Intelligent information processing method and system based on child cognitive development data

Abstract

This invention relates to the field of medical information technology, and discloses an intelligent information processing method and system based on children's cognitive development data. The method includes: performing segmented fluctuation decomposition on cognitive development data to obtain segmented fluctuation characteristics, and constructing a developmental difference matrix and individual developmental trajectory curves accordingly. A group reference set is used to determine the group average developmental sequence and the group fluctuation envelope interval. Using the individual trajectory curve as a baseline, segment-by-segment deviation analysis is performed on the group average sequence to obtain a difference sequence and developmental deviation degree. Segments continuously located outside the envelope interval are considered as locally abnormal developmental segments, and finally combined into a developmental state assessment vector. This invention can improve the accuracy of intelligent information processing based on children's cognitive development data.

Description

Technical Field

[0001] This invention relates to the field of medical information technology, and in particular to an intelligent information processing method and system based on children's cognitive development data. Background Technology

[0002] Current technologies for processing children's cognitive development data typically rely on simple comparisons of single-dimensional test scores or only calculate the overall mean. This fails to provide synchronous analysis of multidimensional data sequences, neglecting the asynchronicity of developmental rates across different cognitive dimensions and the inter-dimensional interactions within an individual. Furthermore, traditional methods lack effective decomposition of data fluctuations during development, often treating discrepancies in test scores as measurement errors and directly smoothing them. This results in the loss of information on intra-segment fluctuation amplitudes reflecting cognitive stability, making it difficult to distinguish between normal developmental fluctuations and potential abnormal patterns.

[0003] Due to the aforementioned limitations, existing technologies cannot construct individual developmental trajectory curves that simultaneously include both central trends and fluctuation envelopes, nor can they generate dynamic fluctuation envelope intervals based on population reference sets for segmental deviation analysis between individuals and the population. This results in coarse and lagging calculations of developmental deviation, making it impossible to accurately pinpoint the specific age period at which local abnormal developmental segments occur. Furthermore, it cannot integrate cross-dimensional differences, overall deviation levels, and local abnormal information into a unified developmental status assessment vector, leading to insufficient sensitivity and specificity of the assessment results, making it difficult to meet the clinical needs for early intervention and personalized guidance. Summary of the Invention

[0004] This invention provides an intelligent information processing method and system based on children's cognitive development data, the main purpose of which is to solve the problem of low accuracy in intelligent information processing based on children's cognitive development data.

[0005] To achieve the above objectives, the present invention provides an intelligent information processing method based on children's cognitive development data, comprising:

[0006] S1. Obtain cognitive development data and a group reference set for the target process, and perform segmented fluctuation decomposition on the multidimensional data sequence of the cognitive development data to obtain the segmented fluctuation characteristics of the target process;

[0007] S2. Arrange the cross-dimensional difference coefficients between the segmented fluctuation characteristics in chronological order to obtain the developmental difference matrix of the target process;

[0008] S3. Using the segmented fluctuation feature intra-segment basic value sequence as the central trajectory, and using the intra-segment fluctuation amplitude corresponding to the intra-segment basic value sequence as the vertical expansion radius of the central trajectory in the corresponding time period, perform bilateral expansion to obtain the individual development trajectory curve of the target process.

[0009] S4. Based on the statistical characteristics of the mean base value of individuals in the population reference set and the fluctuation amplitude within the segment, determine the population average development sequence and population fluctuation envelope interval of the target process, respectively.

[0010] S5. Using the central base value sequence of the individual development trajectory curve as the developmental baseline, perform segmented deviation analysis on the population average developmental sequence to obtain the difference sequence of the target process and the corresponding developmental deviation.

[0011] S6. The segments in the difference sequence that are continuously located outside the population fluctuation envelope are taken as local abnormal developmental segments, and the developmental difference matrix, the developmental deviation degree and the local abnormal developmental segments are combined into the developmental state evaluation vector of the target process.

[0012] In a preferred embodiment, the step of acquiring cognitive development data and a group reference set of the target process, and performing segmented fluctuation decomposition on the multidimensional data sequence of the cognitive development data to obtain the segmented fluctuation characteristics of the target process, includes:

[0013] The multidimensional data sequence of the target process is divided into equal-length time periods according to age timestamps.

[0014] The arithmetic mean of the original evaluation values ​​within the equal-length time period is used as the base value within the equal-length time period.

[0015] The summation of the absolute values ​​of the differences between the original evaluation values ​​and the baseline values ​​within the equal-length time period yields the cumulative fluctuation amount for the equal-length time period.

[0016] The ratio of the total cumulative fluctuation to the number of data points within the equal-length time period is taken as the fluctuation amplitude within the equal-length time period.

[0017] By combining the basic value within the segment with the fluctuation amplitude within the segment in chronological order, the segmented fluctuation characteristics of the target process are obtained.

[0018] In a preferred embodiment, arranging the cross-dimensional difference coefficients among the segmented fluctuation characteristics in chronological order to obtain the developmental difference matrix of the target process includes:

[0019] By selecting fluctuation features of any dimension from the segmented fluctuation features, the dimension pairs of the target process are obtained;

[0020] The cross-dimensional difference coefficient of the target process is calculated based on the intra-segment basic value difference and the total intra-segment fluctuation amplitude of the dimension pair.

[0021] Arrange the cross-dimensional difference coefficients in chronological order to obtain the row vector of the target process, and use the row vector as the first row to iterate through all dimensions of the segmented fluctuation features to obtain the developmental difference matrix of the target process.

[0022] In a preferred embodiment, the formula for calculating the cross-dimensional difference coefficient is as follows:

[0023]

[0024] in, For the first Wei and Di Vi in the Cross-dimensional difference coefficients for isochronous intervals This is the sequence number of the first dimension. This is the sequence number for the second dimension. These are the sequence numbers of the isochronous intervals. For the first The dimension in the first The basic value within a time period, For the first The dimension in the first The basic value within a time period, The total number of isochronous intervals. For the first The dimension in the first The fluctuation range within a given time period For the first The dimension in the first The fluctuation range within a given time period.

[0025] In a preferred embodiment, the step of using the intra-segment basic value sequence of the segmented fluctuation characteristics as the central trajectory, and using the intra-segment fluctuation amplitude corresponding to the intra-segment basic value sequence as the vertical expansion radius of the central trajectory within the corresponding time period for bilateral expansion, to obtain the individual developmental trajectory curve of the target process, includes:

[0026] Using the age timestamp of the target process as the horizontal axis and the intra-segment basic value of the segmented fluctuation characteristics as the vertical axis, the intra-segment basic values ​​of equal time periods in the target process are connected sequentially in chronological order to obtain the central broken line of the target process;

[0027] The fluctuation range of the straight line segment on the central broken line within the corresponding equal time period is taken as the vertical expansion radius of the straight line segment;

[0028] The upper and lower boundary segments of the target process are obtained by translating the straight line segments by the vertical extension radius in the vertical direction.

[0029] The upper boundary line segment and the lower boundary line segment are connected sequentially in chronological order to obtain the upper boundary polyline and the lower boundary polyline of the target process; wherein, when the vertical expansion radius of adjacent time periods of equal length in the target process is the same, the endpoints of the earlier time boundary line segment in the target process and the endpoints of the later time boundary line segment in the target process are connected point-to-point; when the vertical expansion radius of adjacent time periods of equal length in the target process is different, the upper boundary endpoints of the earlier time boundary line segment in the target process and the upper boundary endpoints of the later time boundary line segment in the target process are connected by vertical line segments.

[0030] Using the central polyline as the central baseline, the upper boundary polyline as the upper envelope, and the lower boundary polyline as the lower envelope, the individual developmental trajectory curve of the target process is constructed together.

[0031] In a preferred embodiment, the step of using the central polyline as the central baseline, the upper boundary polyline as the upper envelope, and the lower boundary polyline as the lower envelope to jointly construct the individual developmental trajectory curve of the target process includes:

[0032] The central polyline, the upper boundary polyline, and the lower boundary polyline are discretely sampled at fixed intervals within a common range of independent variable values ​​to obtain the common sampling column and corresponding ordinate values ​​of the target process.

[0033] Based on the same sampling x-coordinate position in the common sampling column, extract the corresponding center line discrete point, upper boundary line discrete point, and lower boundary line discrete point on the center line, upper boundary line, and lower boundary line.

[0034] The midpoint between the discrete points of the upper boundary polyline and the discrete points of the lower boundary polyline along the vertical axis is taken as the midpoint of the envelope of the target process.

[0035] The midpoint between the discrete point of the central polyline and the midpoint of the envelope along the vertical axis is taken as the final point of the target process;

[0036] Connect the final points sequentially according to the ascending order of the horizontal coordinates in the common sampling column to obtain the individual development trajectory curve of the target process.

[0037] In a preferred embodiment, determining the population average developmental sequence and population fluctuation envelope interval of the target process based on the statistical characteristics of the mean baseline values ​​and intra-segment fluctuation amplitudes of the population reference set includes:

[0038] The mean basic values ​​of individuals in the population reference set are arranged in chronological order to obtain the population average developmental sequence of the target process;

[0039] The minimum and maximum values ​​of the fluctuation amplitude within the reference set segment of the group are used as the lower and upper bounds, respectively, to define the group fluctuation envelope interval of the target process.

[0040] In a preferred embodiment, the step of using the central baseline sequence of the individual developmental trajectory curve as the developmental baseline and performing segment-by-segment deviation analysis on the population average developmental sequence to obtain the difference sequence of the target process and the corresponding developmental deviation includes:

[0041] The difference between the base value in the central base value sequence of the individual development trajectory curve and the population average base value in the corresponding time period in the population average development sequence is arranged in timestamp order to obtain the difference sequence of the target process.

[0042] The ratio of the number of differences in the difference sequence that fall outside the population fluctuation envelope interval of the target process to the total number of differences in the difference sequence is taken as the developmental deviation of the target process.

[0043] In a preferred embodiment, the step of taking segments in the difference sequence that are continuously located outside the population fluctuation envelope as local aberrant developmental segments, and combining the developmental difference matrix, the developmental deviation degree, and the local aberrant developmental segments into a developmental state assessment vector for the target process includes:

[0044] The positional relationship between the difference in the difference sequence and the lower and upper boundaries of the population fluctuation envelope interval in the corresponding time period is determined sequentially: the position of the first difference between the lower and upper boundaries is marked as the starting point of the current segment in the target process, and the sequence is traversed sequentially along the increasing direction of the difference sequence number to obtain the local abnormal development segment of the target process.

[0045] The developmental difference matrix, the developmental deviation degree, and the local abnormal developmental segments are sequentially concatenated to obtain the developmental status assessment vector of the target process.

[0046] To address the above problems, the present invention also provides an intelligent information processing system based on children's cognitive development data, the system comprising:

[0047] The segmented fluctuation feature module acquires the cognitive development data and group reference set of the target process, and performs segmented fluctuation decomposition on the multidimensional data sequence of the cognitive development data to obtain the segmented fluctuation features of the target process.

[0048] The developmental difference matrix module arranges the cross-dimensional difference coefficients between the segmented fluctuation characteristics in chronological order to obtain the developmental difference matrix of the target process;

[0049] The individual development trajectory curve module takes the intra-segment basic value sequence of the segmented fluctuation characteristics as the central trajectory, and uses the intra-segment fluctuation amplitude corresponding to the intra-segment basic value sequence as the vertical expansion radius of the central trajectory in the corresponding time period for bilateral expansion to obtain the individual development trajectory curve of the target process.

[0050] The developmental fluctuation module determines the population average developmental sequence and population fluctuation envelope interval of the target process based on the statistical characteristics of the mean of the baseline values ​​of individuals in the population reference set and the fluctuation amplitude within the segment, respectively.

[0051] The developmental deviation module uses the central base value sequence of the individual developmental trajectory curve as the developmental baseline, performs segment-by-segment deviation analysis on the population average developmental sequence, and obtains the difference sequence of the target process and the corresponding developmental deviation.

[0052] The developmental status assessment module identifies segments in the difference sequence that are continuously located outside the population fluctuation envelope as local abnormal developmental segments, and combines the developmental difference matrix, the developmental deviation degree, and the local abnormal developmental segments into a developmental status assessment vector for the target process.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] 1. This technology decomposes multidimensional data sequences of cognitive development into segmented fluctuations, separating and extracting the intra-segment basic values ​​and intra-segment fluctuation amplitudes within each equal-length time period, thus achieving dual quantification of developmental central trends and developmental stability. Based on the developmental difference matrix constructed from the segmented fluctuation characteristics, the system records the cross-dimensional difference coefficients of any two dimensions across all age groups, fully preserving the dynamic change patterns of developmental asynchrony between different cognitive domains. By expanding the intra-segment basic value sequence as the central trajectory and the intra-segment fluctuation amplitude as the vertical expansion radius to generate individual developmental trajectory curves, the individual's developmental path along the age axis and its permissible fluctuation boundaries are accurately characterized, providing a high-fidelity representation of individual development for subsequent analysis.

[0055] 2. This technique utilizes the mean of individual baseline values ​​in a population reference set to generate a population-average developmental sequence. It then defines the population fluctuation envelope interval based on the minimum and maximum values ​​of fluctuation amplitude within each segment, establishing a dynamic population comparison benchmark. By performing segment-by-segment deviation analysis on the central baseline sequence of individual developmental trajectory curves and the population-average developmental sequence to obtain a difference sequence, and combining this with the developmental deviation calculated from the population fluctuation envelope interval, it achieves precise quantification of the overall degree of developmental abnormality in individuals. Furthermore, by identifying local abnormal developmental segments continuously located outside the envelope interval in the difference sequence, it accurately pinpoints the specific age period in which the abnormality occurred. The developmental status assessment vector, formed by sequentially concatenating the developmental difference matrix, developmental deviation, and local abnormal developmental segments, integrates three types of information: cross-dimensional differences, global deviation, and local abnormalities, significantly improving the information completeness and interpretability of the developmental status assessment. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating an intelligent information processing method based on children's cognitive development data according to an embodiment of the present invention.

[0057] Figure 2 This is a functional block diagram of an intelligent information processing system based on children's cognitive development data provided in an embodiment of the present invention;

[0058] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0059] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0060] This application provides an intelligent information processing method based on children's cognitive development data. The executing entity of this intelligent information processing method based on children's cognitive development data includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the intelligent information processing method based on children's cognitive development data can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0061] Reference Figure 1The diagram shown is a flowchart illustrating an intelligent information processing method based on children's cognitive development data according to an embodiment of the present invention. In this embodiment, the intelligent information processing method based on children's cognitive development data includes:

[0062] In this invention embodiment, the step of acquiring cognitive development data and a group reference set of the target process, and performing segmented fluctuation decomposition on the multidimensional data sequence of the cognitive development data to obtain the segmented fluctuation characteristics of the target process, is specifically used for:

[0063] The multidimensional data sequence of the target process is divided into equal-length time periods according to age timestamps.

[0064] The arithmetic mean of the original evaluation values ​​within the equal-length time period is used as the base value within the equal-length time period.

[0065] The summation of the absolute values ​​of the differences between the original evaluation values ​​and the baseline values ​​within the equal-length time period yields the cumulative fluctuation amount for the equal-length time period.

[0066] The ratio of the total cumulative fluctuation to the number of data points within the equal-length time period is taken as the fluctuation amplitude within the equal-length time period.

[0067] By combining the basic value within the segment with the fluctuation amplitude within the segment in chronological order, the segmented fluctuation characteristics of the target process are obtained.

[0068] Specifically, during the segmentation, a fixed time interval is first determined, such as six months or one year. Then, based on the time interval to which the age timestamp of each data point belongs, the data point is assigned to the corresponding equal-length time interval. For each dimension, all assessment values ​​in its data sequence are fully allocated to each equal-length time interval, ensuring that each time interval may contain multiple data points or may contain no data points.

[0069] Specifically, all the original evaluation values ​​of this dimension within the time period are added together to obtain the total. Then, the number of data points of this dimension within the time period is counted, and the base value within the segment is obtained by dividing the total by the number of data points.

[0070] Specifically, each original evaluation value for that dimension within the time period is subtracted from the calculated baseline value within the segment, and the absolute value of the difference is taken to obtain the absolute deviation of each data point relative to the baseline value within the segment. Then, these absolute deviation values ​​of all data points within the time period are added together one by one, and the sum is the cumulative fluctuation amount for that equal-length time period.

[0071] Specifically, the cumulative fluctuation of this dimension within the time period is divided by the number of data points for this dimension within the time period. The resulting ratio is the fluctuation amplitude within the segment. This ratio reflects the average fluctuation of each data point in this dimension within the age range relative to the baseline value within the segment, eliminating the influence of the number of data points on the total fluctuation.

[0072] Specifically, first, the time sequence of all equal-length time intervals is listed. Then, for each equal-length time interval, the basic value within the interval and the fluctuation amplitude within the interval are taken as a feature pair and arranged in chronological order to obtain the feature sequence of that dimension.

[0073] Furthermore, after this operation, each dimension forms a subset of data within each equal-length time period. This subset contains all the original assessment values ​​for that dimension within that age range. The partitioning results of all dimensions across all equal-length time periods collectively constitute the equal-length time period structure of the target process.

[0074] Furthermore, if a dimension has no data points within a certain time interval of equal length, the intra-interval cardinality for that interval is recorded as missing. The intra-interval cardinality represents the central level of that dimension within that age range, reflecting the typical performance of children in that cognitive domain. The above arithmetic mean operation is performed on all dimensions and all time intervals of equal length to obtain the intra-interval cardinality for each dimension in each time interval.

[0075] Furthermore, the cumulative volatility measures the total amplitude of all assessment values ​​for that dimension within a given age range around the baseline value within that segment. A larger value indicates more significant data fluctuation within that time period. If there is only one data point within a certain equal-length time period, the cumulative volatility is zero because the difference between that data point and the baseline value within the segment is zero. If there are no data points within that time period, the cumulative volatility is recorded as missing. The above summation operation is performed on all dimensions and all equal-length time periods to obtain the cumulative volatility for each dimension in each equal-length time period.

[0076] Furthermore, if there is only one data point within a certain equal-length time period, the fluctuation range within that period is zero. If there are no data points within that time period, the fluctuation range within that period is recorded as missing. The fluctuation range within a period provides a quantitative indicator of the dispersion of the measured values ​​for that dimension within that age range; a larger value indicates more dispersed data and more unstable cognitive performance in children. Performing the above division operation on all dimensions and all equal-length time periods yields the fluctuation range within each dimension for each equal-length time period.

[0077] Furthermore, for multidimensional data sequences, combining the feature sequences of all dimensions constitutes the complete segmented fluctuation characteristics of the target process. Each element in the segmented fluctuation characteristics contains the central level and degree of fluctuation of a specific dimension within a specific age range.

[0078] In summary, by using a unified time division benchmark, the alignment difficulties caused by the inconsistency of sampling time points of data from different dimensions are eliminated, enabling direct comparison of assessment data from different cognitive domains and individuals within the same age window, and providing a standardized time framework for subsequent fluctuation decomposition and cross-dimensional analysis.

[0079] In summary, using the arithmetic mean can effectively suppress random measurement errors that may exist in a single assessment, extract the central trend of individual cognitive levels within each age group, and obtain stable and reliable baseline values ​​within the segment, representing the typical developmental level of children in that cognitive dimension within that time period, thus providing an accurate baseline for constructing developmental trajectories.

[0080] In summary, by accumulating the absolute deviation of each data point from the baseline, the dispersion of all evaluation data within a time period is quantified, avoiding the problem of positive and negative deviations canceling each other out, and fully preserving the original amplitude of fluctuation information, thus providing basic data for subsequent quantitative development stability.

[0081] In summary, by dividing by the number of data points, the impact of differences in assessment frequency within different time periods on the total fluctuation is eliminated. The resulting intra-segment fluctuation amplitude is comparable across time periods and can truly reflect the average instability of individual cognitive performance within each age group. It is a key indicator for assessing the degree of developmental fluctuation.

[0082] In summary, by organically integrating the central level and fluctuation degree of each time period into a feature pair and arranging them in chronological order, a structured developmental feature sequence is formed. This not only preserves developmental trend information but also includes fluctuation stability information, providing a unified data expression form for subsequent calculation of cross-dimensional difference coefficients, construction of individual developmental trajectory curves, and group comparison.

[0083] In an embodiment of the present invention, the step of arranging the cross-dimensional difference coefficients among the segmented fluctuation characteristics in chronological order to obtain the developmental difference matrix of the target process is specifically used for:

[0084] By selecting fluctuation features of any dimension from the segmented fluctuation features, the dimension pairs of the target process are obtained;

[0085] The cross-dimensional difference coefficient of the target process is calculated based on the intra-segment basic value difference and the total intra-segment fluctuation amplitude of the dimension pair.

[0086] Arrange the cross-dimensional difference coefficients in chronological order to obtain the row vector of the target process, and use the row vector as the first row to iterate through all dimensions of the segmented fluctuation features to obtain the developmental difference matrix of the target process.

[0087] Specifically, the segmented fluctuation feature includes the intra-segment basic values ​​and intra-segment fluctuation amplitudes of all dimensions in each equal-length time period. First, the index of the first dimension is selected, and then the index of the second dimension is selected. The two indices are different. The intra-segment basic value sequences and intra-segment fluctuation amplitude sequences of these two dimensions in all equal-length time periods are extracted respectively. These two dimensions and their corresponding data sequences are treated as a dimension pair.

[0088] Specifically, for each equal-length time period, firstly, extract the intra-segment basic value of the first dimension and the intra-segment basic value of the second dimension from the dimension pair. Calculate the absolute value of the difference between these two intra-segment basic values; this absolute value is called the intra-segment basic value difference. Then, extract the intra-segment fluctuation range of the first dimension and the intra-segment fluctuation range of the second dimension, and add these two intra-segment fluctuation ranges to obtain the total intra-segment fluctuation range. Next, calculate the intra-segment basic value difference divided by the total intra-segment fluctuation range to obtain a preliminary ratio. Subsequently, calculate a time adjustment factor based on the current equal-length time period number and the total number of equal-length intervals. Specifically, divide the current equal-length time period number by the total number of equal-length intervals to obtain a time ratio, square this time ratio, and then add one to obtain the time adjustment factor.

[0089] Specifically, the calculated cross-dimensional difference coefficients for this dimension pair are arranged into a row vector according to the chronological order of equal-length time periods. The first element of the row vector corresponds to the cross-dimensional difference coefficient for the first equal-length time period, the second element corresponds to the cross-dimensional difference coefficient for the second equal-length time period, and so on, until the cross-dimensional difference coefficient for the last equal-length time period becomes the last element of the row vector. This row vector completely records the developmental difference variation pattern of this dimension pair across all age ranges.

[0090] Furthermore, for multidimensional data, the number of all possible dimension pairs equals the number of dimensions multiplied by the number of dimensions minus one, then divided by two. Each dimension pair represents a comparison relationship between two cognitive domains. The selection process is not limited by order; any unprocessed dimension pair can be chosen to ensure that each dimension pair is processed once.

[0091] Furthermore, a volatility adjustment factor is calculated based on the difference in intra-segment volatility amplitude between the two dimensions. Specifically, the absolute value of the difference in intra-segment volatility amplitude is calculated, divided by the total intra-segment volatility amplitude to obtain the volatility difference ratio, and then one is added to this ratio to obtain the volatility adjustment factor. Finally, the initial ratio is multiplied by the time adjustment factor and then by the volatility adjustment factor to obtain the final value, which is the cross-dimensional difference coefficient of that dimension pair in the current time period. This method is applied sequentially to each equal-length time period to obtain a sequence of cross-dimensional difference coefficients for that dimension pair across all time periods.

[0092] Furthermore, this row vector is used as the first row of the developmental difference matrix. Then, following the same dimensional pair selection rules, the next unprocessed dimensional pair is selected, its cross-dimensional difference coefficient sequence is repeatedly calculated and arranged into a row vector, which is used as the second row of the developmental difference matrix. This process continues, iterating through all dimensional pairs in the segmented fluctuation features, generating a row vector for each dimensional pair processed and adding it to the next row of the developmental difference matrix. After all possible dimensional pairs have been processed, the number of rows in the developmental difference matrix equals the total number of dimensional pairs, and the number of columns equals the total number of equal-length time periods. Each element in the developmental difference matrix is ​​the cross-dimensional difference coefficient of the corresponding dimensional pair in the corresponding equal-length time period. This matrix fully quantifies the degree of developmental difference between any two cognitive domains in each age interval during the target process.

[0093] In summary, by systematically traversing all possible dimensional combinations, high-dimensional cognitive development data is decomposed into pairwise analytical units, providing an operational basis for cross-dimensional developmental difference analysis. This avoids the complexity and dimensionality curse problems caused by simultaneous comparison of multiple dimensions, and provides clear comparison objects for subsequent calculation of difference coefficients.

[0094] In summary, jointly quantifying the difference in central level between two cognitive domains at the same time period with their respective fluctuations not only reflects the absolute gap in developmental levels between the domains, but also normalizes the differences through fluctuation amplitude, making the difference coefficients of different time periods and different dimensions comparable, and can truly reveal the degree of synchronicity or asynchrony in an individual's development between different cognitive domains.

[0095] In summary, by organizing the difference coefficients of each dimension pair as they change with age into row vectors, and then stacking the row vectors of all dimension pairs in order to form a matrix, the evolutionary patterns of differences between all cognitive domains at all ages are fully recorded. This matrix serves as a structured carrier of developmental status information, which is convenient for subsequent combination with features such as developmental deviation and local abnormal segments to form a comprehensive developmental status assessment vector.

[0096] In this embodiment of the invention, the formula for calculating the cross-dimensional difference coefficient is specifically used for:

[0097]

[0098] in, For the first Wei and Di Vi in the Cross-dimensional difference coefficients for isochronous intervals This is the sequence number of the first dimension. This is the sequence number for the second dimension. These are the sequence numbers of the isochronous intervals. For the first The dimension in the first The basic value within a time period, For the first The dimension in the first The basic value within a time period, The total number of isochronous intervals. For the first The dimension in the first The fluctuation range within a given time period For the first The dimension in the first The fluctuation range within a given time period.

[0099] Specifically, no. The dimension in the first The intra-segment baseline values ​​for each time period are derived from the segmented fluctuation characteristics of the target process. These segmented fluctuation characteristics are obtained by performing segmented fluctuation decomposition on the multidimensional data sequence of cognitive development data, specifically calculated from the arithmetic mean of all original assessment values ​​for that dimension within the same time period. The dimension in the first The basic values ​​within each time period also originate from the same segmented fluctuation feature, extracted from the corresponding time period of another dimension. The dimension in the first The intra-segment fluctuation amplitude for each time period is derived from the intra-segment fluctuation amplitude in the segmented fluctuation characteristics. This value is obtained by dividing the cumulative fluctuation over the same time period by the number of data points within that time period. The dimension in the first The intra-segment fluctuation amplitude of each time period also originates from the intra-segment fluctuation amplitude of the corresponding dimension and time period in the segmented fluctuation characteristics. The sequence number of the isochronous interval. The time intervals are derived from dividing age timestamps into equal-length segments, and are numbered sequentially starting from the first equal-length segment. The total number of equal-length intervals. It is derived from the total number of all equal-length time periods in the entire target process, and this value is determined when dividing the equal-length time periods.

[0100] Furthermore, this calculation formula is used to calculate the first... Wei and Di Vi in the The cross-dimensional difference coefficient for each isochronous interval is fundamentally used to quantify the degree of developmental difference between two different cognitive dimensions within the same age range. The calculation process first extracts the intra-segment baseline values ​​for both dimensions and calculates the absolute value of their difference to obtain the absolute difference in the central levels of the two dimensions. Then, it extracts the intra-segment fluctuation amplitudes for both dimensions, adds them together to obtain the total fluctuation amplitude, and divides the difference in central levels by the total fluctuation amplitude to obtain a baseline ratio. A larger ratio indicates a more significant difference in developmental levels between the two dimensions relative to the fluctuation. Finally, a time adjustment factor is introduced, which is based on the sequence number of the current isochronous interval. Total number Calculation, specifically, is to Divide by The time proportion is obtained, squared, and then incremented by one, so that the factor increases for later age groups. Finally, a volatility difference adjustment factor is introduced. First, the absolute value of the difference in volatility amplitude between the two segments is calculated, divided by the total volatility amplitude to obtain a volatility difference proportion, and then incremented by one. This factor increases as the difference in volatility amplitude between the two dimensions increases. The cross-dimensional difference coefficient obtained by multiplying the three factors comprehensively reflects the combined differences between the two dimensions in terms of centrality, developmental stage, and volatility synchronicity.

[0101] In general, with the isochronous interval number Increase from 1 to In the time adjustment factor Divide by As the ratio increases from near zero to one, the square of that ratio also increases from zero to one, thus the time adjustment factor increases from one to two. This means that for the same pair of dimensions, the cross-dimensional difference coefficient calculated in later age groups will be greater than that in earlier age groups, giving the formula a greater weight for differences in later development. As the difference in the amplitude of fluctuations within the two dimensions increases, the numerator in the fluctuation difference adjustment factor increases while the denominator remains unchanged, thus increasing the proportion of fluctuation differences, and the fluctuation difference adjustment factor increases from one to nearly two. When the amplitudes of fluctuations in the two dimensions are exactly equal, the fluctuation difference adjustment factor equals one, and does not amplify the base ratio; when the difference in the amplitudes of fluctuations in the two dimensions is extremely large, the fluctuation difference adjustment factor approaches two, doubling the final coefficient. In the base ratio, the numerator is the absolute value of the difference in the base values ​​within the segment, and the denominator is the sum of the amplitudes of fluctuations within the two segments. Therefore, when the difference in the central level increases, the numerator increases, and the coefficient increases; when the amplitude of fluctuation in either dimension increases, the denominator increases, and the coefficient decreases. In summary, the cross-dimensional difference coefficient is larger with increasing age, larger central level differences, larger amplitude differences, and smaller amplitudes, and vice versa.

[0102] In an example of the present invention, when the segmented fluctuation feature intra-segment basic value sequence is used as the central trajectory, and the intra-segment fluctuation amplitude corresponding to the intra-segment basic value sequence is used as the vertical expansion radius of the central trajectory within the corresponding time period for bilateral expansion, to obtain the individual development trajectory curve of the target process, it is specifically used for:

[0103] Using the age timestamp of the target process as the horizontal axis and the intra-segment basic value of the segmented fluctuation characteristics as the vertical axis, the intra-segment basic values ​​of equal time periods in the target process are connected sequentially in chronological order to obtain the central broken line of the target process;

[0104] The fluctuation range of the straight line segment on the central broken line within the corresponding equal time period is taken as the vertical expansion radius of the straight line segment;

[0105] The upper and lower boundary segments of the target process are obtained by translating the straight line segments by the vertical extension radius in the vertical direction.

[0106] The upper boundary line segment and the lower boundary line segment are connected sequentially in chronological order to obtain the upper boundary polyline and the lower boundary polyline of the target process; wherein, when the vertical expansion radius of adjacent time periods of equal length in the target process is the same, the endpoints of the earlier time boundary line segment in the target process and the endpoints of the later time boundary line segment in the target process are connected point-to-point; when the vertical expansion radius of adjacent time periods of equal length in the target process is different, the upper boundary endpoints of the earlier time boundary line segment in the target process and the upper boundary endpoints of the later time boundary line segment in the target process are connected by vertical line segments.

[0107] Using the central polyline as the central baseline, the upper boundary polyline as the upper envelope, and the lower boundary polyline as the lower envelope, the individual developmental trajectory curve of the target process is constructed together.

[0108] Specifically, the age timestamp and the corresponding intra-segment base value for each equal-length time period are extracted from the segmented fluctuation characteristics. The age timestamp uses the midpoint age or starting age of the equal-length time period, and all equal-length time periods are arranged in ascending order of age.

[0109] Specifically, the central broken line consists of multiple straight line segments, each connecting the baseline points within two adjacent time intervals of equal length. For each straight line segment, it is necessary to determine its corresponding time interval. Following the connection rules, the first... The equal-length time interval and the first The straight line segment of the base point within the equal-length time interval is the first equal-length time interval. Each time period is of equal length.

[0110] Specifically, for each straight line segment on the central broken line, first determine the coordinates of the two endpoints of the straight line segment in the plane coordinate system. Move the left endpoint of the straight line segment along the positive vertical axis by a distance equal to the vertical extension radius of the straight line segment, resulting in a new point called the upper left endpoint. Move the right endpoint of the straight line segment along the positive vertical axis by the same vertical extension radius, resulting in the upper right endpoint.

[0111] Specifically, all upper boundary segments are arranged according to the time sequence of their corresponding original straight line segments, that is, from the upper boundary segment corresponding to the first equal-length time interval to the upper boundary segment corresponding to the last equal-length time interval. For two adjacent upper boundary segments, the right endpoint of the preceding segment and the left endpoint of the following segment are continuous in the horizontal axis direction, but their ordinates may be different. When the vertical expansion radii of two adjacent equal-length time intervals are the same, the ordinate of the right endpoint of the preceding upper boundary segment is equal to the ordinate of the left endpoint of the following upper boundary segment. In this case, the two endpoints are directly connected by a straight line segment. This connection method is called point-to-point connection.

[0112] Specifically, the generated center polyline, upper boundary polyline, and lower boundary polyline are simultaneously preserved in the same planar coordinate system. The center polyline is designated as the central baseline, representing the central path of the change in the intra-segment baseline value of the target process with age over each equal-length time interval. The upper boundary polyline is designated as the upper envelope, representing the upper limit of upward fluctuation of the target process at each age position. The lower boundary polyline is designated as the lower envelope, representing the lower limit of downward fluctuation of the target process at each age position.

[0113] Furthermore, in a Cartesian coordinate system, the horizontal axis is set to the age timestamp, and the vertical axis is set to the range of values ​​for the basic values ​​within a segment. For the first equal-length time period, the first point is plotted in the coordinate system based on its age timestamp and the basic value within the segment. For the second equal-length time period, the second point is plotted based on its age timestamp and the basic value within the segment, and then a straight line segment connects the first and second points. For the third equal-length time period, the third point is plotted, and then a straight line segment connects the second and third points. This process is repeated, plotting the corresponding point for each additional equal-length time period and connecting the previous point with a straight line segment. When all points for equal-length time periods have been plotted and connected sequentially, the resulting polyline is the central polyline of the target process. Each vertex on the central polyline corresponds to a basic value within an equal-length time period, and each straight line segment connects the basic value points of two adjacent equal-length time periods. The entire polyline fully presents the trend of the basic value within the segment changing with the age timestamp.

[0114] Furthermore, the first segment is extracted from the segmented fluctuation characteristics. The fluctuation amplitude within each equal-length time interval is used as the vertical extension radius of this straight line segment. For the last straight line segment, it connects the... The equal-length time interval and the first The number of equal-length time intervals is the nth. The vertical expansion radius is taken as the first equal-length time interval. The vertical expansion radius is a length value representing the distance a straight line segment extends from the central broken line in both the positive and negative vertical directions. If the fluctuation amplitude within a given time interval is zero, then the vertical expansion radius of that straight line segment is zero. All straight line segments are assigned a unique vertical expansion radius according to the above rules; the vertical expansion radius of each straight line segment may be the same or different.

[0115] Furthermore, connect the upper left endpoint and the upper right endpoint with a straight line segment; this straight line segment is the corresponding upper boundary line segment. Similarly, move the left endpoint of the straight line segment along the negative vertical axis by the distance of the vertical expansion radius to obtain the lower left endpoint. Move the right endpoint of the straight line segment along the negative vertical axis by the distance of the vertical expansion radius to obtain the lower right endpoint. Connect the lower left endpoint and the lower right endpoint with a straight line segment; this straight line segment is the corresponding lower boundary line segment. The upper and lower boundary line segments maintain the same horizontal tilt angle as the original straight line segments; only the vertical coordinate is shifted. When the vertical expansion radius is zero, both the upper and lower boundary line segments coincide with the original straight line segments. Perform the above translation operation on each straight line segment on the central broken line to obtain a set of upper boundary line segments and a set of lower boundary line segments.

[0116] Furthermore, when the vertical expansion radii of two adjacent time periods of equal length are different, the ordinate of the right endpoint of the first upper boundary segment is not equal to the ordinate of the left endpoint of the second upper boundary segment. In this case, a straight line segment perpendicular to the horizontal axis is used to connect these two endpoints, that is, a line is drawn vertically upwards or downwards from the position of the right endpoint to the position of the left endpoint. After performing the above connection operation on all adjacent upper boundary segments, a continuous polyline is formed, called the upper boundary polyline. Performing the same connection operation on all lower boundary segments yields the lower boundary polyline. The upper boundary polyline and the lower boundary polyline constitute the upper and lower fluctuation boundaries of the target process on the age axis, respectively.

[0117] Furthermore, the three lines share the same horizontal axis range, from the age timestamp of the first equal-length time interval to the age timestamp of the last equal-length time interval. At any given age timestamp, the ordinate of the central baseline represents the central level of that age point, the ordinate of the upper envelope represents the upper bound of fluctuation for that age point, and the ordinate of the lower envelope represents the lower bound of fluctuation for that age point. The vertical distance between the central baseline and the upper envelope is equal to the vertical radius of the corresponding line segment, and the vertical distance between the central baseline and the lower envelope is also equal to the same vertical radius. These three lines together constitute the individual developmental trajectory curve of the target process, which graphically and comprehensively describes the central trend and permissible range of fluctuation in an individual's cognitive development from the first to the last equal-length time interval.

[0118] In summary, transforming discrete intra-segment basic values ​​into continuous broken-line patterns intuitively presents the overall trend of individual cognitive development level changes with age. The central broken-line, as the core framework of the developmental trajectory, provides a clear benchmark path for the subsequent construction of the fluctuation envelope.

[0119] In summary, quantifying the fluctuation of individual cognitive performance within each time period as an extension distance in the vertical direction directly correlates the fluctuation amplitude with the line segment of the central broken line, realizing a spatial mapping between the developmental central trend and developmental stability, and providing accurate radius parameters for generating upper and lower boundaries.

[0120] In summary, by using vertical translation operations, symmetrical boundary segments are generated based on each segment of the central polyline, transforming the abstract fluctuation amplitude into a visualized fluctuation range boundary. This fully preserves the independent information of the fluctuation amplitude within each time period, avoiding information loss caused by smoothing or interpolation across time periods.

[0121] In general, different connection methods are used depending on whether the fluctuation amplitudes of adjacent time periods are the same. When the radii are the same, direct point-to-point connection is used to maintain the continuity and smoothness of the polyline. When the radii are different, vertical line segments are used to accurately reflect the abrupt changes in fluctuation amplitude. This allows the upper and lower boundary polylines to truly depict the step-by-step changes in the fluctuation envelope and avoids envelope distortion caused by incorrect connections.

[0122] In summary, the combination of the three broken lines in the same coordinate system forms a complete trajectory curve that includes the central trend of development and the range of developmental fluctuations. This curve not only preserves the typical performance of individuals in each age range, but also shows the allowable fluctuation boundaries, providing a dual graphical and numerical basis for subsequent group comparisons, deviation calculations, and identification of abnormal developmental segments.

[0123] In an embodiment of the present invention, when constructing the individual developmental trajectory curve of the target process by using the central polyline as the central baseline, the upper boundary polyline as the upper envelope, and the lower boundary polyline as the lower envelope, the method is specifically used for:

[0124] The central polyline, the upper boundary polyline, and the lower boundary polyline are discretely sampled at fixed intervals within a common range of independent variable values ​​to obtain the common sampling column and corresponding ordinate values ​​of the target process.

[0125] Based on the same sampling x-coordinate position in the common sampling column, extract the corresponding center line discrete point, upper boundary line discrete point, and lower boundary line discrete point on the center line, upper boundary line, and lower boundary line.

[0126] The midpoint between the discrete points of the upper boundary polyline and the discrete points of the lower boundary polyline along the vertical axis is taken as the midpoint of the envelope of the target process.

[0127] The midpoint between the discrete point of the central polyline and the midpoint of the envelope along the vertical axis is taken as the final point of the target process;

[0128] Connect the final points sequentially according to the ascending order of the horizontal coordinates in the common sampling column to obtain the individual development trajectory curve of the target process.

[0129] Specifically, first, the common value range of the three polylines—the center polyline, the upper boundary polyline, and the lower boundary polyline—on the horizontal axis is determined. This range begins with the age timestamp of the first equal-length time interval and ends with the age timestamp of the last equal-length time interval. Then, a fixed sampling interval is selected. Starting from the minimum value of the common value range, the interval is increased by a fixed interval each time until the maximum value is reached or exceeded, generating a series of equally spaced horizontal axis values. These horizontal axis values ​​are arranged in ascending order to form a sequence, which is called the common sampling column.

[0130] Specifically, each x-coordinate value in the common sampling column is traversed. For the current x-coordinate, the previously calculated y-coordinate value on the central broken line is combined with the current x-coordinate to form a coordinate point, which is called the central broken line discrete point. Similarly, the y-coordinate value on the upper boundary broken line is combined with it to form the upper boundary broken line discrete point, and the y-coordinate value on the lower boundary broken line is combined with it to form the lower boundary broken line discrete point.

[0131] Specifically, for each sampled x-coordinate in the common sampling column, the ordinate values ​​of the upper and lower boundary discrete points of the corresponding x-coordinate are extracted. The average of these two ordinate values ​​is calculated by adding the ordinate values ​​of the upper and lower boundary discrete points and then dividing by two. The result is the ordinate of the midpoint of the envelope at that x-coordinate.

[0132] Specifically, for each sampled x-coordinate in the common sampling column, the ordinate value of the discrete point on the central broken line corresponding to that x-coordinate is extracted, as well as the ordinate value of the midpoint of the envelope corresponding to that x-coordinate. The average of these two ordinate values ​​is calculated, that is, the ordinate value of the discrete point on the central broken line and the ordinate value of the midpoint of the envelope are added together and then divided by two. The result is the ordinate of the final point at that x-coordinate. This x-coordinate is combined with the calculated ordinate of the final point to form a new coordinate point, which is called the final point.

[0133] Specifically, in a planar coordinate system, all points in the final point sequence are extracted; these points are arranged in ascending order of their x-coordinates. Starting with the first final point, a straight line segment connects the first and second final points. Then, another straight line segment connects the second and third final points. This process is repeated, connecting adjacent final points sequentially, until the last final point is connected. All the straight line segments connected end-to-end form a continuous broken line; this broken line is the individual development trajectory curve of the target process.

[0134] Furthermore, for each x-coordinate value in the common sampling column, the corresponding y-coordinate value on the central polyline is calculated. This is done by finding the straight line segment containing the x-coordinate and performing linear interpolation based on the coordinates of the two endpoints of that segment. Similarly, linear interpolation is performed on the upper and lower boundary polylines to obtain the corresponding y-coordinate values. All x-coordinates and their corresponding y-coordinate values ​​on the three polylines together constitute the result of discrete sampling.

[0135] Furthermore, each sampled x-coordinate position corresponds to three discrete points, each belonging to one of three different broken lines. The discrete points of the central broken lines at all sampled x-coordinate positions are arranged in ascending order of x-coordinate to form a set of central broken line discrete points. The discrete points of the upper boundary broken lines at all sampled x-coordinate positions are arranged to form a set of upper boundary broken line discrete points, and the discrete points of the lower boundary broken lines at all sampled x-coordinate positions are arranged to form a set of lower boundary broken line discrete points. The points in these three sets have the same x-coordinate sequence, differing only in their y-coordinates.

[0136] Furthermore, this x-coordinate is combined with the calculated y-coordinate of the envelope midpoint to form a new coordinate point, called the envelope midpoint. The envelope midpoint is located at the exact midpoint of the line connecting the discrete points of the upper and lower boundary polylines, representing the central position of the oscillating envelope at that x-coordinate location. The above calculation is repeated for all sampled x-coordinates to obtain the envelope midpoint for each sampled x-coordinate. These envelope midpoints are arranged in ascending order of their x-coordinates, forming a sequence of envelope midpoints. The envelope midpoint reflects the geometric center lines of the upper and lower envelope lines without considering the central polyline.

[0137] Furthermore, the final point is located precisely at the midpoint of the line connecting the discrete points of the central polygonal line and the midpoint of the envelope, simultaneously considering both the central trajectory of individual development and the geometric center of the envelope. The above calculation is repeated for all sampled x-coordinates to obtain the final point corresponding to each sampled x-coordinate. These final points are arranged in ascending order of x-coordinate, forming a final point sequence. The final point sequence is smoother than the original discrete points of the central polygonal line and incorporates information from the undulating envelope.

[0138] Furthermore, unlike the original central polyline, this curve is obtained by reconnecting the central polyline, upper boundary polyline, and lower boundary polyline after discrete sampling, envelope midpoint calculation, and final point calculation, resulting in better smoothness and stability. The individual developmental trajectory curve fully presents the developmental path of the target process on the age axis, providing a standardized curve shape for subsequent developmental deviation analysis and identification of local abnormal developmental segments.

[0139] In summary, by using a uniform fixed-interval sampling method, the three polylines originally connected by straight line segments are transformed into a discrete set of points with the same abscissa sequence. This eliminates the problems of inconsistent line segment lengths and uneven sampling density in the original polylines, and provides a standardized data alignment basis for subsequent point-to-point calculations at the same abscissa position.

[0140] In summary, by simultaneously acquiring discrete points on three polylines on each common sampling x-axis, the information of the central polyline, the upper boundary polyline, and the lower boundary polyline are completely corresponding at the same x-axis. This allows the use of three strictly registered y-axis values ​​when calculating the midpoint and final point of the envelope, avoiding calculation errors caused by coordinate offset.

[0141] In summary, by calculating the geometric midpoints of the upper and lower envelopes, the central position of the fluctuation envelope is extracted. This midpoint, independent of the central polyline, reflects the symmetry center of the fluctuation range defined by the upper and lower boundaries, providing an intermediate reference point for subsequent secondary fusion with the central polyline.

[0142] In summary, by further integrating the central baseline of individual development with the geometric center line of the fluctuation envelope, a new point sequence with both central tendency and envelope equilibrium characteristics is generated. This final point can inherit the developmental level represented by the central polyline and smooth out local anomalies caused by data sparsity or fluctuation mutations in the original polyline, making the final trajectory curve more robust.

[0143] In summary, by sequentially connecting the final point sequences, a continuous and smooth developmental trajectory curve is formed. This curve not only preserves the core developmental information of individuals at each age but also incorporates the equilibrium characteristics of the fluctuation envelope. Compared with directly using the central broken line, this curve has better noise resistance and continuity, providing a more reliable individual developmental baseline for subsequent segmented deviation analysis with the population average developmental sequence.

[0144] In an example of the present invention, when determining the population average developmental sequence and the population fluctuation envelope interval of the target process based on the statistical characteristics of the mean of the baseline values ​​of individuals in the population reference set and the fluctuation amplitude within the segment, the specific method is as follows:

[0145] The mean basic values ​​of individuals in the population reference set are arranged in chronological order to obtain the population average developmental sequence of the target process;

[0146] The minimum and maximum values ​​of the fluctuation amplitude within the reference set segment of the group are used as the lower and upper bounds, respectively, to define the group fluctuation envelope interval of the target process.

[0147] Specifically, the group reference set contains cognitive development data from multiple individuals, and the intra-segment baseline values ​​for each individual have been calculated for each equal-length time period. For each equal-length time period, the intra-segment baseline values ​​of all individuals in the group reference set for that time period are extracted, and the arithmetic mean of these intra-segment baseline values ​​is calculated. This mean is called the individual baseline mean for that time period. In practice, the intra-segment baseline values ​​of all individuals within that time period are summed one by one, and then divided by the total number of individuals in the group reference set. The result is the individual baseline mean for that time period.

[0148] Specifically, the intra-segment fluctuation amplitude of each individual in the group reference set has been calculated for each equal-length time interval. For each equal-length time interval, the intra-segment fluctuation amplitude values ​​of all individuals in the group reference set for that time interval are retrieved to form a numerical set. The smallest value in this set is identified as the minimum intra-segment fluctuation amplitude for that time interval. The largest value in this set is identified as the maximum intra-segment fluctuation amplitude for that time interval.

[0149] Furthermore, following the chronological order of equal-length time intervals, the individual baseline mean is calculated sequentially for each time interval, from the first to the last. All calculated individual baseline means are then arranged chronologically into a sequence, with the first element corresponding to the first equal-length time interval, the second element to the second, and so on, until the last element corresponds to the last equal-length time interval. This chronologically arranged sequence of individual baseline means constitutes the population-average developmental sequence for the target process. The population-average developmental sequence represents the average cognitive developmental level of the reference population at each age interval, serving as a benchmark for subsequent comparisons with individual developmental trajectories.

[0150] Furthermore, following the chronological order of equal-length time intervals, minimum and maximum values ​​are extracted for each equal-length time interval to obtain the minimum and maximum fluctuation ranges within each interval. For each equal-length time interval, the minimum value is used as the lower boundary, and the maximum value is used as the upper boundary. These two boundary values ​​together define a numerical range within that time interval, which is called the population fluctuation envelope interval for that time interval. All population fluctuation envelope intervals for equal-length time intervals are organized chronologically to form a set of population fluctuation envelope intervals covering the entire age range. The population fluctuation envelope interval represents the normal range of cognitive fluctuation amplitude for the reference group within that age range. Any individual whose intra-segment fluctuation amplitude falls outside this interval is considered to have abnormal fluctuation.

[0151] In summary, by calculating the arithmetic mean of the intra-segment baseline values ​​of all individuals in each equal-length time period in the group reference set, and organizing them into a sequence according to age timestamps, a baseline curve representing the normal developmental level of the group is constructed. This sequence serves as a reference standard for subsequent calculation of individual developmental deviations, providing a unified quantitative basis for comparing individuals with the group, and accurately identifying the degree to which an individual's development is ahead or behind the average level of the group.

[0152] In summary, within each equal-length time period, the minimum value of the fluctuation range within all individuals in the population reference set is extracted as the lower boundary, and the maximum value is extracted as the upper boundary, forming the normal fluctuation range for that time period. This range reflects the normal variation limit of the cognitive stability of the population within the corresponding age group, providing a dynamic threshold standard based on population statistics for judging whether the fluctuation range within an individual's segment is abnormal. At the same time, taking the minimum and maximum values ​​directly as the lower and upper boundaries instead of the mean or quantiles can completely preserve the actual fluctuation boundary of the population and avoid missing extreme individuals who are still within the normal range of the population due to statistical compression.

[0153] In this invention embodiment, the step of using the central baseline sequence of the individual developmental trajectory curve as the developmental baseline and performing segment-by-segment deviation analysis on the population average developmental sequence to obtain the difference sequence of the target process and the corresponding developmental deviation is specifically used for:

[0154] The difference between the base value in the central base value sequence of the individual development trajectory curve and the population average base value in the corresponding time period in the population average development sequence is arranged in timestamp order to obtain the difference sequence of the target process.

[0155] The ratio of the number of differences in the difference sequence that fall outside the population fluctuation envelope interval of the target process to the total number of differences in the difference sequence is taken as the developmental deviation of the target process.

[0156] Specifically, each baseline value in the central baseline value sequence of the individual developmental trajectory curve corresponds to an equal-length time period. This baseline value is the central value obtained by resampling the intra-segment baseline values ​​extracted from the segmented fluctuation characteristics after constructing the individual developmental trajectory curve. Each population average baseline value in the population average developmental sequence corresponds to the mean of the individual baseline values ​​for the same time period. For each equal-length time period, the baseline value for that time period is taken from the central baseline value sequence of the individual developmental trajectory curve, and the population average baseline value for that time period is also taken from the population average developmental sequence. The difference between the two is calculated, i.e., the difference for that time period is obtained by subtracting the population average baseline value from the individual baseline value.

[0157] Specifically, each difference in the difference sequence corresponds to an equal-length time period, and this equal-length time period has a predefined group fluctuation envelope interval, which is defined by a lower boundary and an upper boundary. For each difference in the difference sequence, it is determined whether the difference falls within the group fluctuation envelope interval of the corresponding time period, that is, whether the difference is greater than or equal to the lower boundary and less than or equal to the upper boundary.

[0158] Furthermore, if the individual baseline value is greater than the population average baseline value, the difference is positive; if the individual baseline value is less than the population average baseline value, the difference is negative; if the two are equal, the difference is zero. Following the timestamp order of equal-length time periods, the difference for each time period is calculated sequentially from the first to the last time period. These differences are then arranged into a sequence, where the first element corresponds to the difference for the first time period, the second element to the difference for the second time period, and so on, until the last element corresponds to the difference for the last time period. This sequence of differences arranged in timestamp order is the difference sequence of the target process. The difference sequence reflects the degree and direction of deviation between the individual developmental level and the population average developmental level in each age interval.

[0159] Furthermore, if the difference includes the endpoints between the lower and upper boundaries, the difference is considered to fall within the interval; if the difference is less than the lower boundary or greater than the upper boundary, the difference is considered to fall outside the interval. All differences in the difference sequence are iterated through, and the total number of differences falling outside the group's fluctuation envelope is counted. Simultaneously, the total number of differences in the difference sequence, i.e., the total number of equal-length time intervals, is also counted. The ratio of the number of differences falling outside the interval to the total number of differences is the developmental deviation of the target process. The developmental deviation is a value between zero and one. Zero indicates that all differences fall within the group's fluctuation envelope, meaning the individual's development is entirely within the normal fluctuation range of the group; one indicates that all differences fall outside the interval, meaning the individual's development deviates from the normal range of the group at all ages. The larger the developmental deviation, the more severe the overall deviation of the individual's cognitive development from the group's average level.

[0160] In summary, by calculating the difference between the individual development center baseline and the population average baseline over time periods, and organizing the difference into a sequence according to age, the absolute developmental gap between individuals and the population is transformed into directional time series data. This difference sequence not only retains the sign information of whether an individual is ahead or behind the population, but also fully records the dynamic process of the deviation changing with age, providing basic data for subsequent calculation of developmental deviation and identification of local abnormal developmental segments.

[0161] In summary, by statistically analyzing the proportion of differences in the difference sequence that exceed the population fluctuation envelope to the total number of differences, the degree of individual overall developmental deviation is quantified into a standardized index between zero and one. This developmental deviation eliminates the influence of the total number over an equal time period, making individuals of different age spans and different assessment frequencies comparable. At the same time, this index comprehensively reflects the overall frequency of an individual's deviation from the normal fluctuation range of the population across all age groups, providing a simple and effective quantitative basis for assessing the overall degree of abnormality in an individual's cognitive development.

[0162] In an embodiment of the present invention, when the segment continuously located outside the population fluctuation envelope in the difference sequence is taken as a local abnormal development segment, and the developmental difference matrix, the developmental deviation degree, and the local abnormal development segment are combined into a developmental state evaluation vector of the target process, it is specifically used for:

[0163] The positional relationship between the difference in the difference sequence and the lower and upper boundaries of the population fluctuation envelope interval in the corresponding time period is determined sequentially: the position of the first difference between the lower and upper boundaries is marked as the starting point of the current segment in the target process, and the sequence is traversed sequentially along the increasing direction of the difference sequence number to obtain the local abnormal development segment of the target process.

[0164] The developmental difference matrix, the developmental deviation degree, and the local abnormal developmental segments are sequentially concatenated to obtain the developmental status assessment vector of the target process.

[0165] Specifically, starting from the first difference in the difference sequence, extract the lower and upper boundaries of the group fluctuation envelope interval of that difference and its corresponding time period. Determine if the difference is greater than or equal to the lower boundary and less than or equal to the upper boundary. If the difference lies between the lower and upper boundaries, mark it as the starting point of the current segment and record its position in the difference sequence. If the difference is not within the interval, continue moving to the next difference and repeat the above judgment operation until the first difference within the interval is found. After finding the starting point, starting from the next difference, sequentially traverse each subsequent difference in the increasing direction of the difference sequence number.

[0166] Specifically, the developmental difference matrix is ​​first converted into a row vector form, that is, each row in the matrix is ​​concatenated sequentially to form a one-dimensional sequence. The original developmental difference matrix has multiple rows and columns; all its elements are extracted in row-major order and arranged into a long sequence, which serves as the first component of the developmental status assessment vector. Then, the developmental deviation value, a real number between zero and one, is appended directly to the end of this sequence after the converted developmental difference matrix.

[0167] Furthermore, for each difference encountered, it is determined whether it lies outside the population fluctuation envelope of the corresponding time period, i.e., whether the difference is less than the lower boundary or greater than the upper boundary. If the difference lies outside the interval, it is recorded as part of a local abnormal development segment. The process continues until the first difference within the interval is encountered, at which point the current local abnormal development segment ends. The start and end numbers of this segment, as well as the equal-length time intervals corresponding to all differences within the segment, are recorded. Then, starting from the next difference at the current end position, the next difference within the interval is searched as the starting point of a new segment, and the above process is repeated until the entire difference sequence is traversed. All recorded consecutive difference segments outside the interval together constitute the set of local abnormal development segments of the target process. Each local abnormal development segment contains the start time, end time, and difference values ​​for each time interval within the segment. These segments identify situations where individual development continuously deviates from the normal population fluctuation range within a specific age range.

[0168] Furthermore, all information from the local abnormal developmental segments is sequentially added after the developmental deviation value. Each local abnormal developmental segment comprises multiple segments, and each segment needs to record the start and end time interval numbers, as well as the differences between the time intervals within the segment. The information from these segments is unfolded sequentially according to their occurrence time. For each segment, the start and end numbers are recorded first, followed by the differences between the time intervals within that segment, and then the information for the next segment is recorded. After all the segment information is sequentially concatenated, it is appended to the developmental deviation value. This forms a complete one-dimensional sequence containing all cross-dimensional difference information of the developmental difference matrix, the overall developmental deviation value, and the specific locations and values ​​of local abnormal developmental segments. This sequence is the developmental status assessment vector for the target process. The developmental status assessment vector, as the final output, can be used for subsequent classification, comparison, or early warning analysis.

[0169] In summary, by identifying consecutive difference segments in the difference sequence that fall outside the population fluctuation envelope, the starting and ending age ranges of individual development deviations from the normal range of the population can be accurately located. Each local abnormal development segment directly corresponds to the period of continuous cognitive developmental abnormality, providing specific time windows and quantitative basis for clinical diagnosis, early intervention and individualized education program development, and avoiding the limitation of the overall deviation index masking the local abnormal period.

[0170] In summary, by integrating cross-dimensional developmental differences, overall developmental deviations, and local abnormal developmental periods into a structured vector representation, this vector contains multi-dimensional matrix-based differences, global quantitative indicators, and local segment location information, forming a comprehensive digital profile of an individual's cognitive developmental status. This facilitates subsequent automated analysis and decision support using machine learning classification, similarity retrieval, or threshold warning methods.

[0171] Compared with the prior art, the present invention has the following beneficial effects:

[0172] 1. This technology decomposes multidimensional data sequences of cognitive development into segmented fluctuations, separating and extracting the intra-segment basic values ​​and intra-segment fluctuation amplitudes within each equal-length time period, thus achieving dual quantification of developmental central trends and developmental stability. Based on the developmental difference matrix constructed from the segmented fluctuation characteristics, the system records the cross-dimensional difference coefficients of any two dimensions across all age groups, fully preserving the dynamic change patterns of developmental asynchrony between different cognitive domains. By expanding the intra-segment basic value sequence as the central trajectory and the intra-segment fluctuation amplitude as the vertical expansion radius to generate individual developmental trajectory curves, the individual's developmental path along the age axis and its permissible fluctuation boundaries are accurately characterized, providing a high-fidelity representation of individual development for subsequent analysis.

[0173] 2. This technique utilizes the mean of individual baseline values ​​in a population reference set to generate a population-average developmental sequence. It then defines the population fluctuation envelope interval based on the minimum and maximum values ​​of fluctuation amplitude within each segment, establishing a dynamic population comparison benchmark. By performing segment-by-segment deviation analysis on the central baseline sequence of individual developmental trajectory curves and the population-average developmental sequence to obtain a difference sequence, and combining this with the developmental deviation calculated from the population fluctuation envelope interval, it achieves precise quantification of the overall degree of developmental abnormality in individuals. Furthermore, by identifying local abnormal developmental segments continuously located outside the envelope interval in the difference sequence, it accurately pinpoints the specific age period in which the abnormality occurred. The developmental status assessment vector, formed by sequentially concatenating the developmental difference matrix, developmental deviation, and local abnormal developmental segments, integrates three types of information: cross-dimensional differences, global deviation, and local abnormalities, significantly improving the information completeness and interpretability of the developmental status assessment.

[0174] like Figure 2 The diagram shown is a functional block diagram of an intelligent information processing system based on children's cognitive development data provided in an embodiment of the present invention.

[0175] The intelligent information processing system 100 based on children's cognitive development data described in this invention can be installed in an electronic device. Depending on the functions implemented, the intelligent information processing system 100 may include a segmented fluctuation feature module 101, a developmental difference matrix module 102, an individual developmental trajectory curve module 103, a developmental fluctuation module 104, a developmental deviation module 105, and a developmental status assessment module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0176] In this embodiment, the functions of each module / unit are as follows:

[0177] The segmented fluctuation feature module acquires the cognitive development data and group reference set of the target process, and performs segmented fluctuation decomposition on the multidimensional data sequence of the cognitive development data to obtain the segmented fluctuation features of the target process.

[0178] The developmental difference matrix module arranges the cross-dimensional difference coefficients between the segmented fluctuation characteristics in chronological order to obtain the developmental difference matrix of the target process;

[0179] The individual development trajectory curve module takes the intra-segment basic value sequence of the segmented fluctuation characteristics as the central trajectory, and uses the intra-segment fluctuation amplitude corresponding to the intra-segment basic value sequence as the vertical expansion radius of the central trajectory in the corresponding time period for bilateral expansion to obtain the individual development trajectory curve of the target process.

[0180] The developmental fluctuation module determines the population average developmental sequence and population fluctuation envelope interval of the target process based on the statistical characteristics of the mean of the baseline values ​​of individuals in the population reference set and the fluctuation amplitude within the segment, respectively.

[0181] The developmental deviation module uses the central base value sequence of the individual developmental trajectory curve as the developmental baseline, performs segment-by-segment deviation analysis on the population average developmental sequence, and obtains the difference sequence of the target process and the corresponding developmental deviation.

[0182] The developmental status assessment module identifies segments in the difference sequence that are continuously located outside the population fluctuation envelope as local abnormal developmental segments, and combines the developmental difference matrix, the developmental deviation degree, and the local abnormal developmental segments into a developmental status assessment vector for the target process.

[0183] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0184] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0185] Furthermore, the functional modules 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. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0186] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0187] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0188] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent information processing method based on child cognitive development data, characterized by, The method includes: S1. Obtain cognitive development data and a group reference set for the target process, and perform segmented fluctuation decomposition on the multidimensional data sequence of the cognitive development data to obtain the segmented fluctuation characteristics of the target process; S2. Arrange the cross-dimensional difference coefficients between the segmented fluctuation characteristics in chronological order to obtain the developmental difference matrix of the target process; S3. Using the segmented fluctuation feature intra-segment basic value sequence as the central trajectory, and using the intra-segment fluctuation amplitude corresponding to the intra-segment basic value sequence as the vertical expansion radius of the central trajectory in the corresponding time period, perform bilateral expansion to obtain the individual development trajectory curve of the target process. S4. Based on the statistical characteristics of the mean base value of individuals in the population reference set and the fluctuation amplitude within the segment, determine the population average development sequence and population fluctuation envelope interval of the target process, respectively. S5. Using the central base value sequence of the individual development trajectory curve as the developmental baseline, perform segmented deviation analysis on the population average developmental sequence to obtain the difference sequence of the target process and the corresponding developmental deviation. S6. The segments in the difference sequence that are continuously located outside the population fluctuation envelope are taken as local abnormal developmental segments, and the developmental difference matrix, the developmental deviation degree and the local abnormal developmental segments are combined into the developmental state evaluation vector of the target process.

2. The intelligent information processing method based on child cognitive development data according to claim 1, characterized in that, The acquisition of cognitive development data and a group reference set for the target process, and the segmented fluctuation decomposition of the multidimensional data sequence of the cognitive development data to obtain the segmented fluctuation characteristics of the target process, include: The multidimensional data sequence of the target process is divided into equal-length time periods according to age timestamps. The arithmetic mean of the original evaluation values ​​within the equal-length time period is used as the base value within the equal-length time period. The summation of the absolute values ​​of the differences between the original evaluation values ​​and the baseline values ​​within the equal-length time period yields the cumulative fluctuation amount for the equal-length time period. The ratio of the total cumulative fluctuation to the number of data points within the equal-length time period is taken as the fluctuation amplitude within the equal-length time period. By combining the basic value within the segment with the fluctuation amplitude within the segment in chronological order, the segmented fluctuation characteristics of the target process are obtained.

3. The intelligent information processing method based on child cognitive development data according to claim 1, characterized in that, The step of arranging the cross-dimensional difference coefficients among the segmented fluctuation characteristics in chronological order to obtain the developmental difference matrix of the target process includes: By selecting fluctuation features of any dimension from the segmented fluctuation features, the dimension pairs of the target process are obtained; The cross-dimensional difference coefficient of the target process is calculated based on the intra-segment basic value difference and the total intra-segment fluctuation amplitude of the dimension pair. Arrange the cross-dimensional difference coefficients in chronological order to obtain the row vector of the target process, and use the row vector as the first row to iterate through all dimensions of the segmented fluctuation features to obtain the developmental difference matrix of the target process.

4. The intelligent information processing method based on children's cognitive development data as described in claim 3, characterized in that, The formula for calculating the cross-dimensional difference coefficient includes: in, For the first Wei and Di Vi in the Cross-dimensional difference coefficients for isochronous intervals This is the sequence number of the first dimension. This is the sequence number for the second dimension. These are the sequence numbers of the isochronous intervals. For the first The dimension in the first The basic value within a time period, For the first The dimension in the first The basic value within a time period, The total number of isochronous intervals. For the first The dimension in the first The fluctuation range within a given time period For the first The dimension in the first The fluctuation range within a given time period.

5. The intelligent information processing method based on child cognitive development data according to claim 1, characterized in that, The step of using the intra-segment basic value sequence of the segmented fluctuation characteristics as the central trajectory, and using the intra-segment fluctuation amplitude corresponding to the intra-segment basic value sequence as the vertical expansion radius of the central trajectory within the corresponding time period for bilateral expansion, to obtain the individual development trajectory curve of the target process, includes: Using the age timestamp of the target process as the horizontal axis and the intra-segment basic value of the segmented fluctuation characteristics as the vertical axis, the intra-segment basic values ​​of equal time periods in the target process are connected sequentially in chronological order to obtain the central broken line of the target process; The fluctuation range of the straight line segment on the central broken line within the corresponding equal time period is taken as the vertical expansion radius of the straight line segment; The upper and lower boundary segments of the target process are obtained by translating the straight line segments by the vertical extension radius in the vertical direction. The upper boundary line segment and the lower boundary line segment are connected sequentially in chronological order to obtain the upper boundary polyline and the lower boundary polyline of the target process; wherein, when the vertical expansion radius of adjacent time periods of equal length in the target process is the same, the endpoints of the earlier time boundary line segment in the target process and the endpoints of the later time boundary line segment in the target process are connected point-to-point; when the vertical expansion radius of adjacent time periods of equal length in the target process is different, the upper boundary endpoints of the earlier time boundary line segment in the target process and the upper boundary endpoints of the later time boundary line segment in the target process are connected by vertical line segments. Using the central polyline as the central baseline, the upper boundary polyline as the upper envelope, and the lower boundary polyline as the lower envelope, the individual developmental trajectory curve of the target process is constructed together.

6. The intelligent information processing method based on child cognitive development data according to claim 5, characterized in that, The step of constructing the individual developmental trajectory curve of the target process by using the central polygonal line as the central baseline, the upper boundary polygonal line as the upper envelope, and the lower boundary polygonal line as the lower envelope includes: The central polyline, the upper boundary polyline, and the lower boundary polyline are discretely sampled at fixed intervals within a common range of independent variable values ​​to obtain the common sampling column and corresponding ordinate values ​​of the target process. Based on the same sampling x-coordinate position in the common sampling column, extract the corresponding center line discrete point, upper boundary line discrete point, and lower boundary line discrete point on the center line, upper boundary line, and lower boundary line. The midpoint between the discrete points of the upper boundary polyline and the discrete points of the lower boundary polyline along the vertical axis is taken as the midpoint of the envelope of the target process. The midpoint between the discrete point of the central polyline and the midpoint of the envelope along the vertical axis is taken as the final point of the target process; Connect the final points sequentially according to the ascending order of the horizontal coordinates in the common sampling column to obtain the individual development trajectory curve of the target process.

7. The intelligent information processing method based on child cognitive development data according to claim 1, characterized by, The step of determining the population average developmental sequence and population fluctuation envelope interval of the target process based on the statistical characteristics of the mean base value and the fluctuation amplitude within the population reference set includes: The mean basic values ​​of individuals in the population reference set are arranged in chronological order to obtain the population average developmental sequence of the target process; The minimum and maximum values ​​of the fluctuation amplitude within the reference set segment of the group are used as the lower and upper bounds, respectively, to define the group fluctuation envelope interval of the target process.

8. The intelligent information processing method based on children's cognitive development data as described in claim 1, characterized in that, The step of using the central baseline sequence of the individual developmental trajectory curve as the developmental baseline, and performing segment-by-segment deviation analysis on the population average developmental sequence to obtain the difference sequence of the target process and the corresponding developmental deviation degree includes: The difference between the base value in the central base value sequence of the individual development trajectory curve and the population average base value in the corresponding time period in the population average development sequence is arranged in timestamp order to obtain the difference sequence of the target process. The ratio of the number of differences in the difference sequence that fall outside the population fluctuation envelope interval of the target process to the total number of differences in the difference sequence is taken as the developmental deviation of the target process.

9. The intelligent information processing method based on children's cognitive development data as described in claim 1, characterized in that, The step of taking segments in the difference sequence that are continuously located outside the population fluctuation envelope as local abnormal developmental segments, and combining the developmental difference matrix, the developmental deviation degree, and the local abnormal developmental segments into a developmental state assessment vector for the target process, includes: The positional relationship between the difference in the difference sequence and the lower and upper boundaries of the population fluctuation envelope interval in the corresponding time period is determined sequentially: the position of the first difference between the lower and upper boundaries is marked as the starting point of the current segment in the target process, and the sequence is traversed sequentially along the increasing direction of the difference sequence number to obtain the local abnormal development segment of the target process. The developmental difference matrix, the developmental deviation degree, and the local abnormal developmental segments are sequentially concatenated to obtain the developmental status assessment vector of the target process.

10. An intelligent information processing system based on children's cognitive development data, for implementing an intelligent information processing method based on children's cognitive development data according to any one of claims 1-9, characterized in that, The system includes: The segmented fluctuation feature module acquires the cognitive development data and group reference set of the target process, and performs segmented fluctuation decomposition on the multidimensional data sequence of the cognitive development data to obtain the segmented fluctuation features of the target process. The developmental difference matrix module arranges the cross-dimensional difference coefficients between the segmented fluctuation characteristics in chronological order to obtain the developmental difference matrix of the target process; The individual development trajectory curve module takes the intra-segment basic value sequence of the segmented fluctuation characteristics as the central trajectory, and uses the intra-segment fluctuation amplitude corresponding to the intra-segment basic value sequence as the vertical expansion radius of the central trajectory in the corresponding time period for bilateral expansion to obtain the individual development trajectory curve of the target process. The developmental fluctuation module determines the population average developmental sequence and population fluctuation envelope interval of the target process based on the statistical characteristics of the mean of the baseline values ​​of individuals in the population reference set and the fluctuation amplitude within the segment, respectively. The developmental deviation module uses the central base value sequence of the individual developmental trajectory curve as the developmental baseline, performs segment-by-segment deviation analysis on the population average developmental sequence, and obtains the difference sequence of the target process and the corresponding developmental deviation. The developmental status assessment module identifies segments in the difference sequence that are continuously located outside the population fluctuation envelope as local abnormal developmental segments, and combines the developmental difference matrix, the developmental deviation degree, and the local abnormal developmental segments into a developmental status assessment vector for the target process.

Images