Data processing method and device for negative emotion assessment based on pupil wave
Through a negative emotion evaluation method based on pupil waves, different emotions images are presented through image display devices and pupil waves are collected, differential waves are generated and information extracted, and negative emotions risk index is calculated, which solves the problem of the existing technology that it is difficult to identify patients with early depression. Problem, accurate assessment and early intervention of negative emotions.
Patent Information
- Application Number
- CN202111184281.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-11
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-10-11
AI Technical Summary
The prior art is difficult to effectively identify patients with early depression. Since the early depression does not have typical depression characteristics, common diagnostic methods cannot identify mild and mild and moderate depression.
Through a negative emotion evaluation method based on pupil wave, the image display device is used to present calm, happy and negative emotions images, collect pupil waves, generate happy and negative difference waves, extract information characteristics, input full connection evaluation model, and calculate negative emotions by calculating the negative ones Emotional risk index, used to assess depression, anxiety, and stressful emotions.
Accurate assessment of negative emotions levels is achieved, able to identify early depression patients, provide early intervention and treatment, avoid the development of depression, is low cost and easy to collect data.
Smart Images

Figure CN113903076B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of negative emotion assessment, and in particular to a data processing method and device for negative emotion assessment based on pupil waves. Background Art
[0002] Negative emotions can lead to a decline in the ability to experience emotions, and negative emotions may develop into mental illnesses. For example, depression is a mental illness caused by emotional disorders, which is mainly manifested by emotional attention bias, memory loss (mainly working memory), abnormal cognitive style, and abnormal expressions / language / speech / brain waves / skin electricity / fMRI / heart rate / eye movement behavior (eye movement trajectory, gaze position, gaze time) and other signals. The more severe the depression, the more obvious these indicators are.
[0003] Early depression is atypical depression, the early stage of depression, and refers to the critical depression population between normal people and depression. Timely detection of early depression can prevent the further development of depression, and early intervention and treatment can effectively avoid the development of depression.
[0004] In the early stages of depression, the physiological signals (resting EEG / fMRI, etc.) and behavioral signals (expression / voice / gait, etc. in a natural state) of people with depression are very different from those of normal people, and they can still work, live and study normally. Therefore, the common diagnosis and identification methods of depression cannot identify people with early depression. Summary of the invention
[0005] The embodiments of the present application provide a data processing method and device for negative emotion assessment based on pupil waves, which can assess negative emotions and provide assistance for identifying those with early negative emotions.
[0006] On the one hand, an embodiment of the present application provides a data processing method for negative emotion assessment based on pupil waves, comprising:
[0007] Using an image display device to sequentially present a calm emotion image, a happy emotion image, and a negative emotion image;
[0008] Collecting corresponding pupil waves when the evaluation subject watches the calm emotion image, the happy emotion image, and the negative emotion image to obtain a calm pupil wave, a happy pupil wave, and a negative pupil wave;
[0009] generating a happy difference wave and a negative difference wave respectively according to the calm pupil wave, the happy pupil wave and the negative pupil wave;
[0010] According to the happiness difference wave and the negativity difference wave, the happiness information features and the negativity information features are extracted respectively;
[0011] The extracted happy information features and negative information features are input into a two-layer fully connected evaluation model to obtain the negative emotion risk index AR.
[0012] In an optional embodiment, generating a happy difference wave and a negative difference wave respectively according to the calm pupil wave, the happy pupil wave and the negative pupil wave comprises:
[0013] Taking the calm pupil wave as the baseline, a difference wave between the happy pupil wave and the calm pupil wave is generated, and the difference wave is the happy difference wave;
[0014] Taking the calm pupil wave as a baseline, a difference wave between the negative pupil wave and the calm pupil wave is generated, and the difference wave is a negative difference wave.
[0015] In an optional embodiment, generating a happy difference wave and a negative difference wave respectively according to the calm pupil wave, the happy pupil wave and the negative pupil wave comprises:
[0016] Get the average of the calm pupil wave;
[0017] The difference between the average values of the happy pupil wave and the calm pupil wave is used to obtain the happy difference wave.
[0018] The negative pupil wave is obtained by subtracting the average value of the negative pupil wave from the calm pupil wave.
[0019] In an optional embodiment, according to the happiness difference wave and the negativity difference wave, respectively extracting happiness information features and negativity information features includes:
[0020] The happiness difference wave and the negative difference wave are respectively input into two channels of a one-dimensional convolutional neural network, and the two channels process the input happiness difference wave or negative difference wave respectively to extract happiness information features and negative information features.
[0021] In an optional embodiment, according to the happiness difference wave and the negativity difference wave, respectively extracting happiness information features and negativity information features includes:
[0022] The two channels respectively perform spatial dimension fusion and channel dimension abstraction and dimensionality upgrading on the input happiness difference wave or negative difference wave;
[0023] Align dimensions of multi-scale features.
[0024] In an optional embodiment, after aligning the dimensions of the multi-scale features, it also includes: based on the dimensionally aligned multi-scale features, two channels use a width-channel attention module to respectively extract happiness information features and negative information features.
[0025] In an optional embodiment, the extracted happiness information features and negative information features are input into a two-layer fully connected regression evaluation model to calculate the negative emotion risk index AR, including:
[0026] The two-layer fully connected regression evaluation model fuses the happiness information features and negative information features extracted by the one-dimensional convolutional neural network to obtain the negative emotion risk index AR.
[0027] In an optional embodiment, the negative emotion assessment includes depression emotion assessment, anxiety emotion assessment and stress emotion assessment;
[0028] When the negative emotion assessment is a depression emotion assessment, the negative emotion image is a sadness emotion image;
[0029] When the negative emotion assessment is an anxiety emotion assessment, the negative emotion image is a fear emotion image;
[0030] When the negative emotion assessment is a stress emotion assessment, the negative emotion image is a tension emotion image.
[0031] In a second aspect, an embodiment of the present application provides a data processing device for negative emotion assessment based on pupil waves, comprising:
[0032] An image display unit, which is used to sequentially present a calm emotion image, a happy emotion image, and a negative emotion image;
[0033] A collection unit, which is used to collect the corresponding pupil waves when the evaluation object watches the calm emotion image, the happy emotion image and the negative emotion image, and obtain the calm pupil wave, the happy pupil wave and the negative pupil wave;
[0034] A difference wave generating unit, which is used to generate a happy difference wave and a negative difference wave, wherein the happy difference wave is a difference wave of the happy pupil wave generated with the calm pupil wave as a baseline; and the negative difference wave is a difference wave of the negative pupil wave generated with the calm pupil wave as a baseline;
[0035] an information feature extraction unit, used to extract a happiness information feature and a negative information feature respectively based on the happiness difference wave and the negative difference wave;
[0036] The evaluation unit is used to process the extracted happy information features and negative information features to obtain a negative emotion risk index AR.
[0037] In an optional embodiment, the image display device is a virtual reality device.
[0038] In an optional embodiment, the acquisition unit includes a camera provided on the virtual reality device.
[0039] In an optional embodiment, the information feature extraction unit uses a one-dimensional convolutional neural network to extract happy information features and negative information features.
[0040] In an optional embodiment, the evaluation unit uses a two-layer fully connected regression evaluation model to fuse the extracted happiness information features and negative information features to obtain a negative emotion risk index.
[0041] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method of the above embodiment when the program is executed by a processor.
[0042] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the above embodiment when executing the program.
[0043] The method of the embodiment of the present application processes pupil waves induced by different emotions and can evaluate the level of negative emotions. At the same time, because a single mode is used, data collection is easy and the cost is low. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 A flowchart of an embodiment of a method of the present application;
[0045] Figure 2 A structural block diagram of an embodiment of the device of the present application;
[0046] Figure 3 A schematic diagram of the structure of the computer device of the present application. DETAILED DESCRIPTION
[0047] In order to enable those skilled in the art to better understand the present application, the embodiments of the present application are described in detail below with reference to the accompanying drawings, but this is not intended to limit the present application.
[0048] Figure 1 This is a flow chart of an embodiment of the method of the present application. Figure 1 , a data processing method for negative emotion assessment based on pupil waves, comprising:
[0049] Using an image display device to sequentially present a calm emotion image, a happy emotion image, and a negative emotion image;
[0050] The pupil waves corresponding to the evaluation object when watching the calm emotion images, the happy emotion images and the negative emotion images are collected to obtain the calm pupil wave, the happy pupil wave and the negative pupil wave;
[0051] According to the calm pupil wave, the happy pupil wave and the negative pupil wave, the happy difference wave and the negative difference wave are generated respectively;
[0052] According to the happiness difference wave and the negativity difference wave, the happiness information features and the negativity information features are extracted respectively;
[0053] The extracted happy information features and negative information features are input into a two-layer fully connected evaluation model to obtain the negative emotion risk index AR.
[0054] The method of the embodiment of the present application uses pupillary waves induced by emotions as basic information for negative emotion evaluation to achieve the evaluation of negative emotion levels and provide help for identifying those with early negative emotions.
[0055] The negative emotion assessment of the embodiments of the present application includes but is not limited to depression emotion assessment, anxiety emotion assessment and stress emotion assessment.
[0056] When the negative emotion being assessed is depression, the negative emotion image adopts a sad emotion image, the negative pupil wave is a sad pupil wave, the negative difference wave is a sad difference wave, the negative information feature is a sad information feature, and the negative emotion risk index obtained is a depression risk index.
[0057] When the negative emotion being assessed is anxiety, the negative emotion image adopts the fear emotion image, the negative pupil wave is the fear pupil wave, the negative difference wave is the fear difference wave, the negative information feature is the fear information feature, and the negative emotion risk index obtained is the anxiety emotion risk index.
[0058] When the negative emotion being assessed is a stress emotion, the negative emotion image adopts a tension emotion image, the negative pupil wave is a tension pupil wave, the negative difference wave is a tension difference wave, the negative information feature is a tension information feature, and the negative emotion risk index obtained is a stress emotion risk index.
[0059] The negative emotion risk index AR can be used to evaluate the degree of negative emotions. The larger the negative emotion risk index AR is, the higher the degree of negative emotions is. Taking the depression risk index AR as an example,
[0060] AR < 0.5, no depression;
[0061] 0.5≤AR<0.7, mild depression;
[0062] 0.7≤AR<0.85, moderate depression;
[0063] AR≥0.85, severe depressive mood.
[0064] The pupil of a person changes with the change of emotions. In the embodiment of the present application, by collecting the eye information of the evaluation object, a waveform based on the change of pupil diameter under different emotions, i.e., pupil wave, is obtained. The pupil wave is processed accordingly to obtain the happy information features and negative information features corresponding to the emotions. The happy information features and negative information features are processed with a two-layer fully connected regression evaluation model to obtain the negative emotion risk index AR. The negative emotion risk index AR can be used to evaluate whether the evaluation object has negative emotions and the level of negative emotions.
[0065] At the same time, the embodiment of the present application only collects pupil waves. Since the pupil waves use a single mode, data collection is easy and the cost is low.
[0066] According to the calm pupil wave, the happy pupil wave and the negative pupil wave, a happy difference wave and a negative difference wave are generated respectively, including: taking the calm pupil wave as a baseline, generating a difference wave between the happy pupil wave and the calm pupil wave, the difference wave is a happy difference wave. Taking the calm pupil wave as a baseline, generating a difference wave between the negative pupil wave and the calm pupil wave, the difference wave is a negative difference wave.
[0067] Taking the calm pupil wave as a baseline, including: obtaining an average value of the calm pupil wave.
[0068] Generating a difference wave of the happy pupil wave includes: subtracting an average value of the happy pupil wave from an average value of the calm pupil wave to obtain a happy difference wave.
[0069] Generating a difference wave of a negative pupil wave includes: subtracting the negative pupil wave from an average value of a calm pupil wave to obtain a negative pupil wave.
[0070] According to the happiness difference wave and the negative difference wave, the happiness information features and the negative information features are extracted respectively, including: inputting the happiness difference wave into a one-dimensional convolutional neural network for processing to extract the happiness information features; inputting the negative difference wave into a one-dimensional convolutional neural network for processing to extract the negative information features.
[0071] In an exemplary embodiment, the one-dimensional convolutional neural network has two channels. The happy difference wave and the sad negative difference wave are respectively input into the two channels of the one-dimensional convolutional neural network, and the happy difference wave is input into one of the two channels of the one-dimensional convolutional neural network for processing to extract the happy information feature. The negative difference wave is input into the other of the two channels of the one-dimensional convolutional neural network for processing to extract the negative information feature.
[0072] In some embodiments, a one-dimensional convolutional neural network extracts happiness information features and extracts negative information features, including: two channels respectively perform spatial dimension fusion and channel dimension abstraction upscaling on the input happiness difference wave or negative difference wave; align the dimensions of multi-scale features. One channel performs spatial dimension fusion and channel dimension abstraction upscaling on the input happiness difference wave, and then aligns the dimensions of multi-scale features. The other channel performs spatial dimension fusion and channel dimension abstraction upscaling on the input negative difference wave, and then aligns the dimensions of multi-scale features.
[0073] In an exemplary embodiment, after aligning the dimensions of the multi-scale features, it also includes: based on the multi-scale features after dimension alignment, the two channels use a width-channel attention module to extract the happy information features and the negative information features respectively. For example, the two channels are distinguished by the first channel and the second channel, the first channel processes the happy difference wave, and the second channel processes the negative difference wave. The processing of the happy difference wave by the first channel includes: performing spatial dimension fusion and abstract dimension upgrade of the channel dimension on the input happy difference wave; aligning the dimensions of the multi-scale features; and extracting the happy information features using the width-channel attention module. The processing of the negative difference wave by the second channel includes: performing spatial dimension fusion and abstract dimension upgrade of the channel dimension on the input negative difference wave; aligning the dimensions of the multi-scale features; and extracting the negative information features using the width-channel attention module.
[0074] In some embodiments, the extracted happy information features and negative information features are input into a two-layer fully connected hierarchical regression evaluation model to calculate the negative emotion risk index AR, including: the two-layer fully connected regression evaluation model fuses the happy information features and negative information features extracted by the one-dimensional convolutional neural network to obtain the negative emotion risk index AR.
[0075] In the embodiment of the present application, the depression risk index is taken as an example. A depression risk index AR < 0.5 indicates normal, and a depression risk index AR ≥ 0.5 indicates that there may be depression. In the exemplary embodiment, the depression risk level is as follows:
[0076] AR < 0.5, no depression;
[0077] 0.5≤AR<0.7, mild depression;
[0078] 0.7≤AR<0.85, moderate depression;
[0079] AR≥0.85, severe depressive mood.
[0080] In the method provided in the embodiment of the present application, emotion-induced pupil waves (emotional pupil waves) are used to evaluate negative emotions. The problem that natural pupil waves cannot express negative emotions is avoided. Because people with mild and mild-to-moderate negative emotions are no different from normal people in work and life, but their emotions have been disturbed, which is manifested as insufficient experience of happiness and excessive experience of negative emotions. Therefore, emotional pupil waves can express the negative emotional state of people with emotional disorders.
[0081] The method of the embodiment of the present application uses the difference value of the pupil wave to avoid the problem of inaccurate absolute value of the pupil wave caused by different pupil sizes due to individual differences and the influence of light illumination on the pupil.
[0082] In the evaluation method of the embodiment of the present application, the collection of emotional pupil waves can be induced by using virtual reality emotional images or by using two-dimensional emotional images. For example, a laptop or desktop monitor can be used to provide a two-dimensional emotional image. The camera of the image display device or an external camera can be used to collect eye images and pupil waves.
[0083] In some embodiments, the image display device may be a virtual reality device, which can provide virtual reality images that induce different emotions, and the virtual reality images can quickly and accurately induce corresponding emotions when the evaluation subject is immersed in the viewing experience.
[0084] The images in the embodiments of the present application include videos and pictures.
[0085] The embodiment of the present application provides a data processing device for negative emotion assessment based on pupil waves, which can implement the method of the above embodiment. The above method embodiment can be used to understand the device of the embodiment of the present application, and the following embodiment of the device can also be used to understand the method of the above embodiment. The device of the embodiment of the present application includes:
[0086] An image display unit 10, which is used to sequentially present a calm emotion image, a happy emotion image, and a negative emotion image;
[0087] A collection unit 20, which is used to collect the corresponding pupil waves when the evaluation object watches the calm emotion image, the happy emotion image and the negative emotion image, and obtain the calm pupil wave, the happy pupil wave and the negative pupil wave;
[0088] A difference wave generating unit 30, which is used to generate a happy difference wave and a negative difference wave, wherein the happy difference wave is a difference wave of the happy pupil wave generated with the calm pupil wave as a baseline; and the negative difference wave is a difference wave of the negative pupil wave generated with the calm pupil wave as a baseline;
[0089] An information feature extraction unit 40, which is used to extract a happy information feature and a negative information feature based on the happy difference wave and the negative difference wave, respectively;
[0090] The evaluation unit 50 is used to process the extracted happiness information features and negative information features to obtain a depression risk index AR.
[0091] The device of the embodiment of the present application can process pupil waves induced by emotions, and use them as basic information for negative emotion evaluation, thereby realizing the evaluation of negative emotion levels and providing help for identifying those with early negative emotions.
[0092] The negative emotion risk index AR can be used to evaluate the degree of negative emotion. The larger the negative emotion risk index AR is, the higher the degree of negative emotion is. Taking the depression risk index AR as an example, AR < 0.5 means there is no depression;
[0093] 0.5≤AR<0.7, mild depression;
[0094] 0.7≤AR<0.85, moderate depression;
[0095] AR≥0.85, severe depressive mood.
[0096] In some embodiments, the image display unit 10 may be a virtual reality device. In an exemplary embodiment, the virtual reality device may be a head-mounted virtual reality device, such as virtual reality glasses, a virtual reality helmet, etc. The virtual reality device displays a virtual reality scene, so that the evaluation object can be immersed in the scene, and the corresponding emotions can be quickly and accurately induced, and more accurate pupil waves can be collected.
[0097] In some embodiments, the acquisition unit 20 includes a camera disposed on the image display unit 10. For example, a camera disposed on a virtual reality device. The camera is disposed on the image display unit 10, and can accurately and in real time collect eye information when the evaluation object is viewing the image. Of course, the acquisition unit 20 may also include a separately disposed camera. The acquisition unit 20 may also include an image processing module. The image processing module can process the image collected by the camera to obtain a pupil wave. The image processing module may be integrated into the camera, or may be disposed on an electronic device such as a computer.
[0098] In some embodiments, the information feature extraction unit 40 uses a one-dimensional convolutional neural network to extract happy information features and negative information features.
[0099] In some embodiments, the evaluation unit 50 uses a two-layer fully connected regression evaluation model to fuse the extracted happiness information features and negative information features to obtain a negative emotion risk index.
[0100] The following is a method for processing the depression assessment data of the assessment subjects using the embodiment of the present application, and an assessment using the PHQ-9 self-rating depression scale. The specific assessment results are shown in Table 1 below.
[0101] Table 1
[0102]
[0103] (PHQ9 score: 0-4, no depression; 5-9, possible mild depression; 10-14, possible moderate depression; 15-19, possible moderate to severe depression; 20-27, possible severe depression)
[0104] As shown in Table 1, a total of 13 people were tested, and 4 were found to have early mild depression, accounting for 30.77%.
[0105] In a third aspect, the embodiments of the present application provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the method of the above embodiment are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.
[0106] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the methods recorded in the above method embodiments.
[0107] Those skilled in the art can clearly understand that the technical solution of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (Field-ProgrammaBLE GateArray, FPGA), an integrated circuit (Integrated Circuit, IC), etc.
[0108] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0109] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0110] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0113] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk, etc., and other media that can store program codes.
[0114] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0115] An embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the above embodiment when executing the program.
[0116] See also Figure 3 , which is a schematic diagram of the structure of a computer device according to an embodiment of the present application. Figure 3 As shown, the computer device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .
[0117] The communication bus 302 is used to realize the connection and communication between these components.
[0118] The user interface 303 may include a display screen (Display) and a camera (Camera). The optional user interface 303 may also include a standard wired interface and a wireless interface.
[0119] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0120] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire terminal 300, and executes various functions and processes data of the terminal 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.
[0121] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program.
[0122] exist Figure 3In the computer device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 301 can be used to call the application stored in the memory 305 and specifically execute the steps of the method of any of the above embodiments.
[0123] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.
Claims
1. A data processing method for negative emotion assessment based on pupil waves, characterized in that: include: Using an image display device to sequentially present a calm emotion image, a happy emotion image, and a negative emotion image; The pupil waves corresponding to the evaluation object when watching the calm emotion image, the happy emotion image and the negative emotion image are collected to obtain the calm pupil wave, the happy pupil wave and the negative pupil wave; the pupil wave is a waveform formed based on the change of pupil diameter under different emotions; According to the calm pupil wave, the happy pupil wave and the negative pupil wave, respectively generating a happy difference wave and a negative difference wave, including: taking the calm pupil wave as a baseline, generating a difference wave between the happy pupil wave and the calm pupil wave, the difference wave being a happy difference wave; taking the calm pupil wave as a baseline, generating a difference wave between the negative pupil wave and the calm pupil wave, the difference wave being a negative difference wave; According to the happiness difference wave and the negativity difference wave, the happiness information features and the negativity information features are extracted respectively; The extracted happy information features and negative information features are input into a two-layer fully connected evaluation model to obtain the negative emotion risk index AR.
2. The method according to claim 1, wherein: Generating a happy difference wave and a negative difference wave respectively according to the calm pupil wave, the happy pupil wave and the negative pupil wave, including: Get the average of the calm pupil wave; The difference between the average values of the happy pupil wave and the calm pupil wave is used to obtain the happy difference wave. The negative pupil wave is obtained by subtracting the average value of the negative pupil wave from the calm pupil wave.
3. The method according to claim 1, wherein: According to the happiness difference wave and the negative difference wave, the happiness information features and the negative information features are extracted respectively, including: The happiness difference wave and the negative difference wave are respectively input into two channels of a one-dimensional convolutional neural network, and the two channels process the input happiness difference wave or negative difference wave respectively to extract happiness information features and negative information features.
4. The method according to claim 3, wherein: According to the happiness difference wave and the negative difference wave, the happiness information features and the negative information features are extracted respectively, including: The two channels respectively perform spatial dimension fusion and channel dimension abstraction and dimensionality upgrading on the input happiness difference wave or negative difference wave; Align dimensions of multi-scale features.
5. The method according to claim 4, wherein: After aligning the dimensions of the multi-scale features, it also includes: based on the dimensionally aligned multi-scale features, two channels use width-channel attention modules to respectively extract happy information features and negative information features.
6. The method according to claim 5, wherein: The extracted happy information features and negative information features are input into a two-layer fully connected regression evaluation model to calculate the negative emotion risk index AR, including: The two-layer fully connected regression evaluation model fuses the happiness information features and negative information features extracted by the one-dimensional convolutional neural network to obtain the negative emotion risk index AR.
7. The method according to claim 1, wherein: Negative emotion assessment includes depression emotion assessment, anxiety emotion assessment and stress emotion assessment; When the negative emotion assessment is a depression emotion assessment, the negative emotion image is a sadness emotion image; When the negative emotion assessment is an anxiety emotion assessment, the negative emotion image is a fear emotion image; When the negative emotion assessment is a stress emotion assessment, the negative emotion image is a tension emotion image.
8. A data processing device for negative emotion assessment based on pupil waves, comprising: An image display unit, which is used to sequentially present a calm emotion image, a happy emotion image, and a negative emotion image; A collection unit, which is used to collect the corresponding pupil waves when the evaluation object watches the calm emotion image, the happy emotion image and the negative emotion image, and obtain the calm pupil wave, the happy pupil wave and the negative pupil wave; the pupil wave is a waveform formed based on the change of pupil diameter under different emotions; A difference wave generating unit, which is used to generate a happy difference wave and a negative difference wave, wherein the happy difference wave is a difference wave between a happy pupil wave and a calm pupil wave generated with a calm pupil wave as a baseline; and the negative difference wave is a difference wave between a negative pupil wave and a calm pupil wave generated with a calm pupil wave as a baseline; an information feature extraction unit, used to extract a happiness information feature and a negative information feature respectively based on the happiness difference wave and the negative difference wave; The evaluation unit is used to process the extracted happy information features and negative information features to obtain a negative emotion risk index AR.
9. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.
