Early Diagnosis System for Parkinson's Disease Based on Handwriting Behavioral Feature Recognition

Abstract

The present invention discloses an early diagnosis system for Parkinson's disease based on handwriting behavior feature recognition, belonging to the technical field of Parkinson's disease, and includes a data acquisition module, a data processing module, a model construction module, a test optimization module, a prediction diagnosis module, and an intelligent control module. The present invention solves the problems that the existing methods cannot perform early diagnosis of Parkinson's disease based on handwriting behavior feature recognition, cannot provide early intervention and treatment suggestions for patients, and reduce the treatment effect. The present invention predicts the real-time data of handwriting behavior and performs early diagnosis of Parkinson's disease based on the optimal early diagnosis model of Parkinson's disease, determines the early diagnosis result of Parkinson's disease, and formulates an early control plan for Parkinson's disease to perform intelligent control on early-stage Parkinson's disease patients. It can perform early diagnosis of Parkinson's disease based on handwriting behavior feature recognition, can provide early intervention and treatment suggestions for patients, and can improve the treatment effect.

Description

Technical Field

[0001] The present invention relates to the technical field of Parkinson's disease, and in particular to an early diagnosis system for Parkinson's disease based on handwriting behavior feature recognition. Background Art

[0002] Parkinson's disease, also often referred to as "Parkinson's paralysis," is a neurodegenerative disease. The main cause of this disease is the degeneration and death of dopaminergic neurons in the substantia nigra, which may be related to multiple factors such as genetics, environmental factors, and aging of the nervous system. It is generally recognized that aging is the most important factor in the occurrence of Parkinson's disease. The disease has a significant high incidence in the elderly. At present, there are still great difficulties in the early diagnosis of Parkinson's disease, resulting in many patients not receiving timely treatment in the early stages of the disease, affecting the treatment effect and prognosis.

[0003] Chinese patent with publication number CN117222355A discloses a method for treating, preventing or ameliorating Parkinson's disease with putinizumab, wherein a mobile device is provided to a patient, the mobile device is programmed to receive and transmit data obtained to measure the patient's passive and / or active movement; data transmitted from the mobile device is collected; the data obtained from the patient is compared with control data to assess the presence or extent of motor deficits in the individual, and / or the data obtained from the patient is monitored for a period of time sufficient to identify changes in the patient's active or passive motor function; however, the patent has the following defects:

[0004] The existing methods cannot perform early diagnosis of Parkinson's disease based on handwriting behavior feature recognition, cannot provide early intervention and treatment suggestions for patients, and thus reduce the treatment effect. Summary of the invention

[0005] The purpose of the present invention is to provide an early diagnosis system for Parkinson's disease based on handwriting behavior feature recognition, which can perform early diagnosis of Parkinson's disease based on handwriting behavior feature recognition, provide early intervention and treatment suggestions for patients, improve treatment effects, and solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The Parkinson's disease early diagnosis system based on handwriting behavior feature recognition includes:

[0008] A data collection module, used to collect the user's brain electrical activity change data, the user's handwriting data and the user's handwriting drawing data, and determine the handwriting behavior perception data based on the non-invasive electroencephalogram;

[0009] A data processing module, used for processing the handwriting behavior perception data based on the non-invasive electroencephalogram to determine the handwriting behavior feature data based on the non-invasive electroencephalogram;

[0010] A model construction module, configured to construct an early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition according to the needs of early diagnosis of Parkinson's disease;

[0011] A test and optimization module, configured to test, evaluate and optimize the early diagnosis model for Parkinson's disease, and determine an optimal early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition;

[0012] A prediction and diagnosis module, configured to predict and perform early diagnosis of Parkinson's disease on real-time handwriting behavior data, and determine an early diagnosis result of Parkinson's disease based on handwriting behavior feature recognition;

[0013] An intelligent control module, configured to formulate an early control plan for Parkinson's disease based on handwriting behavior feature recognition, and perform intelligent control on early-stage Parkinson's disease patients.

[0014] Preferably, the data acquisition module includes:

[0015] An electroencephalogram acquisition unit, configured to monitor and acquire the brain function and cognitive state of a user during writing based on non-invasive electroencephalogram, and acquire electroencephalogram activity change data of the user;

[0016] A handwriting acquisition unit, configured to monitor and acquire the handwritten characters of a user during writing based on computer vision, and acquire handwritten character data of the user;

[0017] A painting acquisition unit, configured to monitor and acquire the handwritten paintings of a user during writing based on computer vision, and acquire handwritten painting data of the user;

[0018] Among them, based on the electroencephalogram activity change data of the user, the handwritten character data of the user, and the handwritten painting data of the user, handwriting behavior perception data based on non-invasive electroencephalogram is determined.

[0019] Preferably, the data acquisition module further includes:

[0020] A word count real-time acquisition module, configured to real-time acquire the number of complete characters completed per unit time during the writing process of a user; wherein, the value range of the unit time is 2 min - 8 min;

[0021] A text area acquisition module, configured to, after each unit time is completed, acquire the area occupied by each character corresponding to each character completed within each unit time for each character completed within each unit time;

[0022] A writing index parameter acquisition module, configured to acquire writing index parameters corresponding to the unit time according to the number of complete characters of the user per unit time and the area occupied by each character corresponding to each character completed within each unit time;

[0023] Among them, the writing index parameter is obtained through the following formula:

[0024]

[0025] Among them, R represents the writing index parameter; n represents the number of unit times experienced by the user's writing; S zi represents the total writing area corresponding to the i-th unit time; S zi-1 represents the total writing area corresponding to the (i - 1)-th unit time; N i represents the number of complete written characters corresponding to the i-th unit time; N i-1 represents the number of complete written characters corresponding to the (i - 1)-th unit time; f n represents the standard deviation of the number of complete written characters corresponding to n unit times; N p represents the average value of the number of complete written characters corresponding to n unit times; S p represents the average value of the total writing area corresponding to n unit times; S dij represents the area occupied by the characters of the j-th complete written character in the i-th unit time;

[0026] An adjustment module is used to adjust the time interval of handwritten character acquisition by using the difference value of the writing index parameters of every two adjacent unit times.

[0027] Preferably, the adjustment module includes:

[0028] A writing index parameter extraction module is used to extract the writing index parameters of every two adjacent unit times;

[0029] A difference value acquisition module is used to obtain the difference value of the writing index parameters of every two adjacent unit times by using the writing index parameters of every two adjacent unit times;

[0030] A first group of writing index parameter acquisition module is used to extract the writing index parameters of two unit times corresponding to the maximum difference value in the difference values of the writing index parameters of every two adjacent unit times as the first group of writing index parameters;

[0031] A second group of writing index parameter acquisition module is used to extract the writing index parameters of two unit times corresponding to the minimum difference value in the difference values of the writing index parameters of every two adjacent unit times as the second group of writing index parameters;

[0032] A collection time interval adjustment coefficient acquisition module is used to obtain a collection time interval adjustment coefficient by using the first group of writing index parameters and the second group of writing index parameters, where the collection time interval adjustment coefficient is obtained through the following formula:

[0033]

[0034] Among them, K represents the acquisition time interval adjustment coefficient; k represents the number of writing index parameters except for the first group of writing index parameters and the second group of writing index parameters; R i represents the value corresponding to the i-th writing index parameter except for the first group of writing index parameters and the second group of writing index parameters; C max and C min respectively represent the maximum difference and the minimum difference in the difference values of the writing index parameters for every two adjacent unit times; R max01 and R max02 respectively represent the writing index parameters for two unit times corresponding to the first group of writing index parameters; R min01 and R min02 respectively represent the writing index parameters for two unit times corresponding to the second group of writing index parameters;

[0035] A comparison module, configured to compare the acquisition time interval adjustment coefficient with a preset adjustment coefficient threshold;

[0036] An adjustment execution module, configured to, when the acquisition time interval adjustment coefficient exceeds the preset adjustment coefficient threshold, adjust the time interval for current handwritten character acquisition by using the acquisition time interval adjustment coefficient to obtain an adjusted time interval for handwritten character acquisition;

[0037] Among them, the adjusted time interval for handwritten character acquisition is obtained through the following formula:

[0038] T = [1 + log 10 (1 + K)] · T0

[0039] Among them, T represents the adjusted time interval for handwritten character acquisition; T0 represents the current time interval for handwritten character acquisition; K represents the acquisition time interval adjustment coefficient.

[0040] Preferably, the data processing module includes:

[0041] A data cleaning unit, configured to clean the handwriting behavior perception data;

[0042] Obtain handwriting behavior perception data based on non-invasive electroencephalogram;

[0043] Cleaning the handwriting behavior perception data based on non-invasive electroencephalogram includes:

[0044] Performing consistency check on the handwriting behavior perception data based on non-invasive electroencephalogram;

[0045] Check whether the non-invasive electroencephalogram-based handwriting behavior perception data meets the requirements according to the reasonable value ranges and mutual relationships of each variable in the data;

[0046] Remove the inconsistent data that exceeds the normal range, is logically unreasonable or contradictory in the non-invasive electroencephalogram-based handwriting behavior perception data;

[0047] Process the invalid values and missing values in the non-invasive electroencephalogram-based handwriting behavior perception data;

[0048] Remove the invalid data and missing data that are worthless for the early diagnosis of Parkinson's disease in the non-invasive electroencephalogram-based handwriting behavior perception data;

[0049] Determine the handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease.

[0050] Preferably, the data processing module further includes:

[0051] A data conversion unit for converting the cleaned handwriting behavior perception data;

[0052] Obtain the cleaned handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease;

[0053] Convert the handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease;

[0054] Eliminate the dimensional differences between the handwriting behavior perception data;

[0055] Determine the handwriting behavior perception data with data standardization;

[0056] A feature extraction unit for extracting features from the converted handwriting behavior perception data;

[0057] Obtain the converted handwriting behavior perception data with data standardization;

[0058] Extract features from the handwriting behavior perception data with data standardization;

[0059] Extract the features that can reflect the early diagnosis of Parkinson's disease;

[0060] Determine the non-invasive electroencephalogram-based handwriting behavior feature data.

[0061] Preferably, the model construction module includes:

[0062] A data division unit for dividing the handwriting behavior feature data;

[0063] Obtain the non-invasive electroencephalogram-based handwriting behavior feature data;

[0064] Partition the handwriting behavior feature data based on non-invasive electroencephalogram;

[0065] Determine the training data set and the test data set;

[0066] A model training unit for constructing an early diagnosis model for Parkinson's disease;

[0067] According to the early diagnosis requirements of Parkinson's disease based on handwriting behavior feature recognition, select a neural network model framework suitable for the early diagnosis of Parkinson's disease;

[0068] Based on the training data set, train the selected neural network model framework suitable for the early diagnosis of Parkinson's disease;

[0069] Determine the early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition.

[0070] Preferably, the test optimization module includes:

[0071] A test evaluation unit for testing and evaluating the early diagnosis model for Parkinson's disease;

[0072] Obtain the early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition;

[0073] Based on the test data set, test and evaluate the early diagnosis model for Parkinson's disease;

[0074] Determine the test evaluation result of the early diagnosis model for Parkinson's disease;

[0075] An optimization adjustment unit for optimizing and adjusting the early diagnosis model for Parkinson's disease;

[0076] Obtain the test evaluation result of the early diagnosis model for Parkinson's disease;

[0077] Mine and analyze the test evaluation result of the early diagnosis model for Parkinson's disease;

[0078] Determine the optimization adjustment plan for the early diagnosis model for Parkinson's disease;

[0079] Optimize and adjust the early diagnosis model for Parkinson's disease according to the optimization adjustment plan for the early diagnosis model for Parkinson's disease;

[0080] Determine the optimal early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition.

[0081] Preferably, the prediction and diagnosis module includes:

[0082] A data acquisition unit for acquiring real-time data of handwriting behavior based on non-invasive electroencephalogram;

[0083] According to the need for early diagnosis of Parkinson's disease based on handwriting behavior feature recognition, the EEG changes, handwritten characters, and hand-drawn paintings of users are monitored and collected in real time to obtain real-time handwriting behavior data based on non-invasive electroencephalogram.

[0084] A prediction and diagnosis unit for predicting and early diagnosing Parkinson's disease for the real-time handwriting behavior data.

[0085] Obtain the optimal early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition.

[0086] Input the real-time handwriting behavior data based on non-invasive electroencephalogram into the optimal early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition.

[0087] Predict and early diagnose Parkinson's disease for the real-time handwriting behavior data based on non-invasive electroencephalogram based on the optimal early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition.

[0088] Determine the early diagnosis result of Parkinson's disease based on handwriting behavior feature recognition.

[0089] Among them, the early diagnosis result of Parkinson's disease based on handwriting behavior feature recognition includes: the user is an early-stage Parkinson's disease patient or the user is not an early-stage Parkinson's disease patient.

[0090] When the user is an early-stage Parkinson's disease patient, formulate an early-stage Parkinson's disease management and control plan to conduct intelligent management and control on early-stage Parkinson's disease patients.

[0091] Preferably, the intelligent management and control module includes:

[0092] A strategy formulation unit for formulating an early-stage Parkinson's disease management and control plan.

[0093] Obtain the early diagnosis result of Parkinson's disease based on handwriting behavior feature recognition.

[0094] Mine and analyze the early diagnosis result of Parkinson's disease based on handwriting behavior feature recognition.

[0095] Determine the early-stage Parkinson's disease management and control plan based on handwriting behavior feature recognition.

[0096] An intelligent management and control unit for conducting intelligent management and control on early-stage Parkinson's disease patients.

[0097] Obtain the early-stage Parkinson's disease management and control plan based on handwriting behavior feature recognition.

[0098] Based on the early-stage Parkinson's disease management and control plan, conduct intelligent management and control on early-stage Parkinson's disease patients, give early warnings to early-stage Parkinson's disease patients, and formulate personalized management and treatment measures for early-stage Parkinson's disease patients.

[0099] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0100] The present invention collects handwriting behavior perception data based on non-invasive electroencephalogram, processes the handwriting behavior perception data, determines handwriting behavior characteristic data, constructs an early diagnosis model for Parkinson's disease according to the early diagnosis requirements of Parkinson's disease, tests, evaluates and optimizes the early diagnosis model for Parkinson's disease, determines the optimal early diagnosis model for Parkinson's disease, predicts the real-time data of handwriting behavior and makes an early diagnosis of Parkinson's disease based on the optimal early diagnosis model for Parkinson's disease, determines the early diagnosis result of Parkinson's disease, and formulates an early management and control plan for Parkinson's disease to intelligently manage and control patients with early Parkinson's disease. It can make an early diagnosis of Parkinson's disease based on the recognition of handwriting behavior characteristics, provide early intervention and treatment suggestions for patients, and improve the treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] Figure 1 It is a structural block diagram of an early diagnosis system for Parkinson's disease based on the recognition of handwriting behavior characteristics of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0102] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0103] In order to solve the problems that the prior art cannot make an early diagnosis of Parkinson's disease based on the recognition of handwriting behavior characteristics, cannot provide early intervention and treatment suggestions for patients, and reduces the treatment effect, please refer to Figure 1 , the following technical solutions are provided in this embodiment:

[0104] An early diagnosis system for Parkinson's disease based on the recognition of handwriting behavior characteristics includes: a data acquisition module, a data processing module, a model construction module, a test and optimization module, a prediction and diagnosis module, and an intelligent management and control module.

[0105] It should be noted that through the interactive communication between the data acquisition module, the data processing module, the model construction module, the test and optimization module, the prediction and diagnosis module, and the intelligent management and control module, an early diagnosis of Parkinson's disease can be made based on the recognition of handwriting behavior characteristics, early intervention and treatment suggestions can be provided for patients, and the treatment effect can be improved.

[0106] Among them, the data acquisition module is used to collect the user's electroencephalogram activity change data, the user's handwritten text data, and the user's handwritten painting data, and determine the handwriting behavior perception data based on non-invasive electroencephalogram;

[0107] In this embodiment, the data acquisition module includes:

[0108] An electroencephalogram acquisition unit, configured to monitor and acquire the brain function and cognitive state of the user during the writing process based on non-invasive electroencephalogram, and acquire the electroencephalogram activity change data of the user;

[0109] It should be noted that an electroencephalogram is a graph obtained by amplifying and recording the spontaneous bioelectric potential of the brain from the scalp through a precision electronic instrument. It is the spontaneous and rhythmic electrical activity of a group of brain cells recorded through electrodes. By real-time monitoring of the patient's brain function, it helps to understand the development and changes of the condition and guide the adjustment of the treatment plan.

[0110] A handwriting acquisition unit, configured to monitor and acquire the handwritten characters of the user during the writing process based on computer vision, and acquire the handwritten character data of the user;

[0111] A drawing acquisition unit, configured to monitor and acquire the handwritten drawings of the user during the writing process based on computer vision, and acquire the handwritten drawing data of the user;

[0112] Among them, based on the electroencephalogram activity change data of the user, the handwritten character data of the user, and the handwritten drawing data of the user, the handwriting behavior perception data based on non-invasive electroencephalogram is determined.

[0113] Among them, the data processing module is configured to process the handwriting behavior perception data based on non-invasive electroencephalogram to determine the handwriting behavior feature data based on non-invasive electroencephalogram;

[0114] Specifically, the data acquisition module further includes:

[0115] A word count real-time acquisition module, configured to real-time acquire the number of complete words completed per unit time during the writing process of the user; wherein, the value range of the unit time is 2 min - 8 min;

[0116] A text area acquisition module, configured to, after each unit time is completed, acquire the area occupied by each word corresponding to each word completed within each unit time for each word completed within each unit time;

[0117] A writing index parameter acquisition module, configured to acquire the writing index parameter corresponding to the unit time according to the number of complete words of the user per unit time and the area occupied by each word corresponding to each word completed within each unit time;

[0118] Among them, the writing index parameter is obtained through the following formula:

[0119]

[0120] Among them, R represents the writing index parameter; n represents the number of unit times experienced by the user's writing; S zi represents the total writing area corresponding to the i-th unit time; S zi-1 represents the total writing area corresponding to the (i - 1)-th unit time; N i represents the number of complete characters written in the i-th unit time; N i-1 represents the number of complete characters written in the (i - 1)-th unit time; f n represents the standard deviation of the number of complete characters written in n unit times; N p represents the average value of the number of complete characters written in n unit times; S p represents the average value of the total writing area in n unit times; S dij represents the area occupied by the j-th complete character in the i-th unit time;

[0121] An adjustment module, which is used to adjust the time interval of handwritten character acquisition by using the difference value of the writing index parameters of every two adjacent unit times.

[0122] The technical effects of the above technical solution are as follows: Through the word count real-time acquisition module, the system can monitor in real time the number of complete characters completed by the user in each unit time during the writing process, so as to provide instant writing progress feedback for the user. The character area acquisition module can accurately calculate the area occupied by each character after each unit time ends, which provides a detailed data basis for subsequent writing analysis. The writing index parameter acquisition module calculates the writing index parameters through complex formulas, comprehensively considering multiple factors (such as writing area, number of characters, standard deviation, average value, etc.), making the analysis of writing behavior more comprehensive and in-depth.

[0123] The adjustment module uses the difference value of the writing index parameters of two adjacent unit times to dynamically adjust the time interval of handwritten character acquisition. This means that the system can automatically optimize the acquisition strategy according to the user's writing speed and habits to improve the accuracy and efficiency of data acquisition. Through real-time monitoring and dynamic adjustment, this technical solution can better adapt to the user's writing rhythm, reduce writing interruptions or data loss caused by inappropriate acquisition time intervals, and thus enhance the user's writing experience. The detailed writing data collected by this technical solution can provide valuable empirical materials for writing research, helping to deeply understand various factors and their interrelationships in the writing process. At the same time, these data can also be used for teaching evaluation to help teachers better understand students' writing habits and levels, so as to formulate more targeted teaching plans.

[0124] In summary, through means such as real-time monitoring, precise analysis, and dynamic adjustment, the above technical solution not only improves the accuracy and efficiency of handwritten character collection, but also provides a better writing experience for users, and provides strong support for writing research and teaching.

[0125] Specifically, the adjustment module includes:

[0126] A writing index parameter extraction module, configured to extract writing index parameters for every two adjacent unit times;

[0127] A difference value acquisition module, configured to obtain the difference value of the writing index parameters for every two adjacent unit times by using the writing index parameters for every two adjacent unit times;

[0128] A first group of writing index parameter acquisition modules, configured to extract the writing index parameters for two unit times corresponding to the maximum difference value in the difference values of the writing index parameters for every two adjacent unit times as the first group of writing index parameters;

[0129] A second group of writing index parameter acquisition modules, configured to extract the writing index parameters for two unit times corresponding to the minimum difference value in the difference values of the writing index parameters for every two adjacent unit times as the second group of writing index parameters;

[0130] An acquisition time interval adjustment coefficient acquisition module, configured to obtain an acquisition time interval adjustment coefficient by using the first group of writing index parameters and the second group of writing index parameters, where the acquisition time interval adjustment coefficient is obtained through the following formula:

[0131]

[0132] where K represents the acquisition time interval adjustment coefficient; k represents the number of writing index parameters other than the first group of writing index parameters and the second group of writing index parameters; R i represents the value corresponding to the i-th writing index parameter other than the first group of writing index parameters and the second group of writing index parameters; C max and C min respectively represent the maximum difference value and the minimum difference value in the difference values of the writing index parameters for every two adjacent unit times; R max01 and R max02 respectively represent the writing index parameters for two unit times corresponding to the first group of writing index parameters; R min01 and R min02 respectively represent the writing index parameters for two unit times corresponding to the second group of writing index parameters;

[0133] A comparison module, configured to compare the acquisition time interval adjustment coefficient with a preset adjustment coefficient threshold;

[0134] An adjustment execution module, which is used to adjust the time interval for current handwritten character acquisition by using the acquisition time interval adjustment coefficient when the acquisition time interval adjustment coefficient exceeds a preset adjustment coefficient threshold, so as to obtain an adjusted time interval for handwritten character acquisition;

[0135] Wherein, the adjusted time interval for handwritten character acquisition is obtained through the following formula:

[0136] T = [1 + log 10 (1 + K)]·T0

[0137] Wherein, T represents the adjusted time interval for handwritten character acquisition; T0 represents the current time interval for handwritten character acquisition; K represents the acquisition time interval adjustment coefficient.

[0138] The technical effects of the above technical solution are as follows: The writing index parameter extraction module and the difference value acquisition module can accurately extract the writing index parameters of every two adjacent unit times from a large amount of data and calculate the difference value between them. This provides key data support for subsequent adjustment of the acquisition time interval. The first group of writing index parameter acquisition module and the second group of writing index parameter acquisition module can capture extreme situations during the writing process by identifying the writing index parameters corresponding to the maximum difference value and the minimum difference value. These extreme situations often reflect sudden changes in writing speed or style, which have important reference value for adjusting the acquisition time interval.

[0139] The acquisition time interval adjustment coefficient acquisition module uses a complex formula to comprehensively consider multiple writing index parameters and difference values, and scientifically calculates the acquisition time interval adjustment coefficient. This coefficient takes into account both the overall trend of writing speed and the influence of extreme situations, ensuring the rationality and effectiveness of the adjustment. The comparison module and the adjustment execution module can automatically decide whether to adjust the current time interval for handwritten character acquisition according to the comparison result between the acquisition time interval adjustment coefficient and the preset adjustment coefficient threshold. This intelligent adjustment mechanism can flexibly adapt to the actual writing situation of users, improving the adaptability and accuracy of data acquisition.

[0140] Through the above technical solution, the system can dynamically adjust the time interval for handwritten character acquisition, ensuring that, without affecting the accuracy of data acquisition, unnecessary acquisition times are reduced as much as possible, thereby improving the acquisition efficiency. At the same time, since the acquisition time interval is more in line with the actual writing habits of users, the writing experience of users will also be correspondingly improved. This technical solution also reflects the characteristics of personalization and precision. By independently analyzing and adjusting the writing data of each user, the system can better adapt to the writing habits and needs of different users, providing more accurate data support for subsequent writing analysis, evaluation and teaching.

[0141] In summary, through a series of fine module designs and algorithm implementations, the above technical solutions effectively improve the efficiency and accuracy of handwritten character collection, while enhancing the user experience and personalized service capabilities.

[0142] In this embodiment, the data processing module includes:

[0143] A data cleaning unit for cleaning the handwriting behavior perception data;

[0144] Obtain handwriting behavior perception data based on non-invasive electroencephalogram;

[0145] Cleaning the handwriting behavior perception data based on non-invasive electroencephalogram includes:

[0146] Perform consistency checks on the handwriting behavior perception data based on non-invasive electroencephalogram;

[0147] According to the reasonable value ranges and mutual relationships of each variable in the handwriting behavior perception data based on non-invasive electroencephalogram, check whether the handwriting behavior perception data based on non-invasive electroencephalogram meets the requirements;

[0148] Remove inconsistent data that exceeds the normal range, is logically unreasonable or contradictory in the handwriting behavior perception data based on non-invasive electroencephalogram;

[0149] Perform invalid value and missing value processing on the handwriting behavior perception data based on non-invasive electroencephalogram;

[0150] Remove invalid data and missing data that are worthless for the early diagnosis of Parkinson's disease in the handwriting behavior perception data based on non-invasive electroencephalogram;

[0151] Determine the handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease;

[0152] A data conversion unit for converting the cleaned handwriting behavior perception data;

[0153] Obtain the handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease after cleaning;

[0154] Convert the handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease;

[0155] Eliminate the dimensionality differences between the handwriting behavior perception data;

[0156] Determine the handwriting behavior perception data with data standardization;

[0157] A feature extraction unit for extracting features from the converted handwriting behavior perception data;

[0158] Obtain the penmanship behavior perception data with data normalization after conversion;

[0159] Extract features from the penmanship behavior perception data with data normalization;

[0160] Extract the features that can reflect the early diagnosis of Parkinson's disease;

[0161] Determine the penmanship behavior feature data based on non-invasive electroencephalogram.

[0162] Among them, the model construction module is used to construct an early diagnosis model of Parkinson's disease based on penmanship behavior feature recognition according to the early diagnosis requirements of Parkinson's disease;

[0163] In this embodiment, the model construction module includes:

[0164] The data division unit is used to divide the penmanship behavior feature data;

[0165] Obtain the penmanship behavior feature data based on non-invasive electroencephalogram;

[0166] Divide the penmanship behavior feature data based on non-invasive electroencephalogram;

[0167] Determine the training data set and the test data set;

[0168] The model training unit is used to construct an early diagnosis model of Parkinson's disease;

[0169] According to the early diagnosis requirements of Parkinson's disease based on penmanship behavior feature recognition, select a neural network model framework suitable for the early diagnosis of Parkinson's disease;

[0170] Based on the training data set, train the selected neural network model framework suitable for the early diagnosis of Parkinson's disease;

[0171] Determine the early diagnosis model of Parkinson's disease based on penmanship behavior feature recognition.

[0172] Among them, the test and optimization module is used to test, evaluate and optimize the early diagnosis model of Parkinson's disease, and determine the optimal early diagnosis model of Parkinson's disease based on penmanship behavior feature recognition;

[0173] In this embodiment, the test and optimization module includes:

[0174] The test and evaluation unit is used to test and evaluate the early diagnosis model of Parkinson's disease;

[0175] Obtain the early diagnosis model of Parkinson's disease based on penmanship behavior feature recognition;

[0176] Based on the test data set, test and evaluate the early diagnosis model of Parkinson's disease;

[0177] Determine the test evaluation results based on the early diagnosis model for Parkinson's disease;

[0178] Optimization and adjustment unit, used to optimize and adjust the early diagnosis model for Parkinson's disease;

[0179] Obtain the test evaluation results based on the early diagnosis model for Parkinson's disease;

[0180] Mine and analyze the test evaluation results based on the early diagnosis model for Parkinson's disease;

[0181] Determine the optimization and adjustment plan based on the early diagnosis model for Parkinson's disease;

[0182] Optimize and adjust the early diagnosis model for Parkinson's disease according to the optimization and adjustment plan based on the early diagnosis model for Parkinson's disease;

[0183] Determine the optimal early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition.

[0184] Among them, the prediction and diagnosis module is used to predict and early diagnose Parkinson's disease for the real-time data of handwriting behavior, and determine the early diagnosis results of Parkinson's disease based on handwriting behavior feature recognition;

[0185] In this embodiment, the prediction and diagnosis module includes:

[0186] Data acquisition unit, used to acquire the real-time data of handwriting behavior based on non-invasive electroencephalogram;

[0187] According to the early diagnosis requirements of Parkinson's disease based on handwriting behavior feature recognition, monitor and collect the user's electroencephalogram activity changes, handwritten words and handwritten paintings in real time, and acquire the real-time data of handwriting behavior based on non-invasive electroencephalogram;

[0188] Prediction and diagnosis unit, used to predict and early diagnose Parkinson's disease for the real-time data of handwriting behavior;

[0189] Obtain the optimal early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition;

[0190] Input the real-time data of handwriting behavior based on non-invasive electroencephalogram into the optimal early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition;

[0191] Based on the optimal early diagnosis model for Parkinson's disease based on handwriting behavior feature recognition, predict and early diagnose the real-time data of handwriting behavior based on non-invasive electroencephalogram;

[0192] Determine the early diagnosis results of Parkinson's disease based on handwriting behavior feature recognition;

[0193] Among them, the early diagnosis results of Parkinson's disease based on handwriting behavior feature recognition include: the user is an early-stage Parkinson's disease patient or the user is not an early-stage Parkinson's disease patient;

[0194] When the user is an early-stage Parkinson's disease patient, formulate an early-stage Parkinson's disease control plan to intelligently control early-stage Parkinson's disease patients.

[0195] Among them, the intelligent control module is used to formulate an early-stage Parkinson's disease control plan based on handwriting behavior feature recognition and intelligently control early-stage Parkinson's disease patients.

[0196] In this embodiment, the intelligent control module includes:

[0197] A strategy formulation unit, which is used to formulate an early-stage Parkinson's disease control plan;

[0198] Obtain the early diagnosis results of Parkinson's disease based on handwriting behavior feature recognition;

[0199] Mine and analyze the early diagnosis results of Parkinson's disease based on handwriting behavior feature recognition;

[0200] Determine the early-stage Parkinson's disease control plan based on handwriting behavior feature recognition;

[0201] An intelligent control unit, which is used to intelligently control early-stage Parkinson's disease patients;

[0202] Obtain the early-stage Parkinson's disease control plan based on handwriting behavior feature recognition;

[0203] Based on the early-stage Parkinson's disease control plan, intelligently control early-stage Parkinson's disease patients, give early warnings to early-stage Parkinson's disease patients, and formulate personalized control and treatment measures for early-stage Parkinson's disease patients.

[0204] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0205] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An early diagnosis system for Parkinson's disease based on handwriting behavior feature recognition, characterized in that, Including: A data acquisition module, which is used to collect the data of the user's electroencephalogram activity change, the user's handwritten text data and the user's hand-drawn data, and determine the handwriting behavior perception data based on non-invasive electroencephalogram; Obtain the acquisition time interval adjustment coefficient by using the first group of writing index parameters and the second group of writing index parameters. When the acquisition time interval adjustment coefficient exceeds the preset adjustment coefficient threshold, use the acquisition time interval adjustment coefficient to adjust the time interval of the current handwritten text acquisition, and obtain the adjusted time interval of the handwritten text acquisition; A data processing module, which is used to process the handwriting behavior perception data based on non-invasive electroencephalogram and determine the handwriting behavior feature data based on non-invasive electroencephalogram; A model construction module, which is used to construct an early Parkinson's disease diagnosis model based on handwriting behavior feature recognition according to the early Parkinson's disease diagnosis requirements; A test and optimization module, which is used to test, evaluate and optimize the early Parkinson's disease diagnosis model, and determine the optimal early Parkinson's disease diagnosis model based on handwriting behavior feature recognition; A prediction and diagnosis module, which is used to predict and early diagnose the real-time data of handwriting behavior, and determine the early Parkinson's disease diagnosis result based on handwriting behavior feature recognition; An intelligent control module, which is used to formulate an early Parkinson's disease control plan based on handwriting behavior feature recognition and conduct intelligent control on early Parkinson's disease patients; The data acquisition module further includes: A word count real-time acquisition module, which is used to real-time collect the number of complete words completed per unit time during the user's writing process; wherein, the value range of the unit time is 2min - 8min; A text area acquisition module, which is used to obtain the area occupied by each word corresponding to each word completed within each unit time after each unit time is completed; A writing index parameter acquisition module, which is used to obtain the writing index parameter corresponding to the unit time according to the number of complete words of the user per unit time and the area occupied by each word completed within each unit time; Wherein, the writing index parameter is obtained by the following formula: Among them, R represents the writing index parameter; n represents the number of unit times experienced by the user's writing; S zi represents the total writing area corresponding to the i-th unit time; S zi-1 represents the total writing area corresponding to the (i - 1)-th unit time; N i represents the number of complete written characters corresponding to the i-th unit time; N i-1 represents the number of complete written characters corresponding to the (i - 1)-th unit time; f n represents the standard deviation of the number of complete written characters corresponding to n unit times; N p represents the average value of the number of complete written characters corresponding to n unit times; S p represents the average value of the total writing area corresponding to n unit times; S dij represents the area occupied by the characters of the j-th complete written character in the i-th unit time; An adjustment module, which is used to adjust the time interval of the handwritten text acquisition by using the difference value of the writing index parameters of every two adjacent unit times.

2. The early Parkinson's disease diagnosis system based on handwriting behavior feature recognition according to claim 1, wherein The data acquisition module includes: An electroencephalogram acquisition unit, which is used to monitor and collect the brain function and cognitive state of the user during the writing process based on non-invasive electroencephalogram, and obtain the user's electroencephalogram activity change data; A handwritten acquisition unit, which is used to monitor and collect the user's handwritten text during the writing process based on computer vision, and obtain the user's handwritten text data; A drawing acquisition unit, which is used to monitor and collect the user's hand-drawn during the writing process based on computer vision, and obtain the user's hand-drawn data; Wherein, based on the user's electroencephalogram activity change data, the user's handwritten text data and the user's hand-drawn data, the handwriting behavior perception data based on non-invasive electroencephalogram is determined.

3. The early Parkinson's disease diagnosis system based on handwriting behavior feature recognition according to claim 2, the adjustment module includes: A writing index parameter extraction module for extracting writing index parameters for every two adjacent unit times; A difference value acquisition module for obtaining the difference value of the writing index parameters for every two adjacent unit times by using the writing index parameters for every two adjacent unit times; A first set of writing index parameter acquisition modules for extracting the writing index parameters for two unit times corresponding to the maximum difference value in the difference values of the writing index parameters for every two adjacent unit times as the first set of writing index parameters; A second set of writing index parameter acquisition modules for extracting the writing index parameters for two unit times corresponding to the minimum difference value in the difference values of the writing index parameters for every two adjacent unit times as the second set of writing index parameters; An acquisition time interval adjustment coefficient acquisition module for obtaining an acquisition time interval adjustment coefficient by using the first set of writing index parameters and the second set of writing index parameters, wherein the acquisition time interval adjustment coefficient is obtained by the following formula: Among them, K represents the acquisition time interval adjustment coefficient; k represents the number of writing index parameters except for the first group of writing index parameters and the second group of writing index parameters; R i represents the value corresponding to the i-th writing index parameter except for the first group of writing index parameters and the second group of writing index parameters; C max and C min respectively represent the maximum difference and the minimum difference in the differences of the writing index parameters for every two adjacent unit times; R max01 and R max02 respectively represent the writing index parameters for two unit times corresponding to the first group of writing index parameters; R min01 and R min02 respectively represent the writing index parameters for two unit times corresponding to the second group of writing index parameters; A comparison module for comparing the acquisition time interval adjustment coefficient with a preset adjustment coefficient threshold; An adjustment execution module for, when the acquisition time interval adjustment coefficient exceeds the preset adjustment coefficient threshold, adjusting the time interval of the current handwritten character acquisition by using the acquisition time interval adjustment coefficient to obtain the adjusted time interval of the handwritten character acquisition; Wherein, the adjusted time interval of the handwritten character acquisition is obtained by the following formula: Wherein, T represents the adjusted time interval of the handwritten character acquisition; T0 represents the current time interval of the handwritten character acquisition; K represents the acquisition time interval adjustment coefficient.

4. The early Parkinson's disease diagnosis system based on handwriting behavior feature recognition according to claim 3, characterized in that The data processing module includes: A data cleaning unit for cleaning the handwriting behavior perception data; Obtain handwriting behavior perception data based on non-invasive electroencephalogram; Cleaning the handwriting behavior perception data based on non-invasive electroencephalogram includes: Performing consistency check on the handwriting behavior perception data based on non-invasive electroencephalogram; According to the reasonable value range and mutual relationship of each variable in the handwriting behavior perception data based on non-invasive electroencephalogram, checking whether the handwriting behavior perception data based on non-invasive electroencephalogram meets the requirements; Removing inconsistent data that exceeds the normal range, is logically unreasonable or contradictory in the handwriting behavior perception data based on non-invasive electroencephalogram; Performing invalid value and missing value processing on the handwriting behavior perception data based on non-invasive electroencephalogram; Removing invalid data and missing data that are of no value for the early diagnosis of Parkinson's disease in the handwriting behavior perception data based on non-invasive electroencephalogram; Determining the handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease.

5. The early Parkinson's disease diagnosis system based on handwriting behavior feature recognition according to claim 4, characterized in that The data processing module further includes: A data conversion unit for converting the cleaned handwriting behavior perception data; Obtain the handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease after cleaning; Converting the handwriting behavior perception data that is valuable for the early diagnosis of Parkinson's disease; Eliminating the dimension difference between the handwriting behavior perception data; Determining the handwriting behavior perception data with data standardization; A feature extraction unit for extracting features from the converted handwriting behavior perception data; Obtain the handwriting behavior perception data with data normalization after conversion; Extract features from the handwriting behavior perception data with data normalization; Extract the features that can reflect the early diagnosis of Parkinson's disease; Determine the handwriting behavior feature data based on non-invasive electroencephalogram.

6. The early diagnosis system for Parkinson's disease based on handwriting behavior feature recognition according to claim 5, wherein The model construction module includes: A data division unit for dividing the handwriting behavior feature data; Obtain the handwriting behavior feature data based on non-invasive electroencephalogram; Divide the handwriting behavior feature data based on non-invasive electroencephalogram; Determine the training data set and the test data set; A model training unit for constructing an early diagnosis model of Parkinson's disease; According to the early diagnosis requirements of Parkinson's disease based on handwriting behavior feature recognition, select a neural network model framework suitable for the early diagnosis of Parkinson's disease; Based on the training data set, train the selected neural network model framework suitable for the early diagnosis of Parkinson's disease; Determine the early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition.

7. The early Parkinson's disease diagnosis system based on handwriting behavior feature recognition according to claim 6, wherein The test and optimization module includes: A test evaluation unit for testing and evaluating the early diagnosis model of Parkinson's disease; Obtain the early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition; Based on the test data set, test and evaluate the early diagnosis model of Parkinson's disease; Determine the test evaluation result of the early diagnosis model of Parkinson's disease; An optimization and adjustment unit for optimizing and adjusting the early diagnosis model of Parkinson's disease; Obtain the test evaluation result of the early diagnosis model of Parkinson's disease; Mine and analyze the test evaluation result of the early diagnosis model of Parkinson's disease; Determine the optimization and adjustment plan for the early diagnosis model of Parkinson's disease; Optimize and adjust the early diagnosis model of Parkinson's disease according to the optimization and adjustment plan for the early diagnosis model of Parkinson's disease; Determine the optimal early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition.

8. The early Parkinson's disease diagnosis system based on handwriting behavior feature recognition according to claim 7, characterized in that, The prediction and diagnosis module includes: A data acquisition unit for acquiring the real-time data of handwriting behavior based on non-invasive electroencephalogram; According to the early diagnosis requirements of Parkinson's disease based on handwriting behavior feature recognition, monitor and collect the user's electroencephalogram activity changes, handwritten characters and handwritten paintings in real time, and obtain the real-time data of handwriting behavior based on non-invasive electroencephalogram; A prediction and diagnosis unit for predicting and early diagnosing the real-time data of handwriting behavior; Obtain the optimal early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition; Input the real-time data of handwriting behavior based on non-invasive electroencephalogram into the optimal early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition; Based on the optimal early diagnosis model of Parkinson's disease based on handwriting behavior feature recognition, predict and early diagnose the real-time data of handwriting behavior based on non-invasive electroencephalogram; Determine the early diagnosis result of Parkinson's disease based on handwriting behavior feature recognition; Among them, the early diagnosis result of Parkinson's disease based on handwriting behavior feature recognition includes: the user is an early-stage Parkinson's disease patient or the user is not an early-stage Parkinson's disease patient; When the user is an early-stage Parkinson's disease patient, formulate an early-stage management and control plan for Parkinson's disease and conduct intelligent management and control on the early-stage Parkinson's disease patient.

9. The early Parkinson's disease diagnosis system based on handwriting behavior feature recognition according to claim 8, characterized in that, The intelligent control module includes: A policy formulation unit, which is used to formulate an early-stage control plan for Parkinson's disease; Obtain the early-stage diagnosis results of Parkinson's disease based on handwriting behavior feature recognition; Mine and analyze the early-stage diagnosis results of Parkinson's disease based on handwriting behavior feature recognition; Determine the early-stage control plan for Parkinson's disease based on handwriting behavior feature recognition; An intelligent control unit, which is used to perform intelligent control on early-stage Parkinson's disease patients; Obtain the early-stage control plan for Parkinson's disease based on handwriting behavior feature recognition; Perform intelligent control on early-stage Parkinson's disease patients based on the early-stage control plan for Parkinson's disease, give timely warnings to early-stage Parkinson's disease patients, and formulate personalized control and treatment measures for early-stage Parkinson's disease patients.

Images