A method and apparatus for extracting optical illusion attributes in a visual brain-computer interface
By obtaining the text and graphic feedback results of the optical illusion feedback, the target results of the optical illusion attributes are determined, which solves the problem of inconsistent optical illusion feedback results and achieves accuracy and reliability in optical illusion attribute extraction.
Patent Information
- Application Number
- CN202611170260.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-04
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2046-08-04
AI Technical Summary
In existing technologies, there is an inconsistency between the textual feedback and the graphical feedback of optical illusion feedback results, which leads to inaccurate extraction of optical illusion attributes and affects the subsequent control process.
By acquiring the text and graphic feedback results of the photopsychoscopic feedback, the first and second attribute results of each photopsychoscopic attribute are determined respectively, and the target attribute result is determined based on the conflict value. Historical stimulus records are used for consistency verification and supplementary data collection to generate accurate photopsychoscopic attribute extraction results.
This improved the accuracy of optical illusion attribute extraction, providing a reliable basis for subsequent control processes and solving the problem of inconsistent attribute extraction among multimodal feedback results.
Smart Images

Figure CN122673728B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of brain-computer interface technology, and in particular to a method and apparatus for extracting optical illusion attributes in a visual brain-computer interface. Background Technology
[0002] In existing research on photopsia-based brain-computer interfaces, the actual triggered photopsia images often require subjective descriptions from the subjects to obtain photopsia feedback results. These feedback results can be textual or drawn, using natural language or hand-drawn graphics. Further attribute extraction is then performed on these feedback results to obtain attributes corresponding to the photopsia images. However, due to differences in subject expression, inaccurate or conflicting textual and drawn feedback structures may occur, hindering effective attribute extraction and impacting subsequent modulation processes. Therefore, a method for accurate attribute extraction from multimodal photopsia feedback results is urgently needed to ensure the extraction of useful target attributes from the subjects' photopsia feedback. Summary of the Invention
[0003] This invention provides a method and apparatus for extracting optical illusion attributes from a visual brain-computer interface, in order to solve the problem in the prior art that it is impossible to effectively extract attributes from optical illusion feedback results.
[0004] This invention provides a method for extracting photopsychic attributes in a visual brain-computer interface, comprising the following steps: acquiring photopsychic feedback results; the photopsychic feedback results include text feedback results and drawing feedback results; determining a first attribute result corresponding to the text feedback result and a second attribute result corresponding to the drawing feedback result for each photopsychic attribute; for each photopsychic attribute: determining a conflict value between the first attribute result and the second attribute result corresponding to the photopsychic attribute; if the conflict value is greater than a preset first conflict threshold, determining a target attribute result corresponding to the photopsychic attribute from the first attribute result and the second attribute result according to a data extraction strategy corresponding to the photopsychic attribute; generating an attribute extraction result corresponding to the photopsychic feedback result based on the target attribute results corresponding to each photopsychic attribute.
[0005] Optionally, the optical illusion attributes include at least one of the following: color attribute, flicker attribute, motion attribute, shape attribute, brightness attribute, position attribute, and size attribute.
[0006] Optionally, when the optical illusion attributes include position attributes and / or size attributes, determining the first attribute result corresponding to the text feedback result and the second attribute result corresponding to the drawing feedback result for each optical illusion attribute includes: performing image recognition on the drawing feedback result to obtain the target contour in the drawing feedback result; performing ellipse fitting on the target contour in a preset coordinate system to obtain the fitting result; and obtaining the second attribute result corresponding to each of the optical illusion attributes based on the fitting result.
[0007] Optionally, the fitting result includes the coordinates of the center point of the fitted ellipse, the length of the major axis, and the length of the minor axis; obtaining the second attribute results corresponding to each of the optical illusion attributes based on the fitting result includes: When the optical illusion attribute includes a position attribute, the center point coordinates are used as the second attribute result corresponding to the position attribute; And / or, When the optical illusion attribute includes a size attribute, the average of the major axis length and the minor axis length is used as the second attribute result corresponding to the size attribute.
[0008] Optionally, determining the target attribute result corresponding to the optical illusion attribute based on the first attribute result and the second attribute result includes: when the optical illusion attribute is at least one of color attribute, flicker attribute, motion attribute, shape attribute, and brightness attribute, the first attribute result is used as the target attribute result corresponding to the optical illusion attribute; when the optical illusion attribute is a position attribute and / or size attribute, the second attribute result is used as the target attribute result.
[0009] Optionally, obtaining the photopsychopathic feedback result includes: obtaining the photopsychopathic feedback result corresponding to the preset electrical stimulation signal based on the triggering of the preset electrical stimulation signal; Before generating the attribute extraction result corresponding to the photopsychoscopic feedback result based on the target attribute results corresponding to each of the photopsychoscopic attributes, the method further includes: acquiring a target historical stimulus record corresponding to the preset electrical stimulation signal; the target historical stimulus record includes the target historical attribute results corresponding to each of the photopsychoscopic attributes; for each photopsychoscopic attribute: performing a consistency check on the target attribute result corresponding to the photopsychoscopic attribute based on the target historical attribute result corresponding to the photopsychoscopic attribute; if the consistency check passes, performing the step of generating the attribute extraction result corresponding to the photopsychoscopic feedback result based on the target attribute results corresponding to each of the photopsychoscopic attributes.
[0010] Optionally, the target historical stimulus record includes at least one of the following: a first historical stimulus record belonging to the same subject as the preset electrical stimulation signal, a second historical stimulus record using the same electrode pair as the preset electrical stimulation signal, and a third historical stimulus record with the same parameters as the preset electrical stimulation signal; And / or, The target historical attribute result includes at least one of the following: a first historical attribute result corresponding to the first historical stimulus record, a second historical attribute result corresponding to the second historical stimulus record, and a third historical attribute result corresponding to the third historical stimulus record.
[0011] Optionally, for each optical illusion attribute: performing consistency verification on the target attribute result corresponding to the optical illusion attribute based on the target historical attribute result corresponding to the optical illusion attribute includes: for each optical illusion attribute: calculating a first similarity between the first historical attribute result and the target attribute result, a second similarity between the second historical attribute result and the target attribute result, and a third similarity between the third historical attribute result and the target attribute result; performing a weighted summation of the first similarity, the second similarity, and the third similarity to generate a consistency score; and generating a consistency verification result corresponding to the target attribute result based on the relationship between the consistency score and a preset score.
[0012] Optionally, determining the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute includes at least one of the following: When the optical illusion attribute includes a color attribute, a conflict value is calculated based on the degree of color overlap between the first attribute result and the second attribute result. When the optical illusion attribute includes a flicker attribute, a conflict value is calculated based on the difference in flicker parameters between the first attribute result and the second attribute result; When the optical illusion attribute includes a motion attribute, a conflict value is calculated based on the difference in motion paths between the first attribute result and the second attribute result. When the optical illusion attribute includes a shape attribute, a conflict value is calculated based on the shape category difference between the first attribute result and the second attribute result; When the optical illusion attribute includes a brightness attribute, a conflict value is calculated based on the brightness difference between the first attribute result and the second attribute result. When the optical illusion attribute includes a position attribute, a conflict value is calculated based on the positional distance between the first attribute result and the second attribute result. When the optical illusion attribute includes a size attribute, a conflict value is calculated based on the area difference between the first attribute result and the second attribute result.
[0013] Optionally, the method further includes: evaluating the target attribute result according to at least one evaluation dimension to generate a confidence level corresponding to the target attribute result; acquiring supplementary data when the confidence level is less than a preset confidence threshold and / or when the conflict value is greater than a preset second conflict threshold; wherein the preset second conflict threshold is greater than the preset first conflict threshold; and updating the target attribute result according to the supplementary data.
[0014] The present invention also provides a device for extracting optical illusion attributes of a visual brain-computer interface, comprising the following modules: The acquisition module is used to acquire optical illusion feedback results; the optical illusion feedback results include text feedback results and drawing feedback results. The determination module is used to determine the first attribute result corresponding to the text feedback result and the second attribute result corresponding to the drawing feedback result for each optical illusion attribute; for each optical illusion attribute: determine the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute; if the conflict value is greater than a preset first conflict threshold, determine the target attribute result corresponding to the optical illusion attribute from the first attribute result and the second attribute result according to the data extraction strategy corresponding to the optical illusion attribute; The generation module is used to generate the attribute extraction result corresponding to the optical illusion feedback result based on the target attribute result corresponding to each of the optical illusion attributes.
[0015] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the optical illusion attribute extraction method of the visual brain-computer interface as described above.
[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the optical illusion attribute extraction method of the visual brain-computer interface as described above.
[0017] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the optical illusion attribute extraction method of the visual brain-computer interface as described above.
[0018] This invention provides a method and apparatus for extracting optical illusion attributes in a visual brain-computer interface. For each optical illusion attribute, it determines a first attribute result corresponding to the text feedback result and a second attribute result corresponding to the drawing feedback result, and determines the target attribute result based on the conflict value between the first and second attribute results. This effectively solves the problem of inconsistent attribute extraction between multiple modalities, and can determine a reasonable target attribute result for the optical illusion feedback result when there is a conflict, greatly improving the accuracy of optical illusion attribute extraction and providing a reliable basis for subsequent control processes. Attached Figure Description
[0019] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0020] Figure 1 This is one of the flowcharts illustrating the optical illusion attribute extraction method for the visual brain-computer interface provided by this invention.
[0021] Figure 2 This is a flowchart illustrating the process of extracting attributes from drawing feedback results provided by the present invention.
[0022] Figure 3 This is a schematic diagram of the preset color wheel provided by the present invention.
[0023] Figure 4 This is the second flowchart illustrating the optical illusion attribute extraction method for the visual brain-computer interface provided by this invention.
[0024] Figure 5 This is a flowchart illustrating the process of performing consistency verification on the target attribute results based on the target historical attribute results in step 406 of the present invention.
[0025] Figure 6 This is a flowchart illustrating the process after obtaining the target attribute result in the optical illusion attribute extraction method for the visual brain-computer interface provided by this invention.
[0026] Figure 7 This is a schematic diagram of the optical illusion attribute extraction device for the visual brain-computer interface provided by the present invention.
[0027] Figure 8 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation
[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0029] Figure 1 This is one of the flowcharts illustrating the optical illusion attribute extraction method for the visual brain-computer interface provided by this invention, such as... Figure 1 As shown, the method includes the following: Step 101: Obtain the optical illusion feedback results; the optical illusion feedback results include text feedback results and drawing feedback results.
[0030] Textual feedback results refer to textual results obtained by subjects through natural language description (oral presentation), while graphic feedback results refer to image-based results obtained by subjects through hand-drawn graphics. It is understandable that textual and image-based results are not inherently comparable; therefore, attribute extraction is required for each, and they must be represented according to unified photopsychic attributes before comparison can be made to determine whether they are consistent or conflicting.
[0031] In an optional embodiment, step 101 may specifically include: acquiring a photophanographic feedback result corresponding to a preset electrical stimulation signal based on the triggering of the preset electrical stimulation signal. It is understood that during the modulation of a visual brain-computer interface, the subject is usually made to perceive the expected photophanographic image through the triggering of a preset electrical stimulation signal. Since different subjects have individual differences in their perception area and perception of the electrical stimulation signal, in order to determine whether the subject has truly perceived the expected photophanographic image, it is necessary to further determine whether the photophanographic image actually perceived by the subject is the same as or similar to the expected photophanographic image through the subject's subjective description of the photophanographic feedback result, thereby determining whether the expected photophanographic goal has been achieved. Therefore, the photopsychopathic feedback results obtained in this embodiment of the invention are also obtained from the subjective description of the subject after being triggered by a preset electrical stimulation signal. The photopsychopathic attribute extraction method provided in this embodiment of the invention can accurately extract the attributes of the photopsychopathic feedback results, so that it can be further determined whether the photopsychopathic image actually perceived by the subject is the same as or similar to the expected photopsychopathic image based on the generated attribute extraction results. In other words, the extraction of photopsychopathic attributes in this embodiment of the invention is an important part of the visual brain-computer interface regulation process.
[0032] Step 102: Determine the first attribute result corresponding to the text feedback result and the second attribute result corresponding to the drawing feedback result for each optical illusion attribute.
[0033] In this embodiment of the invention, the optical illusion attributes are preset. In one optional embodiment, they include at least one of the following: color attribute, flicker attribute, motion attribute, shape attribute, brightness attribute, position attribute, and size attribute. Setting multiple optical illusion attributes with different dimensions allows for fine-grained division of the optical illusion feedback results, facilitating precise adjustment of the electrical stimulation signal during subsequent optical illusion control.
[0034] Specifically, in this embodiment of the invention, different processing methods are used to extract attributes from the text feedback results and the drawing feedback results. In one optional embodiment, the first attribute result can be identified from the text feedback result by keyword matching. For example, a keyword library can be preset, which includes multiple keywords corresponding to various optical illusion attributes, such as keywords related to color attributes such as "red," "yellow," and "green," keywords related to shape attributes such as "circle," "rectangle," and "polygon," keywords related to position attributes such as "center," "top left," and "top right," etc. By matching the text feedback result with the preset keyword library, the first attribute result corresponding to each optical illusion attribute in the text feedback result can be determined.
[0035] In another optional embodiment, when the optical illusion attributes include positional and / or size attributes, the process of extracting attributes from the drawing feedback results is as follows: Figure 2 As shown, it includes: Step 201: Perform image recognition on the drawing feedback results to obtain the target contour in the drawing feedback results; Step 202: Under the preset coordinate system, perform ellipse fitting on the target contour to obtain the fitting result; Step 203: Obtain the second attribute results corresponding to each optical illusion attribute based on the fitting results.
[0036] The drawing feedback result can be understood as image data without text description. Therefore, existing image recognition methods can be used to first identify the target contour, and then the second attribute result can be extracted based on the identified target contour. Specifically, considering that the hand-drawn image of the subject may be discontinuous or relatively discrete, and the second attribute result cannot be directly identified through image recognition, in this embodiment of the invention, an ellipse fitting method is used to first fit the identified target contour, and then perform corresponding calculations based on the fitted ellipse (fitting result) to obtain the second attribute result.
[0037] The fitting result includes the coordinates of the center point of the fitted ellipse, the length of the major axis, and the length of the minor axis. In one optional embodiment, step 203 includes: if the optical illusion attribute includes a position attribute, using the center point coordinates as the second attribute result corresponding to the position attribute. In another optional embodiment, step 203 includes: if the optical illusion attribute includes a size attribute, using the average of the major axis length and the minor axis length as the second attribute result corresponding to the size attribute.
[0038] In a further optional embodiment, when the optical illusion attribute includes a color attribute, the process of extracting attributes from the drawing feedback result may further include: obtaining the pixel value corresponding to each pixel point in the drawing feedback result, and determining the second attribute result corresponding to the color attribute from the drawing feedback result based on the pixel value and the range of pixel values corresponding to different colors.
[0039] In an optional embodiment, when the optical illusion attributes include motion attributes and / or flicker attributes, the process of extracting attributes from the drawing feedback results may further include: identifying indicator symbols and / or annotation information in the drawing feedback results used to characterize dynamic perception results, and determining the corresponding dynamic attribute results based on the identification results. The indicator symbols may include at least one of arrows, wavy lines, repeating lines, dashed lines, jittering lines, and multiple contours; the annotation information may include at least one of text, letters, numbers, and graphic markers. For example, the direction of motion can be determined based on the direction of the arrow, and the speed of motion can be determined based on the number, length, thickness, size, or number of repetitions of the arrows; the flicker frequency, flicker intensity, or flicker range can be determined based on the number, distribution, or density of wavy lines, repeating lines, or jittering lines; the dynamic attribute results may also be corrected, supplemented, or have their confidence adjusted in conjunction with the annotation information, without specific limitations in this invention.
[0040] It is understood that the specific process for determining the second attribute result for color attribute, shape attribute, position attribute, motion attribute and blinking attribute in this invention is only an illustrative example. It can also be replaced by other attribute extraction schemes that can achieve the same effect. When some optical illusion attributes cannot be extracted, null values can be used as the second attribute result corresponding to the optical illusion attribute.
[0041] For each optical illusion attribute: perform steps 103 and 104: Step 103: Determine the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute.
[0042] In one optional embodiment, step 103 may include at least one of the following: (1) When the optical illusion attribute includes the color attribute, the conflict value is calculated based on the angular distance between the first attribute result and the second attribute result in the preset color wheel.
[0043] For example, a preset color wheel is as follows: Figure 3 As shown, when the first attribute result is yellow and the second attribute result is green, the color conflict value can be calculated based on the angular distance between the angle (60°) corresponding to yellow and the angle (120°) corresponding to green in the preset color wheel.
[0044] (2) When the optical illusion attribute includes a flicker attribute, the conflict value is calculated based on the difference in flicker parameters between the first attribute result and the second attribute result.
[0045] For example, when the first attribute result is flashing once every 3 seconds and the second attribute result is no flashing, the flashing parameters (such as flashing state, flashing type and flashing frequency) of the two can be determined respectively, and the conflict value can be calculated based on the difference in flashing parameters.
[0046] For example, "blinking once every 3 seconds" can be classified as a blinking state, corresponding to a slow blinking type and a blinking frequency of 1 / 3 Hz; "not blinking" can be classified as a non-blinking state, corresponding to a blinking frequency of 0 Hz. Since the two states are inconsistent in terms of blinking, the corresponding blinking state difference value can be taken as 1 (0 indicates consistent blinking states). Furthermore, they differ in blinking type, so the corresponding blinking type difference value can be taken as 1 (similarly, 0 indicates consistent blinking types). Even further, they are also inconsistent in blinking frequency, so the corresponding blinking frequency difference value can be calculated based on the difference in blinking frequencies. By weighted summing the blinking state difference value, blinking type difference value, and blinking frequency difference value, the conflict value corresponding to the blinking attribute is obtained.
[0047] (3) When the optical illusion attribute includes motion attribute, the conflict value is calculated based on the difference in motion path between the first attribute result and the second attribute result.
[0048] For example, the difference in motion paths can be calculated by calculating the Hausdorff distance or the Fraser distance between the first attribute result and the second attribute result, and the Hausdorff distance or the Fraser distance can be used as the conflict value.
[0049] (4) When the optical illusion attribute includes shape attribute, the conflict value is calculated based on the difference in shape category between the first attribute result and the second attribute result.
[0050] Specifically, the shape categories corresponding to the first attribute result and the second attribute result can be determined separately, and a conflict value can be calculated based on the difference between the shape categories. For example, if the first attribute result is a quadrilateral and the second attribute result is a pentagon, then the absolute value of the difference in the number of sides of the polygons can be used as the shape category difference, i.e., the conflict value is |4-5|=1. It can be understood that the larger the difference in the number of sides of the shapes corresponding to the first attribute result and the second attribute result, the higher the corresponding conflict value.
[0051] (5) When the optical illusion attribute includes the brightness attribute, the conflict value is calculated based on the brightness difference between the first attribute result and the second attribute result.
[0052] The brightness attributes reported by the test subjects can be either subjective brightness level descriptions or corresponding quantitative brightness indices. In some implementations, subjective brightness level descriptions can be converted into numerical brightness levels through a preset mapping relationship to unify the calculation of brightness conflict values.
[0053] For example, when the first attribute result is "very bright" and the second attribute result is "moderately bright", the corresponding brightness levels for each can be determined first, and the conflict value can be calculated based on the difference between the brightness levels. For instance, a mapping relationship between brightness level descriptions and level values can be established in advance, mapping "very bright" to level value 3 and "moderately bright" to level value 2, and the absolute value of the difference between the two level values can be used as the brightness difference value.
[0054] (6) When the optical illusion attribute includes the position attribute, the conflict value is calculated based on the positional distance between the first attribute result and the second attribute result.
[0055] For example, if the first attribute result is "top left" and the second attribute result is coordinates (45, 30), then in this embodiment of the invention, the first attribute result needs to be converted to a new coordinate system. This involves mapping the text feedback result to the same preset coordinate system as the drawing feedback result to obtain the coordinates corresponding to the first attribute result, for example, (20, 20). Then, the Euclidean distance between the two coordinates is calculated to determine the conflict value between the first and second attribute results. It is understood that for text feedback results such as "top left" and "top right," corresponding standard coordinates can be preset to facilitate determining the coordinates corresponding to the first attribute result.
[0056] (7) When the optical illusion attribute includes the size attribute, the conflict value is calculated based on the area difference between the first attribute result and the second attribute result.
[0057] For example, if the first attribute result is a smaller spot and the second attribute result is 0.5 (i.e., the average of the major and minor axis lengths of the fitted ellipse), then similar to the position attribute, the first attribute result needs to be converted into the corresponding area value. For example, if the preset area value of the smaller spot is 0.2, then the normalized difference between 0.2 and 0.5 can be calculated, and the calculated result can be used as the conflict value.
[0058] Step 104: If the conflict value is greater than the preset first conflict threshold, determine the target attribute result corresponding to the optical illusion attribute based on the first attribute result and the second attribute result.
[0059] Understandably, different first conflict thresholds can be set for different optical illusion attributes. For example, for the color attribute, if the conflict value is not 0, it means that the colors indicated by the first attribute result and the second attribute result are different, and one of them must be wrong; there is no situation where they are approximately the same. Therefore, the first conflict threshold corresponding to the color attribute can be set to 0. However, for the position attribute, the drawing feedback results may have some inaccuracies. For example, if the subject makes some deviations when drawing, mistakenly drawing the outline of the central area in the upper left of the central area, the coordinates corresponding to the first attribute result and the second attribute result will not be completely consistent, with some deviation, but the general positions are close. Therefore, the first attribute result and the second attribute result should be considered consistent. Based on this, the first conflict threshold corresponding to the position attribute can be set as a preset distance threshold, such as the Euclidean distance threshold between the positions corresponding to the first attribute result and the positions corresponding to the second attribute result. For example, the first conflict threshold can be set to 3% to 10% of the width and / or height of the display area, or set to 5% to 15% of the outer area size of the target graphic. When the conflict value corresponding to the location attribute is less than or equal to the first conflict threshold, the two can be considered to be basically consistent in terms of location attribute; when the conflict value corresponding to the location attribute is greater than the first conflict threshold, the two can be considered to have a large conflict in terms of location attribute.
[0060] In an optional embodiment, step 104, which determines the target attribute result corresponding to the optical illusion attribute based on the first attribute result and the second attribute result, specifically includes: when the optical illusion attribute is at least one of color, flicker, motion, shape, and brightness attributes, the first attribute result is used as the target attribute result; when the optical illusion attribute is a position attribute and / or size attribute, the second attribute result is used as the target attribute result. In other words, this invention sets different extraction priorities for different optical illusion attributes. For optical illusion attributes such as color, flicker, motion, shape, and brightness, which are easier to extract from text feedback results, the first attribute result corresponding to the text feedback result is preferentially used as the target attribute result. For optical illusion attributes such as position and size, which are less convenient to describe in text and more suitable for hand-drawing, the second attribute result corresponding to the drawing feedback result is preferentially used as the target attribute result.
[0061] As can be seen, in the embodiments of the present invention, by comparing each optical illusion attribute with the corresponding first conflict threshold through the above steps 103 and 104, the corresponding target attribute result can be obtained.
[0062] Step 105: Generate the attribute extraction results corresponding to the optical illusion feedback results based on the target attribute results corresponding to each optical illusion attribute.
[0063] For example, the target attribute results corresponding to each optical illusion attribute can be integrated to obtain the attribute extraction result corresponding to the optical illusion feedback result.
[0064] Through the above process, the embodiments of the present invention effectively resolve conflicts in the optical illusion feedback results of different modalities, and perform fine-grained conflict determination based on the first conflict threshold corresponding to different optical illusion attributes, thereby improving the accuracy and effectiveness of attribute extraction.
[0065] In an optional embodiment, the present invention also provides a method for extracting optical illusion attributes in a visual brain-computer interface, such as... Figure 4 As shown, it includes: Step 401: Based on the triggering of the preset electrical stimulation signal, obtain the optical hallucination feedback result corresponding to the preset electrical stimulation signal; Step 402: Determine the first attribute result corresponding to the text feedback result and the second attribute result corresponding to the drawing feedback result for each optical illusion attribute; For each optical illusion attribute: perform steps 403 and 404: Step 403: Determine the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute; Step 404: If the conflict value is greater than the preset first conflict threshold, determine the target attribute result corresponding to the optical illusion attribute based on the first attribute result and the second attribute result; Step 405: Obtain the target historical stimulus record corresponding to the preset electrical stimulation signal; the target historical stimulus record includes the target historical attribute results corresponding to each optical hallucination attribute; Step 406: For each optical illusion attribute: Perform consistency verification on the target attribute result corresponding to the optical illusion attribute based on the target historical attribute result corresponding to the optical illusion attribute; Step 407: If the consistency check passes, generate the attribute extraction results corresponding to the optical illusion feedback results based on the target attribute results corresponding to each optical illusion attribute.
[0066] As can be seen, in the embodiments of the present invention, steps 405 to 407 are used to further verify the target attribute results corresponding to each optical illusion attribute by utilizing the target historical attribute results in the target historical stimulus record, so as to ensure the rationality of the target attribute results.
[0067] Specifically, the target historical stimulus record includes at least one of the following: a first historical stimulus record belonging to the same subject as the preset electrical stimulation signal, a second historical stimulus record using the same electrode pair as the preset electrical stimulation signal, and a third historical stimulus record with the same parameters as the preset electrical stimulation signal. Similarly, the target attribute result also includes at least one of the following: a first historical attribute result corresponding to the first historical stimulus record, a second historical attribute result corresponding to the second historical stimulus record, and a third historical attribute result corresponding to the third historical stimulus record.
[0068] It should be noted that although the first, second, and third historical stimulus records all have a certain correlation with the preset electrical stimulation signal, they are not completely identical to the preset electrical stimulation signal, and their comparability still differs. Therefore, in a further optional embodiment, in order to ensure the referenceability of the target historical attribute results, the target historical stimulus records in this embodiment of the invention simultaneously include: the first historical stimulus record belonging to the same subject as the preset electrical stimulation signal, the second historical stimulus record using the same electrode pair as the preset electrical stimulation signal, and the third historical stimulus record with the same parameters as the preset electrical stimulation signal. The target historical attribute results also simultaneously include: the first historical attribute result corresponding to the first historical stimulus record, the second historical attribute result corresponding to the second historical stimulus record, and the third historical attribute result corresponding to the third historical stimulus record. By integrating the historical attribute results corresponding to multiple historical stimulus records, a more comprehensive and accurate target historical attribute result can be obtained. Specifically, the process of performing consistency verification on the target attribute results based on the target historical attribute results in step 406 is as follows: Figure 5 As shown, it specifically includes: For each optical illusion attribute, perform steps 501 to 503: Step 501: Calculate the first similarity between the first historical attribute result and the target attribute result, the second similarity between the second historical attribute result and the target attribute result, and the third similarity between the third historical attribute result and the target attribute result, respectively. Step 502: Calculate the weighted sum of the first similarity, second similarity, and third similarity to generate a consistency score; Step 503: Based on the relationship between the consistency score and the preset score, generate the consistency verification result corresponding to the target attribute result.
[0069] In this regard, considering that the first historical attribute result that only satisfies the same subject has relatively low reference value for the target attribute result, while the third historical attribute result that is the same as the preset electrical stimulation signal parameter has relatively high reference value for the target attribute result, when performing weighted summation in step 502, the settings can be adjusted according to the reference value of different historical attribute results for the target attribute result, so as to reduce the interference of historical stimulation records with weak comparability.
[0070] It should be noted that the above-mentioned target historical stimulus records are only one example. They can be further subdivided, for example, into historical stimulus records 1, which belong to the same subject as the preset electrical stimulation signal, use the same electrode pair, and have the same electrical stimulation signal parameters; historical records 2, which belong to the same subject as the preset electrical stimulation signal, use the same electrode pair, but have different electrical stimulation signal parameters; historical stimulus records 3, which belong to different subjects as the preset electrical stimulation signal, use the same electrode pair, and have the same electrical stimulation signal parameters; historical stimulus records 4, which belong to the same subject as the preset electrical stimulation signal; historical stimulus records 5, which use the same electrode pair as the preset electrical stimulation signal; and so on. Historical stimulus record 1 has the highest similarity weight, and the similarity weight of subsequent historical stimulus records decreases sequentially, thus obtaining the weighted consistency score.
[0071] In a further optional embodiment, the optical illusion attribute extraction method for visual brain-computer interfaces provided by the present invention, after obtaining the target attribute result, such as... Figure 6 As shown, it also includes: Step 601: Evaluate the target attribute result based on at least one evaluation dimension and generate the confidence score corresponding to the target attribute result; Step 602: If the confidence level is less than a preset confidence threshold and / or the conflict value is greater than a preset second conflict threshold, acquire supplementary data; wherein the preset second conflict threshold is greater than the preset first conflict threshold. Step 603: Update the target attribute results based on the supplementary collected data.
[0072] The evaluation dimensions may include at least one of the following: attribute extraction quality, intermodal consistency, historical consistency, and topological rationality. Attribute extraction quality can be determined by analyzing the clarity of the visual illusion feedback results, for example, 1 point for clarity, 0.7 points for partial ambiguity, and 0 points for ambiguity. Intermodal consistency can be calculated based on the spatial distance between the first and second attribute results. Historical consistency can be calculated based on the similarity between the target attribute result and the target's historical attribute results. Topological rationality can be calculated based on the deviation between the target attribute result and the expected attribute result corresponding to the preset electrical stimulation signal. In this invention, the number of evaluation dimensions and the specific division of dimensions are not limited; dimensions can be increased or decreased according to actual circumstances. Furthermore, the method of determining each dimension is not limited; other methods can be used to replace them, as long as they can represent the evaluation results corresponding to different dimensions.
[0073] Understandably, if the confidence level is too low or the conflict value is too high, it indicates that the extracted target attribute results are not reliable or have low accuracy. Therefore, it is necessary to re-determine the results based on the acquired supplementary data. In this embodiment of the invention, the supplementary data can guide the subjects to supplement the textual and graphical feedback results through targeted optical illusion attribute queries.
[0074] In summary, the optical illusion attribute extraction method for visual brain-computer interfaces provided by this invention, for each optical illusion attribute, determines its first attribute result corresponding to the text feedback result and its second attribute result corresponding to the drawing feedback result, and determines the target attribute result based on the conflict value between the first attribute result and the second attribute result. This can effectively solve the problem of inconsistent attribute extraction between multiple modalities, and can determine a reasonable target attribute result for the optical illusion feedback result when there is a conflict, greatly improving the accuracy of optical illusion attribute extraction and providing a reliable basis for subsequent control processes.
[0075] The optical illusion attribute extraction device for the visual brain-computer interface provided by the present invention is described below. The optical illusion attribute extraction device for the visual brain-computer interface described below and the optical illusion attribute extraction method for the visual brain-computer interface described above can be referred to in correspondence.
[0076] like Figure 7 As shown, the optical illusion attribute extraction device 700 for a visual brain-computer interface provided in this embodiment of the invention includes: The acquisition module 701 is used to acquire optical illusion feedback results; the optical illusion feedback results include text feedback results and drawing feedback results. The determining module 702 is used to determine the first attribute result corresponding to the text feedback result and the second attribute result corresponding to the drawing feedback result for each optical illusion attribute; for each optical illusion attribute: determine the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute; if the conflict value is greater than a preset first conflict threshold, determine the target attribute result corresponding to the optical illusion attribute from the first attribute result and the second attribute result according to the data extraction strategy corresponding to the optical illusion attribute; The generation module 703 is used to generate the attribute extraction result corresponding to the optical illusion feedback result based on the target attribute result corresponding to each of the optical illusion attributes.
[0077] In an optional embodiment of the present invention, the optical illusion attribute includes at least one of the following: color attribute, flicker attribute, motion attribute, shape attribute, brightness attribute, position attribute, and size attribute.
[0078] In an optional embodiment of the present invention, the determining module 702 is further configured to, when the optical illusion attributes include position attributes and / or size attributes, perform image recognition on the drawing feedback result to obtain the target contour in the drawing feedback result; perform ellipse fitting on the target contour in a preset coordinate system to obtain the fitting result; and obtain the second attribute result corresponding to each of the optical illusion attributes based on the fitting result.
[0079] In an optional embodiment of the present invention, the fitting result includes the center point coordinates, major axis length, and minor axis length of the fitted ellipse; the determining module 702 is further configured to, when the optical illusion attribute includes a position attribute, use the center point coordinates as the second attribute result corresponding to the position attribute; and / or, when the optical illusion attribute includes a size attribute, use the average of the major axis length and the minor axis length as the second attribute result corresponding to the size attribute.
[0080] In an optional embodiment of the present invention, the determining module 702 is further configured to, when the optical illusion attribute is at least one of color attribute, flicker attribute, motion attribute, shape attribute, and brightness attribute, use the first attribute result corresponding to the optical illusion attribute as the target attribute result; and when the optical illusion attribute is a position attribute and / or size attribute, use the second attribute result as the target attribute result.
[0081] In an optional embodiment of the present invention, the acquisition module 701 is further configured to acquire a photopsychopathic feedback result corresponding to the preset electrical stimulation signal based on the triggering of the preset electrical stimulation signal; the device further includes a verification module configured to acquire a target historical stimulation record corresponding to the preset electrical stimulation signal before generating an attribute extraction result corresponding to the photopsychopathic feedback result based on the target attribute results corresponding to each of the photopsychopathic attributes; the target historical stimulation record includes target historical attribute results corresponding to each of the photopsychopathic attributes; for each photopsychopathic attribute: perform a consistency verification on the target attribute result corresponding to the photopsychopathic attribute based on the target historical attribute result corresponding to the photopsychopathic attribute; if the consistency verification passes, execute the step of generating an attribute extraction result corresponding to the photopsychopathic feedback result based on the target attribute results corresponding to each of the photopsychopathic attributes.
[0082] In an optional embodiment of the present invention, the target historical stimulus record includes at least one of the following: a first historical stimulus record belonging to the same subject as the preset electrical stimulation signal, a second historical stimulus record using the same electrode pair as the preset electrical stimulation signal, and a third historical stimulus record with the same parameters as the preset electrical stimulation signal. And / or, The target historical attribute result includes at least one of the following: a first historical attribute result corresponding to the first historical stimulus record, a second historical attribute result corresponding to the second historical stimulus record, and a third historical attribute result corresponding to the third historical stimulus record.
[0083] In an optional embodiment of the present invention, the verification module is further configured to, for each of the optical illusion attributes: calculate a first similarity between the first historical attribute result and the target attribute result, a second similarity between the second historical attribute result and the target attribute result, and a third similarity between the third historical attribute result and the target attribute result; perform a weighted summation of the first similarity, the second similarity, and the third similarity to generate a consistency score; and generate a consistency verification result corresponding to the target attribute result based on the relationship between the consistency score and a preset score.
[0084] In an optional embodiment of the present invention, the determining module 702 is further configured to, When the optical illusion attribute includes a color attribute, a conflict value is calculated based on the angular distance between the first attribute result and the second attribute result in a preset color wheel. When the optical illusion attribute includes a flicker attribute, a conflict value is calculated based on the difference in flicker parameters between the first attribute result and the second attribute result; When the optical illusion attribute includes a motion attribute, a conflict value is calculated based on the difference in motion paths between the first attribute result and the second attribute result. When the optical illusion attribute includes a shape attribute, a conflict value is calculated based on the shape category difference between the first attribute result and the second attribute result; When the optical illusion attribute includes a brightness attribute, a conflict value is calculated based on the brightness difference between the first attribute result and the second attribute result. When the optical illusion attribute includes a position attribute, a conflict value is calculated based on the positional distance between the first attribute result and the second attribute result. When the optical illusion attribute includes a size attribute, a conflict value is calculated based on the area difference between the first attribute result and the second attribute result.
[0085] In an optional embodiment of the present invention, the apparatus further includes: an evaluation module, configured to evaluate the target attribute result according to at least one evaluation dimension, generate a confidence level corresponding to the target attribute result; acquire supplementary collected data if the confidence level is less than a preset confidence threshold and / or if the conflict value is greater than a preset second conflict threshold; wherein the preset second conflict threshold is greater than the preset first conflict threshold; and update the target attribute result according to the supplementary collected data.
[0086] In summary, the optical illusion attribute extraction device for the visual brain-computer interface provided in this embodiment of the invention, for each optical illusion attribute, determines its first attribute result corresponding to the text feedback result and its second attribute result corresponding to the drawing feedback result, and determines the target attribute result based on the conflict value between the first attribute result and the second attribute result. This can effectively solve the problem of inconsistent attribute extraction between multiple modalities, and can determine a reasonable target attribute result for the optical illusion feedback result when there is a conflict, which greatly improves the accuracy of optical illusion attribute extraction and provides a reliable basis for the subsequent control process.
[0087] Figure 8 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 8As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840, wherein the processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute a visual brain-computer interface-based method for extracting photoillusion attributes. This method includes: acquiring photoillusion feedback results; the photoillusion feedback results include text feedback results and drawing feedback results; determining a first attribute result corresponding to the text feedback result and a second attribute result corresponding to the drawing feedback result for each photoillusion attribute; for each photoillusion attribute: determining a conflict value between the first attribute result and the second attribute result corresponding to the photoillusion attribute; if the conflict value is greater than a preset first conflict threshold, determining a target attribute result corresponding to the photoillusion attribute from the first attribute result and the second attribute result according to the data extraction strategy corresponding to the photoillusion attribute; and generating an attribute extraction result corresponding to the photoillusion feedback result based on the target attribute results corresponding to each photoillusion attribute.
[0088] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0089] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the optical illusion attribute extraction method for the visual brain-computer interface provided by the above methods. The method includes: acquiring optical illusion feedback results; the optical illusion feedback results include text feedback results and drawing feedback results; determining a first attribute result corresponding to the text feedback result and a second attribute result corresponding to the drawing feedback result for each optical illusion attribute; for each optical illusion attribute: determining a conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute; if the conflict value is greater than a preset first conflict threshold, determining a target attribute result corresponding to the optical illusion attribute from the first attribute result and the second attribute result according to the data extraction strategy corresponding to the optical illusion attribute; and generating an attribute extraction result corresponding to the optical illusion feedback result based on the target attribute results corresponding to each optical illusion attribute.
[0090] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a method for extracting optical illusion attributes from a visual brain-computer interface provided by the methods described above. This method includes: acquiring optical illusion feedback results; the optical illusion feedback results including text feedback results and drawing feedback results; determining a first attribute result corresponding to the text feedback result and a second attribute result corresponding to the drawing feedback result for each optical illusion attribute; for each optical illusion attribute: determining a conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute; if the conflict value is greater than a preset first conflict threshold, determining a target attribute result corresponding to the optical illusion attribute from the first attribute result and the second attribute result according to a data extraction strategy corresponding to the optical illusion attribute; and generating an attribute extraction result corresponding to the optical illusion feedback result based on the target attribute results corresponding to each optical illusion attribute.
[0091] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0092] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for extracting light hallucination properties of a visual brain-computer interface, characterized in that, include: Obtain optical illusion feedback results; the optical illusion feedback results include text feedback results and drawing feedback results; Determine the first attribute result corresponding to the text feedback result and the second attribute result corresponding to the drawing feedback result for each optical illusion attribute; For each optical illusion attribute: determine the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute; If the conflict value is greater than a preset first conflict threshold, a target attribute result corresponding to the optical illusion attribute is determined based on the first attribute result and the second attribute result. Based on the target attribute results corresponding to each of the aforementioned optical illusion attributes, the attribute extraction results corresponding to the optical illusion feedback results are generated; The determination of the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute includes at least one of the following: When the optical illusion attribute includes a color attribute, a conflict value is calculated based on the angular distance between the first attribute result and the second attribute result in a preset color wheel. When the optical illusion attribute includes a flicker attribute, a conflict value is calculated based on the difference in flicker parameters between the first attribute result and the second attribute result; When the optical illusion attribute includes a motion attribute, a conflict value is calculated based on the difference in motion paths between the first attribute result and the second attribute result. When the optical illusion attribute includes a shape attribute, a conflict value is calculated based on the shape category difference between the first attribute result and the second attribute result; When the optical illusion attribute includes a brightness attribute, a conflict value is calculated based on the brightness difference between the first attribute result and the second attribute result. When the optical illusion attribute includes a position attribute, a conflict value is calculated based on the positional distance between the first attribute result and the second attribute result. When the optical illusion attribute includes a size attribute, a conflict value is calculated based on the difference between the first attribute result and the second attribute result. 2.The photic hallucination attribute extraction method of visual brain-computer interface according to claim 1, wherein, The optical illusion attributes include at least one of the following: color attribute, blink attribute, motion attribute, shape attribute, brightness attribute, position attribute, and size attribute. 3.The method of claim 2, wherein, When the optical illusion attributes include positional attributes and / or size attributes, determining the first attribute result corresponding to the text feedback result and the second attribute result corresponding to the drawing feedback result for each optical illusion attribute includes: Image recognition is performed on the drawing feedback result to obtain the target contour in the drawing feedback result; Under a preset coordinate system, the target contour is fitted with an ellipse to obtain the fitting result; Based on the fitting results, the second attribute results corresponding to each of the optical illusion attributes are obtained. 4.The visual brain-computer interface photopsia attribute extraction method of claim 3, wherein, The fitting results include the coordinates of the center point of the fitted ellipse, the length of the major axis, and the length of the minor axis. The step of obtaining the second attribute results corresponding to each of the optical illusion attributes based on the fitting results includes: When the optical illusion attribute includes a position attribute, the center point coordinates are used as the second attribute result corresponding to the position attribute; And / or, When the optical illusion attribute includes a size attribute, the average of the major axis length and the minor axis length is used as the second attribute result corresponding to the size attribute. 5.The method of claim 1, wherein, The step of determining the target attribute result corresponding to the optical illusion attribute based on the first attribute result and the second attribute result includes: When the optical illusion attribute is at least one of color attribute, blinking attribute, motion attribute, shape attribute, and brightness attribute, the optical illusion attribute is represented by the first attribute result as the target attribute result. When the optical illusion attribute is a position attribute and / or a size attribute, the result of the second attribute is used as the result of the target attribute. 6.The photic hallucination attribute extraction method of visual brain-computer interface according to claim 1, wherein, The process of obtaining the photopsychopathic feedback result includes: obtaining the photopsychopathic feedback result corresponding to the preset electrical stimulation signal based on the triggering of the preset electrical stimulation signal; Before generating the attribute extraction result corresponding to the optical illusion feedback result based on the target attribute results corresponding to each of the optical illusion attributes, the process further includes: Acquire the target historical stimulus record corresponding to the preset electrical stimulation signal; the target historical stimulus record includes the target historical attribute results corresponding to each of the optical hallucination attributes; For each of the optical illusion attributes: perform a consistency check on the target attribute results corresponding to the optical illusion attribute based on the target historical attribute results corresponding to the optical illusion attribute; If the consistency check passes, the step of generating the attribute extraction result corresponding to the optical illusion feedback result is performed based on the target attribute results corresponding to each of the optical illusion attributes.
7. The photopsia attribute extraction method of visual brain-computer interface according to claim 6, wherein, The target historical stimulus record includes at least one of the following: a first historical stimulus record belonging to the same subject as the preset electrical stimulation signal, a second historical stimulus record using the same electrode pair as the preset electrical stimulation signal, and a third historical stimulus record with the same parameters as the preset electrical stimulation signal; And / or, The target historical attribute result includes at least one of the following: a first historical attribute result corresponding to the first historical stimulus record, a second historical attribute result corresponding to the second historical stimulus record, and a third historical attribute result corresponding to the third historical stimulus record.
8. The method for extracting optical illusion attributes of a visual brain-computer interface according to claim 7, characterized in that, For each of the optical illusion attributes: a consistency check is performed on the target attribute result corresponding to the optical illusion attribute based on the target historical attribute result corresponding to the optical illusion attribute, including: For each of the aforementioned optical illusion properties: Calculate the first similarity between the first historical attribute result and the target attribute result, the second similarity between the second historical attribute result and the target attribute result, and the third similarity between the third historical attribute result and the target attribute result, respectively. The first similarity, the second similarity, and the third similarity are weighted and summed to generate a consistency score; Based on the relationship between the consistency score and the preset score, a consistency verification result corresponding to the target attribute result is generated.
9. The method for extracting optical illusion attributes of a visual brain-computer interface according to claim 1, characterized in that, The method also includes: The target attribute result is evaluated based on at least one evaluation dimension to generate the confidence level corresponding to the target attribute result; If the confidence level is less than a preset confidence threshold and / or if the conflict value is greater than a preset second conflict threshold, supplementary data is acquired; wherein the preset second conflict threshold is greater than the preset first conflict threshold. The target attribute result is updated based on the supplementary collected data.
10. A device for extracting optical illusion attributes of a visual brain-computer interface, characterized in that, include: The acquisition module is used to acquire optical illusion feedback results; the optical illusion feedback results include text feedback results and drawing feedback results. The determination module is used to determine the first attribute result corresponding to the text feedback result and the second attribute result corresponding to the drawing feedback result for each optical illusion attribute; For each optical illusion attribute: determine the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute; When the conflict value is greater than a preset first conflict threshold, the target attribute result corresponding to the optical illusion attribute is determined from the first attribute result and the second attribute result according to the data extraction strategy corresponding to the optical illusion attribute. The generation module is used to generate the attribute extraction result corresponding to the optical illusion feedback result based on the target attribute result corresponding to each of the optical illusion attributes. The determination of the conflict value between the first attribute result and the second attribute result corresponding to the optical illusion attribute includes at least one of the following: When the optical illusion attribute includes a color attribute, a conflict value is calculated based on the angular distance between the first attribute result and the second attribute result in a preset color wheel. When the optical illusion attribute includes a flicker attribute, a conflict value is calculated based on the difference in flicker parameters between the first attribute result and the second attribute result; When the optical illusion attribute includes a motion attribute, a conflict value is calculated based on the difference in motion paths between the first attribute result and the second attribute result. When the optical illusion attribute includes a shape attribute, a conflict value is calculated based on the shape category difference between the first attribute result and the second attribute result; When the optical illusion attribute includes a brightness attribute, a conflict value is calculated based on the brightness difference between the first attribute result and the second attribute result. When the optical illusion attribute includes a position attribute, a conflict value is calculated based on the positional distance between the first attribute result and the second attribute result. When the optical illusion attribute includes a size attribute, a conflict value is calculated based on the difference between the first attribute result and the second attribute result.
11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the optical illusion attribute extraction method for a visual brain-computer interface as described in any one of claims 1 to 9.
12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the optical illusion attribute extraction method for visual brain-computer interfaces as described in any one of claims 1 to 9.
13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the optical illusion attribute extraction method for visual brain-computer interfaces as described in any one of claims 1 to 9.
Citation Information
Patent Citations
Device and method for generating phosphene for simulating prothetic vision
CN101690687A
Electrical stimulation method, device and equipment and storage medium
CN120079037A
