Intelligent terminal disturbance of consciousness interaction awakening system and method based on traditional Chinese medicine rules

Abstract

The invention discloses an intelligent terminal disturbance-of-consciousness interactive waking-up system and method based on traditional Chinese medicine rules, and relates to the technical field of intelligent medical treatment, the system comprises a data acquisition module for acquiring clinical multi-dimensional data of a disturbance-of-consciousness patient, constructing an initial patient clinical information matrix through data cleaning and standardization processing, and sending the initial patient clinical information matrix to an intelligent terminal; the intervention plan generation module is used for obtaining a preliminary intervention intensity curve aiming at the structured disturbance of consciousness characteristic data set, setting upper and lower limits of intervention intensity and time by adopting a boundary condition constraint technology aiming at the preliminary intervention intensity curve, and meanwhile, obtaining an intervention plan through a smoothness weight distribution method; adjusting importance parameters of the time points to obtain a smooth intervention execution plan; according to the intelligent terminal disturbance of consciousness interaction awakening system and method based on the traditional Chinese medicine rules, precise and personalized intervention of patients with disturbance of consciousness is achieved, the treatment effect is improved, and a new thought and method are provided for clinical practice.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical technology, and in particular to an intelligent terminal consciousness disorder interactive awakening system and method based on traditional Chinese medicine rules. Background Art

[0002] Patient health management and personalized treatment are core areas of modern medical development, crucial for improving treatment outcomes and optimizing the allocation of medical resources. In particular, in the management of chronic and complex diseases, accurately predicting patient needs and developing personalized treatment plans not only improves the patient experience but also reduces medical risks.

[0003] However, existing methods often overly rely on single statistical models or generalized treatment templates when processing patient data, overlooking the dynamic evolution of individual patient differences and the multidimensional interactive needs during treatment. This makes treatment plans difficult to adapt to the patient's actual condition at different stages, especially during long-term treatment, when patient responses may fluctuate due to multiple factors, making it difficult for existing methods to effectively capture these changes. In this context, a key research challenge is how to accurately characterize individual differences and predict the dynamic changes in interactive treatment needs within complex and volatile patient data. First, factors such as patient age, gender, disease duration, and level of consciousness are intertwined and jointly influence treatment needs, but existing technologies struggle to integrate these factors into a dynamic, continuous predictive model. The lack of systematic analysis of patient constitutional characteristics, particularly personalized modeling based on Traditional Chinese Medicine (TCM) constitution identification theory, limits the specificity of treatment plans and the generation of treatment schedules and stimulation intensity curves tailored to the patient's specific stage. These two technical factors are closely related: the inadequate dynamic modeling of individual differences limits the effective integration of constitutional characteristics, while the lack of constitutional characteristics further exacerbates the limitations of predictive models. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent terminal consciousness disorder interactive awakening system and method based on traditional Chinese medicine rules. By integrating multi-dimensional patient data and combining traditional Chinese medicine constitution identification theory, a dynamic prediction model is constructed to generate a personalized treatment schedule and stimulation intensity curve, and possible treatment responses can be predicted in advance.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent terminal interactive awakening system for consciousness disorders based on traditional Chinese medicine rules, the system comprising a data acquisition module for acquiring clinical multidimensional data of patients with consciousness disorders, constructing an initial patient clinical information matrix through data cleaning and standardization processing, and obtaining a structured consciousness disorder feature data set; an intervention plan generation module for obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature data set, and using boundary condition constraint technology to set upper and lower limits of intervention intensity and time for the preliminary intervention intensity curve, and adjusting the importance parameters of time points through a smoothness weight distribution method to obtain a smooth intervention execution plan. The data feedback and analysis module collects the patient's consciousness disorder improvement feedback data during the intervention period in real time according to the smooth intervention execution plan. If the feedback data deviates from the preset threshold range, the rule base parameters are adjusted through dynamic rule updating technology. At the same time, combined with interpolation error correction and curve continuity verification, the intervention schedule and stimulation intensity curve are updated to determine the optimized intervention execution plan; the personalized adaptation module adopts personalized threshold setting technology for the optimized intervention execution plan, adjusts the triggering conditions of consciousness-promoting intervention according to individual differences, and integrates the latest feedback data into the intervention intensity curve through real-time data fusion method to obtain the final dynamic intervention execution logic.

[0006] Preferably, the preliminary intervention intensity curve obtained for the structured consciousness disorder feature data set includes using a pre-established symptom matching rule for the structured consciousness disorder feature data set, combining the patient state classification method, dividing the patient state into acute phase and remission phase, and determining the patient's consciousness disorder classification result.

[0007] Preferably, obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature data set also includes extracting individualized consciousness disorder symptom frequency and consciousness disorder duration characteristics from the consciousness disorder classification results, using intervention priority sorting logic to determine the patient's core symptom intervention needs, and obtaining a personalized symptom priority vector.

[0008] Preferably, obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature data set also includes constructing a preliminary intervention time point distribution logic based on a personalized symptom priority vector in combination with historical data weight analysis through a schedule generation algorithm to determine the initial consciousness disorder intervention schedule.

[0009] Preferably, the preliminary intervention intensity curve obtained for the structured consciousness disorder feature data set also includes an initial consciousness disorder intervention schedule, which uses time interval subdivision logic to divide the schedule into smaller time units, and at the same time, through key node extraction technology, identifies the peak period of consciousness disorder as the core intervention point to obtain a detailed intervention time frame.

[0010] Preferably, obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature data set also includes calculating the initial stimulation intensity from the refined intervention time frame in combination with the intensity decision model, and calculating the stimulation intensity of the midpoint between adjacent key nodes through the intensity value interpolation formula to obtain the preliminary intervention intensity curve.

[0011] Preferably, the personalized threshold setting technology is used to adjust the triggering conditions of the consciousness disorder intervention according to individual differences. The specific formula is: ;in, represents the threshold of individual i, represents the average value of historical data of individual i, represents the standard deviation of the historical data of individual i, represents the standard deviation adjustment parameter, and i represents the individual number index.

[0012] Preferably, the standard deviation adjustment parameter The specific formula is: ; in, represents the standard deviation adjustment parameter, represents the variance of feedback data of individual i, represents the time delay from the start of intervention to the response of individual i, It represents the frequency of intervention received by individual i in unit time, and i represents the individual number index.

[0013] Preferably, the time delay from the start of intervention to the response of individual i is Specifically, it is the difference between the time point when individual i first shows a measurable response and the time point when individual i first receives intervention.

[0014] A method for interactively promoting consciousness disturbances on smart terminals based on traditional Chinese medicine rules, using the aforementioned interactively promoting consciousness disturbances on smart terminals based on traditional Chinese medicine rules, comprises obtaining multidimensional clinical data of patients with consciousness disturbances, constructing an initial patient clinical information matrix through data cleaning and standardization, and obtaining a structured consciousness disturbance feature dataset; obtaining a preliminary intervention intensity curve for the structured consciousness disturbance feature dataset, and using boundary condition constraint technology to set upper and lower limits for intervention intensity and time for the preliminary intervention intensity curve. Simultaneously, using a smoothness weight distribution method, the importance parameters of time points are adjusted to obtain a smooth intervention execution plan; according to the smooth intervention execution plan, real-time feedback data on improvement in consciousness disturbances of patients during the intervention period is collected; if the feedback data deviates from a preset threshold range, the rule base parameters are adjusted using a dynamic rule updating technology, and the intervention schedule and stimulation intensity curve are updated in combination with interpolation error correction and curve continuity verification to determine an optimized intervention execution plan; for the optimized intervention execution plan, personalized threshold setting technology is used to adjust the triggering conditions of consciousness promotion intervention according to individual differences, and the latest feedback data is integrated into the intervention intensity curve through a real-time data fusion method to obtain the final dynamic intervention execution logic.

[0015] It can be seen from the above technical solution that the present invention has the following beneficial effects: The intelligent terminal consciousness disorder interactive awakening system and method based on traditional Chinese medicine rules obtains multi-dimensional clinical data of patients, constructs a consciousness disorder feature data set, and classifies consciousness disorders. According to the classification results, individual characteristics are extracted, the core symptom intervention needs are determined, and an initial intervention schedule is generated. The time interval segmentation and key node extraction technology are used to identify the peak period of consciousness disorder and refine the intervention time frame. The intensity decision model is combined to calculate the stimulation intensity and generate a smooth intervention execution plan. Patient feedback data is collected in real time, the rule base parameters are dynamically adjusted, and the intervention plan is updated. Finally, the dynamic intervention execution logic is obtained through personalized threshold setting and real-time data fusion. The present invention realizes precise and personalized intervention for patients with consciousness disorders, can effectively alleviate symptoms, improve treatment effects, and provide new ideas and methods for clinical practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a system module connection diagram of the intelligent terminal consciousness disorder interactive awakening system based on traditional Chinese medicine rules of the present invention; Figure 2 This is a flow chart of the method for interactive awakening of consciousness disorders in smart terminals based on traditional Chinese medicine rules of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, the present invention provides a technical solution: an intelligent terminal consciousness disorder interactive awakening system based on traditional Chinese medicine rules, the system comprising a data acquisition module for acquiring clinical multidimensional data of patients with consciousness disorders, constructing an initial patient clinical information matrix through data cleaning and standardization processing, and obtaining a structured consciousness disorder feature data set; an intervention plan generation module for obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature data set, and using boundary condition constraint technology to set upper and lower limits of intervention intensity and time for the preliminary intervention intensity curve, and adjusting the importance parameters of time points through a smoothness weight distribution method to obtain a smooth intervention execution plan; The data feedback and analysis module collects the patient's consciousness disorder improvement feedback data during the intervention period in real time according to the smooth intervention execution plan. If the feedback data deviates from the preset threshold range, the rule base parameters are adjusted through dynamic rule updating technology. At the same time, combined with interpolation error correction and curve continuity verification, the intervention schedule and stimulation intensity curve are updated to determine the optimized intervention execution plan; the personalized adaptation module adopts personalized threshold setting technology for the optimized intervention execution plan, adjusts the triggering conditions of consciousness awakening intervention according to individual differences, and integrates the latest feedback data into the intervention intensity curve through real-time data fusion method to obtain the final dynamic intervention execution logic.

[0019] The main function of the data acquisition module is to obtain clinical multidimensional data of patients with impaired consciousness and convert these data into a structured impaired consciousness feature data set through a standard processing flow, so that the system can subsequently execute precise intervention control logic.

[0020] The first step is to collect and define the source of raw data. The dimensions of data collection cover five categories: physiological indicators, behavioral characteristics, symptom assessment, emotional state, and environmental factors. Each type of data is provided by different devices and systems: Physiological indicators include blood pressure, heart rate, body temperature, respiratory rate, and electroencephalogram signals, with a sampling frequency of once per minute; behavioral indicators include sleep duration and dietary records, with a sampling frequency of once per day; symptom assessment uses a self-assessment questionnaire covering the degree of impaired consciousness, duration, and triggers, with a frequency of twice daily; environmental factors such as light, noise, and air pressure are obtained through mobile applications calling local or network APIs and updated once an hour.

[0021] Step 2: Data Cleaning Rules: Missing Value Filling: If a metric is missing for a specific time period, the system will use the mean of the patient's five most recent consecutive records to fill in the missing value. For example, if a patient's heart rate data is missing at the 120th minute, the system will look back at the heart rates of minutes 115, 116, 117, 118, and 119, calculate the mean, and use this to fill in the missing value for minute 120. Outlier Removal: Based on the distribution of the patient's historical data, the system defines an outlier as an observation that falls outside the range of the historical mean by 5 percent. For example, if the patient's historical mean heart rate is 75, a heart rate recording below 71 or above 78 is considered an anomaly and removed. Duplicate Data Merging: When multiple similar data records are collected within a minute, the median is retained as the representative value. Inconsistency Correction: For data with inconsistent units (such as mmHg and kilopascals), the system converts them to the international standard unit of mmHg, with 1 kilopascal equal to 7.5 mmHg.

[0022] The third step is to describe the data normalization method: All data items are uniformly normalized and ranged from 0 to 1. Range normalization is performed by subtracting the minimum value from the current value and dividing it by the difference between the maximum and minimum values. The maximum and minimum values ​​are selected based on the patient's historical heart rate over the past seven days. For example, if a patient's maximum heart rate over the past seven days is 98 and the minimum is 62, and the current heart rate is 80, the normalized value is (80 minus 62) divided by (98 minus 62), which is 0.5.

[0023] The fourth step is to construct a clinical information matrix: The standardized data is structured into a time-based matrix, with time (in minutes) on the horizontal axis and the standardized feature values ​​on the vertical axis. Based on recording 1440 time points per day (one per minute), each patient forms a matrix with 1440 rows and several columns per day. The number of columns corresponds to the number of features, typically between 30 and 50. Each row represents a snapshot of their overall health status at that point in time.

[0024] Step 5: Structured Feature Extraction Method Description: To capture trend signals before and after the onset of impaired consciousness, the system uses a sliding time window technique to segment the data series into windows. The default sliding window width is 180 minutes. That is, over a continuous 180-minute period, the system calculates: the difference between the maximum and minimum values, which serves as an indicator of fluctuation intensity; the mean rate of change of the data within this period, determined by dividing the difference between the means of the previous and next segments by the time interval; and the frequency of impaired consciousness-related events within the window, such as the number of times the self-assessed impaired consciousness index exceeds 0.8. Each type of calculation generates a new set of statistical features. Ultimately, the system forms multiple derived indicators based on the original matrix, which are used to construct a prediction model for impaired consciousness events.

[0025] Step 6. Data storage and output interface control: After completing the above processing, all structured data are stored in individualized database tables with the patient's unique number as the primary key. The system provides a standardized output interface to push the latest updated daily data set to subsequent modules. The interface supports data verification, historical data callback and error log feedback. The default update frequency is once every 24 hours and can be set to a higher frequency as needed. For structured consciousness disorder feature data sets, pre-established symptom matching rules are used, combined with patient status classification methods, to divide the patient's status into acute and remission phases, and determine the patient's consciousness disorder classification results. This part of the function is based on the structured consciousness disorder feature data set. Through symptom matching rules and patient status classification methods, it completes the consciousness disorder status judgment at the current time point and its adjacent time periods, and outputs the consciousness disorder classification results accordingly. The complete process is divided into four steps: state determination, state trend smoothing, rule matching and classification output.

[0026] The initial judgment calculation process of the state of consciousness disorder: the system judges the sampled data every minute, builds a judgment matrix based on three characteristic indicators, and determines whether it is in the "acute stage". The three characteristic indicators are as follows: Consciousness Disorder Score: The scoring scale uses a standardized "Consciousness Disorder Score Form," which is entered by the patient's caregiver once daily, morning and evening, via mobile phone. Each time, the caregiver selects a level between "Unconscious" (corresponding to a score of 0.0) and "Comatose" (corresponding to a score of 1.0) based on their current symptoms of consciousness disorder. The system maps this selection to a decimal value between 0 and 1, with accuracy to one decimal place. To achieve higher temporal resolution, the system uses linear interpolation to fill in the gaps between two scores at the minute level. For example, if the caregiver scores 0.3 at 8:00 AM and 0.9 at 8:00 PM, the system will linearly interpolate 720 sampling points per minute over this 12-hour period, constructing a complete consciousness disorder curve. The value of each interpolated point is calculated from the time difference and score difference between the two consecutive scores, ensuring a continuous and usable intensity estimate at any given time. In addition, the system's preset intervention trigger threshold is 0.7. If the intensity score at a given time point is greater than or equal to 0.7, that point is scored as 1, otherwise it is scored as 0. This score is used to determine whether to trigger intervention and serves as input for threshold determination and intensity decision-making model calculations. The scoring mechanism is designed to take into account convenience, individual subjective accuracy, and compatibility with subsequent algorithms, ensuring that the degree of impaired consciousness is quantifiable, traceable, and responsive.

[0027] Neural Signal Fluctuation Score: The baseline indicator is the 30-minute moving amplitude of the average power in the high-frequency band of the EEG. Every minute, the system calculates the relative rate of change in power over the past 30 minutes (subtracting the previous 30-minute average from the current time point, then dividing the result by the previous 30-minute average). A relative rate of change greater than 0.2 is scored as 1, otherwise 0. EEG power data is acquired through a head-mounted EEG acquisition device worn by the patient at a sampling rate of 64 times per second. The system then performs bandpass filtering to extract the high-frequency band and averages it to the minute level.

[0028] The sum of the two scores is calculated, with a maximum of 2 points. If the score at a time point is 2, it is marked as "acute phase"; otherwise, it is marked as "remission phase." This process runs once a minute in the system background, automatically outputting the current status mark.

[0029] Time trend correction mechanism: In order to avoid misjudgment of short-term fluctuations, the system introduces a sliding window trend smoothing method. The window length is 360 minutes, and it slides every 60 minutes to count the number of acute phase time points in the current window. The threshold ratio is set to 50%, that is, if the number of acute phase time points in a window is greater than or equal to 180, the entire window is marked as "acute phase"; otherwise, it is "remission phase". Each time point can belong to multiple sliding windows. The system summarizes the status of all windows covering the time point and uses the majority voting principle to determine the final status. If 2 or more of the 3 sliding windows are judged to be "acute phase", the final status of the time point is "acute phase".

[0030] Symptom matching rules and calculation of consciousness disorder determination: The system has five pre-defined categories of disorders of consciousness, each corresponding to a rule template. The rule template consists of a list of features, each corresponding to a condition and scoring criteria. An example rule (organic disorders of consciousness) includes the following features: circadian rhythm disturbance (more than two nocturnal awakenings or more than three hours of total daytime sleep in the daily routine); disorientation (a time or place orientation error rate greater than 0.5 in the assessment record); attention fluctuation (average reaction time fluctuation rate greater than 0.4 in interactive tasks); disorganized speech (a proportion of abnormal semantic expressions greater than 0.3 in the speech recording); and associated neurological signs (any of paresis, dystonia, or nystagmus during monitoring). Each rule is scored one point, for a maximum total score of five. The system performs a daily match calculation against all rules within the last seven days of feature data, accumulating the scores for each rule. The rule with the highest cumulative score is selected as the primary category. In case of a tie, the rule with the higher score from the last three days is selected as the primary category, with the other rule being recorded as a secondary category.

[0031] Classification Output Structure and Interface Format: The system outputs state of consciousness assessment and disorder of consciousness identification results every 24 hours, including: minute-by-minute state of consciousness labels (e.g., wakefulness, drowsiness, delirium, minimally conscious state, vegetative state, coma, etc.); 360-minute trend labels for state of consciousness (e.g., increased fluctuation, improved clarity of consciousness, persistent hyporesponsiveness, etc.); currently identified primary and secondary disorders of consciousness; detailed scoring for each rule template (listing the matching status and score of each feature); and a summary of key feature values, including daily maximum, minimum, and mean values ​​for parameters such as disorientation score, attention maintenance index, language disorganization index, autonomous activity level (e.g., number of steps per unit time or number of interactions), and EEG fluctuation rate. The system encapsulates all of this output in a structured data format (e.g., JSON or CSV) for subsequent access by intervention modules and adjustment of intervention strategy intensity. The system also supports retrospective querying of historical records and dynamic echoing of rule parameters, ensuring a closed-loop feedback loop between state identification and intervention optimization. All threshold parameters (such as orientation error frequency of 0.5, attention fluctuation rate of 0.4, EEG fluctuation of 20%, sliding window of 360 minutes, etc.) are based on the statistical distribution of characteristic data of 1,000 previous clinical patients with impaired consciousness, and are set after review by a team of clinical experts in neurology. They are scientific and universal. At the same time, the system reserves a manual fine-tuning interface to support parameter adjustment and personalized adaptation based on individual difference scenarios.

[0032] By combining structured data on impaired consciousness characteristics with symptom matching rules, this solution accurately classifies the patient's current state of consciousness and precisely identifies impaired consciousness, significantly improving the targeted nature and individual adaptability of intervention decisions. By introducing a multi-dimensional indicator comprehensive judgment mechanism and a time trend smoothing algorithm, the system effectively reduces the risk of misjudgment due to short-term fluctuations (such as transient unresponsiveness and loss of attention) and improves the stability and continuity of state of consciousness identification. Furthermore, the matching rules are constructed based on a large sample of clinical data from patients with impaired consciousness, and the classification results have high clinical reliability, providing solid data support and an algorithmic foundation for the personalized adjustment and dynamic optimization of subsequent intervention plans.

[0033] Individualized characteristics of the frequency and duration of consciousness disorders are extracted from the consciousness disorder classification results. The intervention priority sorting logic is used to determine the patient's core symptom intervention needs and obtain a personalized symptom priority vector.

[0034] This module aims to quantify the frequency and duration of abnormal consciousness states, based on the results of disorder of consciousness classification. Furthermore, combined with symptom-based intervention prioritization logic, a structured mechanism for prioritizing intervention targets is established for each individual. The entire process consists of three phases: feature extraction of disorder of consciousness (e.g., decreased orientation, fluctuating attention, and language disturbances); symptom pattern recognition (identifying patterns of consciousness such as periodic fluctuations, acute exacerbations, or persistent hyporesponsiveness); and priority vector generation. This prioritized vector is then weighted based on symptom severity, scope of impact, and intervention feasibility, ultimately forming a personalized reference sequence for intervention strategies. Phase 1: Individualized feature extraction of disorder of consciousness. To calculate the frequency of disorder of consciousness, the system acquires minute-by-minute data on the patient's state of consciousness for the past seven consecutive days, labeling each minute as either "abnormal" (e.g., drowsiness, delirium, unresponsiveness, minimally conscious state, vegetative state, etc.) or "awake." By traversing each minute, the system identifies the transition from "awake" to "abnormal" state, with each transition being recorded as a disorder of consciousness episode. For example, if the status label switches from "awake to abnormal" five times in 10,080 time points, the frequency of impaired consciousness is 5 episodes per 7 days. Frequency of impaired consciousness: Based on the number of episodes per 7 days, the system categorizes frequency into three categories: high frequency (5 or more episodes per 7 days); medium frequency (3 to 4 episodes per 7 days); and low frequency (less than 3 episodes per 7 days). Duration of impaired consciousness is calculated by recording the start and end time of each impaired consciousness state (i.e., abnormal period) and calculating the duration of each abnormal period in minutes. For example, if an abnormal period starts at the 3000th minute and ends at the 3300th minute, the duration is 300 minutes. The system counts all abnormal periods over the past 7 days and calculates the average as the "average duration." Duration of impaired consciousness is categorized as follows: long duration (240 minutes or more); medium duration (120 to 239 minutes); and short duration (less than 120 minutes). After the system completes the grade classification of the above two indicators, it marks the current patient as a "frequency-duration" composite type, such as "high frequency and long duration", "medium frequency and short duration", etc., for the precise formulation of subsequent individualized intervention strategies.

[0035] Intervention priority sorting logic. Intervention goal definition: This system sets three core intervention goals for the management of impaired consciousness: reducing the frequency of impaired consciousness attacks, shortening the duration of a single attack, and alleviating the degree of impaired consciousness during an attack (such as drowsiness, minimally conscious state, vegetative state, coma, etc.). Based on the "frequency-duration" composite type identified in the first stage, the system establishes a matching relationship between nine symptom types and corresponding intervention priority vectors. The priority is 1 as the highest and 3 as the lowest. The specific template is as follows: high-frequency long duration: [1, 2, 3]; high-frequency medium duration: [1, 3, 2]; high-frequency short duration: [1, 3, 2]; medium-frequency long duration: [2, 1, 3]; medium-frequency medium duration: [2, 3, 1]; medium-frequency short duration: [3, 2, 1]; low-frequency long duration: [2, 1, 3]; low-frequency medium duration: [3, 2, 1]; low-frequency short duration: [3, 2, 1]. Once the system has classified the frequency and duration of a patient's impaired consciousness, it automatically uses the corresponding priority template to prioritize the initial intervention strategy for that individual. For example, if a patient is classified as "high frequency, long duration," the system will select the priority vector [1, 2, 3], meaning the priority intervention goal is to reduce the frequency of attacks, followed by shortening the duration of each attack, and finally, alleviating the severity of the disturbance during the attack. This priority mechanism provides a basis for intelligent scheduling of subsequent intervention measures and personalized resource allocation.

[0036] Priority vector fine-tuning mechanism If the system detects that a patient has experienced severe comorbid symptoms within the past three days, it will fine-tune the original intervention priority vector. The specific adjustment rules are as follows: intervention targets with a score of 2 in the original vector will be adjusted to 1, and those with a score of 1 will be adjusted to 2, ensuring that the characteristics of impaired consciousness associated with currently significant comorbid symptoms are prioritized for response and intervention. In terms of output structure, the system outputs the final processing results as a three-dimensional vector, with each dimension representing the ranking of three types of intervention targets: reducing the frequency of attacks, shortening the duration of attacks, and alleviating the severity of attacks. For example, [2, 1, 3] indicates that the current top priority intervention target is shortening the duration of each impaired consciousness attack, followed by reducing the frequency of attacks, and finally alleviating the severity of the disorder during an attack. This priority vector is generated daily and updated every 24 hours. It is used to weight the intensity curve and trigger decision control nodes in subsequent intervention plans. The threshold setting for all intervention decisions is based on clear quantitative evidence and three authoritative data sources to ensure the scientific and reproducible nature of the standards. First, the system collected continuous state monitoring data from 1,000 patients with impaired consciousness. The median and upper and lower quartiles of key indicators (such as seizure frequency, duration of a single abnormal state, orientation score, and attention fluctuations) were calculated to clarify the distribution range of these characteristics in actual clinical practice. Second, the system referenced the classification thresholds recommended by international standards for the assessment of impaired consciousness (such as RASS and CAM-ICU) for indicators such as seizure frequency (e.g., ≥2 per day, severe fluctuation) and duration (e.g., ≥240 minutes, long-term disturbance) and adjusted its internal parameters accordingly. Finally, through the annotation, verification, and discussion of real-world clinical data by neurology and geriatric psychiatry experts, a multi-round parameter tuning mechanism was established to determine the cutoff values ​​for each categorized variable. For example, the definition of "high frequency" as a frequency of impaired consciousness greater than or equal to five times per seven days and "long duration" as a single episode greater than or equal to 240 minutes were based on the overlap between the 75th percentile of the sample statistics and the recommended values ​​in international standards, demonstrating sufficient statistical support and medical consistency.

[0037] By extracting individualized features of the frequency and duration of consciousness disorders from the consciousness disorder classification results, and combining them with intervention priority sorting logic to generate a personalized symptom priority vector, this solution can accurately identify patients' primary intervention needs at different stages, shifting intervention strategies from a unified template to individual customization. This method, based on a multidimensional consciousness state data-driven discrimination mechanism, significantly improves the targetedness and responsiveness of intervention plans, avoids inappropriate resource allocation and poor intervention effects, enhances the system's intelligent adaptability and ability to identify individual differences, and provides an efficient and adjustable decision-making support tool for the continuous optimization of consciousness disorder management.

[0038] Based on the personalized DCP intervention priority vector and the patient's historical abnormal consciousness state data, the system constructs a preliminary intervention time point distribution logic tailored to the patient's specific seizure pattern and generates an initial daily intervention schedule. This process consists of five main steps: modeling the high probability of DCP, calculating time period weights, converting priority ratios, configuring the intervention time point distribution, and outputting and updating the schedule. The first step, modeling the high probability of DCP, is to extract 1440 daily time points of consciousness (abnormal or lucid periods) from the patient's minute-by-minute consciousness state data for the past 14 days. The system then divides the daily timeline into 24 60-minute segments. The system then counts the cumulative number of "abnormal" minutes in each segment over the 14-day period. For example, if a patient experiences 420 abnormal states between 9:00 AM and 10:00 AM, the probability of abnormality for that segment is 420 divided by 840, which equals 0.5 (840 is the maximum possible number of minutes in that segment over the 14-day period). This process is repeated for all hourly segments, ultimately generating a relative probability of DCP for each 24-hour segment. Step 2: Time Segment Weight Calculation: To achieve normalization, the system normalizes the time segment with the highest probability of occurrence to a weight of 1, and scales the remaining time segments proportionally. This generates a 24-dimensional time segment weight vector, which serves as a reference for subsequent intervention point configuration. Step 3: Priority Ratio Conversion Logic: The system reads the priority vector for impaired consciousness intervention generated by the preceding module. For example, [1, 2, 3] represents reducing the frequency, duration, and severity of impaired consciousness, respectively, with corresponding intervention resource ratios of 60%, 30%, and 10%, respectively. This ratio was extracted by an expert team based on intervention response data from 100 typical patients, balancing intervention effectiveness and resource allocation. Based on this ratio, the system determines a resource allocation structure for 48 fixed daily intervention time points (one every 30 minutes, covering the entire day). Step 4: Intervention Time Point Distribution Configuration: Taking priority 1 as an example, 60% of the time points, or 29 points, need to be configured. The system prioritizes the hourly segments with the highest probability of an impaired consciousness, sorting them by weight until the target distribution weight of 60% (e.g., a target weight of 5.76 units) is met, and 29 intervention points are evenly distributed across the corresponding time segments. The allocation logic for priority 2 and priority 3 is similar, with 14 and 5 time points configured respectively. If a certain hour period is selected by multiple priority targets at the same time, the system automatically shortens the intervention interval of that period to 20 minutes to ensure the intervention density and coverage intensity of the priority targets. Step 5, schedule output mechanism: The system sorts the 48 intervention time points by minute, and each point is accompanied by three pieces of information: the specific time (such as 540 minutes is 9 am), the intervention target identifier (such as frequency control), and the corresponding time period weight value (such as 0.85). It is output in a structured data format for subsequent reading and use by the "Intervention Intensity Allocation Module". The schedule is updated once a day. The system automatically runs the algorithm 10 minutes before midnight every day, generates an updated table based on the latest 14 days of data, and archives the log to support backtracking and manual verification.All parameter settings are derived from clinical research and expert consensus: 48 daily time points represent the optimal cognitive load limit for patients, 30-minute intervals align with circadian rhythms of consciousness, priority ratios are empirically optimized, and a 14-day window reflects the stability of behavioral patterns. This schedule generation algorithm, through distributed weight evaluation and goal-driven configuration, constructs a highly personalized and rhythm-matched time distribution for interventions for disorders of consciousness, ensuring both engineering feasibility and clinical compatibility.

[0039] For the initial intervention schedule for impaired consciousness, the time interval segmentation logic is used to divide the schedule into smaller time units. At the same time, through the key node extraction technology, the peak period of impaired consciousness is identified as the core intervention point to obtain a detailed intervention time framework.

[0040] After the initial DCP intervention schedule is generated, to further improve the accuracy of intervention rhythm and time-matching efficiency, the system introduces time interval segmentation logic and key node extraction technology to refine and reconstruct the daily intervention schedule, creating a refined intervention timeframe that aligns with the individual DCP episode rhythm. This technical process consists of five steps: time unit division, abnormal state density matrix construction, high-risk threshold calculation, key node extraction, and structured intervention point allocation. The first step is time unit segmentation: the original intervention schedule is based on a 30-minute interval, for a total of 48 points. To improve temporal responsiveness, the system divides the 1440 minutes of the day into 144 10-minute time units, numbered 1 to 144, covering 00:00 to 00:10, 00:10 to 00:20, and finally 23:50 to 00:00. This 10-minute granularity is based on system performance testing and the clinical response window for DCP intervention. It meets the requirements of refined monitoring while avoiding the burden on patients caused by frequent interventions. The second step is to construct a density scoring matrix. The system uses the patient's minute-by-minute consciousness data from the past seven days to count the frequency of "abnormal consciousness states" (such as lethargy, delirium, minimally conscious state, vegetative state, coma, etc.) within each 10-minute segment, assigning one point for each occurrence. The final score for each 10-minute segment ranges from 0 to 98 (7 days multiplied by the maximum possible score of 14). For example, if time period numbered 78 (13:00-13:10) has 14 abnormal states, its density score is 14. Based on this, the system constructs a 144-dimensional density vector, which serves as the probabilistic basis for identifying high-risk periods. The third step is to calculate and classify the peak threshold. The system sorts the density vectors and selects the top 20% of the time periods as candidate high-risk periods, namely the first 29 time periods. The lowest score among these 29 time periods is then calculated as the lower threshold. For example, if the score of the 29th time period is 12, all time periods with a score of 12 or higher are marked as "high-risk periods." This 20% ratio is derived from multiple rounds of clinical research, which shows that approximately 15%-25% of time periods experience over 80% of episodes of impaired consciousness. This serves as the basis for establishing key intervention windows. Through these steps, the system can effectively identify and focus on key time points with high incidence of impaired consciousness, enabling more intensive and precise intervention rhythms, and providing a refined input foundation for subsequent intervention target superposition, intensity adjustment, and timing balance.

[0041] Next, the system performs continuous merging processing on the time periods marked as high risk for impaired consciousness. If the interval between adjacent high-risk segments does not exceed one 10-minute segment (i.e. within 10 minutes), they will be merged into a continuous "core node segment". After the merger, the system will check the total duration of each core node segment. If it is less than 20 minutes (i.e. less than 2 consecutive high-risk segments), it is considered that the clinical intervention value is insufficient and it will be removed from the configuration. Ultimately, the system retains a maximum of 5 core node segments for concentrated delivery of high-frequency intervention time points. The fourth step is the time point structure configuration algorithm: the system expands the number of daily intervention time points from the initial 48 to a maximum of 72 points, and gives priority to allocating them to core node segments within the scope of resource constraints. Each core segment is configured with 2 to 4 intervention points based on its duration, and one is set every 10 to 15 minutes by default. For example, if a core segment is between 08:40 and 09:20, covering four 10-minute segments, the system may set three time points, namely 08:40, 09:00, and 09:20, to ensure the time density of intervention response during the high-incidence time period. In non-core segment areas, the system focuses its intervention on the "medium-risk segment" with a density score between 30% and 60%. These time periods are possible secondary attack peaks, and the system configures auxiliary time points on an average hourly basis, with a maximum of one per hour, to control the spread of abnormal conditions through moderate intervention. For the remaining time periods after the density score is lower than 60%, that is, the low-risk area, the system no longer configures any time points to avoid unnecessary intervention operations and waste of system resources, and also to reduce the daily burden on patients. The fifth step involves generating and formatting the intervention timeframe. The system ultimately generates a structured list of no more than 72 intervention timepoints, each containing the following key information: time number (1 to 144, corresponding to one of the 144 10-minute segments throughout the day), point type ("core point" or "auxiliary point"), high-risk segment identifier (segment number if core), density score (reflecting the historical probability of abnormal consciousness at that timepoint), and ranking weight (which serves as a dynamic weight input for the subsequent intervention intensity adjustment module). This timeframe is automatically refreshed before 00:00 daily and synchronously output to the system's intervention intensity scheduling module and patient terminal devices, enabling 24 / 7 closed-loop feedback control. This refined intervention timeframe, by precisely identifying and enhancing coverage of high-risk periods for disorders of consciousness and combining it with a density-driven point distribution strategy, achieves an effective combination of high temporal resolution, high intervention targeting, and low system burden, ensuring a scientific, adaptable, and operationally sound intervention cadence for individualized disorders of consciousness management.

[0042] This technical solution effectively improves the accuracy and pertinence of the intervention rhythm by subdividing the time intervals of the initial consciousness disorder intervention schedule and combining key node extraction technology to identify the peak period of consciousness disorder as the core intervention point. By dividing the daily timeline into 144 10-minute units and accurately identifying the high-incidence time period based on the symptom density distribution of the past 7 days, the system can dynamically lock the core period with the highest probability of consciousness disorder, centrally allocate intervention resources, and achieve a high degree of matching between the intervention timing and the onset rhythm. At the same time, under the premise of ensuring response sensitivity, this method reasonably controls the total number of intervention points, avoids waste of resources and excessive intervention, and provides a high-resolution time control mechanism for personalized and precise intervention, enhancing the system's adaptability and clinical applicability.

[0043] From the refined intervention time frame, combined with the intensity decision model, the initial stimulation intensity is calculated, and the stimulation intensity of the intermediate points between adjacent key nodes is calculated through the intensity value interpolation formula to obtain the preliminary intervention intensity curve.

[0044] After establishing a detailed intervention timeframe, to ensure continuity and precision in intervention, the system introduces an intensity decision model to calculate initial stimulation intensity values ​​for each core intervention node. Interpolation is then used to complete the intensity values ​​at intermediate points between nodes, thereby forming a continuous preliminary intervention intensity curve for the entire 1440 minutes of the day. This process can be broken down into four sequential technical steps: core node intensity calculation, normalized weight assignment, interpolation segment division, and interpolation execution.

[0045] Step 1: Calculate the initial stimulation intensity for core nodes. The system first identifies all marked core intervention nodes. Each node has three input features: Density score: This refers to the cumulative number of "acute phases" that occurred within the 10-minute time period of the node over the past seven days, ranging from 0 to 98. The system divides this value by 98 to obtain a normalized density score, D, ranging from 0 to 1. Symptom intervention priority: This refers to the intervention target that the node primarily responds to, with a priority of 1, 2, or 3. The system assigns weights, W, to these priorities, of 0.6, 0.3, and 0.1, respectively. These weights were determined by an expert panel through a weight sensitivity analysis to ensure targeted intervention. Time period risk weight: This refers to the probability of impaired consciousness within the hourly time period of the node. This value, calculated previously, ranges from 0 to 1 and is denoted as R. The system uses these three values ​​to calculate the initial stimulation intensity, S, using a weighted average: S = D multiplied by 0.5, plus W multiplied by 0.3, plus R multiplied by 0.2. Among the above parameter coefficients, 0.5, 0.3, and 0.2 represent the weightings for historical density, intervention target priority, and temporal risk, respectively. This ratio was determined by the system through iterative analysis of 500 patient responses, balancing time dependence and individual response variability. The resulting S value is limited to a range of 0.2 to 1. If the calculated value is less than 0.2, the system automatically adjusts it to 0.2; if it is greater than 1, the system sets it to 1.

[0046] Step 2: Definition of interpolation segments. The system arranges all core intervention nodes in chronological order, marks their positions in the 144 time periods throughout the day, and then takes all empty segments between two adjacent nodes in sequence to define an interpolation segment. For example, if the first node is in the 48th segment (i.e., 8 a.m.) and the second node is in the 60th segment (i.e., 10 a.m.), the interpolation segment contains 11 points from the 49th to the 59th segment. The system sets the minimum length of the interpolation segment to 2 segments (i.e., 20 minutes) and the maximum length to 9 segments (i.e., 90 minutes). If the length exceeds this, segmented interpolation will be performed. This interval is determined by clinical intervention response lag and neurological recovery mechanism research, and can take into account both continuity and physiological tolerance.

[0047] Step 3: Interpolation. Within each interpolation segment, the system uses linear interpolation to calculate the stimulus intensity for each intermediate segment. Let the starting node intensity be A, the ending node intensity be B, and the number of interpolation points be N. The intensity corresponding to the nth interpolation point (counting from 1) is: the starting intensity plus the difference multiplied by the proportion of the nth point's length to the segment length. That is, A plus B minus A, multiplied by n divided by N plus 1. For example, if A is 0.6, B is 0.9, and N is 3, the intensities of the three interpolation points are: point 1: 0.675; point 2: 0.75; point 3: 0.825. This algorithm ensures that the interpolated values ​​change continuously and smoothly between the previous and next nodes, avoiding system shocks caused by sudden interventions.

[0048] Step 4: Intensity curve integration and output. The system aggregates the intensity values ​​of all core nodes and the intensity values ​​of the intermediate points generated in the interpolation segment to form an intervention intensity sequence for the entire day of 1440 minutes. The intensity of unset time periods in the sequence is set to 0 by default, indicating a non-intervention state. Ultimately, the system generates a set of preliminary intervention intensity curve data sets that are updated daily. Each data point contains the time position, intervention intensity value, and whether it is a core point mark. The system supports users or doctors to set the maximum intervention intensity upper limit, the minimum response stimulation threshold, and the prohibition of intervention constraints during special time periods to control the overall shape of the curve and enhance individualized adjustment capabilities.

[0049] This technical solution combines the refined intervention time frame with the intensity decision model, accurately calculates the initial stimulation intensity based on node characteristics, and uses linear interpolation to complete the intensity values ​​of the intermediate points between adjacent key nodes, thereby constructing a complete, continuous, and rhythmic preliminary intervention intensity curve. This method significantly improves the dynamic matching ability of the intervention plan, ensuring sufficient stimulation response intensity at key time points, while achieving a natural transition of intensity in non-core sections, avoiding physiological shock or system interference caused by sudden intervention. At the same time, the intensity curve is controllable and adjustable, providing a stable foundation for subsequent smoothing processing and real-time feedback correction, enhancing the accuracy, continuity, and execution effect of personalized intervention plans.

[0050] For the preliminary intervention intensity curve, boundary condition constraint technology is used to set the upper and lower limits of intervention intensity and time. At the same time, the importance parameters of time points are adjusted through the smoothness weight distribution method to obtain a smooth intervention execution plan.

[0051] To ensure the feasibility and rhythmic stability of the initial intervention intensity curve, after generating a baseline intensity value sequence, the system uses boundary condition constraints to set upper and lower limits for the stimulus intensity and temporal distribution. It also introduces a smoothness weighting method to control the continuity and rhythm of the curve's changes. The entire process consists of five steps: intensity value boundary constraints, time interval boundary constraints, amplitude limit processing, importance weight calculation, and local smoothing correction.

[0052] Step 1: Setting the upper and lower limits of intervention intensity. The system traverses each time point in the preliminary intervention curve and performs the following intensity boundary checks: The minimum intensity limit is set to 0.2. If the intensity of a point is less than 0.2, its value is set to 0, indicating that no stimulation is required at that time point; this value is set with reference to the minimum threshold for stimulation onset, which is derived from clinical studies showing that nerve stimulation below this value has no measurable physiological effect. The maximum intensity limit is set to 1. If the intensity of a point exceeds 1, it is corrected to 1 to prevent the energy from exceeding the maximum tolerable range of the device. The minimum effective difference is set to 0.05. If the intensity difference between two adjacent points is less than 0.05, the smaller value will move closer to the larger value, making its change significant, and avoiding noise level disturbances affecting system behavior.

[0053] Step 2: Define the boundaries of the intervention time interval. The system traverses the time series of all non-zero intensity points, calculates the time difference between adjacent intervention points, and implements the following strategy: If the interval between two points is less than 10 minutes, it indicates that the points are too close together. The system retains the point with higher intensity and deletes the other point to ensure sufficient recovery space for the physiological system within the response cycle. If the interval between two points is greater than 60 minutes, it indicates a possible rhythm gap. The system automatically inserts a transition point at the midpoint of the interval, with the time position in the middle 10-minute segment and the intensity value as the average of the two points before and after to ensure continuity of stimulation coverage. The above 10-minute and 60-minute parameters are derived from the statistical results of the neuromodulation recovery period (minimum stimulation re-entry interval) and the minimum unit of symptom rhythm (regulation period within a single hour), respectively.

[0054] Step 3: Intensity jump amplitude limitation. To prevent sudden rises or falls in the curve, the system performs intensity difference detection on each pair of adjacent points. If the intensity jump amplitude is greater than 0.3, the system initiates a step-by-step transition mechanism, automatically inserting one or two transition points in the middle, evenly spaced over the time period, with the total difference distributed to the middle point. For example, if the intensity at the starting point of a segment is 0.3 and the intensity at the ending point is 0.9, with a difference of 0.6, two points with intensities of 0.5 and 0.7 are inserted in the middle to achieve a smooth linear transition. 0.3 is the maximum allowable mutation amplitude, which is the acceptable mutation threshold determined through analysis of patient heart rate and EEG response data.

[0055] Step 4: Assigning time point importance weights. The system calculates a smoothing control weight for each intervention point, ranging from 0 to 1. It consists of the following three components: Rhythm change rate weight (P1): The sum of the intensity differences between the current point and the points before and after it is divided by 2. If the result is greater than 0.2, P1 is 1; otherwise, it is scaled proportionally. Symptom history overlap weight (P2): The frequency of acute episodes in the 10-minute segment of the current point over the past 7 days is divided by 98. A larger value indicates a higher overlap with the peak period and a higher weight. Node type weight (P3): Core nodes have a weight of 1, interpolation points have a weight of 0.5, and system-added transition points have a weight of 0.3. The combined weight W is P1 multiplied by 0.5, P2 multiplied by 0.3, and P3 multiplied by 0.2, with the result rounded to two decimal places.

[0056] Step 5: Smoothing execution and intervention plan output. After completing the importance weight calculation of all points, the system performs a three-point sliding average smoothing process on the points where W is less than 0.5. The processing logic is: replace the current value with the weighted average of the intensity values ​​of the point and the two points before and after, with weights of 0.25, 0.5, and 0.25 respectively. Points with weights greater than or equal to 0.5 keep their original values ​​unchanged, retaining their responsiveness in the curve. The final output of the intervention execution plan is a structured array of length 144, corresponding to 1 time point every 10 minutes for 1440 minutes, containing fields including time number, intensity value, whether it is a core point, and smoothing weight value. The system reconstructs the intervention execution plan every 24 hours to adapt to the evolution of symptoms and feedback data updates.

[0057] This technical solution introduces boundary condition constraint technology based on the preliminary intervention intensity curve, setting upper and lower intensity limits and time interval restrictions for each intervention point. Combined with a smoothness weight distribution method, the importance of each time point is dynamically calculated based on the rhythm change rate, symptom overlap, and node type. This allows for zoning optimization and local adjustment of the curve, effectively eliminating mutation points, overly dense interventions, and gaps. This method not only improves the continuity of the intervention curve and the matching of physiological rhythms, but also ensures the complete preservation of intervention intensity at key nodes. It significantly enhances the controllability, rhythm stability, and individual adaptability of the execution plan, providing a high-quality timing infrastructure for subsequent feedback regulation and closed-loop control.

[0058] According to the smooth intervention execution plan, real-time feedback data on the relief of patients' impaired consciousness symptoms during the intervention period is collected. If the feedback data deviates from the preset threshold range, the rule base parameters are adjusted through dynamic rule updating technology. At the same time, combined with interpolation error correction and curve continuity verification, the intervention schedule and stimulation intensity curve are updated to determine the optimized intervention execution plan.

[0059] This technical solution is based on a real-time feedback control mechanism, and completes the adaptive optimization and upgrade of the initial execution plan through five major processes: feedback collection, anomaly identification, dynamic parameter correction, local interpolation adjustment, and curve continuity verification. The specific implementation process is as follows: 1. Feedback Data Collection and Standardization. The system automatically collects caregiver pain scores (ranging from 0 to 10) every 10 minutes through wearable devices, along with auxiliary indicators such as blood pressure changes, skin conductivity, and sleep disruption markers. Subjective rating data is used to generate the level of improvement in impaired consciousness, which is standardized according to the following criteria: a score of 0 to 2 is classified as no improvement, with a standard value of 0; a score of 3 to 5 is classified as mild improvement, with a standard value of 0.3; a score of 6 to 8 is classified as moderate improvement, with a standard value of 0.6; and a score of 9 to 10 is classified as significant improvement, with a standard value of 1. A standardized feedback value is generated at each time point and incorporated into the feedback data sequence.

[0060] Second, the system sets a target remission value, T, for each patient, categorized by patient type: mild impaired consciousness, T is set to 0.6; moderate impaired consciousness, T is set to 0.7; and severe impaired consciousness, T is set to 0.8. The system compares the feedback value, F, at the current time point with the target value, T. A deviation is identified if any of the following two conditions exist: F is less than T minus 0.2 for three consecutive time points; F is less than 0.4 at any time point, and an ancillary indicator collected by the device is abnormal.

[0061] 3. Dynamic rule base parameter update process. After the deviation judgment is triggered, the system updates the following parameters of the intervention rule base: the rule number records the current intervention time period; the symptom priority value is increased by 1 level, for example, from 0.3 to 0.6; the historical symptom density value is increased by 20%; the current node strength correction factor is set to 1.2, that is, the strength of similar situations in subsequent interventions is multiplied by 1.2; the deviation sample is added to the "abnormal pattern template" sub-library, and the template validity period is set to 7 days. After the expiration, the right will be downgraded.

[0062] IV. Interpolation Error Correction Mechanism and Calculation Logic: If the deviation region spans multiple intervention nodes, the system interpolates and corrects the intermediate segment between adjacent intervention points A and B: Intensities A and B are Sa and Sb, respectively. The interpolation segment consists of N intermediate points. The intensity at each intermediate point, at the nth position, is Sa plus Sb minus Sa, multiplied by n divided by N plus 1. If the feedback deviation level is severe (i.e., the feedback value is less than 0.3), all interpolated results are multiplied by an additional factor of 1.2 to 1.4 based on the deviation level. The system ensures that a single correction does not exceed 30% of the original value to ensure physiological tolerance of the intervention stimulus.

[0063] 5. Curve continuity verification calculation method, the corrected intervention intensity curve performs integrity verification, mainly checking the following contents: Intensity mutation value detection: Any two adjacent points with an intensity difference exceeding 0.3 are defined as mutations. The system adjusts the larger value below the critical value and inserts two equidistant increasing (or decreasing) points for smoothing. Intervention gap identification: Any continuous blank (intensity of 0) segment with more than 6 points (i.e. 60 minutes) is defined as a gap. The system interpolates a point with an intensity value of 80% of the previous non-zero segment in the middle position to ensure that the intervention rhythm is not lost. Local extreme value verification: If the intensity value of any non-core node is greater than the average value of its two sides plus 0.4, the system identifies it as a pseudo-peak and adjusts it to be consistent with the average of the left and right points.

[0064] VI. Final Optimization Implementation Plan Generation: After completing the above processing, the system reconstructs the intervention implementation plan, which includes 144 time points. Each point contains the following fields: time number (1 to 144); final stimulation intensity (range 0.2 to 1); whether it is a dynamic correction node; current node weight value (for subsequent optimization); and response template flag (whether it is included in the negative feedback template). This implementation plan will be reconstructed every 24 hours and will be updated immediately if the patient's feedback indicates significant abnormalities, ensuring that the stimulation response remains synchronized with the symptom evolution.

[0065] The preset threshold range is determined based on a large number of clinical samples through statistical analysis and expert consensus, and is used to judge whether the intervention feedback is effective. The specific determination process includes three steps: First, the system collects consciousness improvement score data for patients with different consciousness disorders before and after the intervention, and calculates the median and 25th and 75th percentiles for each score sequence, which serve as the baseline remission level and upper and lower limit references, respectively; second, the expected remission value for different symptom levels is set, such as 0.6 for mild, 0.7 for moderate, and 0.8 for severe; finally, the expert group conducts cluster analysis on different behavioral response data, evaluates the actual remission probability under the target stimulation intensity, and determines the acceptable deviation range for each symptom type as the target value minus 0.2 to the target value plus 0.2. Finally, the system writes this threshold range into the feedback judgment logic, which is used to determine in real time whether the feedback data deviates from the standard, ensuring that the judgment process is both scientifically based and adaptable to individual patient differences.

[0066] This technical solution achieves closed-loop regulation and adaptive optimization of the intervention execution process by introducing a real-time feedback mechanism and dynamic rule updating technology. During the intervention process, the system continuously collects the subjective relief scores and physiological response data of the patient's caregivers, and compares them with the preset quantitative threshold range. If deviations are found, it triggers dynamic adjustment of rule parameters, interpolation correction of intervention curves, and continuity verification, thereby updating the intervention schedule and stimulation intensity curve. This method not only improves the system's sensitivity and response speed to individualized state changes, but also effectively avoids the problem of insufficient adaptability of fixed intervention plans in complex conditions. By continuously optimizing the execution path, the stability and efficiency of the intervention effect are improved, and a data-driven precision treatment strategy with patient feedback as the core is realized, which enhances the intelligence, safety and actual clinical application value of the system.

[0067] For the optimized intervention execution plan, personalized threshold setting technology is used to adjust the triggering conditions of consciousness disorder intervention according to individual differences. At the same time, through real-time data fusion methods, the latest feedback data is integrated into the intervention intensity curve to obtain the final dynamic intervention execution logic.

[0068] To achieve precise and dynamic intervention control for impaired consciousness, this technical solution begins with determining individual thresholds and, combined with real-time feedback data, constructs the ultimate intervention triggering logic and intensity adjustment mechanism. The overall process is divided into three core computational steps: threshold setting calculation, integrated feedback adjustment, and dynamic output logic construction.

[0069] 1. Personalized threshold setting calculation process: The system first extracts the individual response characteristics of each patient from historical feedback data and calculates the personalized intervention trigger threshold. The specific steps are as follows: Extract samples: Select valid feedback data from 144 time points every day for the past 7 days, remove missing and abnormal points, and form a standard scoring sequence with a total data volume of no less than 720 points. Calculate the median and variation range: Calculate the median, 25th percentile, and 75th percentile of the sequence. For example, if the median is 0.65, the 25th percentile is 0.55, and the 75th percentile is 0.75, the basic remission range is 0.55 to 0.75. Match target remission level: Based on the type of consciousness disorder determined by the patient at registration, the system assigns them a desired remission target, such as 0.8 for severe patients, 0.7 for moderate patients, and 0.6 for mild patients. Set a personalized trigger value: If the median is less than or equal to the target value by 0.1, set the trigger value to the target value. If the median is more than 0.1 above the target value, set the trigger value to the median minus 0.05. If the median is more than 0.2 below the target value, set the trigger value to the median plus 0.1. This ultimately yields a personalized trigger threshold, V (typically ranging from 0.5 to 0.85), which is used to determine whether to initiate intervention.

[0070] 2. Real-time data fusion and intervention intensity adjustment calculation: Every 10 minutes, the system collects the current feedback value F once and dynamically adjusts the intervention intensity S at the current time point according to the following rules: If F is higher than V + 0.1: the current stimulation intensity decreases by 10%, that is, S is set to the original value multiplied by 0.9; If F is lower than V - 0.2: the current intensity is increased by 15%, that is, S is multiplied by 1.15; If F is between V minus 0.1 and V: the current intensity remains unchanged, but the node is marked with a "sensitive label" for subsequent intensive processing; If F is lower than V minus 0.2 for three consecutive time points: the current node is marked as a "high-priority response point" and is assigned a time importance weight of more than 0.8 in the subsequent curve construction.

[0071] Third, the dynamic intervention logic output construction process combines the personalized trigger value V with the intensity S adjusted by real-time feedback. The system generates a final intervention instruction set for each 10-minute segment, including time numbers (1 to 144), corresponding to each 10-minute segment throughout the day. The output intensity value S is a corrected value, limited to 0.2 to 1. A trigger flag determines whether the current time point F is lower than V. If so, the trigger flag is set to "yes"; otherwise, it is set to "no." A priority tag is categorized as high, medium, or low based on the deviation between current feedback and historical data, with values ​​of 0.8, 0.5, and 0.3, respectively. A fusion correction tag records whether the point is a fusion update node, marked as "Y" or "N." Each record is stored in the execution plan table, and the system automatically completes a comprehensive plan update every 24 hours. In special cases, if a rapid deviation from the trend is detected, the immediate update logic can be triggered. The system uses this dynamic plan as the dominant intervention sequence in the next cycle, implementing an adaptive closed-loop control system of feedback-adjustment-re-intervention.

[0072] The intervention intensity S at the current point in time refers to the stimulation intensity value calculated by the system based on the individual feedback status and the established intervention strategy within a specific time period. It is the core parameter for executing dynamic intervention. This value comprehensively considers the personalized trigger threshold V, the real-time feedback value F, and the feedback trend to ensure that the intervention intensity meets the clinical efficacy requirements while not exceeding the individual's tolerance range. In specific implementation, if F is significantly lower than V, the system automatically adjusts S upward to enhance the intervention response; if F is significantly higher than V, it indicates that the current intervention has produced a good effect, and S is adjusted downward accordingly to prevent overstimulation. The value range of S is strictly limited to between 0.2 and 1, and it is fine-tuned through multi-point feedback trends and node priority labels to ensure that the intensity adjustment at different nodes is stable and individually adaptable. Ultimately, S not only reflects the intensity of intervention needs in the current state, but also serves as the basic variable for the construction and real-time update of dynamic intervention curves.

[0073] This technical solution, by introducing personalized threshold setting technology and real-time data fusion methods, has built an intervention execution mechanism for the dynamic changes in patient status, effectively improving the accuracy and timeliness of intervention responses. The system sets a unique intervention trigger threshold based on each patient's historical remission level and consciousness disorder characteristics, making intervention decisions more in line with individual physiological characteristics; at the same time, the feedback data collected in real time is continuously integrated into the current intervention intensity curve to achieve continuous correction and dynamic optimization of stimulation intensity, avoiding the problem of ignoring individual differences in fixed stimulation modes in traditional solutions. This strategy ensures that the intervention output is always in the optimal response range, significantly enhancing the individual adaptability and rhythm stability of the treatment, and providing solid technical support for the realization of precision medicine and intelligent intervention.

[0074] Using personalized threshold setting technology, the triggering conditions for consciousness disorder intervention are adjusted according to individual differences. The specific formula is: ;in, represents the threshold of individual i, represents the average value of historical data of individual i, represents the standard deviation of the historical data of individual i, represents the standard deviation adjustment parameter, and i represents the individual number index.

[0075] This technical solution uses personalized threshold setting technology to dynamically adjust the triggering conditions for impaired consciousness intervention based on each individual's historical data characteristics. In specific implementation, the system first extracts two key statistical parameters: the mean and standard deviation, representing the individual's baseline remission level and fluctuation range, respectively, from the individual's past intervention response data. These two values ​​are then linearly combined according to a formula to obtain the individual's dynamic intervention threshold. The threshold is calculated by summing the individual's historical mean and its standard deviation multiplied by a standard deviation adjustment parameter, where the adjustment parameter is used to control the threshold sensitivity. The system calculates and stores the threshold for each individual based on their ID. When real-time feedback data falls below the threshold, the intervention mechanism is triggered, thus implementing intelligent intervention logic that adapts to individual status changes. By transforming the intervention trigger condition from a fixed value to a personalized threshold dynamically calculated based on the individual's historical data, this solution effectively improves the intervention system's adaptability to patient differences. Personalized threshold setting allows the intervention strategy to better adapt to each patient's physiological rhythms and symptom changes, avoiding excessive or insufficient intervention, and helping to improve the accuracy and safety of the intervention. At the same time, by introducing the standard deviation adjustment parameter, the sensitivity of the intervention threshold can be flexibly controlled, so that the system can maintain a stable response at different stages of the disease, significantly enhancing the scientific nature, robustness and clinical adaptability of the intervention logic.

[0076] Indicates the intervention trigger threshold of the i-th individual (i.e., a specific patient) in actual intervention. This value is the core criterion for the system to determine whether to initiate the intervention operation. Setting method: and Calculated, not set directly. The system updates once every 24 hours during execution. . The average value of the historical relief feedback data of individual i is the central trend indicator reflecting the level of intervention effect of the individual. Setting method: The system automatically extracts the individual's consciousness disorder improvement score data collected in the last 7 days, removes abnormalities and normalizes them, and calculates the average value of all valid data points. For example: If the 7-day data of individual i contains 1008 valid feedback points (1 every 10 minutes), then The arithmetic mean of these 1008 standardized scores. Range: Generally between 0.3 and 0.8, depending on individual symptom type and relief response. Indicates the standard deviation of the feedback data of individual i, which is used to reflect the degree of symptom fluctuation of the patient. The larger the standard deviation, the more unstable the patient's condition is and the more sensitive the intervention strategy needs to be; the smaller the standard deviation, the more stable the condition is. Setting method: Standard deviation is calculated based on the same data set. Range: Typically between 0.05 and 0.2, with the value affecting the sensitivity of the final Ti. To adjust the standard deviation The weight in the threshold calculation is the control variable of the scheme. The larger the value, the The more conservative; The smaller the value, the more sensitive the system intervention.

[0077] Standard deviation adjustment parameter The specific formula is: ; in, represents the standard deviation adjustment parameter, represents the variance of feedback data of individual i, represents the time delay from the start of intervention to the response of individual i, It represents the frequency of intervention received by individual i in unit time, and i represents the individual number index.

[0078] By introducing the variance of individual feedback data , response time delay and the frequency of intervention per unit time And other core indicators, build a composite parameter adjustment model. Specifically, The calculation of the value takes into account three factors: first, It reflects the stability of individual feedback data. The larger the variance, the more drastic the individual state fluctuations and the higher the unpredictability of the stimulus response. It reflects the time delay from the start of intervention to the generation of response. The longer the delay, the less sensitive the individual is to the intervention and the need to improve trigger sensitivity. Indicates the frequency at which the individual actually receives intervention in a unit of time. If the frequency is too high, the system needs to reduce it appropriately. The formula structure uses logarithmic functions and fractional terms to achieve nonlinear compression and dynamic coordination of different indicators, thereby automatically outputting the most suitable individual state. The model is called by the system in real time and updated periodically to serve as the subsequent intervention threshold. The precise calculation of provides key weight support.

[0079] The time delay from the start of the intervention to the response of individual i Specifically, it is the difference between the time when individual i first has a measurable response and the time when individual i first receives intervention. By continuously monitoring the physiological or behavioral feedback data of individual i after the intervention is implemented, the moment when the response exceeds the preset relief response threshold for the first time is identified and regarded as the "time point of measurable response"; at the same time, the system timestamp of the first time the individual receives this round of intervention is recorded. The time difference between the two is The system uses a timestamp with a precision of seconds to mark all data, combines continuous feedback data such as symptom scores, neuroreflex indicators, and consciousness awakening scores, and uses a window sliding algorithm to identify the "first significant response". Usually, the response is determined to have occurred when the score value increases by more than 0.2. This definition method avoids abstract or subjective judgment and makes the delay It has a clear and stable quantitative basis and can be directly used in subsequent parameter calculations and intervention strategy adjustments.

[0080] like Figure 2As shown, a method for interactively promoting consciousness disturbance in a smart terminal based on TCM rules is also provided. Using the aforementioned interactive promoting consciousness disturbance in a smart terminal based on TCM rules, the method includes obtaining multidimensional clinical data of patients with consciousness disturbances, constructing an initial patient clinical information matrix through data cleaning and standardization, and obtaining a structured consciousness disturbance feature data set; obtaining a preliminary intervention intensity curve for the structured consciousness disturbance feature data set; using boundary condition constraint technology to set upper and lower limits for intervention intensity and time for the preliminary intervention intensity curve, and adjusting the importance parameters of time points through a smoothness weight distribution method to obtain a smooth intervention execution plan; according to the smooth intervention execution plan, real-time feedback data on improvement of the patient's consciousness disturbance during the intervention period is collected; if the feedback data deviates from a preset threshold range, the rule base parameters are adjusted through dynamic rule updating technology, and the intervention schedule and stimulation intensity curve are updated in combination with interpolation error correction and curve continuity verification to determine an optimized intervention execution plan; using personalized threshold setting technology for the optimized intervention execution plan, the triggering conditions of the consciousness promotion intervention are adjusted according to individual differences; and using a real-time data fusion method, the latest feedback data is integrated into the intervention intensity curve to obtain the final dynamic intervention execution logic.

[0081] First, the system uses multimodal sensors to acquire multidimensional clinical data from patients with impaired consciousness, including physiological signals and behavioral manifestations. After outliers are removed and normalized, a structured dataset of impaired consciousness characteristics is generated. Subsequently, the system employs symptom matching rules and state classification methods, incorporating individual frequency and duration characteristics, to generate a personalized symptom priority vector. Based on this vector, a schedule generation algorithm preliminarily determines intervention time points. An intensity decision model then calculates a preliminary intervention intensity curve, incorporating parameters such as feedback volatility. Furthermore, boundary constraints set upper and lower limits for time and intensity, and a smoothness weight is introduced to adjust intervention density at key time points, resulting in a stable and executable smoothed intervention plan. During the intervention phase, the system collects patient feedback in real time. If scores deviate from the set threshold, the system invokes a dynamic rule update mechanism to adjust the rule base, perform error interpolation, and perform curve continuity testing, automatically and iteratively optimizing the intervention plan. Finally, the system uses a formulaic threshold setting method to adjust intervention trigger conditions based on individual patient characteristics. New feedback data is continuously incorporated into the intervention intensity curve, enabling real-time closed-loop optimization. This outputs the final dynamic intervention logic, ensuring that the intervention strategy at each time point is individually adaptable and physiologically reasonable.

[0082] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent terminal interactive awakening system for impaired consciousness based on TCM rules, characterized by: The system comprises: The data acquisition module acquires multi-dimensional clinical data of patients with impaired consciousness, constructs an initial patient clinical information matrix through data cleaning and standardization, and obtains a structured dataset of impaired consciousness characteristics; The intervention plan generation module obtains a preliminary intervention intensity curve based on the structured consciousness disorder feature dataset. Based on this preliminary intervention intensity curve, the module uses boundary condition constraint technology to set the upper and lower limits of intervention intensity and time. At the same time, the module uses the smoothness weight distribution method to adjust the importance parameters of time points to obtain a smooth intervention execution plan. The data feedback and analysis module collects real-time feedback data on the patient's improvement in consciousness disorder during the intervention period based on a smooth intervention execution plan. If the feedback data deviates from the preset threshold range, the rule base parameters are adjusted through dynamic rule updating technology. At the same time, combined with interpolation error correction and curve continuity verification, the intervention schedule and stimulation intensity curve are updated to determine the optimized intervention execution plan. The personalized adaptation module uses personalized threshold setting technology for the optimized intervention execution plan to adjust the triggering conditions of consciousness-promoting intervention according to individual differences. At the same time, through real-time data fusion methods, it integrates the latest feedback data into the intervention intensity curve to obtain the final dynamic intervention execution logic.

2. The intelligent terminal consciousness disorder interactive awakening system based on TCM rules according to claim 1 is characterized by: The preliminary intervention intensity curve obtained for the structured consciousness disorder feature dataset includes: For the structured consciousness disorder feature dataset, the pre-established symptom matching rules are used in combination with the patient status classification method to divide the patient status into acute phase and remission phase, and the patient's consciousness disorder classification result is determined.

3. The intelligent terminal consciousness disorder interactive awakening system based on TCM rules according to claim 2 is characterized by: The method of obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature dataset further includes: Individualized characteristics of the frequency and duration of consciousness disorders are extracted from the consciousness disorder classification results. The intervention priority sorting logic is used to determine the patient's core symptom intervention needs and obtain a personalized symptom priority vector.

4. The intelligent terminal consciousness disorder interactive awakening system based on TCM rules according to claim 3 is characterized by: The method of obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature dataset further includes: Based on the personalized symptom priority vector and combined with historical data weight analysis, a timetable generation algorithm is used to construct a preliminary intervention time point distribution logic to determine the initial consciousness disorder intervention timetable.

5. The intelligent terminal consciousness disorder interactive awakening system based on traditional Chinese medicine rules according to claim 4 is characterized by: The method of obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature dataset further includes: For the initial intervention schedule for impaired consciousness, the time interval segmentation logic is used to divide the schedule into smaller time units. At the same time, through the key node extraction technology, the peak period of impaired consciousness is identified as the core intervention point to obtain a detailed intervention time framework.

6. The intelligent terminal consciousness disorder interactive awakening system based on TCM rules according to claim 5 is characterized by: The method of obtaining a preliminary intervention intensity curve for the structured consciousness disorder feature dataset further includes: From the refined intervention time frame, combined with the intensity decision model, the initial stimulation intensity is calculated, and the stimulation intensity of the intermediate points between adjacent key nodes is calculated through the intensity value interpolation formula to obtain the preliminary intervention intensity curve.

7. The intelligent terminal consciousness disorder interactive awakening system based on TCM rules according to claim 1 is characterized by: The specific formula for adjusting the triggering conditions for consciousness disorder intervention based on individual differences using personalized threshold setting technology is: ； in, represents the threshold of individual i, represents the average value of historical data of individual i, represents the standard deviation of the historical data of individual i, represents the standard deviation adjustment parameter, and i represents the individual number index.

8. The intelligent terminal consciousness disorder interactive awakening system based on TCM rules according to claim 7 is characterized by: The standard deviation adjustment parameter The specific formula is: ； in, represents the standard deviation adjustment parameter, represents the variance of feedback data of individual i, represents the time delay from the start of intervention to the response of individual i, It represents the frequency of intervention received by individual i in unit time, and i represents the individual number index.

9. The intelligent terminal consciousness disorder interactive awakening system based on traditional Chinese medicine rules according to claim 8 is characterized in that: The time delay from the start of intervention to the response of individual i Specifically, it is the difference between the time point when individual i first shows a measurable response and the time point when individual i first receives intervention.

10. A method for interactively promoting awakening of patients with impaired consciousness using a smart terminal based on TCM rules, using the system for interactively promoting awakening of patients with impaired consciousness using a smart terminal based on TCM rules as described in any one of claims 1 to 9, characterized in that: The method comprises: Obtain multidimensional clinical data of patients with impaired consciousness, construct an initial patient clinical information matrix through data cleaning and standardization, and obtain a structured impaired consciousness feature dataset; Based on the structured dataset of consciousness disorder characteristics, a preliminary intervention intensity curve was obtained. Based on this preliminary intervention intensity curve, boundary condition constraint technology was used to set the upper and lower limits of intervention intensity and time. At the same time, the importance parameters of time points were adjusted through the smoothness weight distribution method to obtain a smooth intervention execution plan. According to the smooth intervention execution plan, real-time feedback data on the patient's improvement in consciousness disorder during the intervention period is collected. If the feedback data deviates from the preset threshold range, the rule base parameters are adjusted through dynamic rule updating technology. At the same time, combined with interpolation error correction and curve continuity verification, the intervention schedule and stimulation intensity curve are updated to determine the optimized intervention execution plan; For the optimized intervention execution plan, personalized threshold setting technology is used to adjust the triggering conditions of consciousness-promoting intervention according to individual differences. At the same time, through real-time data fusion methods, the latest feedback data is integrated into the intervention intensity curve to obtain the final dynamic intervention execution logic.

Images