A game-based autism assessment method and system

Abstract

The application provides a game-based autism evaluation method and system, and relates to the technical field of medical rehabilitation. The method comprises the following steps: obtaining an interaction data set generated by a child in a game task; extracting features from the interaction data in the interaction data set to obtain operation features; calculating a comprehensive performance score of the child in the game task according to the operation features; determining the difficulty level of the target game task according to the comprehensive performance score; judging whether the evaluation period is over; if yes, proceeding to the next step; otherwise, updating the game task according to the difficulty level of the target game task; updating the target achievement degree of the individualized education plan; and generating a rehabilitation suggestion based on the update result to complete the evaluation of autism. The application can effectively avoid data fluctuations caused by accidental behaviors such as distraction and temporary operation errors, and significantly improve the stability and objective accuracy of the evaluation result.

Description

Technical Field

[0001] This invention relates to the field of medical rehabilitation technology, and in particular to a game-based autism assessment method and system. Background Technology

[0002] Autism spectrum disorder (ASD) is a typical neurodevelopmental disorder characterized by slowed cognitive response, poor fine motor skills, repetitive behaviors, and short attention spans. It requires long-term, systematic rehabilitation training and periodic ability assessments to develop and adjust individualized educational plans, ensuring the targeted effectiveness of rehabilitation interventions. With the continuous improvement of special rehabilitation medical systems, quantitative assessment and personalized intervention have become core development directions in the field of autism rehabilitation. Utilizing digital interactive methods for non-contact, low-resistance ability assessments can effectively adapt to the behavioral characteristics of children with autism, reduce emotional resistance caused by traditional assessment models, and is gradually being applied to various children's rehabilitation scenarios.

[0003] Currently, the assessment of autistic children's abilities primarily relies on manual scale scoring, offline behavioral observation, or fixed-question training. Some existing solutions incorporate gamified interactive methods to collect basic behavioral data, achieving simple quantitative assessments of abilities. Simultaneously, they categorize task difficulty levels according to standardized criteria to assist rehabilitation personnel in making preliminary judgments about children's cognitive and operational abilities. A few digital assessment systems can record single-test results, perform data statistics using basic algorithms, and preset fixed target values, providing a foundational reference for developing individualized education plans. This represents a preliminary transition in rehabilitation assessment from purely subjective judgment to semi-quantitative analysis.

[0004] However, the existing difficulty adjustment mechanisms are generally quite rigid, often using fixed difficulty levels or simple condition switching modes, which cannot be adapted to children's real-time assessment performance to achieve dynamic optimization and are difficult to match individual dynamic ability levels. At the same time, traditional assessment methods have a single evaluation dimension and often use the results of a single assessment as the basis for evaluation, making it difficult to effectively filter out data fluctuations caused by accidental factors such as distraction and temporary operational errors, resulting in insufficient stability and objectivity of assessment results. Summary of the Invention

[0005] To address the limitations of existing technologies that rely on rigid difficulty adjustment mechanisms, often employing fixed difficulty levels or simple condition switching modes, which fail to adapt dynamically to children's real-time assessment performance and thus cannot match individual evolving abilities, this invention provides a game-based autism assessment method and system.

[0006] The technical solutions provided by the embodiments of the present invention are as follows: A first aspect of this invention provides a game-based autism assessment method, comprising: S1: Obtain the interaction dataset generated by children in game tasks; S2: Extract features from the interactive data in the interactive dataset to obtain operational features; S3: Calculate the child's overall performance score in the game task based on operational characteristics; S4: Determine the difficulty level of the target game task based on the overall performance score; S5: Determine if the evaluation period has ended; if yes, proceed to the next step; otherwise, update the game task according to the difficulty level of the target game task and return to step S1. S6: Update the achievement rate of the individualized education program goals; S7: Based on the updated results, generate rehabilitation suggestions to complete the autism assessment.

[0007] A second aspect of this invention provides a game-based autism assessment system, comprising: processor; The memory stores computer-readable instructions that, when executed by a processor, implement the game-based autism assessment method as described in the first aspect.

[0008] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the game-based autism assessment method of the first aspect.

[0009] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: In this embodiment of the invention, the difficulty level of the target game task is determined by a comprehensive performance score. A closed-loop process is achieved by combining this with an assessment cycle. If the assessment cycle's end conditions are not met, the game task is updated based on the adapted difficulty level, and interaction data is re-collected. This allows for adaptive dynamic adjustment based on the child's real-time assessment performance, adapting to the child's dynamically changing ability level. Simultaneously, comprehensive feature extraction is performed on the interaction data, and an objective comprehensive performance score is calculated based on the obtained operational features. This periodic assessment model reduces random interference from single assessments and iteratively updates the achievement of individualized educational goals, effectively avoiding data fluctuations caused by distraction, temporary operational errors, and other accidental behaviors, significantly improving the stability and objectivity of the assessment results. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating a game-based autism assessment method provided in an embodiment of the present invention.

[0012] Figure 2 This is a schematic diagram of the structure of a game-based autism assessment system provided in an embodiment of the present invention. Detailed Implementation

[0013] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0014] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0015] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0016] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0017] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0018] Reference manual attached Figure 1 The diagram shows a flowchart of a game-based autism assessment method provided by an embodiment of the present invention.

[0019] This invention provides a game-based autism assessment method, which can be implemented using a game-based autism assessment device, which can be a terminal or a server. The processing flow of the game-based autism assessment method may include the following steps: S1: Obtain the interaction dataset generated by children in game tasks.

[0020] Optionally, the game tasks may specifically include: social interaction, emotion recognition, executive functions, and feature classification.

[0021] It should be noted that the game tasks are generated by the gamification assessment module, which includes a game engine with multiple built-in assessment scenarios designed based on IEP objectives. This module is responsible for rendering game screens, receiving user input, triggering in-game events, and dynamically adjusting the task difficulty based on feedback from the assessment engine.

[0022] Optionally, the interactive dataset specifically includes: operation location sequence, timestamp sequence, operation label, and operation result.

[0023] The operation position sequence includes the sequence of coordinate points for each touch.

[0024] The timestamp sequence corresponds to the time point of each operation.

[0025] The operation label identifies the type and object of each operation.

[0026] The operation result indicates whether the operation was correct.

[0027] It should be noted that the interactive dataset is collected by the interactive data acquisition module, which is based on a high-precision touchscreen and can record all the operation events of children interacting with the game.

[0028] S2: Extract features from the interactive data in the interactive dataset to obtain operational features.

[0029] It should be noted that the evaluation engine includes a feature extraction submodule and an evaluation calculation submodule, which are responsible for extracting behavioral features from the raw interaction data and evaluating various core capabilities through an algorithm model.

[0030] In one possible implementation, S2 specifically involves extracting features from the accuracy, response time, drag path length, drag smoothness, number of corrections, and repetition rate of the interactive data to obtain operational features.

[0031] The accuracy rate is the ratio of the number of correct operations to the total number of operations.

[0032] The reaction time is the time interval from when the task screen is displayed to when the child performs the first action.

[0033] The drag path length is the sum of the Euclidean distances traversed by the drag trajectory.

[0034] The drag smoothness is the reciprocal of the standard deviation of the path point angle change.

[0035] The number of corrections refers to the total number of times the child performs an undo or correction operation.

[0036] The repetition rate is the proportion of the number of times the same object is repeatedly operated on to the total number of operations.

[0037] In this embodiment of the invention, by uniformly extracting and analyzing multi-dimensional and refined behavioral characteristics, it is possible to comprehensively capture children's operational habits, response speed, motor control level, and behavioral decision-making state during game interaction. This overcomes the limitations of a single evaluation indicator and achieves objective quantitative representation from multiple dimensions such as cognitive response, fine motor skills, behavioral stability, and self-correction ability. Relying on six standardized and quantifiable operational characteristics, it can provide refined and reliable underlying data support for subsequent core ability score calculation, comprehensive performance score assessment, adaptive adjustment of task difficulty, and updating of goal achievement. This effectively reduces subjective evaluation bias and improves the comprehensiveness, objectivity, and accuracy of autism ability assessment, making the assessment results more consistent with children's actual behavioral performance and current ability status.

[0038] S3: Calculate the child's overall performance score in the game task based on operational characteristics.

[0039] Among them, the overall performance score is the holistic quantitative evaluation result of a single game assessment task. It is based on the quantitative scores of each core ability obtained by normalizing multiple behavioral characteristics of children, and is calculated by weighting the scores with the corresponding weight coefficients of different ability dimensions. It can comprehensively integrate children's real performance in cognitive response, fine operation, behavioral decision-making, motor control and other aspects, and objectively reflect children's comprehensive ability level in tasks of current difficulty.

[0040] In one possible implementation, S3 specifically includes sub-steps S301 and S302: S301: Calculate the quantitative score of a child's core competencies based on operational characteristics.

[0041] The specific formula for calculating the quantified score is as follows:

[0042] in, i An index representing core capabilities. C i Indicates the first i A quantitative score for each core competency. j An index representing behavioral characteristics.n This represents the total number of behavioral characteristics. w ij Indicates the first i Under the core capabilities, the first j The weight coefficients of each behavioral feature Indicates the first i Under the core capabilities, the first j An interval normalization transformation function for each behavioral feature. x ij Indicates the first i Under the core capabilities, the first j Feature values ​​of each behavioral characteristic.

[0043] Among them, the weighting coefficient w ij satisfy It is derived from the pre-set Individualized Education Program (IEP) or trained by a machine learning model.

[0044] The interval normalization transformation function is specifically as follows:

[0045] in, This represents the interval normalization transformation function. x This represents the original values ​​of the behavioral features to be normalized. x min This represents the minimum value of a behavioral characteristic in the sample database or historical evaluation data. x max This represents the maximum value of a behavioral characteristic in the sample database or historical evaluation data. ε This represents a very small positive smoothing factor.

[0046] The positive smoothing factor typically ranges from 10. -6 Up to 10 -8 Used to avoid when x max and x min Calculation anomalies occur when the denominator is zero when the values ​​are equal. The smoothing factor can be dynamically set according to the characteristic dimensions, with the dimensionless characteristic taking a value of 10. -8 Dimensional characteristic value is 10 -6 or 10 of the eigenvalue range -6 By introducing a smoothing factor, the computational anomalies caused by the zero eigenvalue range can be avoided while maintaining the accuracy of linear mapping. Simultaneously, it prevents mapping distortion due to excessively large factor values, effectively improving the robustness of the algorithm in real-world clinical applications.

[0047] S302: Calculate the overall performance score based on the quantitative score.

[0048] The specific formula for calculating the overall performance score is as follows:

[0049] in, t Indicates the index of the game task. S t Indicates the first t A score based on the overall performance of each game task. m This represents the total number of dimensions representing core competencies. β i Indicates the first i The weighting coefficients of each core competency.

[0050] Among them, the weighting coefficient β i satisfy According to the objectives set for this task in the individualized education plan.

[0051] In this embodiment of the invention, standardization and unification of various behavioral characteristics are first achieved through interval normalization transformation, eliminating calculation biases caused by differences in the dimensions and numerical ranges of different characteristics. Then, the normalized weight coefficients are combined to integrate multiple behavioral characteristics to calculate the quantitative scores of each core ability. This can accurately break down and quantify the child's ability shortcomings and development level in different dimensions, avoiding the one-sidedness of single-indicator evaluation. Subsequently, a comprehensive performance score is obtained by weighted summation based on the appropriate weights of each core ability. This progressive approach achieves an orderly transformation from underlying behavioral data to individual abilities and then to overall comprehensive level. The reasonable constraints and flexible settings of the weights can meet the rehabilitation goals of individualized education plans. The introduction of smoothing factors ensures the stability of the operation and the robustness of the algorithm under extreme data scenarios. The entire process uses objective quantitative algorithms to replace subjective experience judgments, significantly improving the accuracy, scientificity, and consistency of the assessment results.

[0052] S4: Determine the difficulty level of the target game task based on the overall performance score.

[0053] In one possible implementation, S4 specifically includes sub-steps S401 and S402: S401: Set the difficulty level of the game mission and the target difficulty range.

[0054] It should be noted that the current task difficulty level is set to 1. The target difficulty range is [ S low , S high ](generally S low =0.65, S high =0.85).

[0055] It should be noted that the minimum difficulty threshold S low The threshold of 0.65 is based on sufficient clinical evidence and algorithmic rationale. First, setting a minimum difficulty threshold effectively avoids a floor effect in the assessment process. When a child's overall performance score is below 0.65, it indicates that the current task difficulty exceeds the child's ability, and the task error rate is higher than 35%. If the difficulty is not reduced in time, the child may experience frustration and give up on interaction, resulting in missing assessment data. Second, the minimum difficulty threshold aligns with clinical rehabilitation experience for children with autism. In rehabilitation, when a child's independent completion rate on a corresponding task is below 65%, it can be determined that the task has exceeded their zone of proximal development, requiring difficulty reduction or the provision of auxiliary support. Finally, the minimum difficulty threshold achieves a good signal-to-noise ratio balance. When the score is below 0.65, the signal-to-noise ratio of the assessment results decreases significantly, the child's random guessing behavior increases, and continued data collection contributes less to the assessment results. Therefore, using 0.65 as the difficulty reduction trigger threshold ensures the validity of the assessment data and the stability of the assessment process.

[0056] It should be noted that the highest difficulty threshold S high The threshold of 0.85 is based on sufficient clinical evidence and algorithmic rationale. First, this maximum difficulty threshold effectively avoids a ceiling effect in the assessment process. When a child's overall performance score consistently exceeds 0.85, it indicates that the current task difficulty is too low, and the child can easily complete the task. Maintaining this difficulty level for an extended period will prevent accurate measurement of the child's true ability ceiling. Second, the maximum difficulty threshold allows for reasonable room for improvement. 0.85 represents a stable and good performance level in the current task, eliminating the interference of a single, accidental high score and allowing room for subsequent higher-level tasks and ability enhancement. Finally, the maximum difficulty threshold aligns with clinical feasibility practices in autism assessment. In standardized autism assessment tools, a score reaching 85% of the maximum value is generally considered to indicate that the corresponding domain ability has exceeded the measurement range of the current module. Setting the threshold in accordance with this clinical assessment practice ensures the clinical applicability and comparability of the assessment results.

[0057] It should be noted that the target difficulty range [0.65, 0.85] is designed with overall rationality and clinical applicability. The width of this range (0.2) fully accommodates normal fluctuations in a child's abilities due to fatigue, distraction, etc., during the assessment process, avoiding frequent jumps in difficulty caused by small score changes. Simultaneously, the range is moderate, preventing children from being assessed at an inappropriate difficulty level for extended periods. Furthermore, the lower limit (0.65) and upper limit (0.85) are symmetrically distributed with a median of 0.75, ensuring equivalent sensitivity in triggering difficulty upgrades and downgrades, guaranteeing a stable and balanced assessment process. This range also naturally aligns with the target values ​​of the individualized education plan (0.80–0.95). When a child's score reaches or exceeds the upgrade threshold, their performance is close to or has reached the expected level set by the individualized education plan (IEP), achieving efficient linkage between assessment results and rehabilitation goals.

[0058] Furthermore, the system supports rehabilitation staff in making personalized adjustments to the minimum and maximum difficulty thresholds during the initial configuration assessment phase to adapt to individual differences among children with autism and the needs of different rehabilitation scenarios. Specifically, the adjustable range for the minimum difficulty threshold is set to [0.55, 0.75], and the adjustable range for the maximum difficulty threshold is set to [0.75, 0.95]. Mandatory constraints are also set to ensure that certain conditions are met. By limiting the minimum difference between two thresholds, the difficulty adaptation range is ensured to have a reasonable width, preventing the range from being too narrow and causing frequent difficulty switching or range imbalance. This ensures the stable operation of the adaptive difficulty adjustment mechanism and improves the adaptability and reliability of the overall assessment process.

[0059] S402: Determine the difficulty level of the target game task based on the difficulty level of the game task, the overall performance score, and the target difficulty adaptation range.

[0060] The specific difficulty levels of the target game tasks are as follows:

[0061] in, level Indicates the difficulty level of the target game objective. S high This indicates the highest difficulty threshold. S low Indicates the minimum difficulty threshold. min This indicates taking the minimum value. level Indicates the difficulty level of the game mission.

[0062] Optionally, the difficulty levels of the target game task may specifically include: the first difficulty level, the second difficulty level, and the third difficulty level.

[0063] When the overall performance score exceeds the highest difficulty threshold of the target difficulty adaptation range multiple times consecutively, the difficulty level of the target game task is set to the first difficulty level.

[0064] When the overall performance score is lower than the lowest difficulty threshold of the target difficulty adaptation range multiple times in a row, the difficulty level of the target game task is set to the second difficulty level.

[0065] When the overall performance score falls within the target difficulty range, the target game task's difficulty level is the third difficulty level.

[0066] In this embodiment of the invention, a comprehensive adaptive difficulty adjustment mechanism is constructed by pre-setting fixed difficulty levels and scientifically reasonable difficulty adaptation ranges, combined with dual threshold constraints, symmetrical range design, and threshold standards supported by clinical experience. This mechanism can dynamically match the appropriate game task difficulty level based on the child's real-time comprehensive performance score, effectively avoiding the ceiling effect and floor effect. It avoids problems such as frustration, interaction interruption, and data failure caused by excessive difficulty, and also avoids problems such as inaccurate detection of the child's true ability limit due to excessive difficulty. At the same time, relying on the trigger logic of continuous multiple score judgments, it effectively filters misjudgments caused by accidental fluctuations such as single operation errors and temporary distractions, reduces frequent changes in difficulty, and makes the assessment rhythm more stable. With the addition of a threshold configuration mode that rehabilitation personnel can customize and fine-tune, and the reasonableness of the range is ensured by the forced difference constraint, it fully adapts to the individual ability differences and personalized rehabilitation needs of different autistic children. This ensures that the assessment task always fits the child's zone of proximal development. On the basis of ensuring the objectivity and continuity of the assessment, it continuously improves the interactive experience, assessment data quality, and clinical adaptability of the overall assessment process, providing reliable adaptive adjustment support for the iterative dynamic assessment mode.

[0067] S5: Determine if the evaluation period has ended. If yes, proceed to the next step. Otherwise, update the game task according to the difficulty level of the target game task and return to step S1.

[0068] In this embodiment of the invention, by conditionally determining the assessment cycle, a closed-loop cycle and dynamic control of the assessment process are achieved. When the termination condition is not met, the game task content is iteratively optimized based on the updated difficulty level and fed back to the data collection stage, forming a continuously adaptable cyclical assessment mode to ensure that the task difficulty dynamically matches the child's real-time ability. When the preset termination condition is reached, the cycle is terminated in a timely manner, and the subsequent evaluation process is advanced, avoiding meaningless repetitive assessments and excessively long assessment times. This aligns with the physiological and behavioral characteristics of autistic children, who have limited attention spans, effectively reducing assessment fatigue and resistance, and balancing assessment efficiency with data collection quality.

[0069] S6: Update the achievement of goals for the individualized education program.

[0070] It should be noted that the Personalized Education Program (IEP) dynamic update module automatically calculates the goal achievement rate based on the assessment results, updates the IEP content, and generates rehabilitation suggestions. The IEP dynamic update module stores the child's IEP file, which includes long-term goals (LTG) and short-term goals (STO).

[0071] In one possible implementation, S6 specifically includes sub-steps S601 and S602: S601: Calculate the matching function value.

[0072] The matching function value quantifies the degree of matching between a single assessment result and a preset short-term goal. It is calculated based on the comprehensive score of the assessment period and the corresponding preset target value. The ratio of these two values ​​represents the completion rate of the current capability level, and a minimum value constraint limits the output result to a reasonable range. When the actual comprehensive score exceeds the target requirement, the matching function value remains at its upper limit to avoid overestimating the evaluation result. When the actual comprehensive score fails to reach the preset target, the gap is objectively reflected according to the actual completion rate, thus accurately and steadily quantifying the current task completion level.

[0073] S602: Update the target achievement rate based on the matching function value using a weighted moving average algorithm.

[0074] The weighted moving average algorithm integrates the achievement level of the current assessment with the historical cumulative achievement level. By setting fixed learning weights, it reasonably allocates the contribution ratio of current assessment data and historical data, weakening the interference caused by occasional fluctuations in a single assessment and avoiding large-scale changes in goal achievement. The algorithm uses the task completion status calculated from the current assessment as a short-term reference and the historical goal achievement level as a long-term benchmark, iteratively optimizing the assessment results step by step. This not only objectively reflects the stage-by-stage ability changes and progress trends of children with autism, but also ensures the continuity, stability, and reliability of the assessment data. This makes the evaluation results of individualized education plans more consistent with the child's true long-term development status, improving the scientific rigor and clinical applicability of the overall assessment system.

[0075] The specific formula for updating the goal achievement level is as follows:

[0076]

[0077] in, p An index representing the short-term goals in a personalized education program. A p ( new ) indicates the first p The achievement rate of the updated short-term goals αThis represents the learning rate, with a value ranging from 0 to 1, and is used to control how quickly new evaluation results are updated to reflect historical evaluation results. M ( ) represents a matching function. S This represents the overall score for the evaluation period. Target p Indicates the first p The target value for a short-term goal A p ( old ) indicates the first p The achievement level of the short-term goals before the update.

[0078] Among them, the target value Target p According to the difficulty level setting of the goal in the Individualized Education Program (IEP), the value is usually set in the range of 0.80 to 0.95. Lower values ​​(such as 0.80) are used for goals with lower difficulty (such as basic operation training), and higher values ​​(such as 0.95) are used for goals with higher difficulty (such as multidimensional classification) to reflect the expected level of different rehabilitation stages.

[0079] Furthermore, when When the goal is "achieved", the system determines that the goal has been achieved and automatically triggers the setting of the next level of Individualized Education Program (IEP) goal. θ The default value is 0.85, which is set based on clinical rehabilitation experience: it avoids premature judgment of achievement based on a single, accidental performance (reducing false positives) while ensuring that children can move to the next rehabilitation stage promptly after their performance stabilizes. The system also allows therapists to manually adjust the value within the range of 0.75 to 0.95 according to the child's specific situation. θ value.

[0080] In this embodiment of the invention, relying on the dynamic update module of the individualized education plan, a matching function is used to accurately quantify the degree of matching between the current assessment performance and the short-term rehabilitation goals. The range of quantified results is reasonably constrained to objectively reflect the goal completion rate. Then, a weighted moving average algorithm is used to integrate the current assessment data with historical achievement levels, and the goal achievement rate is updated smoothly and iteratively. This effectively reduces data fluctuations caused by accidental factors in a single assessment, prevents significant deviations in evaluation results, and ensures the continuity and stability of goal evaluation. At the same time, combined with the target values ​​set by differentiated grading, the training requirements of different rehabilitation tasks and ability stages are adapted. With the flexible adjustment of the goal achievement judgment threshold, it can not only scientifically identify the true goal achievement status and reduce the probability of misjudgment, but also automatically connect to advanced rehabilitation goals, realizing the dynamic iteration and intelligent optimization of the individualized education plan. It completely preserves the child's long-term rehabilitation records and ability development trajectory, providing quantitative support for the dynamic adjustment of rehabilitation programs and the assessment of phased effectiveness. This makes the rehabilitation evaluation of autistic children more in line with individual development patterns, significantly improving the pertinence, consistency, and clinical practical value of rehabilitation intervention.

[0081] S7: Based on the updated results, generate rehabilitation suggestions to complete the autism assessment.

[0082] Reference manual attached Figure 2 The diagram shows a schematic of the structure of a game-based autism assessment system provided by the present invention.

[0083] The present invention also provides a game-based autism assessment system 20, applied to the above-mentioned game-based autism assessment method, comprising: Processor 201.

[0084] The memory 202 stores computer-readable instructions that, when executed by the processor 201, implement the game-based autism assessment method as described in the method embodiment.

[0085] The game-based autism assessment system 20 provided by this invention can perform the above-mentioned game-based autism assessment method and achieve the same or similar technical effects. To avoid duplication, this invention will not elaborate further.

[0086] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0087] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0088] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0089] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0090] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0091] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0092] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0093] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0094] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0095] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0097] If the aforementioned functions are implemented as 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 this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] This invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the game-based autism assessment method as described in the method embodiments.

[0099] The present invention provides a computer-readable storage medium that can implement the steps and effects of the game-based autism assessment method described in the above-described method embodiments. To avoid repetition, the present invention will not repeat the details.

[0100] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0101] The following points need to be explained: (1) The accompanying drawings of the embodiments of the present invention only involve the structures involved in the embodiments of the present invention. Other structures can refer to the general design.

[0102] (2) For clarity, the thickness of layers or regions is enlarged or reduced in the drawings used to describe embodiments of the invention, i.e., these drawings are not drawn to scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being “above” or “below” another element, the element may be “directly” located “above” or “below” the other element or there may be intermediate elements.

[0103] (3) Where there is no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0104] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A game-based autism assessment method, characterized in that, include: S1: Obtain the interaction dataset generated by children in game tasks; S2: Extract features from the interactive data in the interactive dataset to obtain operational features; S3: Calculate the child's overall performance score in the game task based on the operational characteristics; S4: Determine the difficulty level of the target game task based on the overall performance score; S5: Determine if the evaluation period has ended; if yes, proceed to the next step. Otherwise, update the game task according to the difficulty level of the target game task, and return to step S1; S6: Update the achievement rate of the individualized education program goals; S7: Based on the updated results, generate rehabilitation suggestions to complete the autism assessment.

2. The game-based autism assessment method according to claim 1, characterized in that, The game tasks specifically include: social interaction, emotion recognition, performance functions, and feature classification.

3. The game-based autism assessment method according to claim 1, characterized in that, The interactive dataset specifically includes: operation location sequence, timestamp sequence, operation label, and operation result.

4. The game-based autism evaluation method of claim 1, wherein, Specifically, S2 is: The operation features are obtained by extracting features from the accuracy, response time, drag path length, drag smoothness, number of corrections, and repetition rate of the interaction data.

5. The game-based autism evaluation method of claim 1, wherein, S3 specifically includes: S301: Calculate a quantitative score of the child's core competencies based on the operational characteristics; S302: Calculate the overall performance score based on the quantified score.

6. The game-based autism evaluation method of claim 1, wherein, S4 specifically includes: S401: Set the difficulty level and target difficulty range of the game task; S402: Determine the difficulty level of the target game task based on the difficulty level of the game task, the overall performance score, and the target difficulty adaptation range.

7. The game-based autism evaluation method of claim 6, wherein, The difficulty levels of the target game task specifically include: the first difficulty level, the second difficulty level, and the third difficulty level; When the overall performance score is greater than the highest difficulty threshold of the target difficulty adaptation range multiple times consecutively, the difficulty level of the target game task is the first difficulty level; When the overall performance score is lower than the lowest difficulty threshold of the target difficulty adaptation range multiple times consecutively, the difficulty level of the target game task is the second difficulty level; When the overall performance falls within the target difficulty adaptation range, the difficulty level of the target game task is the third difficulty level.

8. The game-based autism evaluation method of claim 1, wherein, S6 specifically includes: S601: Calculate the matching function value; S602: Update the target achievement degree based on the matching function value using a weighted moving average algorithm.

9. A game-based autism assessment system, characterized by, include: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the game-based autism assessment method as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the game-based autism assessment method as described in any one of claims 1 to 8.

Images