicks on numbers 1 to 25. When the user clicks on 10, the data collection platform automatically begins playing the message "Please recite the four numbers x, x, x, x, in sequence." The experimenter supervises the first sample user to stop clicking and continues the Schulte Grid experiment after the user has recited the corresponding number. It should be noted that the first two numbers generated in the Schulte Grid experiment are between 0 and 9, and the last two numbers are between 10 and 99, arranged in ascending order. This prevents the user from being unable to fully recall the information due to the overwhelming amount of information. Furthermore, if the first sample user fails to repeat the information, the Schulte Grid experiment will be repeated using this interference mode. This interference mode also uses speakers at maximum volume to ensure the interference effect.

[0081] Pop-up window interference mode: This interference mode simulates the interference of pop-up advertisements and pop-up messages in actual scenes and working environments, and makes appropriate changes in combination with the data collection platform. When the first sample user searches and clicks numbers 1 to 25 in sequence, when it is detected that the first sample user clicks on the number 8, the data collection platform automatically pops up a window as interference. The experimenter supervises the first sample user to stop clicking and asks the user to browse the total time of the current Schulte grid experiment and the time spent on the third mouse click shown in the pop-up window, such as Figure 7 After the above operations are completed, close this pop-up window so that the first sample user can continue to complete the Schulte grid experiment.

[0082] In the above-mentioned Schulte grid experiment processing process, the eye data in the first sample data is obtained through the eye tracker device, and the mouse process of the first sample user is monitored through a pre-developed Python program to obtain the cursor movement data corresponding to the mouse.

[0083] It should be noted that the first sample users were required to complete the same number of Schulte grid experiments in no interference mode, internal and external noise interference mode, memory interference mode, and pop-up window interference mode, and in this process, the eye data and cursor movement data in the first sample data were obtained through the eye tracker device and Python program.

[0084] S220 : For the plurality of first sample data, segment the first sample data according to a preset data segmentation dimension to obtain a plurality of sub-sample data corresponding to each data segmentation dimension.

[0085] Among them, the data segmentation dimensions include: two adjacent mouse click events, events between a mouse click and a mouse lift, events within a first preset duration before a mouse click, and events within a second preset duration after a mouse click. Two adjacent mouse click events can be understood as events in which the first sample user performs two adjacent mouse clicks when simulating a preset experiment. Events between a mouse click and a mouse lift can be understood as events corresponding to the time between a mouse click and a mouse lift when the first sample user performs the preset experiment. The first preset duration can be a pre-set duration before the mouse click. For example, the first preset duration can be 0.1 seconds, that is, events within the first preset duration before a mouse click are events within 0.1 seconds before the mouse click. The second preset duration can be a pre-set duration after a mouse click. For example, the second preset duration can be 0.2 seconds. That is, events within the second preset duration after a mouse click can be events within 0.2 seconds after the mouse click.

[0086] Correspondingly, the sub-sample data corresponding to each data segmentation dimension includes eye movement trajectory data, cursor movement data, duration data, and hand-eye accompaniment data generated by simulating preset experiments. The cursor movement data includes cursor movement trajectory data, and the hand-eye accompaniment data is the correlation data between the cursor movement trajectory data and the eye movement trajectory data.

[0087] Taking the data segmentation dimension of two adjacent mouse click events as an example, the eye movement trajectory data corresponding to the two adjacent mouse click events may include: the average eye movement speed, eye movement distance, average eye movement acceleration, and total eye movement duration of the first sample user between the two adjacent mouse clicks. Cursor motion data can be understood as the cursor movement trajectory data of the electronic device corresponding to the first sample user within a preset duration. The cursor motion data corresponding to two adjacent mouse click events may include: the average cursor movement speed, average movement acceleration, movement distance, and total cursor movement duration between the two adjacent mouse clicks.

[0088] Duration data can be used to represent the total time it takes the first sample user to complete a preset experiment. Hand-eye accompanying data can be understood as the associated data when the first sample user's eyes follow the cursor movement. For example, the hand-eye accompanying data corresponding to two adjacent mouse click events can be the average similarity data of the hand-eye data in the horizontal direction between the two adjacent mouse clicks.

[0089] Specifically, after obtaining multiple first sample data, to ensure the accuracy of subsequent data processing, the first sample data can be preprocessed by data padding, outlier removal, and other data preprocessing to obtain preprocessed first sample data. The first sample data within the experimental duration of each preset experiment is segmented according to two adjacent mouse click events, the event between a mouse click and a mouse lift, the event within a first preset time period before the mouse click, and the event within a second preset time period after the mouse click, to determine subsample data for each preset experiment under each data segmentation dimension.

[0090] For example, in combination with the above example, the preset experiment is a Schulte experiment, the first preset time length is 0.1 seconds, and the second preset time length is 0.2 seconds.

[0091] After obtaining the first sample data, the first sample data can be preprocessed to obtain the preprocessed first sample data. Since a Schulte grid experiment requires searching and clicking numbers 1 to 25 in sequence, for the first sample data of each Schulte grid experiment, if data segmentation is not performed, there will be too much data and too much redundant data. In order to ensure the accuracy of the subsequent concentration assessment, four data segmentation dimensions can be selected: two adjacent mouse click events, events between mouse clicks and lifts, events within 0.1 seconds before mouse clicks, and events within 0.2 seconds after mouse clicks. The first sample data corresponding to each Schulte grid experiment is segmented using these four data segmentation dimensions to obtain sub-sample data under each data segmentation dimension.

[0092] S230: For each data segmentation dimension, determine the indicator evaluation value corresponding to each data indicator under the data segmentation dimension.

[0093] The subsample data corresponding to each data segmentation dimension includes eye movement trajectory data, cursor movement data, duration data, and hand-eye accompaniment data generated by simulating a pre-set experiment. Taking eye movement trajectory data as an example, eye movement trajectory data may include average eye movement velocity, eye movement distance, average eye movement acceleration, and total eye movement duration. The corresponding data indicators may be: average eye movement velocity indicator, eye movement distance indicator, average eye movement acceleration indicator, and total eye movement duration indicator. That is, each subsample data may contain data under multiple data indicators. Accordingly, in a pre-set experiment, each data segmentation dimension has multiple subsample data, each subsample data containing one or more data indicators, meaning that each data indicator may be associated with multiple subsample data. The indicator evaluation value can be used to characterize the correlation between the data indicator and the user's concentration assessment. Specifically, the larger the indicator evaluation value, the stronger the correlation between the data indicator and the user's concentration assessment.

[0094] Specifically, for each data segmentation dimension, one or more data indicators corresponding to the current data segmentation dimension are determined. Furthermore, subsample data associated with each data indicator within each pre-set experiment is determined. To ensure accuracy in subsequent data processing, the subsample data associated with each data indicator can be normalized to obtain normalized subsample data. Indicator evaluation processing is then performed on the normalized subsample data associated with each data indicator to determine the indicator evaluation value corresponding to each data indicator.

[0095] For example, for each data segmentation dimension, one or more data indicators corresponding to the current data segmentation dimension are determined, and subsample data associated with each data indicator in each preset experiment is determined.

[0096] Since the dimensions of different data segmentation are inconsistent and the data ranges are different, in order to improve the training effect of subsequent machine learning models, the Min-Max normalization method can be used to normalize the sub-sample data associated with each data indicator so that the data range of the sub-sample data is between [0,1].

[0097]

[0098] Among them, x norm represents the normalized subsample data associated with each data indicator, x represents the subsample data associated with each data indicator, x min Represents the minimum subsample data associated with each data indicator, x max Indicates the maximum subsample data associated with each data indicator.

[0099] In an embodiment of the present invention, the method for determining the indicator evaluation value can be: determining multiple data indicators of multiple sub-sample data corresponding to the data segmentation dimension; for each data indicator, determining the data mean of the multiple sub-sample data associated with the data indicator, and determining the indicator evaluation value of the data indicator based on the data mean and a preset function.

[0100] The data mean may be an average value obtained by performing mean processing on multiple subsample data associated with the same data indicator. The preset function may be a function for evaluating the correlation between the data indicator and the user's concentration evaluation.

[0101] Optionally, the preset function may be a Pearson correlation coefficient function. The Pearson correlation coefficient function may be expressed as follows:

[0102]

[0103] Among them, x i Indicates the subsample data associated with the data indicator. Indicates the mean value of multiple sub-sample data associated with the data indicator. i is a preset value used to represent the proficiency of performing the preset experiment, y i =0 means unskilled, y i =1 means proficient, Used to characterize the mean proficiency of conducting a preset experiment. xyrepresents the indicator evaluation value, and n represents the number of subsamples associated with the same data indicator. It should be noted that when the indicator evaluation value determined by the Pearson correlation coefficient function is within the range [-1, +1] and the indicator evaluation value is greater than 0.8, it indicates a strong correlation between the data indicator and the user's focus assessment; when the value is between 0.2 and 0.8, it indicates a certain correlation between the data indicator and the user's focus assessment.

[0104] Specifically, for each data segmentation dimension, the data metric to which each subsample data item belongs within each data segmentation dimension is determined. For each data metric, the subsample data associated with each data metric within each preset experiment is determined. Based on the subsample data associated with each data metric and the number of subsample data items, a data mean is determined. Based on the data mean and a preset function, an indicator evaluation value corresponding to the data metric is determined, and whether the data metric should be retained is determined based on the indicator evaluation value.

[0105] S240: Determine whether to retain the indicator evaluation value according to the indicator evaluation value corresponding to each data indicator and the corresponding preset evaluation threshold.

[0106] The preset evaluation threshold may be a pre-set standard value corresponding to the indicator evaluation value. Optionally, when the preset function is a Pearson correlation coefficient function, the preset evaluation threshold may be 0.2.

[0107] Specifically, if the indicator evaluation value of a data indicator is greater than the corresponding preset evaluation threshold, it indicates that the correlation between the data indicator and the user's focus evaluation is strong, and the indicator evaluation value of the data indicator is determined to be retained. Correspondingly, if the indicator evaluation value of a data indicator is less than the corresponding preset evaluation threshold, it indicates that the correlation between the data indicator and the user's focus evaluation is weak, and the corresponding indicator evaluation value is deleted.

[0108] S250: Determine a target indicator based on the quantity of indicator evaluation values ​​of all first sample data under the same data indicator and preset indicator data, and use the target indicator as a feature dimension.

[0109] The number of preset indicators can be understood as the number of pre-set target indicators. Target indicators can be understood as data indicators used for subsequent model training. Target indicators are positively correlated with user focus assessment.

[0110] Specifically, based on the quantitative values ​​of the indicator evaluation values ​​for the same data indicator for all first sample data, the data indicators are sorted from largest to smallest in descending order of quantitative value to obtain a data indicator sorting result. Based on the preset indicator data and the sorting result, a target indicator corresponding to the preset indicator data is determined. That is, the target indicator is the data indicator with the largest quantitative value of the indicator evaluation value.

[0111] Exemplarily, in combination with the above example, take the indicator evaluation value as the Pearson correlation coefficient and the preset indicator data as 12 as an example. The data indicators with a Pearson correlation coefficient greater than 0.2 are retained. And the number of indicator evaluation values ​​corresponding to all the first sample data under each data indicator with a Pearson correlation coefficient greater than 0.2 is determined. According to the number of indicator evaluation values, the data indicators are sorted from large to small, so that the top 12 data indicators in the sorting are used as target indicators, that is, feature dimensions. For example, the feature dimensions may include: the total duration of the mouse movement operation in a Schulte grid experiment, the average mouse speed under two adjacent mouse click events, the average eye movement speed under two adjacent mouse click events, the average similarity of horizontal hand-eye data under two adjacent mouse click events, etc.

[0112] S260: Perform data extraction on the acquired second sample data based on the feature dimension to obtain sample data corresponding to each second sample data under the feature dimension.

[0113] The second sample data may be eye data and cursor motion data collected from the sample user in each interference mode, and the sample data may be the second sample data in the corresponding feature dimension.

[0114] Specifically, before training the focus assessment model, second sample data can be obtained. To improve model accuracy, as much and rich second sample data as possible can be obtained. Data extraction processing is then performed on the second sample data based on the multiple feature dimensions determined to obtain sample data for each feature dimension. The focus assessment model is then trained based on the sample data for the multiple feature dimensions.

[0115] S270: Training the concentration evaluation model based on the second sample data to obtain a usable concentration evaluation model.

[0116] It should be noted that the input of the concentration evaluation model is the second sample data under multiple feature dimensions.

[0117] Specifically, a label corresponding to the input of the focus assessment model is determined, that is, a theoretical focus assessment attribute is determined. Second sample data under multiple feature dimensions is input into the focus assessment model for focus assessment processing to obtain actual focus assessment attributes. A first loss value is determined based on the actual focus assessment attributes and the theoretical focus assessment attributes. Model parameters of the focus assessment model are modified based on the first loss value to obtain a usable focus assessment model.

[0118] When using the first loss value to correct the model parameters in the concentration evaluation model, the convergence of the loss function can be used as a training goal, such as whether the training error is less than the preset error, or whether the error change tends to be stable, or whether the current number of iterations is equal to the preset number. If the detection reaches the convergence condition, such as the training error of the loss function is less than the preset error, or the error change trend tends to be stable, it indicates that the training of the concentration evaluation model is completed, and the iterative training can be stopped at this time. If it is detected that the convergence condition is not currently reached, other second sample data can be further obtained to continue training the concentration evaluation model until the training error of the loss function is within the preset range. When the training error of the loss function reaches convergence, a usable concentration evaluation model can be obtained.

[0119] S280: Input the third sample data into the concentration evaluation model. When the output result of the concentration evaluation model is a preset result, train the interference classification model based on the third sample data and the interference pattern corresponding to the third sample data to obtain a usable interference classification model.

[0120] The third sample data may be sample data under multiple feature dimensions. The preset result may be that the output result of the concentration evaluation model satisfies the interference pattern evaluation condition. That is, the output result of the concentration evaluation model indicates that the user corresponding to the third sample data is not focused.

[0121] Specifically, the third sample data is input into the concentration evaluation model to obtain an output result corresponding to the third sample data. When the output result is consistent with the preset result, it is determined that the user corresponding to the third sample data is not focused. The third sample data corresponding to the output result consistent with the preset result can then be input into the interference classification model to determine the output interference pattern corresponding to the third sample data. Based on the interference pattern corresponding to the third sample data and the output interference pattern output by the interference classification model, a second loss value is determined. Based on the second loss value, the interference classification model is subjected to model parameter correction processing to obtain a usable interference classification model.

[0122] When using the second loss value to correct the model parameters in the interference classification model, the convergence of the loss function can be used as a training goal, such as whether the training error is less than the preset error, or whether the error change tends to be stable, or whether the current number of iterations is equal to the preset number. If the detection reaches the convergence condition, such as the training error of the loss function is less than the preset error, or the error change trend tends to be stable, it indicates that the interference classification model training is completed, and the iterative training can be stopped at this time. If it is detected that the convergence condition is not currently reached, other third sample data can be further obtained to continue training the interference classification model until the training error of the loss function is within the preset range. When the training error of the loss function reaches convergence, a usable interference classification model can be obtained.

[0123] For example, in combination with the above example, the concentration assessment model is a GBDT machine learning model and the interference classification model is an SVM machine learning model. The second sample household number and the third sample data are processed by 10-fold cross validation to complete the training of the concentration assessment model and the interference classification model. After the training is completed, the data to be used under multiple feature dimensions are input into the GBDT machine learning model, and the GBDT machine learning model outputs the concentration assessment attribute accordingly. If the concentration assessment attribute characterizes that the user is not focused, the data to be used can be input into the SVM machine learning model to determine the interference pattern that causes the user to be inattentive based on the interference pattern output by the SVM machine learning model.

[0124] The technical solution of this embodiment obtains a plurality of first sample data in different interference modes and non-interference modes, and performs data segmentation processing on the first sample data based on a pre-set data segmentation dimension to obtain a plurality of sub-sample data corresponding to each data dimension. For each data segmentation dimension, the indicator evaluation value corresponding to each data indicator under the data segmentation dimension is determined, so as to determine the feature dimension based on the indicator evaluation value. The concentration evaluation model is trained based on the second sample data under multiple feature dimensions to obtain a usable concentration evaluation model. After obtaining the usable concentration evaluation model, the third sample data is input into the concentration evaluation model. When the output result of the concentration evaluation model is a preset result, the interference classification model is trained based on the third sample data and the interference pattern corresponding to the third sample data to obtain a usable interference classification model. The present invention realizes the training processing of the concentration evaluation model and the interference classification model to obtain the trained concentration evaluation model and the interference classification model, thereby improving the accuracy of the subsequent concentration evaluation and the accuracy of the interference pattern classification. Subsequently, the target user's pending data is evaluated and analyzed through the trained concentration evaluation model and interference classification model, which reduces the cost of user concentration evaluation. Without affecting the target user, the target user's concentration is evaluated and the interference pattern that affects concentration is determined, making it convenient to remind the target user according to the user's concentration, so as to achieve the purpose of improving user work efficiency.

[0125] Example 3

[0126] Figure 8 This is a schematic diagram of the structure of a device for determining user concentration provided by the third embodiment of the present invention. Figure 8 As shown, the device includes: a data acquisition module 310, a feature extraction module 320, a concentration evaluation module 330 and an interference pattern determination module 340.

[0127] The data acquisition module 310 is used to obtain the target user's pending data within a preset time period, wherein the pending data includes the target user's eye data and cursor movement data; the feature extraction module 320 is used to extract the pending data according to a plurality of predetermined feature dimensions to obtain the corresponding pending data under the feature dimensions, wherein the feature dimensions are determined based on the feature dimensions after processing the first sample data corresponding to the first sample user under multiple interference modes, and the feature dimensions are positively correlated with the user's concentration assessment; the concentration assessment module 330 is used to input the pending data into a pre-trained concentration assessment model for concentration assessment to obtain the target user's concentration assessment attribute; the interference pattern determination module 340 is used to input the pending data into a pre-trained interference classification model when the concentration assessment attribute meets the interference pattern assessment condition to obtain the interference pattern corresponding to the concentration assessment attribute; wherein the interference pattern is used to characterize the type of interference that affects the target user's concentration, and the interference pattern includes any one or more of internal and external noise interference patterns, memory interference patterns, and pop-up window prompt interference patterns of the terminal device.

[0128] The technical solution of this embodiment obtains the target user's data to be processed within a preset time period, and extracts features from the data to be processed through multiple feature dimensions to determine the data to be used under multiple feature dimensions. Based on this, data support is provided for the subsequent evaluation of the target user's concentration. The data to be used is input into the pre-trained concentration evaluation model for concentration evaluation, and the target user's concentration evaluation attribute is obtained, thereby realizing the evaluation of the target user's concentration. When the concentration evaluation attribute meets the interference pattern evaluation condition, the data to be used is input into the interference classification model to obtain the interference pattern corresponding to the concentration evaluation attribute. Based on this, the factors affecting the target user's concentration are determined, which facilitates the subsequent reminder of the target user based on the factors affecting the target user's concentration, so as to achieve the purpose of improving the target user's work efficiency. The present invention solves the problems in the prior art of relying on external devices to evaluate user concentration, which affects the user's normal work, has a poor user experience, and has a high evaluation cost. The present invention evaluates and analyzes the target user's eye data and cursor movement data through a concentration evaluation model and an interference classification model, thereby reducing the cost of user concentration evaluation. Without affecting the target user, the target user's concentration is evaluated and the interference pattern that affects the concentration is determined, which facilitates reminding the target user according to the user's concentration, so as to achieve the purpose of improving user work efficiency.

[0129] On the basis of the above embodiment, optionally, the device also includes: a feature dimension determination module, which includes: a first sample data acquisition unit, which is used to acquire multiple first sample data in different interference modes and non-interference modes, wherein the first sample data is eye data and cursor movement data generated by the first sample user after simulating a preset experiment; a sub-sample data determination unit, which is used to divide the first sample data according to a preset data segmentation dimension for the multiple first sample data, and obtain multiple sub-sample data corresponding to each data segmentation dimension; an indicator evaluation value determination unit, which is used to determine the indicator evaluation value corresponding to each data indicator under the data segmentation dimension for each data segmentation dimension; an indicator evaluation value judgment unit, which is used to determine whether to retain the indicator evaluation value according to the indicator evaluation value corresponding to each data indicator and the corresponding preset evaluation threshold; a target indicator determination unit, which is used to determine the target indicator according to the quantity of the indicator evaluation values ​​of all the first sample data under the same data indicator and the preset indicator data, and use the target indicator as the feature dimension.

[0130] Optionally, the data segmentation dimensions include: two adjacent mouse click events, the event between a mouse click and a mouse lift, the event within a first preset time length before the mouse click, and the event within a second preset time length after the mouse click. Accordingly, the subsample data corresponding to each data segmentation dimension includes eye movement trajectory data, cursor motion data, duration data, and hand-eye accompaniment data generated by a simulated preset experiment. The cursor motion data includes cursor movement trajectory data, and the hand-eye accompaniment data is the correlation data between the cursor movement trajectory data and the eye movement trajectory data.

[0131] Optionally, the indicator evaluation value determination unit is used to determine multiple data indicators of multiple sub-sample data corresponding to the data segmentation dimension; for each data indicator, determine the data mean of the multiple sub-sample data associated with the data indicator, and determine the indicator evaluation value of the data indicator based on the data mean and a preset function; the indicator evaluation value judgment unit is used to determine the indicator evaluation value of the retained data indicator when the indicator evaluation value of the data indicator is greater than the corresponding preset evaluation threshold.

[0132] Optionally, the device further includes: a sample data feature extraction module, configured to perform data extraction for the acquired second sample data based on the feature dimension, so as to obtain sample data corresponding to each second sample data under the feature dimension.

[0133] Optionally, the device also includes: a model training module, used to train the concentration assessment model based on the second sample data to obtain a usable concentration assessment model; input the third sample data into the concentration assessment model, and when the output result of the concentration assessment model is a preset result, train the interference classification model based on the third sample data and the interference pattern corresponding to the third sample data to obtain a usable interference classification model.

[0134] Optionally, the device further includes: a reminder text display module, configured to display a reminder text corresponding to the interference pattern in the interface after obtaining the interference pattern.

[0135] Optionally, the first sample data corresponding to the internal and external noise interference mode is the eye data and cursor movement data generated when the first sample user completes the preset experiment within the third preset time period of noise interference; the first sample data corresponding to the memory interference mode is the eye data and cursor movement data generated when the first sample user performs the preset experiment in the process of retelling the preset content; the first sample data corresponding to the pop-up prompt interference mode is the eye data and cursor movement data generated when the first sample user performs the preset experiment when being constantly disturbed by pop-up prompt information.

[0136] The device for determining user concentration provided by an embodiment of the present invention can execute the method for determining user concentration provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0137] Example 4

[0138] Figure 9 1 is a structural diagram of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0139] like Figure 9As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0140] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0141] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining user concentration.

[0142] In some embodiments, the method for determining user concentration may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining user concentration described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the method for determining user concentration in any other appropriate manner (e.g., by means of firmware).

[0143] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] Computer programs for implementing the method for determining user concentration of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0145] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication unit 19, or installed from the storage unit 18, or installed from the ROM 12. When the computer program is executed by the processor 11, the above-mentioned functions defined in the method of the embodiment of the present invention are performed.

[0146] Example 5

[0147] Embodiment 5 of the present invention further provides a computer-readable storage medium storing computer instructions, the computer instructions being used to cause a processor to execute a method for determining a user's concentration, the method comprising:

[0148] Obtain the target user's data to be processed within a preset time period, wherein the data to be processed includes the target user's eye data and cursor movement data; extract the data to be processed according to a plurality of predetermined feature dimensions to obtain the data to be used corresponding to the feature dimensions, wherein the feature dimensions are feature dimensions determined after processing the first sample data corresponding to the first sample user under a plurality of interference modes, and the feature dimensions are positively correlated with the user's concentration evaluation; input the data to be used into a pre-trained concentration evaluation model for concentration evaluation to obtain the target user's concentration evaluation attribute; when the concentration evaluation attribute meets the interference mode evaluation condition, input the data to be used into a pre-trained interference classification model to obtain the interference mode corresponding to the concentration evaluation attribute; wherein the interference mode is used to characterize the type of interference that affects the target user's concentration, and the interference mode includes any one or more of internal and external noise interference mode, memory interference mode, and pop-up window prompt interference mode of the terminal device.

[0149] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0151] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0152] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0153] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0154] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for determining a user's concentration, characterized in that: include: Acquire data to be processed of a target user within a preset time period, wherein the data to be processed includes eye data and cursor movement data of the target user; Extracting data from the data to be processed according to a plurality of predetermined feature dimensions to obtain data to be used corresponding to the feature dimensions, wherein the feature dimensions are determined based on processing first sample data corresponding to a first sample user under a plurality of interference modes, and the feature dimensions are positively correlated with an assessment of the user's concentration; Inputting the data to be used into a pre-trained concentration evaluation model to perform concentration evaluation, thereby obtaining the concentration evaluation attribute of the target user; When the concentration evaluation attribute satisfies the interference pattern evaluation condition, inputting the to-be-used data into a pre-trained interference classification model to obtain an interference pattern corresponding to the concentration evaluation attribute; The interference pattern is used to characterize the type of interference that affects the concentration of the target user, and the interference pattern includes any one or more of internal and external noise interference patterns, memory interference patterns, and pop-up window prompt interference patterns of terminal devices.

2. The method according to claim 1, characterized in that The method further comprises: determining the plurality of feature dimensions; The determining of the multiple feature dimensions includes: Acquire a plurality of first sample data in different interference modes and a non-interference mode, wherein the first sample data is eye data and cursor movement data generated by the first sample user after simulating a preset experiment; For the plurality of first sample data, segmenting the first sample data according to a preset data segmentation dimension to obtain a plurality of sub-sample data corresponding to each data segmentation dimension; For each data segmentation dimension, determine the indicator evaluation value corresponding to each data indicator under the data segmentation dimension; Determine whether to retain the indicator evaluation value according to the indicator evaluation value corresponding to each data indicator and the corresponding preset evaluation threshold; A target indicator is determined according to the quantity of the indicator evaluation values ​​of all the first sample data under the same data indicator and preset indicator data, and the target indicator is used as the feature dimension.

3. The method according to claim 2, characterized in that The data segmentation dimensions include: two adjacent mouse click events, events between a mouse click and a mouse lift, events within a first preset time length before a mouse click, and events within a second preset time length after a mouse click. Accordingly, the subsample data corresponding to each data segmentation dimension includes eye movement trajectory data, cursor motion data, duration data, and hand-eye accompaniment data generated by a simulated preset experiment. The cursor motion data includes cursor movement trajectory data, and the hand-eye accompaniment data is the associated data between the cursor movement trajectory data and the eye movement trajectory data.

4. The method according to claim 2, characterized in that Determining the indicator evaluation value corresponding to each data indicator under the data segmentation dimension includes: Determining multiple data indicators of multiple sub-sample data corresponding to the data segmentation dimension; For each data indicator, determining a data mean of a plurality of subsample data associated with the data indicator, and determining an indicator evaluation value of the data indicator based on the data mean and a preset function; Accordingly, determining whether to retain the indicator evaluation value corresponding to each data indicator and the corresponding preset evaluation threshold includes: If the indicator evaluation value of the data indicator is greater than the corresponding preset evaluation threshold, it is determined to retain the indicator evaluation value of the data indicator.

5. The method according to any one of claims 2 to 4, characterized in that: After obtaining the feature dimension, the method includes: Data extraction is performed on the acquired second sample data based on the feature dimension to obtain sample data corresponding to each second sample data under the feature dimension.

6. The method according to claim 5, characterized in that The method further comprises: Training the concentration evaluation model based on the second sample data to obtain a usable concentration evaluation model; The third sample data is input into the concentration evaluation model. When the output result of the concentration evaluation model is a preset result, the interference classification model is trained based on the third sample data and the interference pattern corresponding to the third sample data to obtain the usable interference classification model.

7. The method according to claim 1, characterized in that The method further comprises: After obtaining the interference pattern, a reminder text corresponding to the interference pattern is displayed in the interface.

8. The method according to claim 2, characterized in that The first sample data corresponding to the internal and external noise interference mode is the eye data and cursor movement data generated when the first sample user completes the preset experiment within the third preset time period of noise interference; the first sample data corresponding to the memory interference mode is the eye data and cursor movement data generated when the first sample user performs the preset experiment while repeating the preset content; the first sample data corresponding to the pop-up prompt interference mode is the eye data and cursor movement data generated when the first sample user performs the preset experiment when being constantly disturbed by pop-up prompt information.

9. A device for determining a user's concentration, characterized in that include: A data acquisition module, configured to acquire data to be processed from a target user within a preset time period, wherein the data to be processed includes eye data and cursor movement data of the target user; a feature extraction module, configured to extract data from the data to be processed according to a plurality of predetermined feature dimensions to obtain data to be used corresponding to the feature dimensions, wherein the feature dimensions are determined based on first sample data corresponding to a first sample user under a plurality of interference modes, and the feature dimensions are positively correlated with an assessment of the user's concentration; A concentration evaluation module is used to input the to-be-used data into a pre-trained concentration evaluation model to perform concentration evaluation and obtain the concentration evaluation attribute of the target user; an interference pattern determination module, configured to input the to-be-used data into a pre-trained interference classification model to obtain an interference pattern corresponding to the concentration evaluation attribute when the concentration evaluation attribute satisfies an interference pattern evaluation condition; The interference pattern is used to characterize the type of interference that affects the concentration of the target user, and the interference pattern includes any one or more of internal and external noise interference patterns, memory interference patterns, and pop-up window prompt interference patterns of terminal devices.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, where the computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining user concentration according to any one of claims 1 to 8.

Images