A method, apparatus and electronic device for generating a personalized guidance scheme

Abstract

The application provides a personalized guidance scheme generation method and system and an electronic device, relates to the technical field of information, and comprises the following steps: searching for a plurality of test contents; randomly playing the test contents, collecting brain electrical signals of a user in real time; determining and marking test contents of interest of the user based on analysis results of the brain electrical signals; fusing the marked test contents and predetermined training contents to obtain a personalized guidance scheme; playing the personalized guidance scheme to the user and recording eye movement data of the user; and adjusting the personalized guidance scheme by training an optimization model based on the eye movement data to assist in training attention of the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, and in particular to a personalized guidance scheme generation method and device and electronic equipment. BACKGROUND

[0002] Attention, as one of the five intelligence factors, is the preparation state of memory, imagination, thinking and observation, and is the basic condition for brain cognitive activities such as perception, learning and thinking.

[0003] Attention is of great significance to cognitive activities, especially for children. Many children with learning difficulties and communication difficulties are not intelligence problems but have problems in attention. Therefore, lack of concentration may affect the mental health and intellectual development of children.

[0004] Currently, the guidance of attention is mainly through boring learning for forced intervention, which mainly has the following problems: (1) the guidance process is boring and dull, which reduces the enthusiasm of children and increases the training time; (2) the guidance process is monotonous and cannot be adjusted in time, and cannot customize the guidance scheme for each child, which reduces the training effect.

[0005] Therefore, a personalized guidance scheme generation method, device and electronic equipment are provided. SUMMARY

[0006] The present application provides a personalized guidance scheme generation method, device and electronic equipment, which determines and marks the test content of interest to the user by collecting and analyzing the electroencephalogram signal, and obtains a personalized guidance scheme by fusing the test content of interest to the user and the pre-determined training content, to assist in guiding the attention of the user.

[0007] The personalized guidance scheme generation method provided by the present application adopts the following technical scheme, which comprises:

[0008] Finding a plurality of test contents;

[0009] Randomly playing the test content and collecting the electroencephalogram signal of the user in real time;

[0010] Based on the analysis result of the electroencephalogram signal, determining and marking the test content of interest to the user;

[0011] Fusing the marked test content and the pre-determined training content to obtain a personalized guidance scheme;

[0012] Playing the personalized guidance scheme to the user and recording the eye movement data of the user;

[0013] based on the eye movement data, a model is trained to optimize a personalized guidance scheme to assist in training the attention of the user.

[0014] Optionally, the searching for the test content comprises:

[0015] The interest information of the user is obtained.

[0016] Based on the interest information, the test content matching the interest information is searched in a resource library.

[0017] Optionally, based on the analysis result of the electroencephalogram signal, the test content of interest of the user is determined and marked, comprising:

[0018] Based on a preset frequency, it is determined whether the electroencephalogram signal reaches a preset threshold value.

[0019] If yes, it is determined that the currently played test content is the test content of interest of the user.

[0020] The test content of interest of the user is marked.

[0021] Optionally, the fusion of the marked test content and the predetermined training content obtains a personalized guidance scheme, comprising:

[0022] The training content comprises a region of interest.

[0023] Based on the type of the marked test content, the predetermined training content is preprocessed.

[0024] Based on the region of interest, the fusion of the marked test content and the preprocessed training content obtains a personalized guidance scheme.

[0025] Optionally, based on the eye movement data, a model is trained to optimize a personalized guidance scheme to assist in training the attention of the user, comprising:

[0026] Based on the eye movement data, gaze point information about the region of interest is obtained.

[0027] Based on the gaze point information, the marked test content is adjusted by the training optimization model to obtain a new personalized guidance scheme.

[0028] Optionally, it further comprises:

[0029] Within a preset time, gaze point information of a plurality of regions of interest is sequentially collected.

[0030] According to the summary result of the gaze point information, the test content is adjusted.

[0031] The application provides a personalized guidance scheme generation system, which adopts the following technical scheme, comprising:

[0032] A search module is configured to search for a plurality of test contents.

[0033] A collection module is configured to randomly play the test contents and collect brain electrical signals of a user in real time.

[0034] A marking module is configured to determine and mark test contents of interest to the user based on an analysis result of the brain electrical signals.

[0035] A fusion module is configured to fuse the marked test contents and predetermined training contents to obtain a personalized guidance scheme.

[0036] A recording module is configured to play the personalized guidance scheme to the user and record eye movement data of the user.

[0037] An optimization module is configured to optimize the personalized guidance scheme by training an optimization model based on the eye movement data to assist in training attention of the user.

[0038] Optionally, the search module comprises:

[0039] An interest information acquisition submodule is configured to acquire interest information of the user.

[0040] A search submodule is configured to search for the test contents matching the interest information in a resource library based on the interest information.

[0041] Optionally, the marking module comprises:

[0042] A judgment submodule is configured to judge whether the brain electrical signals reach a preset threshold based on a preset frequency.

[0043] A selection submodule is configured to determine that the test content currently played is the test content of interest to the user if yes.

[0044] A marking submodule is configured to mark the test content of interest to the user.

[0045] Optionally, the fusion module comprises:

[0046] The training contents comprise a region of interest.

[0047] A preprocessing submodule is configured to preprocess the predetermined training contents based on a type of the marked test contents.

[0048] A fusion submodule is configured to fuse the marked test contents and the preprocessed training contents based on the region of interest to obtain a personalized guidance scheme.

[0049] Optionally, the optimization module comprises:

[0050] The recording sub-module is configured to obtain gaze point information about the attention-required area based on the eye movement data.

[0051] The optimization sub-module is configured to adjust the marked test content based on the gaze point information by using the training optimization model to obtain a new personalized guidance scheme.

[0052] Optionally, the method further comprises an evaluation module.

[0053] The evaluation module comprises:

[0054] The collection sub-module is configured to sequentially collect gaze point information of the attention-required area within a preset time.

[0055] The adjustment sub-module is configured to adjust the test content according to the summary result of the gaze point information.

[0056] The specification also provides an electronic device, wherein the electronic device comprises:

[0057] a processor; and

[0058] a memory storing computer-executable instructions that, when executed, cause the processor to perform any of the above methods.

[0059] The specification also provides a computer-readable storage medium storing one or more programs that, when executed by a processor, implement any of the above methods.

[0060] In the present application, a plurality of test contents are found; the test contents are randomly played, and brain electrical signals of a user are collected in real time; based on an analysis result of the brain electrical signals, test content of interest of the user is determined and marked; the marked test content and predetermined training content are fused to obtain a personalized guidance scheme; the personalized guidance scheme is played to the user, eye movement data of the user is recorded; and the personalized guidance scheme is adjusted by using a training optimization model based on the eye movement data to assist in training attention of the user. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 A principle schematic diagram of a personalized guidance scheme generation method provided by an embodiment of the specification;

[0062] Figure 2 A flow schematic diagram of a personalized guidance scheme generation method provided by an embodiment of the specification;

[0063] Figure 3 A structural schematic diagram of a personalized guidance scheme generation system provided for an embodiment of the present specification;

[0064] Figure 4 A structural schematic diagram of an electronic device provided for an embodiment of the present specification;

[0065] Figure 5 A principle schematic diagram of a computer readable medium provided for an embodiment of the present specification. DETAILED DESCRIPTION

[0066] The following description is provided so as to enable any person skilled in the art to make or use the present application. The preferred embodiments described in the following description are only examples for implementing the present application and other obvious variations are possible. The general principles defined herein can be applied to other embodiments, variations and modifications without departing from the spirit and scope of the present application.

[0067] Exemplary embodiments of the present application will now be described more fully with reference to the accompanying drawings. The exemplary embodiments of the present application, however, can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art. Like reference numerals refer to like elements throughout the specification.

[0068] In the case of a certain specific embodiment, the features, structures, characteristics or other details described do not exclude the possibility of being combined in one or more other embodiments in a suitable manner, in accordance with the technical idea of the present application.

[0069] In the description of the specific embodiments, the features, structures, characteristics or other details described are intended to enable a person skilled in the art to fully understand the embodiments. However, it does not exclude the possibility that one or more of the specific features, structures, characteristics or other details can not be practiced by a person skilled in the art without one or more of them.

[0070] The flowcharts shown in the drawings are only exemplary illustrations and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps can be further broken down, while some operations / steps can be combined or partially combined, so the actual execution order can be changed according to the actual situation.

[0071] The block diagrams shown in the drawings are merely functional entities and do not necessarily have to correspond to physically independent entities. That is, the functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0072] The term "and / or" or "and / or" includes all combinations of one or more of the associated listed items.

[0073] Figure 1 A schematic diagram of the principle of a personalized guidance scheme generation method provided by an embodiment of the present specification is shown in the figure. The method comprises:

[0074] S1 finds a plurality of test contents;

[0075] S2 randomly plays the test contents and collects the user's brain electrical signals in real time;

[0076] S3 determines and marks the test contents of interest to the user based on the analysis results of the brain electrical signals;

[0077] S4 fuses the marked test contents and the predetermined training contents to obtain a personalized guidance scheme;

[0078] S5 plays the personalized guidance scheme to the user and records the user's eye movement data;

[0079] S6 optimizes the personalized guidance scheme by training the model based on the eye movement data to assist in training the user's attention.

[0080] Attention deficit generally refers to attention deficit hyperactivity disorder, which occurs in childhood and is a group of syndromes characterized by significant difficulty in concentrating attention and short attention span compared with children of the same age. There are many reasons for children's attention deficit, such as:

[0081] 1. Physiological factors: children under the age of 6 have imperfect brain development, and the development of the nervous system is unbalanced, which may lead to attention deficit;

[0082] 2. Sleep factors: if the quality of children's sleep at night is not good, it will cause brain fatigue, resulting in very poor concentration;

[0083] 3. Environmental factors: such as toys on the child's desk, parents watching TV, and too hot or too cold indoor environment, etc., which will make children distracted and lack of concentration;

[0084] 4. Lack of trace elements: zinc can improve children's IQ, accelerate growth and development, and promote appetite. Therefore, if there is a lack of zinc elements, children will lack concentration;

[0085] 5. Attention Deficit Hyperactivity Disorder (ADHD) and autism.

[0086] Based on the present application, a personalized guidance scheme generation method is proposed, which can individualize the guidance of user's attention, and further promote the development of the user's interest points to normal social behavior.

[0087] Specifically, before the generation of the personalized guidance scheme, it is necessary to evaluate whether the user needs attention guidance training.

[0088] Specifically, the user is placed in an evaluation environment and wears relevant brain electrical acquisition equipment. The evaluation environment is relatively quiet, and the device of the present application is placed in front of the user in the evaluation environment. The device of the present application is used to play the estimated content, and the original eye movement data of the user is recorded continuously. The original eye movement data includes but is not limited to fixation time, fixation times, saccade speed, saccade duration, saccade amplitude, saccade latency, saccade direction and eye movement trajectory. The estimated content refers to the video or image used to evaluate whether the user needs attention guidance.

[0089] In an embodiment of the present application, a first interest area is set for the estimated content, and the original eye movement data includes the first fixation time, the dwell time, and the number of fixations in the first interest area. The first interest area is usually the main area that most people often pay attention to in the estimated content, which is set by professionals.

[0090] Based on the original eye movement data, an estimated result is obtained.

[0091] In an embodiment of the present application, the original eye movement data is represented by two-dimensional coordinate data, and a heat map of the estimated content is generated based on the eye movement data, which is used to identify the user's interest in the estimated content. Based on the user's interest in the first interest area in the estimated content, it is determined whether the user has attention deficit.

[0092] In other embodiments of the present application, the medical examination report or medical diagnosis given by professionals can also be combined to determine whether the user has attention deficit.

[0093] If the user has attention deficit, it is determined that the user needs attention guidance training. In order to improve the guidance effect, a personalized guidance scheme is generated for the user. Specifically, as shown in the following formula (1), the method comprises: Figure 2

[0094] S1 find a plurality of test contents;

[0095] ​The test content of each user is different, and the test content that the user is likely to be interested in is filtered based on the interest information of the user, so as to further determine the preference of the user, and thus applied to the training content in the later stage, and the enthusiasm of the user is improved.

[0096] S11 obtains the interest information of the user;

[0097] The interest information is the content that the user is likely to be interested in, which is obtained by the user, friends of the user, parents of the user, etc. The interest information can be words, sentences, etc. obtained by oral or questionnaire.

[0098] S12, based on the interest information, finds the test content matching the interest information in a resource library.

[0099] In an embodiment of the present specification, based on the obtained interest information, a keyword is extracted, and a search is performed in the resource library. Based on the matching degree of the keyword, the matching test content is displayed from high to low, and a preset number of test contents are selected in sequence. The preset number of test contents is determined by a professional in consideration of the test duration and test frequency.

[0100] The resource library is preset, and the resource library stores a plurality of test contents, and the test contents are named by a keyword in advance. The test content includes a plurality of auditory information resources and a plurality of visual information resources. The auditory information resources include but are not limited to audio with fixed frequency, artificial music with melody, and sounds in nature. The visual information resources include but are not limited to object pictures, human pictures, different colors, and settable frequency flashing light sources and animations.

[0101] S2 randomly plays the test content and collects the brain electrical signals of the user in real time;

[0102] The test content is randomly played at a preset frequency, and the brain electrical signals of the user are collected in real time. The preset frequency is a visual stimulation frequency.

[0103] When a constant frequency (usually greater than 5Hz) continuously stimulates the vision of the user, the stimulation modulates the brain electrical signals of the visual cortex of the brain. The brain electrical signals modulated by the external frequency are steady-state visual evoked potentials (SSVEP). The SSVEP is composed of frequency components that are integer multiples of the visual stimulation frequency in the frequency spectrum. Therefore, in an embodiment of the present specification, the brain electrical signals of the user are monitored by SSVEP, and if the user contacts the content of interest, a spike is generated at the corresponding frequency of the frequency domain signal.

[0104] P300 wave, is a waveform of event-related potentials. P represents positive wave, and 300 represents latency of 300 milliseconds. Generally, P300 wave has large amplitude and wide span, is induced by rare, task-related stimulation (called target stimulation), has latency of 300 milliseconds or more, is usually distributed in the central-top region, and has maximum amplitude near the midline. P300 is related to subjective probability, related task, importance of stimulation, decision, decision confidence, uncertainty of stimulation, attention, memory, emotion and other factors. Therefore, in another embodiment of the present specification, the brain electrical signals of the user are monitored by P300, and if the user contacts the content of interest, there will be a significant peak at 300 ms in the time domain signal.

[0105] S3 determines and marks the test content of interest of the user based on the analysis result of the brain electrical signals;

[0106] The monitored brain electrical signals are analyzed, and if there is feedback to the test content and there is obvious brain electrical signal characteristics, the test content is determined as the test content of interest of the user, and the test content of interest of the user is marked.

[0107] S31 determines whether the brain electrical signals reach a preset threshold based on a preset frequency;

[0108] In an embodiment of the present specification, the brain electrical signals of the user are collected by the SSVEP series, and if a sharp peak is generated at a frequency that is an integer multiple of the preset frequency in the frequency domain signal when SSVEP is used for monitoring, it is determined that the brain electrical signals reach the preset threshold, and the corresponding played test content is the test content of interest of the user. If a sharp peak is not generated at a frequency that is an integer multiple of the preset frequency in the frequency domain signal, it is determined that the brain electrical signals do not reach the preset threshold.

[0109] In another embodiment of the present specification, the brain electrical signals of the user are collected by the P300 series, and if there is a significant peak at 300 ms in the time domain signal, it is determined that the brain electrical signals reach the preset threshold, and the corresponding played test content is the test content of interest of the user. If there is no significant peak at 300 ms in the time domain signal, it is determined that the brain electrical signals do not reach the preset threshold.

[0110] Here, the brain electrical signal analysis technology includes but is not limited to the conventional analysis technology of SSVEP and P300.

[0111] If it is determined that the brain electrical signals do not reach the preset threshold, it indicates that the user may not be very interested in the played test content, and then step S1 is repeated, and the test content needs to be reselected.

[0112] S32If yes, it is determined that the currently played test content is the test content of interest to the user;

[0113] If the brain electrical signal reaches a preset threshold, it is determined that the test content currently played corresponding to the brain electrical signal is the test content of interest to the user.

[0114] S33The test content of interest to the user is marked.

[0115] Here, the marking is not marking a certain segment or a certain area in the test content, but marking the test content, representing that the user is interested in the test content. The marked test content can be used in subsequent training.

[0116] S4Fusion of the marked test content and the predetermined training content to obtain a personalized guidance scheme;

[0117] The predetermined training content is a rehabilitation training resource for guiding attention on the market, including images, videos, music, etc. The training content includes an area of interest, wherein the area of interest is an area determined by a professional person that the user is expected to focus on. In this specification, the predetermined training content of the corresponding user is also different based on the different degrees of attention and different ages.

[0118] S41Based on the type of the marked test content, the predetermined training content is preprocessed;

[0119] The training content also includes a low attention area, which is audio, image or video content in the training content except the area of interest.

[0120] The type of test content includes but is not limited to images, audio and video. In an embodiment of the present specification, a predetermined training content is randomly selected, and a plurality of marked test contents are randomly searched, and based on the type of the marked test content, the predetermined training content is preprocessed. Specifically, based on the marked test content, the low attention area in the predetermined training content is edited. As a preferred, the editing includes content weakening and content segmentation, wherein the content weakening includes but is not limited to shortening the audio playing time, reducing the audio playing volume, shortening the image display time, reducing the image display proportion, and increasing the image transparency. The content segmentation includes dividing the video into multiple segments.

[0121] If the type of the training content is completely the same as the type of the test content, the fusion will be disordered, which is not conducive to the later guidance. Therefore, in another embodiment of the present specification, a predetermined training content is randomly selected, a predetermined number of labeled test contents are searched based on the type of the region of interest, and the type of the found test content is different from the type of the region of interest. The predetermined number is a number of test contents required for the fusion of a predetermined training content, which is determined by relevant personnel in advance. Wherein, if the region of interest is one or several pictures, the type of the region of interest is image; if the region of interest is a piece of music or a piece of sound, the type of the region of interest is audio; if the region of interest is an animation, the region of interest is video.

[0122] Then, based on the labeled test content, the low-attention region in the predetermined training content is edited.

[0123] In an embodiment of the present specification, taking the content weakening of the low-attention region in the predetermined training content as an example: if the type of the randomly selected training content is video and the type of the labeled test content is audio, the audio volume of the low-attention region in the training content is reduced.

[0124] If the type of the randomly selected training content is audio and the type of the labeled test content is video, the audio volume of the low-attention region in the training content is reduced.

[0125] If the type of the randomly selected training content is video and the type of the labeled test content is video, the audio volume of the low-attention region in the training content is reduced, and the image transparency of the low-attention region in the training content is increased.

[0126] S42 fuses the labeled test content and the preprocessed training content based on the region of interest to obtain a personalized guidance scheme.

[0127] The labeled test content is fused into the preprocessed training content based on the initial audiovisual resource parameters by using audio processing technology or image processing technology to obtain guidance content, and a personalized guidance scheme is determined based on multiple guidance contents to attract the attention of children and guide the movement and residence of the fixation point of children to normal social attention points. Wherein, the region of interest cannot be weakened and displayed. The initial audiovisual resource parameters include but are not limited to the initial display duration of the image in the labeled test content, the initial display frequency; the initial volume of the audio in the labeled test content, the periodicity.

[0128] S5 plays the personalized guidance scheme to the user and records the eye movement data of the user;

[0129] In an embodiment of the present disclosure, the eye movement data includes, but is not limited to, fixation time, fixation times, saccade speed, saccade duration, saccade amplitude, saccade latency, saccade direction, and eye movement trajectory.

[0130] Specifically, the eye movement data includes the first fixation time of the user on the region of interest, the dwell time, and the number of fixations in the region of interest.

[0131] The user is randomly played each guide content in the personalized guide scheme, and the eye movement data about the guide content is recorded.

[0132] S6 adjusts the personalized guide scheme based on the eye movement data by training the optimization model to assist in training the user's attention;

[0133] S61 obtains fixation point information about the region of interest based on the eye movement data;

[0134] In an embodiment of the present disclosure, a trajectory graph of eye movement data is generated by eye movement data, the fixation point information is determined in combination with the region of interest and the trajectory graph of eye movement data, and the fixation point information includes the first fixation time of the user on the region of interest, the dwell time, and the number of fixations in the region of interest. Each guide content corresponds to a trajectory graph of eye movement data.

[0135] S62 adjusts the marked test content based on the fixation point information by the training optimization model to obtain a new personalized guide scheme.

[0136] The personalized guide scheme is continuously trained, and the training optimization model dynamically adjusts the video resource parameters of the marked test content during the training process. Specifically, if the fixation point information of the user does not reach a preset threshold, the proportion of the marked test content in the guide content is increased in the next guide content, a new guide content is generated, and in an embodiment of the present disclosure, the display duration of the image in the marked test content is increased, the display frequency of the image in the marked test content is increased, the initial volume and periodicity of the audio in the marked test content are increased, and the proportion of the marked test content in the personalized guide scheme is increased.

[0137] If the fixation point information of the user reaches a preset threshold, the proportion of the marked test content in the guide content is reduced in the next guide content, a new guide content is generated, and in an embodiment of the present disclosure, the display duration of the image in the marked test content is reduced, the display frequency of the image in the marked test content is reduced, the initial volume and periodicity of the audio in the marked test content are reduced, and the proportion of the marked test content in the personalized guide scheme is weakened.

[0138] S7 attention evaluation and adjustment of the user.

[0139] In a preset time, the gaze point information of the plurality of regions of interest is collected in sequence; in an embodiment of the present specification, the preset time is 20 minutes.

[0140] According to the summary result of the gaze point information, the test content is adjusted. Specifically, based on the summary result of the plurality of gaze point information, it is judged whether the guiding effect is ideal.

[0141] If it is determined that the guiding effect is ideal, the test content does not need to be adjusted; if it is determined that the guiding effect is not ideal, it means that the selected test content does not effectively attract or guide the user's attention to the interest area in essence, so the test content needs to be adjusted, that is, steps S1-S6 are repeated, and the personalized guiding scheme is reselected.

[0142] The gaze point information includes the first gaze time of the user on the region of interest, the dwell time on the region of interest, and the number of gazes in the region of interest.

[0143] In an embodiment of the present specification, based on the gaze point information of the plurality of regions of interest collected in sequence, if the dwell time of the user on the region of interest is longer and longer, it is determined that the guiding effect is ideal, and if the dwell time of the user on the region of interest does not increase significantly or becomes shorter and shorter, it is determined that the guiding effect is not ideal.

[0144] In another embodiment of the present specification, based on the gaze point information of the plurality of regions of interest collected in sequence, if the first gaze time of the user on the region of interest is shorter and shorter, it is determined that the guiding effect is ideal, and if the first gaze time of the user on the region of interest does not fluctuate significantly or becomes longer and longer, it is determined that the guiding effect is not ideal.

[0145] Figure 3 The embodiment of the present specification provides a structure diagram of a personalized guiding scheme generation system, and the system comprises:

[0146] The searching module 301 is used for searching a plurality of test contents.

[0147] The collecting module 302 is used for randomly playing the test content and collecting the brain electrical signals of the user in real time.

[0148] The marking module 303 is used for determining and marking the test content interested by the user based on the analysis result of the brain electrical signals.

[0149] The fusion module 304 is used for fusing the marked test content and the pre-determined training content to obtain a personalized guiding scheme.

[0150] a recording module 305, configured to record eye movement data of the user while playing the personalized guide scheme to the user;

[0151] an optimization module 306, configured to adjust the personalized guide scheme by training an optimization model based on the eye movement data, to assist in training attention of the user.

[0152] Optionally, the searching module 301 comprises:

[0153] an interest information obtaining sub-module, configured to obtain interest information of the user;

[0154] a searching sub-module, configured to search for the test content matching the interest information in a resource library.

[0155] Optionally, the marking module 303 comprises:

[0156] a judging sub-module, configured to judge whether the EEG signal reaches a preset threshold based on a preset frequency;

[0157] a selecting sub-module, configured to, if yes, determine that the currently played test content is the test content of interest to the user;

[0158] a marking sub-module, configured to mark the test content of interest to the user.

[0159] Optionally, the fusion module 304 comprises:

[0160] the training content comprises a region of interest;

[0161] a preprocessing sub-module, configured to preprocess the predetermined training content based on a type of the marked test content;

[0162] a fusion sub-module, configured to fuse the marked test content and the preprocessed training content based on the region of interest, to obtain the personalized guide scheme.

[0163] Optionally, the optimization module 306 comprises:

[0164] a recording sub-module, configured to obtain gaze point information about the region of interest based on the eye movement data;

[0165] an optimization sub-module, configured to adjust the marked test content by the training optimization model based on the gaze point information, to obtain a new personalized guide scheme.

[0166] Optionally, the method further comprises an evaluation module.

[0167] the evaluation module comprises:

[0168] The collecting sub-module is configured to collect gaze point information of the plurality of regions of interest in sequence within a preset time.

[0169] The adjusting sub-module is configured to adjust the test content according to the summary result of the gaze point information.

[0170] The functions of the device of the embodiments of the present application have been described in the method embodiments described above, and thus the description of the present embodiments will not be described in detail, and the relevant description in the foregoing embodiments can be referred to.

[0171] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, device, or computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0172] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus generate a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The functions specified in one or more flows and / or blocks

[0173] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The functions specified in one or more flows and / or blocks

[0174] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1steps of the functions specified in the block or blocks.

[0175] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. A method for generating a personalized guidance scheme, characterized in that, include: Find several test items; The test content is played randomly, and the user's brainwave signals are collected in real time. Based on the analysis results of the EEG signals, the test content that the user is interested in is determined and marked; Based on the type of the labeled test content, the pre-determined training content is preprocessed; The training content includes regions of interest; wherein, a predetermined training content is randomly selected, multiple labeled test contents are randomly searched, and based on the labeled test contents, the low-interest regions in the predetermined training content are clipped. The labeled test content is integrated into the preprocessed training content to obtain a personalized guidance scheme; The personalized guidance plan is played to the user, and the user's eye movement data is recorded; Based on the eye-tracking data, a personalized guidance scheme is adjusted by training and optimizing the model to assist in training the user's attention.

2. The method as described in claim 1, characterized in that, The search for several test items includes: Obtain the user's interest information; Based on the interest information, the test content that matches it is searched in the resource library.

3. The method as described in claim 1, characterized in that, Based on the analysis results of the EEG signals, the user identifies and labels the test content of interest, including: Based on a preset frequency, determine whether the electroencephalogram (EEG) signal reaches a preset threshold. If so, then the currently playing test content is considered to be test content that the user is interested in; The test content that the user is interested in is marked.

4. The method as described in claim 1, characterized in that, The step of adjusting the personalized guidance scheme based on the eye-tracking data through training and optimization models to assist in training the user's attention includes: Based on the eye-tracking data, fixation point information about the region of interest is obtained; Based on the gaze point information, the labeled test content is adjusted through the training and optimization model to obtain a new personalized guidance scheme.

5. The method as described in claim 4, characterized in that, Also includes: Within a preset time period, gaze point information of multiple regions of interest is collected sequentially. The test content is adjusted based on the summarized results of the fixation point information.

6. A system for generating personalized guidance schemes, characterized in that, include: The search module is used to find a number of test items; The acquisition module is used to randomly play the test content and acquire the user's EEG signals in real time. A tagging module is used to determine and tag the test content that the user is interested in based on the analysis results of the EEG signals; The fusion module is used to preprocess predetermined training content based on the type of the labeled test content; The training content includes areas of interest; wherein, a predetermined training content is randomly selected, multiple labeled test content are randomly searched, and based on the labeled test content, low-interest areas in the predetermined training content are clipped; the labeled test content is then integrated into the pre-processed training content to obtain a personalized guidance scheme. The recording module is used to play the personalized guidance plan to the user and record the user's eye movement data; The adjustment module is used to adjust the personalized guidance scheme based on the eye-tracking data by training and optimizing the model, so as to assist in training the user's attention.

7. An electronic device, wherein, The electronic device includes: Processor; and, A memory storing computer-executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1-5.

8. A computer-readable storage medium, wherein, The computer-readable storage medium stores one or more programs that, when executed by a processor, implement the method of any one of claims 1-5.

Images