A method for Chinese character input combining eye tracker and P300 technology

Abstract

This invention discloses a method for Chinese character input combining eye-tracking and P300 technology. The method utilizes the spatial modulation information of the eye-tracking device to select a mode: the eye-tracking device collects the user's visual trajectory in real time, obtaining the coordinates of the user's eye movement points. When the user gazes at the start option, the system detects this intention and generates a command to activate the spelling process. Combining the eye-tracking device and P300 technology, the initials and finals of the Chinese characters are selected. The method then integrates with a Pinyin input method to achieve the function of inputting Chinese characters: after selecting the initials and finals, the user switches to the Pinyin input method, selects the target Chinese character, and thus achieves the Chinese character input function. This invention, combining eye-tracking and P300 technology for Chinese character input, allows users to achieve computer typing functions without taking any action, relying solely on their eyes and brain. Furthermore, the use of a standard Chinese input method's character library enables matching Chinese characters after spelling. This expands the scope of assistive devices for people with movement disorders beyond computer devices themselves, and has significant practical implications.

Description

Technical Field

[0001] This invention belongs to the field of brain science and cognitive science technology, and in particular relates to a method for Chinese character input that combines eye tracker and P300 technology. Background Technology

[0002] Brain-computer interfaces (BCIs) refer to the direct connection established between the brain of a human or animal and an external device, enabling information exchange between the brain and the device. Signal acquisition in BCIs can generally be categorized into three types: non-invasive, semi-invasive, and invasive. Non-invasive BCIs measure the brain's electrical or metabolic activity using wearable devices attached to the scalp (such as EEG caps, near-infrared helmets, or magnetic resonance head coils), requiring no surgery and being safe and non-invasive. Among these, EEG caps are the most commonly used non-invasive sensors, capable of monitoring the firing activity of groups of neurons on the scalp. Their high temporal resolution and lack of harm to the human body make them likely to be the first to be applied in real-world scenarios.

[0003] Currently, mainstream brain-computer interface (BCI) technologies primarily target three types of EEG signals: motor-sensory rhythm signals, steady-state visual evoked potential (SSVEP) signals, and P300 signals. Correspondingly, there are three types of BCIs: motor imagery BCIs, SSVEP BCIs, and P300 BCIs. Compared to the other two, the P300 BCI boasts higher recognition accuracy, offers a greater number of options in experiments, and has a higher actual information transmission rate.

[0004] However, most traditional single-type non-invasive P300 brain-computer interfaces have drawbacks such as insufficient accuracy, poor user experience, and the ability to only recognize data synchronously.

[0005] Eye trackers are important instruments in basic psychological research, typically used to record the eye movement patterns of a person processing visual information. They are widely used in research on attention, visual perception, and reading. Many laptops now include eye trackers as a selling point; for example, the Alienware 17R5 features a Tobii eye tracker. However, because they can only track the gaze path of the human eye and lack confirmation functions, their practical use in daily life is quite limited, usually being used for gaming or professional psychological analysis. Summary of the Invention

[0006] To address the above technical problems, this invention provides a method for Chinese character input that combines an eye tracker and P300 technology. The purpose of this method is to solve the technical problems in the prior art where only the P300 brain-computer interface and the eye tracker are used.

[0007] The technical solution adopted by this invention to solve its technical problem is:

[0008] A method for Chinese character input combining eye tracker and P300 technology, the method includes the following steps:

[0009] Step S100: Determine the spatial location information of the gaze point through the eye tracking signal of the eye tracker, determine the current location of the user's gaze by analyzing the spatial location information, and activate the P300 speller interface after detecting that the gaze has been fixed on the start button for a preset time.

[0010] Step S200: The flashing of the pinyin and function key sequence induces the potential corresponding to the P300 event to generate brain wave signals. After preprocessing the brain wave signals, they are analyzed to determine the character P1 at the pinyin or function key position selected by the user at the current gaze point.

[0011] Step S300: Based on the eye movement spatial information provided by the eye tracking device, determine the character P2 at the preset reference position of the user's current gaze point. If P1 and P2 are the same and the gaze position is a consonant or a vowel, write the input of P300 into the buffer. If P1 and P2 are the same and the gaze position is a function key position, execute the function key instruction. Repeat steps S200 and S300 until the selection of consonants and vowels is completed.

[0012] Step S400: Invoke the Pinyin input method, determine the target Chinese character based on the selected initial and final consonants, and realize the function of spelling Chinese characters.

[0013] Preferably, step S100 includes:

[0014] Step S110: Correct the user's eye movement information before spelling begins, and use a Python library to obtain the raw spatial eye movement information;

[0015] Step S120: As the user's eyes move, the eye tracker acquires the user's gaze coordinates;

[0016] Step S130: Select valid data from the obtained user gaze point coordinates and remove abnormal coordinates. Abnormal coordinates are the coordinates of sample points collected during blinking and rapid gaze shift.

[0017] Step S140: Write the eye-tracking visual trajectory coordinates represented by the user sampling point coordinates into the buffer;

[0018] Step S150: Determine whether the coordinates of the buffer are located on the start key and remain there for a preset duration. If so, activate the spelling process.

[0019] Preferably, step S130 specifically includes:

[0020] Step S131: Eliminate coordinates of eye blinks that the eye tracker cannot detect: Mark the coordinates of eye blinks that the eye tracker cannot detect as (-1, -1), and eliminate points with coordinates less than 0 to eliminate coordinates of eye blinks that the eye tracker cannot detect;

[0021] Step S132: Remove the coordinates of saccades captured by the eye tracker: Based on the sampling rate of the eye tracker, obtain the distance between two sampling points, that is, obtain the eye movement velocity; through the velocity threshold recognition and classification algorithm, identify the sampling points with eye movement velocities greater than a certain threshold as saccade samples and remove them, while retaining the coordinates of the sampling points of the user's gaze target.

[0022] Preferably, step S200 includes:

[0023] Step S210: Use Python tool libraries to track and obtain eye movement information, and simultaneously detect the distribution of gaze point coordinates over time;

[0024] Step S220: Activate the P300 speller of the brain-computer interface system, and the display screen flashes pinyin or other function key sequences;

[0025] Step S230: Collect brainwave signals using an EEG acquisition device;

[0026] Step S240: After filtering and amplifying the acquired EEG signal, decode it to determine the character P1 at the location of the selected pinyin or function key at the user's current gaze point.

[0027] Preferably, step S240 includes:

[0028] Step S241: Read a brainwave signal of at least 2500ms;

[0029] Step S242: Analyze the timing position of P300 in the EEG signal, and compare it with the timing of the character flashing stimulus sequence to determine the row and column position of the stimulus, thereby determining the character P1 at the position of the pinyin or function key that the user is looking at at this time.

[0030] Preferably, step S300 includes:

[0031] Step S310: Record the spatial location information of the sample points recorded by the current user's eye movement information, and calculate the expected spatial coordinates through the host computer as the reference position of the fixation point;

[0032] Step S320: Input the coordinates of the reference position of the gaze point into the computer cache;

[0033] Step S330: Compare the horizontal and vertical coordinates of the fixation point with the position information of each function key to obtain the character P2 of the reference position of the eye tracker at this time;

[0034] Step S340: Compare the contents of P1 and P2. If P1 and P2 are the same and the gaze position is an initial or final, write the input of P300 into the buffer. If P1 and P2 are the same and the gaze position is a function key position, execute the function key instruction and return to step S200 until the selection of the initial and final is completed.

[0035] Preferably, step S400 includes:

[0036] Step S410: Determine the current pinyin as Y1 based on the selected initial and final consonant, and input the pinyin Y1 into the input field;

[0037] Step S420: After inputting Y1, the standard Chinese input method's character library will be automatically called, and Y1 will be matched with the input method's character library. The most matching and most commonly used character will be selected as the candidate character. If not, the P300 speller will be activated by looking at PageUp, and the next page will be used to find a Chinese character that meets the requirements.

[0038] Step S430: After determining the Chinese character H1, output it to the input field, and return to step S200 to spell the next Chinese character.

[0039] Preferably, after step S400, the method further includes:

[0040] Step S500: The user gazes at the Del function key for a preset duration; the eye tracker's eye tracking system determines that the user's current gaze point is in the function key selection area, the stimulus sequence flashes to induce the P300 signal, and determines whether to delete the current Chinese character or Pinyin. If determined, the last Chinese character in the display output area or the last Pinyin input in the current buffer is deleted.

[0041] This invention achieves the following beneficial effects: it realizes a Chinese character spelling scheme combining an eye tracker and a P300 speller, allowing users to spell Chinese characters by moving their eyes without manually clicking keyboard keys. Furthermore, it optimizes and innovates upon the classic P300 speller, improving its accuracy. Additionally, by combining the Chinese character library provided by standard Chinese input methods, it can match the spelled characters with the correct ones. This expands assistive devices for people with movement disorders beyond just computer devices, and has significant practical implications. Attached Figure Description

[0042] Figure 1 This is a flowchart of a method for Chinese character input that combines an eye tracker with P300 technology according to the present invention;

[0043] Figure 2 This is a flowchart illustrating an embodiment of the method for Chinese character input that combines an eye tracker with P300 technology according to the present invention.

[0044] Figure 3 Diagram showing the electrode configuration of the electrode cap for a brain-computer interface;

[0045] Figure 4 A diagram illustrating the process of spelling out a sequence of pinyin for a display screen;

[0046] Figure 5 A schematic diagram of the effective pixel area for spelling out the pinyin sequence on the display. Detailed Implementation

[0047] To enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0048] This invention addresses existing problems by proposing a method for Chinese character input that combines an eye tracker with P300 technology, enabling asynchronous, reliable, and accurate Chinese character spelling input. An example implementation of this invention involves an eye tracker capturing the user's visual trajectory in real time. Once the user has a spelling intention, they express it by looking at the start button. The eye-tracking system automatically detects this intention and generates a command to activate the spelling process.

[0049] The eye tracker is responsible for spatial modulation information, while the P300 is responsible for temporal modulation information. The eye tracker collects the user's visual information in real time to determine the current position of the user's gaze (screen coordinates A1). At the same time, by gazing at a target point, the user can activate the command at that target point (spelling pinyin or using a function key such as PageUp) by analyzing the P300 components.

[0050] For example, to spell the Chinese word "patent": Step 1: Look at the start button on the computer screen to activate the spelling process; Step 2: Select "Zh" from the initial consonant stimulation sequence that appears on the screen and look at it, ignoring other irrelevant initial consonants. This allows the eye-tracking device to determine the character P1 at the position of the first pinyin selected by the user. At the same time, the pinyin stimulation sequence flashes, inducing the P300 potential. Analyzing the P300 potential at this time determines the spelling result P2 of the brain-computer interface. Step 3: If P1 and P2 match, the system automatically inputs the pinyin at this position into the computer's buffer. Repeat the above steps until the vowel of the first Chinese character is also spelled; Step 4: Call the Chinese character library of the computer's standard Chinese input method, the system automatically performs pinyin comparison, and outputs the candidate Chinese character to the computer screen; Step 5: After looking at the target Chinese character among the candidate characters for a period of time, the eye-tracking device and the P300 speller jointly determine that the user has selected the Chinese character to input, and output the selected Chinese character on the screen. The same applies to inputting the second Chinese character.

[0051] For example, to delete a pinyin or Chinese character that has been entered but was entered incorrectly, step 1 is to stare at the Del key for a period of time; step 2 is for the eye tracker's eye-tracking system to determine that the user is currently selecting the function key area, and at the same time, the stimulus sequence flashes to induce the P300 signal. After considering both factors, it is determined whether to delete the character. Once determined, the last Chinese character in the output area of ​​the display screen or the last pinyin entered in the buffer is deleted.

[0052] Figure 1 This is a flowchart of a method for Chinese character input that combines an eye tracker with P300 technology according to the present invention; Figure 2 This is a flowchart illustrating an embodiment of the method for Chinese character input that combines an eye tracker with P300 technology according to the present invention. Figure 3 Diagram showing the electrode configuration of the electrode cap for a brain-computer interface; Figure 4 A diagram illustrating the process of spelling out a sequence of pinyin for a display screen; Figure 5 A schematic diagram of the effective pixel area for spelling out the pinyin sequence on the display.

[0053] The implementation process specifically includes the following steps:

[0054] Step S100: Determine the spatial location information of the gaze point through the eye tracking signal of the eye tracker, determine the current location of the user's gaze by analyzing the spatial location information, and activate the P300 speller interface after detecting that the gaze has been fixed on the start button for a preset time.

[0055] Step S200: The flashing of the pinyin and function key sequence induces the potential corresponding to the P300 event to generate brain wave signals. After preprocessing the brain wave signals, they are analyzed to determine the character P1 at the pinyin or function key position selected by the user at the current gaze point.

[0056] Step S300: Based on the eye movement spatial information provided by the eye tracking device, determine the character P2 at the preset reference position of the user's current gaze point. If P1 and P2 are the same and the gaze position is a consonant or a vowel, write the input of P300 into the buffer. If P1 and P2 are the same and the gaze position is a function key position, execute the function key instruction. Repeat steps S200 and S300 until the selection of consonants and vowels is completed.

[0057] Step S400: Invoke the Pinyin input method, determine the target Chinese character based on the selected initial and final consonants, and realize the function of spelling Chinese characters.

[0058] We selected the Tobii Eye Tracks 4c (a common eye tracker model) with a sampling rate of 90Hz. After correcting the visual information, we used a Python program to obtain the coordinates of the user's gaze point. Furthermore, to distinguish whether the recorded location information corresponds to the user's gaze point, we introduced the concept of eye velocity. Location information recorded when the eye velocity exceeds a certain threshold is considered invalid and is not used.

[0059] Because the eye tracker may be affected by the subject's blinking, looking away, or eye movement exceeding the sampling range when sampling the user's eye movement information, resulting in some invalid sampling, the valid sampling points are obtained by removing these invalid sampling points such as blinking and eye movement.

[0060] On the other hand, the recorded information includes the time information of each sampling point. At this time, the eye movement speed of the eye saccade can be roughly calculated by calculating the distance between two sampling points (the calculation t2-t1 can be roughly considered as 1 / 90, because 90 is the sampling frequency of the selected eye tracker).

[0061]

[0062] At the same time, the electroencephalogram (EEG) is analyzed using the BCI system, and the timing characteristics of the evoked P300 signal on the EEG are used to determine the pinyin or function key of the event-related potential that was triggered at that time.

[0063] The specific implementation process of the above steps is as follows:

[0064] Step S110: Correct the user's eye movement information before spelling begins, and use a Python library to obtain the raw spatial eye movement information;

[0065] Step S120: As the user's eyes move, the eye tracker acquires the user's gaze coordinates;

[0066] Step S130: Select valid data from the obtained user gaze point coordinates and remove abnormal coordinates. Abnormal coordinates are the coordinates of sample points collected during blinking and rapid gaze shift.

[0067] Step S140: Write the eye-tracking visual trajectory coordinates represented by the user sampling point coordinates into the buffer;

[0068] Step S150: Determine whether the coordinates of the buffer are located on the start key and remain there for a preset duration. If so, activate the spelling process.

[0069] Furthermore, step S130 specifically includes:

[0070] Step S131: Eliminate coordinates of eye blinks that the eye tracker cannot detect: Mark the coordinates of eye blinks that the eye tracker cannot detect as (-1, -1), and eliminate points with coordinates less than 0 to eliminate coordinates of eye blinks that the eye tracker cannot detect;

[0071] Step S132: Remove the coordinates of saccades captured by the eye tracker: Based on the sampling rate of the eye tracker, obtain the distance between two sampling points, that is, obtain the eye movement velocity; through the velocity threshold recognition and classification algorithm, identify the sampling points with eye movement velocities greater than a certain threshold as saccade samples and remove them, while retaining the coordinates of the sampling points of the user's gaze target.

[0072] In one embodiment, step S200 includes:

[0073] Step S210: Use Python tool libraries to track and obtain eye movement information, and simultaneously detect the distribution of gaze point coordinates over time;

[0074] Step S220: Activate the P300 speller of the brain-computer interface system, and the display screen flashes pinyin or other function key sequences;

[0075] Step S230: Collect brainwave signals using an EEG acquisition device;

[0076] Step S240: After filtering and amplifying the acquired EEG signal, decode it to determine the character P1 at the location of the selected pinyin or function key at the user's current gaze point.

[0077] In one embodiment, step S240 includes:

[0078] Step S241: Read a brainwave signal of at least 2500ms;

[0079] Step S242: Analyze the timing position of P300 in the EEG signal, and compare it with the timing of the character flashing stimulus sequence to determine the row and column position of the stimulus, thereby determining the character P1 at the position of the pinyin or function key that the user is looking at at this time.

[0080] To enhance the user experience, a "rest area" is provided for the eye-tracking device on the display screen. This area does not provide any services related to spelling or function keys, but only serves as a visual fixation point for the user when thinking. If the user's gaze point position during step S100 is the spatial coordinate of the rest area, then the spelling process will not be triggered or step S200 will not be entered until the gaze point becomes the start key. This can actually realize an asynchronous P300 speller.

[0081] When the gaze point is within the coordinate range of the start button, the timer will start. When the timer reaches 2 seconds, it is determined that the user is gazing and has the intention to spell, so step S200 is activated and the timer is cleared. If the gaze point is within the coordinate range of the rest area space, the timer will continue to be cleared.

[0082] In one embodiment, step S300 includes:

[0083] Step S310: Record the spatial location information of the sample points recorded by the current user's eye movement information, and calculate the expected spatial coordinates through the host computer as the reference position of the fixation point;

[0084] Step S320: Input the coordinates of the reference position of the gaze point into the computer cache;

[0085] Step S330: Compare the horizontal and vertical coordinates of the fixation point with the position information of each function key to obtain the character P2 of the reference position of the eye tracker at this time;

[0086] Step S340: Compare the contents of P1 and P2. If P1 and P2 are the same and the gaze position is an initial or final, write the input of P300 into the buffer. If P1 and P2 are the same and the gaze position is a function key position, execute the function key instruction and return to step S200 until the selection of the initial and final is completed.

[0087] Specifically, if you find that you have selected the wrong initial consonant when selecting the final consonant, you can select the DEL function key in the final consonant area. After selecting the DEL key, the initial consonant will be deleted, and you will return to the initial consonant selection interface to reselect the initial consonant until the initial consonant and final consonant have been selected.

[0088] In one embodiment, step S400 includes:

[0089] Step S410: Determine the current pinyin as Y1 based on the selected initial and final consonant, and input the pinyin Y1 into the input field;

[0090] Step S420: After inputting Y1, the standard Chinese input method's character library will be automatically called, and Y1 will be matched with the input method's character library. The most matching and most commonly used character will be selected as the candidate character. If not, the P300 speller will be activated by looking at PageUp, and the next page will be used to find a Chinese character that meets the requirements.

[0091] Step S430: After determining the Chinese character H1, output it to the input field, and return to step S200 to spell the next Chinese character.

[0092] In this implementation example, the computer host uses EEG to detect the user's EEG and captures the EEG sequence over a period of time. The brain-computer interface system processes the captured EEG signal, obtains the EEG signal of 0.1-30Hz through a filter, amplifies the signal, and performs time series analysis on the processed EEG signal. By comparing the timing of the induced P300 signal and the time characteristics of row and column flashing, the row and column of the fixation point are determined, thereby determining the pinyin being spelled at this time.

[0093] If only an eye tracker is used, it can only determine the position of the gaze and cannot be used for keyboard spelling. However, when combined with the P300 spelling device, it can provide ALS (amyotrophic lateral sclerosis) patients with a more real-time and efficient typing solution, allowing them to start spelling as they wish. The spatial modulation information of the eye tracker can greatly improve the accuracy and performance of the P300 spelling device, eliminating concerns about repeatedly deleting inputs due to the low accuracy of the P300 spelling device.

[0094] In one embodiment, step S400 is followed by:

[0095] Step S500: The user gazes at the Del function key for a preset duration; the eye tracker's eye tracking system determines that the user's current gaze point is in the function key selection area, the stimulus sequence flashes to induce the P300 signal, and determines whether to delete the current Chinese character or Pinyin. If determined, the last Chinese character in the display output area or the last Pinyin input in the current buffer is deleted.

[0096] This invention achieves the following beneficial results: It provides a Chinese character spelling scheme combining an eye tracker and the P300 speller. Using the eye tracker as a reference for the P300 speller allows users to spell Chinese characters simply by moving their eyes without manually clicking keyboard keys. This reduces the repetitive spelling problems caused by the inaccuracy of the traditional P300 model, improving spelling efficiency and accuracy. Furthermore, by combining the Chinese character library provided by standard Chinese input methods (such as Google and iFlytek), it enables matching Chinese characters after spelling. This allows ALS patients to more conveniently and efficiently type Chinese characters using the spelling scheme provided by this patent, demonstrating strong practical value. Using the eye tracker also reduces visual fatigue caused by the frequent flickering during P300 spelling. On the other hand, optimizing the experimental paradigm of the classic P300 speller using information provided by the eye tracker also has reference value for research on ERP (Event-Related Potential) brain-computer interface technology.

[0097] The above provides a detailed description of a method for Chinese character input combining an eye tracker and P300 technology, as provided by this invention. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are merely for the purpose of helping to understand the core ideas of this invention. It should be noted that those skilled in the art can make various improvements and modifications to this invention without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this invention.

Claims

1. A method for realizing Chinese character input by combining an eye tracker with P300 technology, characterized in that, The method comprises the following steps: Step S100: determining the spatial position information of the fixation point through the eye tracking signal of the eye tracker, determining the position where the user's current gaze is located by analyzing the spatial position information, and triggering the P300 speller interface after detecting that the gaze stays at the start key for a preset time length; step S100 comprises: Step S110: correcting the eye movement information of the user before spelling starts, and obtaining the original spatial eye movement information using a Python library; Step S120: as the user's eyes move, the eye tracker acquires the fixation coordinates of the user; Step S130: selecting valid data from the acquired fixation point coordinates of the user, and eliminating abnormal coordinates, wherein the abnormal coordinates are sample point coordinates collected during blinking and rapid eye movement; Step S140: writing the eye movement visual trajectory coordinates represented by the sample point coordinates of the user into a buffer; Step S150: determining whether the coordinates of the buffer are located on the start key and last for a preset time length, and if so, activating the spelling process; The step S130 specifically comprises: Step S131: eliminating the coordinates of eye blinking that cannot be captured by the eye tracker: the coordinates of eye blinking that cannot be captured by the eye tracker are calibrated as (-1, -1), and the coordinates less than 0 are eliminated, i.e., the coordinates of eye blinking that cannot be captured by the eye tracker are eliminated; Step S132: eliminating the coordinates of saccades captured by the eye tracker: according to the sampling rate of the eye tracker, the distance between two sampling points is obtained, i.e., the eye movement speed is obtained; through a speed threshold identification classification algorithm, the sampling points with an eye movement speed greater than a certain threshold are determined as saccade samples and are eliminated, and the sampling point coordinates of the user's fixation target are retained; Step S200: the P300 event corresponding potential generated by the flashing of the pinyin and function key sequence induces an electroencephalogram signal, the electroencephalogram signal is preprocessed and analyzed, and the character P1 selected at the current fixation point of the user is determined; Step S300: according to the eye movement spatial information provided by the eye tracking device, the character P2 at the preset reference position of the current fixation point of the user is determined, if the P1 and the P2 are consistent and the fixation position is an initial or a final, the input of the P300 is written into the buffer, if the P1 and the P2 are consistent and the fixation position is a function key position, the instruction of the function key is executed, and steps S200 and S300 are repeated until the selection of the initial and the final is completed; Step S400: calling the pinyin input method, determining the target Chinese character according to the selected initial and final, and realizing the spelling function of Chinese characters.

2. The method of claim 1, wherein, Step S200 comprises: Step S210: tracking and acquiring eye movement information through a Python tool library, and detecting the distribution of the gaze fixation point coordinates in time; Step S220: activating the P300 speller of the brain-computer interface system, and displaying the flashing of the pinyin or other function key sequence on the screen; Step S230: acquiring an electroencephalogram signal through an electroencephalogram acquisition device; Step S240: after filtering and signal amplification of the acquired electroencephalogram signal, decoding the electroencephalogram signal to determine the character P1 selected at the current fixation point of the user.

3. The method of claim 2, wherein, Step S240 comprises: Step S241: reading a brain wave signal for at least 2500 ms; Step S242: analyzing the P300 time sequence position in the brain wave signal, and comparing with the time sequence of the character flickering stimulation sequence to determine the row and column positions of the stimulation, thereby determining the character P1 at the position of the pin yin or function key that the user gazes at.

4. The method of claim 3, wherein, Step S300 includes: Step S310: recording the spatial position information of the sample point of the current user eye movement information record, and calculating the expectation of the spatial coordinates by the host computer as the reference position of the gaze point; Step S320: inputting the coordinates of the reference position of the gaze point into the computer buffer area; Step S330: comparing the horizontal and vertical coordinates of the gaze point with the position information of each function key to obtain the character P2 at the reference position of the eye tracker at this time; Step S340: comparing the contents of P1 and P2, if P1 and P2 are consistent and the gaze position is an initial or final, then write the P300 input into the buffer area, if P1 and P2 are consistent and the gaze position is a function key position, then execute the instruction of the function key, and return to step S200 until the selection of the initial and final is completed.

5. The method of claim 4, wherein, Step S400 includes: Step S410: determining the current pin yin as Y1 according to the selected initial and final, and inputting the pin yin Y1 into the input field; Step S420: after inputting Y1, the standard Chinese input method Chinese character library will be automatically called, and the matching between Y1 and the input method Chinese character library will be performed to select the most commonly used Chinese characters as the selected Chinese characters; if not, the gaze PageUp is activated to enter the next page to find the required Chinese characters; Step S430: after determining the Chinese character H1, outputting it to the input field, and returning to step S200 for spelling the next Chinese character.

6. The method of claim 5, wherein, Step S400 further includes: Step S500: gaze at the Del function key for a preset time; the eye movement tracking system of the eye tracker determines that the current gaze point of the user is in the selection function key area, the stimulation sequence flickers to induce the P300 signal, and determines whether to delete the current Chinese character or pin yin, and after the determination, deletes the last Chinese character in the display screen output area or the last pin yin input in the buffer area.

Images