Internet of Things-Based Psychological Assessment Method and System

Abstract

The present application relates to the field of Internet technology, and specifically to a psychological assessment method and system based on the Internet of Things. The psychological assessment system based on the Internet of Things includes: a page setting unit, an Internet of Things device, a prediction unit, a page adjustment unit, and a determination unit. The present application adjusts the psychological assessment questions on the page to be displayed to the current test-taker based on the prediction of the attention focus coordinate range and the prediction of the credibility of the answers to the psychological assessment questions, so as to repeat the display of some psychological assessment questions instead of all psychological assessment questions. This can at least solve the technical problem of displaying all psychological assessment questions twice to the same test-taker, and at least improve the user experience.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and specifically to a psychological assessment method and system based on the Internet of Things. Background Art

[0002] With the development of computer and communication technologies, the Internet has emerged, and the Internet of Things, for example, is a branch of the Internet. Internet users can use the Internet for shopping, communication, and other operations.

[0003] The internet is also used for psychological assessments. Test-takers can use a browser to open a page containing psychological assessment questions and answer them. The page containing the psychological assessment questions can be hosted on a server. Based on the test-taker's responses, the server generates an evaluation report.

[0004] Existing psychological assessment methods typically present the same test questions on different pages to test takers to determine the credibility of the answers. To ensure credibility, all psychological assessment questions are often presented to the same test taker twice, affecting the test taker's user experience. Summary of the Invention

[0005] This application provides an Internet of Things-based psychological assessment method and system, which aims to solve the technical problem of existing psychological assessment methods that all psychological assessment questions are presented to the same test taker twice. Since all psychological assessment questions are not presented to the same test taker twice, the user experience can be improved.

[0006] On the one hand, the present application provides a psychological assessment method based on the Internet of Things. The psychological assessment method based on the Internet of Things includes: setting a plurality of psychological assessment questions in a plurality of pages, wherein the plurality of pages are set in the same coordinate system; obtaining the current tester's facial image, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate through the Internet of Things device; performing a first prediction through an attention focus area prediction model to obtain an attention focus coordinate range corresponding to the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate, wherein the attention focus coordinate range is represented by coordinates in the coordinate system, and the attention focus area prediction model is trained based on historical testers' eye gaze direction, historical testers' eye distance between the page, historical testers' pupil area, historical testers' blinking frequency, historical testers' heart rate, and historical attention focus coordinate range; performing a prediction on the page to be displayed to the current tester among the plurality of pages. The first adjustment is to make the psychological assessment test questions to be displayed to the current tester fall within the attention focus coordinate range obtained by the first prediction; determine the number of asymmetric pixels on the current tester's face based on the current tester's facial image; determine the psychological assessment test questions that the current tester is gazing at on the page displayed to the current tester based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction, and the distance between the current tester's eyes and the page; predict whether the answer to the psychological assessment test questions that the current tester is gazing at is credible based on the number of asymmetric pixels on the current tester's face and a test question answer credibility classification model, wherein the test question answer credibility classification model is trained based on the number of asymmetric pixels on the faces of historical testers and the credibility results of historical test question answers corresponding to the number of asymmetric pixels on the faces of historical testers; when the answer to the psychological assessment test questions that the current tester is gazing at is uncredible, integrate the psychological assessment test questions with uncredible answers into the page to be displayed to the current tester and fall within the attention focus coordinate range obtained by the first prediction.

[0007] Optionally, the psychological assessment method based on the Internet of Things also includes: when the number of psychological assessment questions that have been integrated exceeds a predetermined value, re-acquiring the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate through the Internet of Things device; performing a second prediction through the attention focus area prediction model to obtain an attention focus coordinate range corresponding to the re-acquired current tester's eye gaze direction, the re-acquired distance between the current tester's eyes and the page, the re-acquired current tester's pupil area, the re-acquired current tester's blinking frequency, and the re-acquired current tester's heart rate; and performing a second adjustment on the pages to be displayed to the current tester among the multiple pages, so that the psychological assessment questions to be displayed to the current tester fall within the attention focus coordinate range obtained through the second prediction.

[0008] Optionally, the Internet of Things-based psychological assessment method also includes: integrating the test questions in the page that has been displayed to the current tester and that fall outside the attention concentration coordinate range obtained by the second prediction into the page to be displayed to the current tester and that fall within the attention concentration coordinate range obtained by the first prediction or the second prediction; if the first adjustment or the second adjustment of the page has been performed, then performing a third adjustment on the page to be displayed to the current tester among the multiple pages, so that the color of the psychological assessment test questions displayed to the current tester is changed to a specific color.

[0009] Optionally, the psychological assessment method based on the Internet of Things also includes: counting the total area of the current tester's gaze based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, and the page that has been displayed to the current tester; obtaining the current tester's body image through the Internet of Things device; calculating the number of changes in the current tester's body pixel values based on different body images of the current tester; predicting whether the current tester has entered a fatigue period based on a fatigue prediction model, the counted total area of the current tester's gaze, the number of unreliable answers obtained through prediction, and the calculated number of changes in the current tester's body pixel values, wherein the fatigue prediction model is trained based on historical testers' total gaze areas, historical numbers of unreliable answers, and historical changes in testers' body pixel values; when it is predicted that the current tester has entered a fatigue period, pausing the psychological assessment and entering a rest period of the second time period.

[0010] Optionally, the Internet of Things-based psychological assessment method also includes: after the rest period ends, resuming the psychological assessment and displaying the page obtained after the third adjustment, wherein the first adjustment and / or the second adjustment include: text spacing adjustment, paragraph spacing adjustment, single-line display word count adjustment and / or text size adjustment.

[0011] On the other hand, the present application provides a psychological assessment system based on the Internet of Things. The psychological assessment system based on the Internet of Things includes: a page setting unit, configured to set a plurality of psychological assessment test questions on a plurality of pages, wherein the plurality of pages are set in the same coordinate system; an Internet of Things device, configured to obtain a facial image of a current tester, an eye gaze direction of the current tester, a distance between the eyes of the current tester and the page, a pupil area of the current tester, a blinking frequency of the current tester, and a heart rate of the current tester; a prediction unit, configured to make a first prediction using an attention focus area prediction model to obtain an attention focus coordinate range corresponding to the eye gaze direction of the current tester, the distance between the eyes of the current tester and the page, the pupil area of the current tester, the blinking frequency of the current tester, and the heart rate of the current tester, wherein the attention focus coordinate range is represented by coordinates in the coordinate system, and the attention focus area prediction model is trained based on the eye gaze direction, the distance between the eyes of the current tester and the page, the pupil area of the current tester, the blinking frequency of the current tester, the heart rate of the current tester, and the historical attention focus coordinate range of the historical tester; and a page adjustment unit, configured to adjust the page to be displayed to the current tester among the plurality of pages. The first adjustment is performed so that the psychological assessment test questions displayed to the current tester fall within the attention focus coordinate range obtained by the first prediction; the determination unit is configured to: determine the number of asymmetric pixels on the current tester's face according to the current tester's facial image; determine the psychological assessment test questions that the current tester is looking at in the page displayed to the current tester according to the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction and the distance between the current tester's eyes and the page; wherein the prediction unit is further configured to: determine the number of asymmetric pixels on the current tester's face according to the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction and the distance between the current tester's eyes and the page; A classification model of the number of symmetrical pixels and the credibility of the test answer predicts whether the answer to the psychological assessment test question currently being looked at is credible, wherein the classification model of the credibility of the test answer is trained based on the number of asymmetrical pixels on the faces of historical testers and the credibility results of the historical test answer corresponding to the number of asymmetrical pixels on the faces of historical testers; the page adjustment unit is further configured to: when the answer to the psychological assessment test question currently being looked at is uncredible, integrate the psychological assessment test question with an uncredible answer into the page to be displayed to the current tester and fall within the attention concentration coordinate range obtained by the first prediction.

[0012] Optionally, the Internet of Things device is further configured to: when the number of psychological assessment test questions that have undergone the integration exceeds a predetermined value, re-acquire the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate; the prediction unit is further configured to: perform a second prediction through the attention focus area prediction model to obtain an attention focus coordinate range corresponding to the re-acquired current tester's eye gaze direction, the re-acquired distance between the current tester's eyes and the page, the re-acquired current tester's pupil area, the re-acquired current tester's blinking frequency, and the re-acquired current tester's heart rate; the page adjustment unit is further configured to: perform a second adjustment on the page to be displayed to the current tester among the multiple pages, so that the psychological assessment test questions to be displayed to the current tester fall within the attention focus coordinate range obtained through the second prediction.

[0013] Optionally, the page adjustment unit is further configured to: integrate the test questions in the page that has been displayed to the current tester and fall outside the attention concentration coordinate range obtained by the second prediction into the page to be displayed to the current tester and fall within the attention concentration coordinate range obtained by the first prediction or the second prediction; if the first adjustment or the second adjustment of the page has been performed, then perform a third adjustment on the page to be displayed to the current tester among the multiple pages, so that the color of the psychological assessment test questions displayed to the current tester is changed to a specific color.

[0014] Optionally, the Internet of Things device is further configured to: obtain a body image of the current tester; the determination unit is further configured to: count the total gaze area of the current tester based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, and the page that has been displayed to the current tester; calculate the number of changes in the current tester's body pixel values based on different body images of the current tester; the prediction unit is further configured to: predict whether the current tester has entered a fatigue period based on a fatigue prediction model, the counted total gaze area of the current tester, the number of unreliable answers obtained through prediction, and the calculated number of changes in the current tester's body pixel values, wherein the fatigue prediction model is trained based on historical testers' total gaze areas, historical numbers of unreliable answers, and historical changes in testers' body pixel values; the page adjustment unit is further configured to: when it is predicted that the current tester has entered a fatigue period, suspend the psychological assessment and enter a rest period of the second time period.

[0015] Optionally, the page adjustment unit is further configured to: after the rest period ends, resume the psychological assessment and display the page obtained after the third adjustment, wherein the first adjustment and / or the second adjustment include: text spacing adjustment, paragraph spacing adjustment, single-line display word count adjustment and / or text size adjustment.

[0016] This application adjusts the psychological assessment questions on the page to be displayed to the current tester based on the prediction of the attention focus coordinate range and the prediction of whether the answers to the psychological assessment questions are credible or not, so as to repeatedly display some psychological assessment questions instead of all psychological assessment questions. This can at least solve the technical problem of displaying all psychological assessment questions to the same tester twice, and at least improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 It is a flow chart of a psychological assessment method based on the Internet of Things according to an exemplary embodiment of the present application.

[0019] Figure 2 It is a structural diagram of a psychological assessment system based on the Internet of Things of an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0021] The terms "first" and "second" and the like in this application are used to distinguish between different objects, rather than to describe a particular order. Furthermore, 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 comprising a series of steps, operations, components, or modules is not limited to the listed steps, operations, components, or modules, but may optionally include steps, operations, components, or modules not listed, or may optionally include other steps, operations, components, or modules inherent to the process, method, product, or device.

[0022] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0023] The embodiments of this application provide a psychological assessment method and system based on the Internet of Things, which will be described in detail below. It should be noted that the order of description of the following embodiments does not constitute a limitation on the order of specific implementation. The order of description includes but is not limited to the order of step description or operation description and the order of description of system components.

[0024] The psychological assessment method and system of the exemplary embodiment of the present application can be implemented through the Internet. During the implementation process, the server that implements the psychological assessment method can generate a page, which contains psychological assessment questions. The user accesses the Internet through a browser, accesses the server's URL, browses the page generated by the server, and answers the psychological assessment questions on the page. Based on the user's answers to the psychological assessment questions, a psychological assessment report for the user can be generated. The user here can be referred to as a tester. During the implementation process, it is also necessary to use Internet of Things devices, such as eye trackers, cameras, webcams, heart rate sensors, etc. that can be connected to the Internet. Such Internet of Things devices can communicate with the server so as to transmit the obtained information to the server. The psychological assessment system of the present application can be implemented on a server.

[0025] Reference Figure 1The exemplary embodiment of the psychological assessment method based on the Internet of Things includes: setting a plurality of psychological assessment test questions in a plurality of pages, wherein the plurality of pages are set in the same coordinate system; obtaining the current tester's facial image, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate through the Internet of Things device; performing a first prediction through an attention focus area prediction model to obtain an attention focus coordinate range corresponding to the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate, wherein the attention focus coordinate range is represented by coordinates in the coordinate system, and the attention focus area prediction model is trained based on historical testers' eye gaze directions, historical testers' eye distances between the page, historical testers' pupil areas, historical testers' blinking frequencies, historical testers' heart rates, and historical attention focus coordinate ranges; and performing a first prediction on the plurality of pages to be displayed to the current tester. The page is first adjusted so that the psychological assessment test questions to be displayed to the current tester fall within the attention focus coordinate range obtained through the first prediction; the number of asymmetric pixels on the current tester's face is determined based on the current tester's facial image; the psychological assessment test question that the current tester is gazing at on the page displayed to the current tester is determined based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction, and the distance between the current tester's eyes and the page; based on the number of asymmetric pixels on the current tester's face and a test question answer credibility classification model, it is predicted whether the answer to the psychological assessment test question that the current tester is gazing at is credible, wherein the test question answer credibility classification model is trained based on the number of asymmetric pixels on the faces of historical testers and the credibility results of historical test question answers corresponding to the number of asymmetric pixels on the faces of historical testers; when the answer to the psychological assessment test question that the current tester is gazing at is uncredible, the psychological assessment test question with the uncredible answer is integrated into the page that will be displayed to the current tester and falls within the attention focus coordinate range obtained through the first prediction.

[0026] For example, a psychological assessment question on a page consists of a stem and options. The stem describes the question, for example, asking for the user's opinion on something. The options correspond to opinions, such as "agree" and "disagree." Alternatively, "partially agree," "completely agree," "partially disagree," and "completely disagree" correspond to A, B, C, and D, respectively. For multiple pages in the same coordinate system, the range of the questions on the page corresponds to the coordinate range.

[0027] As an example, the IoT device can be a camera or a camera that captures the tester's facial image, and the IoT device can be an eye tracker, a heart rate sensor, and a distance sensor. The eye tracker can obtain the tester's eye gaze direction, the tester's pupil area, and the tester's blinking frequency. The heart rate sensor can obtain the tester's heart rate. The distance sensor can obtain the distance between the tester's eyes and the page.

[0028] As an example, the attention focus area prediction model can predict the attention focus coordinate range. The attention focus coordinate range is represented by coordinates in the page's coordinate system and can be a closed area. It can determine whether the psychological assessment question falls within the attention focus coordinate range (i.e., whether it is inside or outside the attention focus coordinate range). If the question stem and options of the psychological assessment question do not completely fall within the attention focus coordinate range, it can be determined that the psychological assessment question is outside the attention focus coordinate range. The attention focus area prediction model can use a neural network model or a support vector machine model. The model can be trained using corresponding historical data.

[0029] In an exemplary embodiment, a back-propagation neural network model may be used, a sigmoid activation function may be used for the classifier, and a linear rectifier function may be used for a prediction model such as an attention region prediction model. The prediction evaluation metric used may be mean square error, root mean square error, mean absolute error, or mean absolute percentage error.

[0030] As an example, the first adjustment includes not only adjusting the psychological assessment test questions to fall within the corresponding range in the page to be displayed, but also includes: text color adjustment, text spacing adjustment, paragraph spacing adjustment, single-line display word count adjustment and / or text size adjustment.

[0031] For example, by flipping the test subject's facial image, a flipped image can be obtained. By comparing the pre-flip and post-flip images, the difference between the two images can be obtained. The difference may include pixel differences. Specifically, when the grayscale values of symmetrical positions differ, or when the grayscale value difference exceeds a predetermined difference value, the corresponding pixels are considered asymmetrical. Trigonometric operations can be used to determine the psychological assessment question that the current test subject is looking at on the page being presented to the test subject.

[0032] For example, a test answer credibility classification model can employ a neural network classifier or a support vector machine classifier. Model training can be performed based on relevant historical data. When integrating psychological assessment questions with unreliable answers into the page displayed to the current test-taker, it is also necessary to ensure that the integrated psychological assessment questions fall within the predicted attention focus coordinate range.

[0033] In an exemplary embodiment, the psychological assessment method based on the Internet of Things also includes: when the number of psychological assessment questions that have undergone the integration exceeds a predetermined value, re-acquiring the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate through the Internet of Things device; performing a second prediction through the attention focus area prediction model to obtain an attention focus coordinate range corresponding to the re-acquired current tester's eye gaze direction, the re-acquired distance between the current tester's eyes and the page, the re-acquired current tester's pupil area, the re-acquired current tester's blinking frequency, and the re-acquired current tester's heart rate; and performing a second adjustment on the pages to be displayed to the current tester among the multiple pages, so that the psychological assessment questions to be displayed to the current tester fall within the attention focus coordinate range obtained through the second prediction.

[0034] Retraining based on the number of unreliable answers to correct the focus coordinate range ensures that the predicted focus coordinate range is more consistent with the actual situation, improves the accuracy of answering questions, and improves the accuracy of psychological assessment results. For example, the predetermined value can be 1, 2, 3, 5, 10, or other values.

[0035] In an exemplary embodiment, the Internet of Things-based psychological assessment method also includes: integrating the test questions in the page that has been displayed to the current tester and that fall outside the attention concentration coordinate range obtained by the second prediction into the page to be displayed to the current tester and that fall within the attention concentration coordinate range obtained by the first prediction or the second prediction; if the first adjustment or the second adjustment of the page has been performed, then performing a third adjustment on the page to be displayed to the current tester among the multiple pages, so that the color of the psychological assessment test questions displayed to the current tester is changed to a specific color.

[0036] This integration ensures that the psychological assessment questions on the previously completed pages fall within the current test-taker's attentional coordinate range, resulting in more realistic and accurate assessment results. To further focus the test-taker's attention, a third adjustment is made: the color of the psychological assessment questions is changed to a more eye-catching color, such as red.

[0037] In an exemplary embodiment, the psychological assessment method based on the Internet of Things also includes: counting the total area of the current tester's gaze based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, and the page that has been displayed to the current tester; obtaining the current tester's body image through the Internet of Things device; calculating the number of changes in the current tester's body pixel values based on different body images of the current tester; predicting whether the current tester has entered a fatigue period based on a fatigue prediction model, the counted total area of the current tester's gaze, the number of unreliable answers obtained through prediction, and the calculated number of changes in the current tester's body pixel values, wherein the fatigue prediction model is trained based on historical testers' total gaze areas, historical numbers of unreliable answers, and historical changes in testers' body pixel values; when it is predicted that the current tester has entered a fatigue period, pausing the psychological assessment and entering a rest period of the second time period.

[0038] As an example, the number of changes in body pixel values can be calculated based on the grayscale value difference between two body images. For example, the grayscale value difference between two consecutively captured body images can be statistically calculated. When the grayscale value differences between all body images are statistically calculated, the total number of changes in body pixel values can be obtained by summing them up for subsequent processing. The actual size corresponding to each pixel can be calculated, and then the total area of the subject's gaze can be calculated based on the number of pixels in the eye annotation on the page. When calculating the number of pixels in the eye annotation on the page, the coordinates of the subject's eye projection on the page in the coordinate system, the subject's eye gaze direction, the distance between the subject's eye and the page, and the page displayed to the subject can be used to calculate the coordinate range of the eye scans, thereby determining the number of pixels within the scanned coordinate range. The IoT device that captures the subject's body image can include a webcam, a camera, etc. The fatigue prediction model can be a neural network model. The corresponding historical data can be used as training data to train a back-propagation neural network model. The back-propagation neural network model uses a linear rectifier function, and the prediction evaluation metric used can be mean squared error, root mean square error, mean absolute error, or mean absolute percentage error. The fatigue prediction model is a classifier model. This model can be used to predict whether the test subject has entered the fatigue period, so that the test can be stopped in time when entering the fatigue period, further ensuring the accuracy of the test results.

[0039] In an exemplary embodiment, the Internet of Things-based psychological assessment method also includes: after the rest period ends, resuming the psychological assessment and displaying the page obtained after the third adjustment, wherein the first adjustment and / or the second adjustment include: text spacing adjustment, paragraph spacing adjustment, single-line display word count adjustment and / or text size adjustment.

[0040] The color can be changed through the third adjustment, and the color can be changed to a color that can attract the current tester's attention in a targeted manner.

[0041] Reference Figure 2 The exemplary embodiment of the Internet of Things-based psychological assessment system includes: a page setting unit, configured to: set multiple psychological assessment test questions in multiple pages, wherein the multiple pages are set in the same coordinate system; an Internet of Things device, configured to: obtain a current tester's facial image, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate; a prediction unit, configured to: perform a first prediction through an attention focus area prediction model to obtain an attention focus coordinate range corresponding to the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate, wherein the attention focus coordinate range is represented by coordinates in the coordinate system, and the attention focus area prediction model is trained based on historical testers' eye gaze directions, historical testers' eye distances between the page, historical testers' pupil areas, historical testers' blinking frequencies, historical testers' heart rates, and historical attention focus coordinate ranges; a page adjustment unit, configured to: adjust the number of pages to be displayed to the current tester The first adjustment is performed on the page of the current tester so that the psychological assessment test questions displayed to the current tester fall within the attention focus coordinate range obtained by the first prediction; the determination unit is configured to: determine the number of asymmetric pixels on the face of the current tester according to the facial image of the current tester; determine the psychological assessment test questions that the current tester is looking at in the page displayed to the current tester according to the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the gaze direction of the current tester's eyes and the distance between the current tester's eyes and the page; wherein the prediction unit is further configured to: determine the number of asymmetric pixels on the face of the current tester according to the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the gaze direction of the current tester's eyes and the distance between the current tester's eyes and the page; The page adjustment unit is further configured to: when the answer to the psychological assessment question being stared at by the current tester is unreliable, integrate the psychological assessment question with an unreliable answer into the page to be displayed to the current tester and make it fall within the attention concentration coordinate range obtained by the first prediction.

[0042] In an exemplary embodiment, the Internet of Things device is further configured to: when the number of psychological assessment test questions that have undergone the integration exceeds a predetermined value, re-acquire the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate; the prediction unit is further configured to: perform a second prediction through an attention focus area prediction model to obtain an attention focus coordinate range corresponding to the re-acquired current tester's eye gaze direction, the re-acquired distance between the current tester's eyes and the page, the re-acquired current tester's pupil area, the re-acquired current tester's blinking frequency, and the re-acquired current tester's heart rate; the page adjustment unit is further configured to: perform a second adjustment on the page to be displayed to the current tester among the multiple pages, so that the psychological assessment test questions to be displayed to the current tester fall within the attention focus coordinate range obtained through the second prediction.

[0043] In an exemplary embodiment, the page adjustment unit is further configured to: integrate the test questions in the page that has been displayed to the current tester and fall outside the attention focus coordinate range obtained by the second prediction into the page to be displayed to the current tester and fall within the attention focus coordinate range obtained by the first prediction or the second prediction; if the first adjustment or the second adjustment of the page has been performed, then perform a third adjustment on the page to be displayed to the current tester among the multiple pages, so that the color of the psychological assessment test questions displayed to the current tester is changed to a specific color.

[0044] In an exemplary embodiment, the Internet of Things device is further configured to: obtain a body image of the current tester; the determination unit is further configured to: count the total gaze area of the current tester based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, and the page that has been displayed to the current tester; calculate the number of changes in the current tester's body pixel values based on different body images of the current tester; the prediction unit is further configured to: predict whether the current tester has entered a fatigue period based on a fatigue prediction model, the counted total gaze area of the current tester, the number of unreliable answers obtained through prediction, and the calculated number of changes in the current tester's body pixel values, wherein the fatigue prediction model is trained based on historical testers' total gaze areas, historical numbers of unreliable answers, and historical changes in testers' body pixel values; the page adjustment unit is further configured to: when it is predicted that the current tester has entered a fatigue period, suspend the psychological assessment and enter a rest period of a second time period.

[0045] In an exemplary embodiment, the page adjustment unit is further configured to: after the rest period ends, resume the psychological assessment and display the page obtained after the third adjustment, wherein the first adjustment and / or the second adjustment include: text spacing adjustment, paragraph spacing adjustment, single-line display word count adjustment and / or text size adjustment.

[0046] The above system embodiments can be implemented with reference to the method embodiments, and all the above technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0047] This application uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for technical personnel in this field, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A psychological assessment method based on the Internet of Things, characterized in that: include: Setting a plurality of psychological assessment test questions on a plurality of pages, wherein the plurality of pages are set in the same coordinate system; Obtaining the current tester's facial image, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, the current tester's pupil area, the current tester's blinking frequency, and the current tester's heart rate through the IoT device; performing a first prediction using an attention focus region prediction model to obtain an attention focus coordinate range corresponding to a current tester's eye gaze direction, a distance between the current tester's eyes and the page, a current tester's pupil area, a current tester's blink frequency, and a current tester's heart rate, wherein the attention focus coordinate range is represented by coordinates in the coordinate system, and the attention focus region prediction model is trained based on historical testers' eye gaze directions, historical testers' eye distances from the page, historical testers' pupil areas, historical testers' blink frequencies, historical testers' heart rates, and historical attention focus coordinate ranges; Performing a first adjustment on a page to be displayed to the current tester among the multiple pages so that the psychological assessment test questions to be displayed to the current tester fall within the attention focus coordinate range obtained by the first prediction; determining the number of asymmetric pixels on the face of the current test subject based on the facial image of the current test subject; determining the psychological assessment question that the current test subject is gazing at on the page presented to the current test subject based on the coordinates of the projected position of the current test subject's eyes on the page in the coordinate system, the gaze direction of the current test subject's eyes, and the distance between the current test subject's eyes and the page; Predicting whether the answer to the psychological assessment question the current test subject is looking at is credible based on the number of asymmetric pixels on the current test subject's face and a credibility classification model for the test question answer, wherein the credibility classification model for the test question answer is trained based on the number of asymmetric pixels on the faces of historical test subjects and credibility results of historical test question answers corresponding to the number of asymmetric pixels on the faces of historical test subjects; When the answer to the psychological assessment question currently being looked at by the test subject is unreliable, integrating the psychological assessment question with the unreliable answer into a page to be displayed to the current test subject and the page falls within the attention focus coordinate range obtained by the first prediction; When the number of psychological assessment test questions that have been integrated exceeds a predetermined value, the current test subject's eye gaze direction, the distance between the current test subject's eyes and the page, the current test subject's pupil area, the current test subject's blinking frequency, and the current test subject's heart rate are re-acquired through the Internet of Things device; performing a second prediction using the attention focus region prediction model to obtain an attention focus coordinate range corresponding to the reacquired eye gaze direction of the current tester, the reacquired distance between the eyes of the current tester and the page, the reacquired pupil area of the current tester, the reacquired blink frequency of the current tester, and the reacquired heart rate of the current tester; Performing a second adjustment on a page to be displayed to the current tester among the plurality of pages so that the psychological assessment test questions to be displayed to the current tester fall within the attention focus coordinate range obtained by the second prediction; Integrate the test questions on the page that has been displayed to the current test subject and that fall outside the attention focus coordinate range obtained by the second prediction into the page that will be displayed to the current test subject and that fall within the attention focus coordinate range obtained by the first prediction or the second prediction; If the first adjustment or the second adjustment of the page has been performed, a third adjustment is performed on the page to be displayed to the current tester among the plurality of pages, so that the color of the psychological assessment test questions displayed to the current tester is changed to a specific color; Counting the total area of the current tester's gaze based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the current tester's eye gaze direction, the distance between the current tester's eyes and the page, and the page displayed to the current tester; Obtain the body image of the current tester through the IoT device; Calculate the amount of change in pixel values of the current tester's body based on different body images of the current tester; Predicting whether the current test subject has entered a fatigue period based on a fatigue prediction model, the total gaze area of the current test subject, the number of unreliable answers obtained through prediction, and the calculated number of changes in the current test subject's body pixel values, wherein the fatigue prediction model is trained based on historical test subjects' total gaze area, the number of historical unreliable answers, and the number of historical changes in the test subject's body pixel values; When it is predicted that the current test subject has entered the fatigue period, the psychological assessment is suspended and a rest period of the second time period is entered.

2. The Internet of Things-based psychological assessment method according to claim 1, wherein: Also includes: When the rest period is over, resume the psychological assessment and display the page obtained after the third adjustment. The first adjustment and / or the second adjustment include: adjusting the spacing between characters, adjusting the spacing between paragraphs, adjusting the number of characters displayed in a single line, and / or adjusting the size of the characters.

3. A psychological assessment system based on the Internet of Things, characterized by: include: The page setting unit is configured to: set a plurality of psychological assessment test questions on a plurality of pages, wherein the plurality of pages are set in the same coordinate system; The IoT device is configured to: obtain a facial image of the current tester, a gaze direction of the current tester, a distance between the eyes of the current tester and the page, a pupil area of the current tester, a blink frequency of the current tester, and a heart rate of the current tester; a prediction unit configured to: perform a first prediction using an attention focus region prediction model to obtain an attention focus coordinate range corresponding to a current tester's eye gaze direction, a distance between the current tester's eyes and the page, a current tester's pupil area, a current tester's blink frequency, and a current tester's heart rate, wherein the attention focus coordinate range is represented by coordinates in the coordinate system, and the attention focus region prediction model is trained based on historical testers' eye gaze directions, historical testers' eye distances from the page, historical testers' pupil areas, historical testers' blink frequencies, historical testers' heart rates, and historical attention focus coordinate ranges; a page adjustment unit configured to: perform a first adjustment on a page to be displayed to the current tester among the plurality of pages so that the psychological assessment test questions to be displayed to the current tester fall within the attention focus coordinate range obtained by the first prediction; The determining unit is configured to: determine the number of asymmetric pixels on the face of the current tester based on the facial image of the current tester; determine the psychological assessment question that the current tester is gazing at on the page presented to the current tester based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the gaze direction of the current tester's eyes, and the distance between the current tester's eyes and the page; The prediction unit is further configured to: predict whether the answer to the psychological assessment test question that the current test subject is looking at is credible based on the number of asymmetric pixels on the current test subject's face and a test answer credibility classification model, wherein the test answer credibility classification model is trained based on the number of asymmetric pixels on the faces of historical test subjects and credibility results of historical test answer corresponding to the number of asymmetric pixels on the faces of historical test subjects; The page adjustment unit is further configured to: when the answer to the psychological assessment question currently being focused on by the test subject is unreliable, integrate the psychological assessment question with the unreliable answer into the page to be displayed to the current test subject and place it within the attention focus coordinate range obtained by the first prediction; The IoT device is further configured to: when the number of psychological assessment test questions that have undergone the integration exceeds a predetermined value, re-acquire the current test subject's eye gaze direction, the distance between the current test subject's eyes and the page, the current test subject's pupil area, the current test subject's blinking frequency, and the current test subject's heart rate; The prediction unit is further configured to: perform a second prediction using an attention focus region prediction model to obtain an attention focus coordinate range corresponding to the reacquired eye gaze direction of the current tester, the reacquired distance between the eyes of the current tester and the page, the reacquired pupil area of the current tester, the reacquired blink frequency of the current tester, and the reacquired heart rate of the current tester; The page adjustment unit is further configured to: perform a second adjustment on the page to be displayed to the current tester among the plurality of pages, so that the psychological assessment test questions to be displayed to the current tester fall within the attention focus coordinate range obtained by the second prediction; The page adjustment unit is further configured to: integrate test questions in the page that has been displayed to the current tester and that fall outside the attention focus coordinate range obtained by the second prediction into the page to be displayed to the current tester and that fall within the attention focus coordinate range obtained by the first prediction or the second prediction; if the first adjustment or the second adjustment of the page has been performed, perform a third adjustment on the page to be displayed to the current tester among the multiple pages, so that the color of the psychological assessment test questions displayed to the current tester is changed to a specific color; The IoT device is further configured to: obtain a body image of the current test subject; The determining unit is further configured to: count the total gaze area of the current tester based on the coordinates of the projected position of the current tester's eyes on the page in the coordinate system, the gaze direction of the current tester's eyes, the distance between the current tester's eyes and the page, and the page displayed to the current tester; and calculate the number of changes in the pixel values of the current tester's body based on different body images of the current tester; The prediction unit is further configured to predict whether the current test subject has entered a fatigue period based on a fatigue prediction model, the statistical total gaze area of the current test subject, the number of unreliable answers obtained through prediction, and the calculated number of changes in the pixel values of the current test subject's body, wherein the fatigue prediction model is trained based on the total gaze area of historical test subjects, the number of historical unreliable answers, and the number of historical changes in the pixel values of the test subject's body; The page adjustment unit is further configured to: when it is predicted that the current tester has entered a fatigue period, suspend the psychological evaluation and enter a rest period of the second time period.

4. The Internet of Things-based psychological assessment system according to claim 3, wherein: The page adjustment unit is further configured to: after the rest period ends, resume the psychological assessment and display the page obtained after the third adjustment, The first adjustment and / or the second adjustment include: adjusting the spacing between characters, adjusting the spacing between paragraphs, adjusting the number of characters displayed in a single line, and / or adjusting the size of the characters.

Images