Reading ability assessment method and device, storage medium and electronic device

Through an assisted evaluation model based on brain image features, combining resting and task-state brain image data, the brain region distribution characteristics and collaborative correlation are determined, which solves the problem of low accuracy of existing reading ability evaluation methods and achieves more accurate Reading ability assessment.

CN114496244BActive Publication Date: 2024-11-05IFLYTEK CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111676931.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-31
Publication Date
2024-11-05
Estimated Expiration
2041-12-31

AI Technical Summary

Technical Problem

The evaluation accuracy of the existing reading ability evaluation methods is poor, relying on expert experience, time-consuming and labor-intensive, and inconsistent standards, which is not conducive to horizontal comparison of evaluation results.

Method used

Based on the brain image feature set of users to be evaluated, the brain region distribution feature set and brain interval collaboration correlation vector of each cognitive task are determined, and the reading ability evaluation results are generated using auxiliary evaluation models, combining resting and task-state brain image data. , extract features and perform JS divergence calculations to determine the brain area information and defect incidence of cognitive skills, and improve the accuracy and robustness of evaluation.

Benefits of technology

It improves the accuracy and robustness of reading ability assessment, can more accurately identify the brain area and brain interval cooperative relationships that cognitive task depend on, and provides more reliable evaluation results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114496244B_ABST
    Figure CN114496244B_ABST
Patent Text Reader

Abstract

The present disclosure discloses a reading ability assessment method and device, a storage medium and an electronic device, and relates to the field of cognitive neuroscience technology. The reading ability assessment method includes: based on the brain image feature set corresponding to the user to be assessed, determining the brain area distribution feature set corresponding to each of the M cognitive tasks, wherein the brain image feature set is determined based on the resting state brain image data and the task state brain image data of the user to be assessed, and the task state brain image data includes the brain image data taken during the execution of the M cognitive tasks; based on the brain area distribution feature set corresponding to each of the M cognitive tasks, determining the brain area collaboration correlation vector corresponding to the user to be assessed; using an auxiliary assessment model, based on the brain image feature set, the brain area distribution feature set corresponding to each of the M cognitive tasks, and the brain area collaboration correlation information, generating a reading ability assessment result. The present disclosure can improve the accuracy and robustness of the obtained reading ability assessment result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of cognitive neuroscience technology, and in particular to a reading ability assessment method and device, a storage medium, and an electronic device. Background Art

[0002] As we all know, for students, good reading ability is one of the necessary conditions for excellent academic performance. However, the reading ability of different students varies. Some students have better reading ability, while some students have poorer reading ability. Timely discovery of one's own reading ability defects and then taking corresponding practice improvement measures can help the corresponding group of people (such as students) to study and live better. However, the existing evaluation methods that rely on expert experience are not only inaccurate, but also time-consuming and labor-intensive. Summary of the invention

[0003] In view of this, the present disclosure provides a reading ability assessment method and device, a storage medium and an electronic device to solve the problem of poor assessment accuracy of existing reading ability assessment methods.

[0004] In a first aspect, an embodiment of the present disclosure provides a reading ability assessment method, which includes: determining a brain area distribution feature set corresponding to M cognitive tasks based on a brain image feature set corresponding to a user to be assessed, wherein the brain image feature set is determined based on resting-state brain image data and task-state brain image data of the user to be assessed, and the task-state brain image data includes brain image data taken during the execution of M cognitive tasks, where M is a positive integer; determining a collaborative correlation vector between brain regions corresponding to the user to be assessed based on a brain area distribution feature set corresponding to each of the M cognitive tasks; and utilizing an auxiliary assessment model to generate a reading ability assessment result corresponding to the user to be assessed based on the brain image feature set, the brain area distribution feature set corresponding to each of the M cognitive tasks, and the collaborative correlation information between brain regions.

[0005] In combination with the first aspect, in certain implementations of the first aspect, an auxiliary evaluation model is used to generate a reading ability evaluation result corresponding to the user to be evaluated based on a brain image feature set, a brain region distribution feature set corresponding to each of M cognitive tasks, and a collaborative correlation vector between brain regions, including: determining a cognitive feature set corresponding to the user to be evaluated based on defect incidence rates and brain image feature sets corresponding to each of N cognitive skills, wherein the N cognitive skills include cognitive skills corresponding to each of M cognitive tasks; determining an associated brain region feature set corresponding to the user to be evaluated based on dependent brain region information corresponding to each of the N cognitive skills and a brain region distribution feature set corresponding to each of the M cognitive tasks; splicing the cognitive feature set, the associated brain region feature set, and the collaborative correlation vector between brain regions to obtain evaluation index data corresponding to the user to be evaluated; and inputting the evaluation index data into the auxiliary evaluation model to obtain a reading ability evaluation result.

[0006] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: determining the dependent brain region information corresponding to each of the N cognitive skills. Wherein, determining the dependent brain region information corresponding to each of the N cognitive skills includes: for each of the N cognitive skills, obtaining the resting state brain image data samples and task state brain image data samples of H sample users, wherein the task state brain image data samples include the brain image data taken by the sample users during the cognitive tasks corresponding to the cognitive skills, and H is a positive integer; performing feature extraction on the resting state brain image data samples and task state brain image data samples of the H sample users, respectively, to determine the resting state feature set and task state feature set of the H users; based on the resting state feature set and task state feature set of the H users, respectively using JS divergence to calculate the signal distribution difference data of the same brain region of the H users; based on the signal distribution difference data of the same brain region of the H users, determining the dependent brain region information corresponding to the cognitive skill.

[0007] In combination with the first aspect, in certain implementations of the first aspect, the method also includes: determining literature data corresponding to each of the N cognitive skills; performing statistical analysis on the literature data corresponding to each of the N cognitive skills to obtain defect incidence rates corresponding to each of the N cognitive skills.

[0008] In combination with the first aspect, in certain implementations of the first aspect, the N cognitive skills include speech processing skills and / or orthographic skills.

[0009] In combination with the first aspect, in certain implementations of the first aspect, based on the brain area distribution feature sets corresponding to each of the M cognitive tasks, the brain area collaboration correlation vector corresponding to the user to be evaluated is determined, including: based on the brain area distribution feature sets corresponding to each of the M cognitive tasks, performing a summing and averaging operation to obtain a brain area distribution mean feature set; performing matrix decomposition on the brain area distribution mean feature set to select the largest K singular values ​​and the left singular vectors corresponding to the K singular values, where K is a positive integer; based on the K singular values ​​and the left singular vectors corresponding to the K singular values, generating a brain area collaboration correlation vector.

[0010] In combination with the first aspect, in certain implementations of the first aspect, based on the brain image feature set, a brain area distribution feature set corresponding to each of the M cognitive tasks is determined, including: based on S standard brain partition information, the brain image feature set is divided to obtain a mapping relationship between the feature data in the brain image feature set and the S standard brain partitions, where S is a positive integer; based on the mapping relationship, the brain area distribution feature set corresponding to each of the M cognitive tasks is determined.

[0011] In combination with the first aspect, in certain implementations of the first aspect, based on a mapping relationship, a set of brain region distribution features corresponding to each of the M cognitive tasks is determined, including: performing image quality assessment on resting-state brain image data and task-state brain image data to obtain image quality assessment weight data; based on the mapping relationship, determining an initial set of distribution features corresponding to each of the M cognitive tasks; and weighting the initial set of brain region distribution features based on the image quality assessment weight data to obtain a set of brain region distribution features.

[0012] In combination with the first aspect, in certain implementations of the first aspect, the method also includes: obtaining resting-state brain imaging data and task-state brain imaging data of Q sample users, where Q is a positive integer; obtaining evaluation index data corresponding to each of the Q sample users based on the resting-state brain imaging data and task-state brain imaging data of each of the Q sample users; training an initial network model based on the evaluation index data and reading ability label data corresponding to each of the Q sample users to obtain an auxiliary evaluation model.

[0013] In combination with the first aspect, in certain implementations of the first aspect, before determining the brain area distribution feature sets corresponding to each of the M cognitive tasks based on the brain image feature sets corresponding to the user to be evaluated, the method also includes: obtaining the resting-state brain image data and task-state brain image data of the user to be evaluated; performing feature extraction on the resting-state brain image data and the task-state brain image data, respectively, to obtain brain image feature sets for the M cognitive tasks.

[0014] In a second aspect, an embodiment of the present disclosure provides a reading ability assessment device, which includes: a first determination module, used to determine a brain area distribution feature set corresponding to each of M cognitive tasks based on a brain image feature set corresponding to the user to be assessed, wherein the brain image feature set is determined based on resting-state brain image data and task-state brain image data of the user to be assessed, and the task-state brain image data includes brain image data taken during the execution of M cognitive tasks, where M is a positive integer; a second determination module, used to determine a brain area collaboration correlation vector corresponding to the user to be assessed based on a brain area distribution feature set corresponding to each of the M cognitive tasks; and a generation module, used to generate a reading ability assessment result corresponding to the user to be assessed based on the brain image feature set, the brain area distribution feature set corresponding to each of the M cognitive tasks, and the brain area collaboration correlation information using an auxiliary assessment model.

[0015] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor, wherein the processor is used to execute the method mentioned in the first aspect above.

[0016] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the method mentioned in the first aspect.

[0017] Since the brain image feature set is determined based on resting state brain image data and task state brain image data, the disclosed embodiment can make full use of the signal distribution change differences between different brain regions before and after cognitive tasks, and then determine the brain regions that cognitive tasks rely on and the collaborative association relationship between brain regions based on the signal distribution change differences. It can be seen that, combined with the above data, the disclosed embodiment can use the auxiliary evaluation model to improve the accuracy and robustness of the obtained reading ability evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Shown is a schematic diagram of an application scenario provided by an embodiment of the present disclosure.

[0019] Figure 2 The figure is a flow chart of a reading ability assessment method provided in one embodiment of the present disclosure.

[0020] Figure 3 The figure is a schematic diagram of a process for generating a reading ability assessment result corresponding to a user to be assessed provided by an embodiment of the present disclosure.

[0021] Figure 4 The figure is a schematic diagram of a process for determining the dependent brain area information corresponding to each of N cognitive skills provided by an embodiment of the present disclosure.

[0022] Figure 5 Shown is a schematic diagram of brain region signal distribution differences provided by an embodiment of the present disclosure.

[0023] Figure 6 The figure is a schematic diagram of a process for generating a reading ability assessment result corresponding to a user to be assessed provided by an embodiment of the present disclosure.

[0024] Figure 7 The figure is a schematic diagram of a process of determining the brain region collaboration correlation vector corresponding to the user to be evaluated provided by an embodiment of the present disclosure.

[0025] Figure 8 The figure is a schematic diagram of a process for determining a set of brain region distribution features corresponding to each of M cognitive tasks provided by an embodiment of the present disclosure.

[0026] Fig. 9 The figure is a schematic diagram of a process for determining a set of brain region distribution features corresponding to each of M cognitive tasks provided by an embodiment of the present disclosure.

[0027] Fig.10 FIG. 4 is a schematic diagram of an image quality assessment method provided by an embodiment of the present disclosure.

[0028] Fig.11 The figure is a flow chart of a reading ability assessment method provided in one embodiment of the present disclosure.

[0029] Fig.12 Shown is a schematic diagram of the structure of a reading ability assessment device provided by an embodiment of the present disclosure.

[0030] Fig.13 Shown is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0032] Reading, as an activity to acquire information and knowledge, has extraordinary significance. For students, good reading ability is one of the necessary conditions for excellent academic performance. Reading ability can be comprehensively assessed based on abilities such as speech processing ability and rapid naming ability. However, the reading abilities of different students vary. Some students have better reading abilities, while some students have poorer reading abilities. Especially for students with dyslexia, poor reading ability even affects their daily study and life. Dyslexia refers to a state in which a person has normal intelligence and no obvious neurological or organic damage, but has difficulty acquiring effective reading skills and has special learning difficulties in reading. Timely discovery of one's own reading ability defects and the adoption of corresponding practice improvement measures can help the corresponding population (such as students) to study and live better.

[0033] Therefore, how to accurately evaluate reading ability has become an urgent problem to be solved. However, the main idea of ​​existing reading ability evaluation methods is to rely on expert experience for evaluation, which is time-consuming and labor-intensive, not only has low accuracy, but also has inconsistent standards, which is not conducive to horizontal comparison of evaluation results in multiple studies.

[0034] In order to solve the above problems, the embodiments of the present disclosure provide a reading ability assessment method and device, a storage medium and an electronic device to solve the problem of poor assessment accuracy of existing reading ability assessment methods.

[0035] Combine the following Figure 1 The application scenarios of the embodiments of the present disclosure are briefly introduced.

[0036] Figure 1 FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure. Figure 1As shown, the application scenario is a reading ability assessment scenario. Specifically, the reading ability assessment scenario includes a server 110, a user terminal 120 and a medical image acquisition device 130 respectively connected to the server 110 for communication. An auxiliary assessment model is deployed in the server 110, and the server 110 is used to execute the reading ability assessment method mentioned in the embodiment of the present disclosure. The user terminal 120 can be a terminal device of the user. It can be understood that the user can be a student user, a parent user or a teacher user, and the embodiments of the present disclosure will not be repeated one by one.

[0037] For example, in actual application, the user uses the user terminal 120 to send a reading ability assessment instruction for user A to the server 110. After receiving the instruction, the server 110 retrieves the brain image data (including resting state brain image data and task state brain image data) of user A from the medical image acquisition device 130, generates the reading ability assessment result of user A based on the brain image data and the auxiliary assessment model, and then sends the reading ability assessment result to the user terminal 120 so that the user terminal 120 presents the result to the user.

[0038] Exemplarily, the training method of the auxiliary evaluation model deployed in the server 110 includes: obtaining resting state brain image data and task state brain image data of each Q sample user, where Q is a positive integer; obtaining evaluation index data corresponding to each Q sample user based on the resting state brain image data and task state brain image data of each Q sample user; training the initial network model based on the evaluation index data and reading ability label data corresponding to each Q sample user to obtain the auxiliary evaluation model. Correspondingly, in the actual application process, the input of the auxiliary evaluation model is the evaluation index data corresponding to the user to be evaluated (obtained by processing the brain image data of the user to be evaluated), and the output is the reading ability evaluation result of the user to be evaluated.

[0039] Exemplarily, the user terminal 120 mentioned above includes but is not limited to a mobile terminal such as a tablet computer, a mobile phone, etc. The medical image acquisition device 130 includes but is not limited to a functional Magnetic Resonance Imaging (fMRI) device.

[0040] Combine the following Figures 2 to 11 A brief introduction to the reading ability assessment method disclosed in the present invention is given.

[0041] Figure 2 FIG. 2 is a flow chart of a method for evaluating reading ability provided by an embodiment of the present disclosure. Figure 2 As shown, the reading ability assessment method provided by the embodiment of the present disclosure includes the following steps.

[0042] Step S210, based on the brain image feature set corresponding to the user to be evaluated, determine the brain region distribution feature set corresponding to each of the M cognitive tasks, where M is a positive integer.

[0043] The user to be evaluated refers to a user who needs to have his / her reading ability evaluated. The user to be evaluated may be a student, a teacher, a student's parent, or a social worker, and the embodiments of the present disclosure do not impose a uniform limitation on this.

[0044] Exemplarily, the brain image feature set is determined based on the resting state brain image data and the task state brain image data of the user to be evaluated. For example, the brain image feature set is obtained by extracting features from the resting state brain image data and the task state brain image data. Among them, the resting state brain image data includes the brain image data of the user to be evaluated in the closed eye state. The task state brain image data includes the brain image data taken by the user to be evaluated during the execution of M cognitive tasks.

[0045] It is understandable that the cognitive task can be set according to the actual situation, as long as it can test the cognitive ability of the user to be evaluated. For example, the cognitive task is to judge whether the head direction of the fish swimming on the screen is the same as that of the fish in front of it by pressing the buttons "3" and "4" of the game controller.

[0046] After obtaining the brain image feature set, the cognitive task performed by the user to be evaluated is used as the classification basis to determine the brain region distribution feature set corresponding to each of the M cognitive tasks. The brain region distribution feature set corresponding to the cognitive task refers to the feature set of the brain region relied on when performing the cognitive task.

[0047] Step S220 , based on the brain region distribution feature sets corresponding to each of the M cognitive tasks, determine the brain region collaboration correlation vector corresponding to the user to be evaluated.

[0048] Exemplarily, the inter-brain area collaborative correlation vector can represent the collaborative correlation relationship between brain areas when the user to be evaluated performs a cognitive task.

[0049] Step S230, using the auxiliary evaluation model, based on the brain image feature set, the brain region distribution feature set corresponding to each of the M cognitive tasks, and the inter-brain region collaborative correlation information, generates a reading ability evaluation result corresponding to the user to be evaluated.

[0050] Exemplarily, the auxiliary evaluation model is an integrated learning model. More specifically, the auxiliary evaluation model includes a primary classifier and a training classifier (also called a secondary classifier). The primary classifier includes but is not limited to a random forest, a support vector machine, a K-nearest neighbor classifier, etc. Correspondingly, the secondary classifier can be implemented based on a logistic regression method to avoid overfitting of the model.

[0051] In some embodiments, the brain image feature set, the brain region distribution feature set corresponding to each of the M cognitive tasks, and the collaborative correlation information between brain regions are spliced, and the splicing result is input into the auxiliary evaluation model to obtain the reading ability evaluation result.

[0052] Exemplarily, in actual application, first, based on the brain image feature set corresponding to the user to be evaluated, the brain area distribution feature set corresponding to each of the M cognitive tasks is determined, and then based on the brain area distribution feature set corresponding to each of the M cognitive tasks, the brain area collaborative correlation vector corresponding to the user to be evaluated is determined. Subsequently, an auxiliary evaluation model is used to generate a reading ability evaluation result corresponding to the user to be evaluated based on the brain image feature set, the brain area distribution feature set corresponding to each of the M cognitive tasks, and the brain area collaborative correlation information.

[0053] Since the brain image feature set is determined based on resting state brain image data and task state brain image data, the disclosed embodiment can make full use of the signal distribution change differences between different brain regions before and after cognitive tasks, and then determine the brain regions that cognitive tasks rely on and the collaborative association relationship between brain regions based on the signal distribution change differences. It can be seen that, combined with the above data, the disclosed embodiment can use the auxiliary evaluation model to improve the accuracy and robustness of the obtained reading ability evaluation results.

[0054] To further clarify the use of the auxiliary evaluation model, Figure 3 This paper gives an example to illustrate how to use the auxiliary assessment model to generate reading ability assessment results.

[0055] Figure 3 The figure shows a flow chart of generating a reading ability evaluation result corresponding to a user to be evaluated provided by an embodiment of the present disclosure. Figure 2 Based on the embodiment shown, Figure 3 The embodiment shown is described below in detail. Figure 3 The embodiment shown and Figure 2 The differences and similarities of the illustrated embodiments are not described in detail.

[0056] like Figure 3 As shown, in the embodiment of the present disclosure, an auxiliary evaluation model is used to generate a reading ability evaluation result corresponding to the user to be evaluated based on a brain image feature set, a brain region distribution feature set corresponding to each of M cognitive tasks, and brain region collaborative correlation information, including the following steps.

[0057] Step S310, based on the defect incidence rates and brain image feature sets corresponding to the N cognitive skills, a cognitive feature set corresponding to the user to be evaluated is determined, where N is a positive integer.

[0058] It can be understood that cognitive skills (also known as cognitive behavioral skills) can be used as reference factors for assessing reading ability, including but not limited to calculation cognitive skills, rapid naming skills, phonetic processing skills and orthographic skills.

[0059] Exemplarily, the N cognitive skills include cognitive skills corresponding to each of the M cognitive tasks. That is, each cognitive task corresponds to one or more cognitive skills, and the cognitive skills corresponding to each of the M cognitive tasks are all included in the above N cognitive skills. In some embodiments, the N cognitive skills can be regarded as all conventional cognitive skills.

[0060] The defect incidence rate corresponding to each of the N cognitive skills can be predetermined. For example, statistical analysis is performed in advance on the contents recorded in the relevant papers and documents to obtain the defect incidence rate corresponding to each of the N cognitive skills. The specific implementation method of step S310 can be to extract features from the brain image feature set according to specific cognitive skill task rules, extract relevant indicator features (such as accuracy, reaction time, and hesitation time, etc.), and then obtain features relative to cognition, and then use the defect incidence rate corresponding to each of the N cognitive skills obtained by statistics to weight the extracted features relative to cognition, so as to obtain a cognitive feature set corresponding to the user to be evaluated.

[0061] Step S320, based on the dependent brain area information corresponding to each of the N cognitive skills and the brain area distribution feature set corresponding to each of the M cognitive tasks, determine the associated brain area feature set corresponding to the user to be evaluated.

[0062] Similarly, the dependent brain region information corresponding to each of the N cognitive skills may also be predetermined. The associated brain region feature set refers to a feature set that can characterize the collaborative association relationship of the brain regions of the user to be evaluated.

[0063] Step S330, concatenating the cognitive feature set, the associated brain region feature set and the inter-brain region collaborative correlation vector to obtain evaluation index data corresponding to the user to be evaluated.

[0064] Step S340: input the evaluation index data into the auxiliary evaluation model to obtain the reading ability evaluation result.

[0065] Since the evaluation index data is obtained by splicing the cognitive feature set, the associated brain region feature set and the inter-brain region collaborative correlation vector, the evaluation index data can characterize the brain region collaborative characteristics and cognitive ability characteristics of the user to be evaluated. It can be seen that the embodiment of the present disclosure can further improve the evaluation accuracy and robustness based on the evaluation index data.

[0066] Combine the following Figure 4 The specific implementation method of determining the dependent brain area information corresponding to each of N cognitive skills is illustrated by examples. Figure 4The figure shows a flow chart of determining the dependent brain region information corresponding to each of N cognitive skills provided by an embodiment of the present disclosure. Figure 3 Based on the embodiment shown, Figure 4 The embodiment shown is described below in detail. Figure 4 The embodiment shown and Figure 3 The differences and similarities of the illustrated embodiments are not described in detail.

[0067] like Figure 4 As shown, in the embodiment of the present disclosure, for each of the N cognitive skills, the following steps S410 to S440 are performed.

[0068] Step S410, obtaining resting state brain image data samples and task state brain image data samples of H sample users, where H is a positive integer.

[0069] Step S420 , performing feature extraction on the resting-state brain image data samples and task-state brain image data samples of the H sample users respectively, and determining the resting-state feature set and task-state feature set of the H users respectively.

[0070] Exemplarily, the brain is divided into 90 brain regions (i.e., the S brain regions mentioned in the following embodiments) according to the preset standard brain partition information. For the brain image evaluation feature set of different brain regions (for functional images and resting states), the following image features are extracted using an image analysis third-party library tool (such as FREESURFER or FSL).

[0071] Specifically, brain image features such as signal-to-noise ratio, signal mean and variance, and offline fitting coefficients are extracted from the time dimension; brain image features such as whole-brain gray matter volume, cortical surface area, brain volume, and fold level are extracted from the spatial dimension; the features in the above time and space dimensions are spliced ​​to obtain the individual user's brain image evaluation feature set (i.e., resting state feature set and task state feature set).

[0072] Step S430: Based on the resting-state feature sets and task-state feature sets of the H users, the signal distribution difference data of the same brain regions of the H users are calculated using JS divergence.

[0073] For each of the H users, 90 pairs of brain region signal distribution difference data are extracted. To further clarify the signal distribution difference of each brain region, the Figure 5 Schematic diagram of the differences in signal distribution in the P brain area is shown.

[0074] Step S440: determining the dependent brain region information corresponding to the cognitive skill based on the signal distribution difference data of the same brain region of each of the H users.

[0075] It can be understood that the greater the difference in signal distribution of the same brain region, the more dependent the cognitive skill is on the brain region. Optionally, based on the signal difference distribution data of the same brain region corresponding to each of the 90 pairs of different brain regions, the top three brain regions with the largest differences (i.e., top3) are selected as the dependent brain regions corresponding to the cognitive skill.

[0076] Based on the method mentioned in the embodiment of the present disclosure, it is possible to accurately analyze and obtain the dependent brain area information corresponding to each of N cognitive skills, thereby providing a prerequisite for the subsequent accurate assessment of reading ability.

[0077] Combine the following Figure 6 The specific method of determining the defect incidence rate corresponding to each of N cognitive skills is illustrated by examples.

[0078] Figure 6 The figure shows a flow chart of generating a reading ability evaluation result corresponding to a user to be evaluated provided by an embodiment of the present disclosure. Figure 3 Based on the embodiment shown, Figure 6 The embodiment shown is described below in detail. Figure 6 The embodiment shown and Figure 3 The differences and similarities of the illustrated embodiments are not described in detail.

[0079] like Figure 6 As shown, in the embodiment of the present disclosure, before the step of determining the cognitive feature set corresponding to the user to be evaluated based on the defect incidence rates and brain image feature sets corresponding to each of the N cognitive skills, the following steps are also included.

[0080] Step S610: determining the literature data corresponding to each of the N cognitive skills.

[0081] For example, CNKI (China National Knowledge Infrastructure) and Web of Science databases were used to collect literature articles on cognitive skills, and then the literature articles were screened and coded to obtain literature data. The coded information mainly includes (1) the title of the paper, author, region and publication time, etc.; (2) the basic characteristics of the research subjects, including the intelligence level, age, screening criteria, etc. of the samples of each group; (3) the outcome indicators and result measurement data of the research, such as the number of people with rapid naming skill defects and other related indicators.

[0082] Step S620: Statistically analyze the literature data corresponding to each of the N cognitive skills to obtain the defect incidence rate corresponding to each of the N cognitive skills.

[0083] Exemplarily, statistical analysis is performed on the literature data using statistical analysis software (such as a Meta-analysis package) to obtain the defect incidence rates corresponding to each of the N cognitive skills.

[0084] The disclosed embodiment can obtain the defect incidence rate corresponding to each of the N cognitive skills with good accuracy. If the cognitive characteristics of the above-mentioned user to be evaluated are weighted based on the obtained defect incidence rate, the representation ability of the obtained cognitive feature set can be further improved, and finally the accuracy of the reading ability evaluation result can be further improved.

[0085] Combine the following Figure 7 An example is given to illustrate the specific method of determining the brain region collaboration correlation vector corresponding to the user to be evaluated. Figure 7 FIG. 1 is a flow chart of determining the brain region collaboration correlation vector corresponding to the user to be evaluated according to an embodiment of the present disclosure. Figure 2 Based on the embodiment shown, Figure 7 The embodiment shown is described below in detail. Figure 7 The embodiment shown and Figure 2 The differences and similarities of the illustrated embodiments are not described in detail.

[0086] like Figure 7 As shown, in the embodiment of the present disclosure, based on the brain region distribution feature sets corresponding to each of the M cognitive tasks, the step of determining the brain region collaboration correlation vector corresponding to the user to be evaluated includes the following steps.

[0087] Step S710, based on the brain region distribution feature sets corresponding to each of the M cognitive tasks, a summing and averaging operation is performed to obtain a brain region distribution mean feature set.

[0088] Step S720, performing matrix decomposition on the brain region distribution mean feature set, and selecting the largest K singular values ​​and the left singular vectors corresponding to the K singular values.

[0089] Step S730: Generate an inter-brain area collaborative correlation vector based on the K singular values ​​and the left singular vectors corresponding to the K singular values, where K is a positive integer.

[0090] For example, M=3, and the Pearson correlation is used to calculate the brain region distribution feature sets corresponding to the three cognitive tasks, and three correlation matrices A1, A2 and A3 are obtained. Then, the three correlation matrices A, A2 and A3 are summed and averaged to obtain the brain region distribution mean feature set A_mean (dimension is n*n). Then, matrix decomposition is performed on A_mean, and the largest K singular values ​​and their corresponding left singular vectors (dimension is n*k) are selected as the association pattern information that depends on the collaboration between brain regions (i.e., the brain region collaboration correlation vector).

[0091] The disclosed embodiment can obtain the inter-brain area collaboration correlation vector representing the brain area collaboration information of the user to be evaluated, thereby providing a prerequisite for further improving the evaluation accuracy.

[0092] Combine the following Figure 8 and Fig. 9 The specific implementation method of the brain area distribution feature set corresponding to each of M cognitive tasks is illustrated by examples.

[0093] Figure 8 FIG. 1 is a flow chart of determining a set of brain region distribution features corresponding to each of M cognitive tasks provided by an embodiment of the present disclosure. Figure 2 Based on the embodiment shown, Figure 8 The embodiment shown is described below in detail. Figure 8 The embodiment shown and Figure 2 The differences and similarities of the illustrated embodiments are not described in detail.

[0094] like Figure 8 As shown, in the embodiment of the present disclosure, based on the brain image feature set, the step of determining the brain area distribution feature set corresponding to each of the M cognitive tasks includes the following steps (steps S810 and S820).

[0095] Step S810, based on the S standard brain partition information, the brain image feature set is divided to obtain a mapping relationship between the feature data in the brain image feature set and the S standard brain partitions, where S is a positive integer.

[0096] Exemplarily, the S standard brain regions refer to standard brain regions, such as the 90 brain regions mentioned above.

[0097] Step S820: Based on the mapping relationship, determine the brain region distribution feature sets corresponding to each of the M cognitive tasks.

[0098] In other words, based on the mapping relationship, the set of brain area distribution features corresponding to each cognitive task is determined.

[0099] Furthermore, if Fig. 9 As shown, in some embodiments, based on the mapping relationship, the step of determining a set of brain region distribution features corresponding to each of the M cognitive tasks includes the following steps (steps S910 to S930).

[0100] Step S910: performing image quality assessment on the resting state brain image data and the task state brain image data to obtain image quality assessment weight data.

[0101] Since image quality can affect the accuracy of evaluation, the embodiment of the present disclosure uses image quality evaluation weight data to further improve the rationality of the evaluation results, making the evaluation results closer to the real results.

[0102] Fig.10 FIG. 1 is a schematic diagram of an image quality assessment method provided by an embodiment of the present disclosure. Fig.10As shown in the figure, the image analysis tool is used to perform multi-dimensional analysis on the image, mainly to extract relevant image quality control evaluation features from the perspectives of signal stability, magnetic field uniformity, geometric deformation and artifact level, such as signal-to-noise ratio, artifact level, foreground-background energy ratio, etc., and finally obtain the image quality assessment weight data.

[0103] exist Fig.10 Indicators 1 to 8 are indicators such as signal-to-noise ratio and artifact level, and dimensions 1 to E are dimensions such as signal stability and magnetic field uniformity. In actual application, the weighted summation is performed from bottom to top, and finally the comprehensive score of brain imaging data quality assessment (i.e., image quality assessment weight data) is obtained.

[0104] Step S920: determining the initial distribution feature sets corresponding to the M cognitive tasks based on the mapping relationship.

[0105] Step S930: weighting the initial brain region distribution feature set based on the image quality assessment weight data to obtain a brain region distribution feature set.

[0106] The disclosed embodiments fully consider the impact of image quality on the evaluation results, thereby further improving the accuracy of the evaluation results.

[0107] It can be understood that the auxiliary evaluation model mentioned in the above embodiment is obtained by training the initial network model. Fig.11 This article gives an example to illustrate the training method of the auxiliary evaluation model.

[0108] Fig.11 FIG. 1 is a flow chart of a reading ability assessment method provided by an embodiment of the present disclosure. Figure 2 Based on the embodiment shown, Fig.11 The embodiment shown is described below in detail. Fig.11 The embodiment shown and Figure 2 The differences and similarities of the illustrated embodiments are not described in detail.

[0109] like Fig.11 As shown, the embodiment of the present disclosure also includes the following steps.

[0110] Step S1110, obtaining resting state brain image data and task state brain image data of Q sample users, where Q is a positive integer.

[0111] For example, in actual application, Q sample users are grouped into a group with poor reading ability (also known as a reading disability group) and a group with normal reading ability (also known as a normal control group). Then, based on the image quality index, the resting state brain imaging data and task state brain imaging data of the Q sample users are grouped into an excellent group and a qualified group. Optionally, if the imaging data is considered poor, the sample user needs to be recalled for retesting.

[0112] Step S1120: Based on the resting-state brain image data and task-state brain image data of the Q sample users, obtain evaluation index data corresponding to each of the Q sample users.

[0113] It can be understood that the evaluation index data corresponding to each of the Q sample users can be generated with reference to the method for generating the evaluation index data corresponding to the to-be-evaluated user mentioned in the above embodiment.

[0114] Step S1130: Based on the evaluation index data and reading ability label data corresponding to each of the Q sample users, an initial network model is trained to obtain an auxiliary evaluation model.

[0115] In some embodiments, the model structures of the initial network model and the auxiliary evaluation model are the same, and the difference lies in the model parameters. That is, the initial network model is trained based on the training data set of the model, and the model parameters of the initial network model are adjusted to obtain the auxiliary evaluation model.

[0116] The embodiment of the present disclosure can train an auxiliary evaluation model suitable for reading ability evaluation scenarios. Based on this, the embodiment of the present disclosure provides a prerequisite for improving the accuracy of evaluation and optimizing the evaluation effect by means of the auxiliary evaluation model obtained through training.

[0117] In some embodiments, before determining the brain area distribution feature sets corresponding to the M cognitive tasks based on the brain image feature set corresponding to the user to be evaluated, it also includes: obtaining the resting state brain image data and the task state brain image data of the user to be evaluated; performing feature extraction on the resting state brain image data and the task state brain image data respectively to obtain the brain image feature set for the M cognitive tasks. Furthermore, during the image acquisition process, the user to be evaluated is reminded to keep his head still. In addition, after obtaining the resting state brain image data and the task state brain image data, a relational database is used to clean the data for missing values, outliers, etc.

[0118] Combination of the above Figures 2 to 11 , describes in detail the method embodiment of the present disclosure, and the following is combined with Fig.12 and Fig.13, describes the device embodiment of the present disclosure in detail. In addition, it should be understood that the description of the method embodiment corresponds to the description of the device embodiment, so the parts not described in detail can refer to the previous method embodiment.

[0119] Fig.12 FIG. 1 is a schematic diagram of the structure of a reading ability assessment device provided by an embodiment of the present disclosure. Fig.12 As shown, the reading ability assessment device provided by the embodiment of the present disclosure includes a first determination module 1210, a second determination module 1220 and a generation module 1230. Specifically, the first determination module 1210 is used to determine the brain region distribution feature set corresponding to each of the M cognitive tasks based on the brain image feature set corresponding to the user to be assessed, wherein the brain image feature set is determined based on the resting state brain image data and the task state brain image data of the user to be assessed, and the task state brain image data includes the brain image data taken during the execution of the M cognitive tasks, and M is a positive integer. The second determination module 1220 is used to determine the brain region collaborative correlation vector corresponding to the user to be assessed based on the brain region distribution feature set corresponding to each of the M cognitive tasks. The generation module 1230 is used to generate the reading ability assessment result corresponding to the user to be assessed based on the brain image feature set, the brain region distribution feature set corresponding to each of the M cognitive tasks, and the brain region collaborative correlation information using the auxiliary assessment model.

[0120] In some embodiments, the generation module 1230 is also used to determine the cognitive feature set corresponding to the user to be evaluated based on the defect incidence rate and brain image feature set corresponding to each of N cognitive skills, wherein the N cognitive skills include cognitive skills corresponding to each of M cognitive tasks; determine the associated brain region feature set corresponding to the user to be evaluated based on the dependent brain region information corresponding to each of the N cognitive skills and the brain region distribution feature set corresponding to each of the M cognitive tasks; splice the cognitive feature set, the associated brain region feature set and the brain region collaborative correlation vector to obtain the evaluation index data corresponding to the user to be evaluated; input the evaluation index data into the auxiliary evaluation model to obtain the reading ability evaluation result.

[0121] In some embodiments, the generation module 1230 is also used to determine the dependent brain region information corresponding to each of the N cognitive skills. Determining the dependent brain region information corresponding to each of the N cognitive skills includes: for each of the N cognitive skills, obtaining the resting state brain image data samples and task state brain image data samples of H sample users, wherein the task state brain image data samples include the brain image data taken by the sample users during the cognitive task corresponding to the cognitive skill, and H is a positive integer; performing feature extraction on the resting state brain image data samples and task state brain image data samples of the H sample users, respectively, to determine the resting state feature set and task state feature set of the H users; based on the resting state feature set and task state feature set of the H users, respectively using JS divergence to calculate the signal distribution difference data of the same brain region of the H users; based on the signal distribution difference data of the same brain region of the H users, determining the dependent brain region information corresponding to the cognitive skill.

[0122] In some embodiments, the generation module 1230 is further used to determine the literature data corresponding to each of the N cognitive skills; perform statistical analysis on the literature data corresponding to each of the N cognitive skills, and obtain the defect incidence rate corresponding to each of the N cognitive skills.

[0123] In some embodiments, the generation module 1230 is also used to perform summing and averaging operations based on the brain area distribution feature sets corresponding to each of the M cognitive tasks to obtain a brain area distribution mean feature set; perform matrix decomposition on the brain area distribution mean feature set to select the largest K singular values ​​and the left singular vectors corresponding to the K singular values, where K is a positive integer; and generate an area-brain collaborative correlation vector based on the K singular values ​​and the left singular vectors corresponding to the K singular values.

[0124] In some embodiments, the first determination module 1210 is also used to divide the brain image feature set based on S standard brain partition information, obtain a mapping relationship between the feature data in the brain image feature set and the S standard brain partitions, where S is a positive integer; based on the mapping relationship, determine the brain area distribution feature set corresponding to each of the M cognitive tasks.

[0125] In some embodiments, the first determination module 1210 is also used to perform image quality assessment on resting-state brain image data and task-state brain image data to obtain image quality assessment weight data; based on the mapping relationship, determine the initial distribution feature set corresponding to each of the M cognitive tasks; and weight the initial brain region distribution feature set based on the image quality assessment weight data to obtain a brain region distribution feature set.

[0126] In some embodiments, the reading ability assessment device also includes a training module, which is used to obtain resting-state brain image data and task-state brain image data of Q sample users, where Q is a positive integer; based on the resting-state brain image data and task-state brain image data of the Q sample users, obtain evaluation index data corresponding to each of the Q sample users; based on the evaluation index data and reading ability label data corresponding to each of the Q sample users, train the initial network model to obtain an auxiliary assessment model.

[0127] Fig.13 Shown is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Fig.13 The electronic device 1300 shown (the electronic device 1300 may be a computer device) includes a memory 1301, a processor 1302, a communication interface 1303 and a bus 1304. The memory 1301, the processor 1302 and the communication interface 1303 are connected to each other through the bus 1304.

[0128] The memory 1301 may be a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory 1301 may store a program. When the program stored in the memory 1301 is executed by the processor 1302, the processor 1302 and the communication interface 1303 are used to execute the various steps of the reading ability assessment method of the embodiment of the present disclosure.

[0129] The processor 1302 can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), a graphics processing unit (GPU) or one or more integrated circuits to execute relevant programs to implement the functions that need to be performed by the units in the reading ability assessment device of the embodiment of the present disclosure.

[0130] The processor 1302 may also be an integrated circuit chip with signal processing capability. In the implementation process, each step of the reading ability assessment method disclosed in the present invention may be completed by an integrated logic circuit of hardware or software instructions in the processor 1302. The above-mentioned processor 1302 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 1301, and the processor 1302 reads the information in the memory 1301, and combines its hardware to complete the functions required to be performed by the units included in the reading ability assessment device of the embodiment of the present disclosure, or executes the reading ability assessment method of the method embodiment of the present disclosure.

[0131] The communication interface 1303 uses a transceiver such as, but not limited to, a transceiver to implement communication between the electronic device 1300 and other devices or a communication network. For example, brain image data can be acquired through the communication interface 1303 .

[0132] The bus 1304 may include a path for transmitting information between various components of the electronic device 1300 (eg, the memory 1301 , the processor 1302 , and the communication interface 1303 ).

[0133] It should be noted that although Fig.13 The electronic device 1300 shown only shows a memory, a processor, and a communication interface, but in the specific implementation process, those skilled in the art should understand that the electronic device 1300 also includes other devices necessary for normal operation. At the same time, according to specific needs, those skilled in the art should understand that the electronic device 1300 may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the electronic device 1300 may also only include the devices necessary to implement the embodiments of the present disclosure, and does not necessarily include Fig.13 All devices shown in .

[0134] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0136] In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0139] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.

[0140] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A reading ability assessment method, characterized in that: include: Based on the brain image feature set corresponding to the user to be evaluated, determine the brain area distribution feature set corresponding to each of the M cognitive tasks, wherein the brain image feature set is determined based on the resting state brain image data and the task state brain image data of the user to be evaluated, the task state brain image data includes the brain image data taken during the execution of the M cognitive tasks, and M is a positive integer; Determining the brain region collaboration correlation vector corresponding to the user to be evaluated based on the brain region distribution feature sets corresponding to each of the M cognitive tasks; Using the auxiliary evaluation model, based on the brain image feature set, the brain region distribution feature set corresponding to each of the M cognitive tasks, and the brain region collaborative correlation vector, a reading ability evaluation result corresponding to the user to be evaluated is generated; The auxiliary evaluation model is used to generate a reading ability evaluation result corresponding to the user to be evaluated based on the brain image feature set, the brain region distribution feature set corresponding to each of the M cognitive tasks, and the brain region collaborative correlation vector, including: Determining a cognitive feature set corresponding to the user to be evaluated based on defect incidence rates corresponding to each of the N cognitive skills and the brain image feature set, wherein the N cognitive skills include cognitive skills corresponding to each of the M cognitive tasks; Determine a set of associated brain region features corresponding to the user to be evaluated based on the dependent brain region information corresponding to each of the N cognitive skills and a set of brain region distribution features corresponding to each of the M cognitive tasks; splicing the cognitive feature set, the associated brain region feature set and the inter-brain region collaborative correlation vector to obtain evaluation index data corresponding to the user to be evaluated; Inputting the evaluation index data into the auxiliary evaluation model to obtain the reading ability evaluation result; The training method of the auxiliary evaluation model includes: obtaining resting-state brain image data and task-state brain image data of Q sample users, where Q is a positive integer; obtaining evaluation index data corresponding to each of the Q sample users based on the resting-state brain image data and task-state brain image data of the Q sample users; and training an initial network model based on the evaluation index data and reading ability label data corresponding to each of the Q sample users to obtain the auxiliary evaluation model.

2. The reading ability assessment method according to claim 1, characterized in that: Also includes: Determining the dependent brain area information corresponding to each of the N cognitive skills; Wherein, determining the dependent brain area information corresponding to each of the N cognitive skills includes: For each of the N cognitive skills, Acquire resting-state brain image data samples and task-state brain image data samples of H sample users, wherein the task-state brain image data samples include brain image data taken by the sample users during the process of performing the cognitive task corresponding to the cognitive skill, and H is a positive integer; Performing feature extraction on the resting-state brain image data samples and task-state brain image data samples of the H sample users respectively, and determining the resting-state feature set and task-state feature set of the H sample users respectively; Based on the resting state feature sets and task state feature sets of the H sample users, respectively calculating the signal distribution difference data of the same brain region of the H sample users using JS divergence; Based on the signal distribution difference data of the same brain region of each of the H sample users, the dependent brain region information corresponding to the cognitive skill is determined.

3. The reading ability assessment method according to claim 1, characterized in that: Also includes: Determine the literature data corresponding to each of the N cognitive skills; Statistical analysis is performed on the literature data corresponding to each of the N cognitive skills to obtain the defect incidence rates corresponding to each of the N cognitive skills.

4. The reading ability assessment method according to claim 1, characterized in that: The N cognitive skills include phonological processing skills and / or orthographic skills.

5. The reading ability assessment method according to any one of claims 1 to 4, characterized in that: The determining of the brain region collaboration correlation vector corresponding to the user to be evaluated based on the brain region distribution feature sets corresponding to each of the M cognitive tasks includes: Based on the brain region distribution feature sets corresponding to each of the M cognitive tasks, a summing and averaging operation is performed to obtain a brain region distribution mean feature set; Performing matrix decomposition on the brain region distribution mean feature set, selecting the largest K singular values ​​and the left singular vectors corresponding to the K singular values, where K is a positive integer; The inter-brain area collaborative correlation vector is generated based on the K singular values ​​and the left singular vectors corresponding to each of the K singular values.

6. The reading ability assessment method according to any one of claims 1 to 4, characterized in that: The determining, based on the brain image feature set, a brain region distribution feature set corresponding to each of the M cognitive tasks comprises: Based on S standard brain partition information, the brain image feature set is divided to obtain a mapping relationship between feature data in the brain image feature set and S standard brain partitions, where S is a positive integer; Based on the mapping relationship, a set of brain region distribution features corresponding to each of the M cognitive tasks is determined.

7. The reading ability assessment method according to claim 6, characterized in that: Based on the mapping relationship, determining the brain region distribution feature sets corresponding to each of the M cognitive tasks includes: Performing image quality assessment on the resting-state brain image data and the task-state brain image data to obtain image quality assessment weight data; Based on the mapping relationship, determining an initial brain region distribution feature set corresponding to each of the M cognitive tasks; The initial brain region distribution feature set is weighted based on the image quality assessment weight data to obtain the brain region distribution feature set.

8. The reading ability assessment method according to any one of claims 1 to 4, characterized in that: Before determining the brain area distribution feature sets corresponding to the M cognitive tasks based on the brain image feature set corresponding to the user to be evaluated, the method further includes: Acquiring the resting-state brain image data and the task-state brain image data of the user to be evaluated; Feature extraction is performed on the resting-state brain image data and the task-state brain image data respectively to obtain the brain image feature sets for the M cognitive tasks.

9. A reading ability assessment device, characterized in that: include: A first determination module is used to determine the brain area distribution feature set corresponding to each of the M cognitive tasks based on the brain image feature set corresponding to the user to be evaluated, wherein the brain image feature set is determined based on the resting state brain image data and the task state brain image data of the user to be evaluated, the task state brain image data includes the brain image data taken during the execution of the M cognitive tasks, and M is a positive integer; A second determination module is used to determine the brain region collaboration correlation vector corresponding to the user to be evaluated based on the brain region distribution feature sets corresponding to each of the M cognitive tasks; A generating module, configured to generate a reading ability evaluation result corresponding to the user to be evaluated by using an auxiliary evaluation model based on the brain image feature set, the brain region distribution feature set corresponding to each of the M cognitive tasks, and the brain region collaborative correlation information; The generation module is also used to determine the cognitive feature set corresponding to the user to be evaluated based on the defect incidence rate corresponding to each of the N cognitive skills and the brain image feature set, wherein the N cognitive skills include the cognitive skills corresponding to each of the M cognitive tasks; determine the associated brain region feature set corresponding to the user to be evaluated based on the dependent brain region information corresponding to each of the N cognitive skills and the brain region distribution feature set corresponding to each of the M cognitive tasks; splice the cognitive feature set, the associated brain region feature set and the brain region collaborative correlation vector to obtain the evaluation index data corresponding to the user to be evaluated; input the evaluation index data into the auxiliary evaluation model to obtain the reading ability evaluation result; The training method of the auxiliary evaluation model includes: obtaining resting-state brain image data and task-state brain image data of Q sample users, where Q is a positive integer; obtaining evaluation index data corresponding to each of the Q sample users based on the resting-state brain image data and task-state brain image data of the Q sample users; and training an initial network model based on the evaluation index data and reading ability label data corresponding to each of the Q sample users to obtain the auxiliary evaluation model.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor, The processor is used to execute the method described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 8.