Medical self-service negative pressure nose washing all-in-one machine

Abstract

The invention provides a medical self-service negative pressure nose washing all-in-one machine, and relates to the technical field of nursing equipment, and the medical self-service negative pressure nose washing all-in-one machine comprises a data reading module which is used for executing user identity recognition, starting the all-in-one machine, and reading user case data and washing reaction records; the real-time interaction module is used for carrying out data interaction with real-time monitoring equipment and acquiring a user nasal cavity data set which comprises nasal cavity resistance sensing data and nasal cavity temperature and humidity data; the decision-making module is used for generating a historical weight factor according to the time sequence concentration degree of the case data of the user, performing a flushing control decision after a flushing constraint is established according to a flushing reaction record, and establishing a decision-making result; the negative pressure control module is used for configuring the negative pressure intensity, the liquid flow rate and the flushing liquid amount and executing negative pressure nasal cavity cleaning. The technical problem that the nasal cavity cleaning effect is poor due to the fact that traditional equipment often adopts standardized nasal cavity cleaning parameters and cannot provide personalized nasal cavity cleaning schemes according to specific conditions and requirements of different users is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of nursing equipment, and particularly to a medical self-service negative pressure nasal irrigation integrated machine. Background Art

[0002] For nasal disease patients, especially those suffering from rhinitis, allergies and colds, traditional nasal irrigation methods include manual flushing, spraying and using drugs, etc. These methods often have some limitations. For example, the nasal irrigation efficiency is low, the operation is complex or the nasal irrigation effect is not persistent. Most of the current nasal irrigation devices on the market are mainly simple flushing or drug spraying, such as manual nasal irrigation pots or drug sprayers. Although these devices provide solutions to a certain extent, there are still deficiencies in terms of operation convenience, nasal irrigation accuracy and individualized nasal irrigation. For example, manual irrigation devices rely on user skills and are prone to improper operation resulting in infection or injury, and traditional devices often adopt standardized nasal irrigation parameters and cannot provide personalized nasal irrigation solutions according to the specific conditions and needs of different users, resulting in poor nasal cavity cleaning effects. Summary of the Invention

[0003] This application provides a medical self-service negative pressure nasal irrigation integrated machine, aiming to solve the technical problem that traditional devices often adopt standardized nasal irrigation parameters and cannot provide personalized nasal irrigation solutions according to the specific conditions and needs of different users, resulting in poor nasal cavity cleaning effects.

[0004] This application discloses a medical self-service negative pressure nasal irrigation integrated machine, which includes: a data reading module, used to perform user identity recognition after being activated by the user, start the integrated machine according to the identity recognition result, and read the user's case data and irrigation reaction records based on the identity recognition result; a real-time interaction module, used to perform data interaction with real-time monitoring devices to obtain a user nasal cavity data set, where the user nasal cavity data set includes nasal resistance sensing data and nasal cavity temperature and humidity data; a decision-making module, used to receive the user's case data, the irrigation reaction records, and the user nasal cavity data set, generate a historical weight factor according to the time series concentration degree of the user's case data, establish irrigation constraints based on the irrigation reaction records, and perform irrigation control decision-making according to the historical weight factor, the user's case data and the user nasal cavity data set to establish a decision result; a negative pressure control module, used to configure the negative pressure intensity, liquid flow rate and irrigation fluid volume according to the decision result and perform negative pressure nasal cavity cleaning.

[0005] One or more technical solutions provided in this application have at least the following beneficial effects:

[0006] The data reading module can automatically load the user's medical records and previous irrigation responses by activating the device and performing user identification. This is used for analyzing and improving future nasal irrigation plans, ensuring the continuity and optimization of nasal irrigation, and ensuring the personalization of the nasal irrigation plan. The real-time interaction module ensures that the device can receive the user's nasal cavity data set in real time, including nasal cavity resistance and temperature and humidity data, through its data interaction function with the real-time monitoring device. The collected data is used to monitor the nasal irrigation process in real time and immediately adjust the irrigation parameters, improving the adaptability and effectiveness of nasal irrigation. The decision-making module generates historical weight factors by analyzing the temporal concentration of the user's medical record data. This helps to prioritize the most relevant and influential historical data in new nasal irrigation decisions. It uses the user's irrigation response records to establish irrigation constraints, ensuring that the nasal irrigation plan conforms to the individual responses of the user in terms of safety and effectiveness. It makes decisions by integrating historical weight factors, medical record data, and real-time nasal cavity data, and formulates the most suitable irrigation plan for the current user status. The negative pressure control module automatically configures the negative pressure intensity, liquid flow rate, and irrigation fluid volume according to the decision result to adapt to different nasal irrigation needs, optimize the irrigation process, ensure the comfort and effectiveness during nasal irrigation, achieve efficient and safe nasal cavity cleaning, reduce discomfort during nasal irrigation, and enhance the user experience.

[0007] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. Brief Description of the Drawings

[0008] Figure 1 It is a schematic structural diagram of a medical self-service negative pressure nasal irrigation machine provided by an embodiment of this application.

[0009] Figure 2 It is a schematic structural diagram of the decision-making module in a medical self-service negative pressure nasal irrigation machine provided by an embodiment of this application.

[0010] Description of the reference numerals: data reading module 10, real-time interaction module 20, decision-making module 30, negative pressure control module 40, data temporal sorting module 31, data volume analysis module 32, zero-point concentration evaluation module 33. Detailed Description of the Invention

[0011] By providing a medical self-service negative pressure nasal irrigation machine in an embodiment of this application, the technical problem that traditional devices often use standardized nasal irrigation parameters and cannot provide personalized nasal irrigation plans according to the specific conditions and needs of different users, resulting in poor nasal cavity cleaning effects, is solved.

[0012] After introducing the basic principle of the present application, various non-limiting implementation manners of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0013] As Figure 1 shown, an embodiment of the present application provides a medical self-service negative pressure nasal irrigation integrated machine, and the integrated machine includes:

[0014] A data reading module 10, configured to perform user identity recognition after being activated by a user, start the integrated machine according to the identity recognition result, and read user case data and irrigation reaction records based on the identity recognition result.

[0015] After the user activates the device, the data reading module performs user identity recognition. Identity recognition usually uses some biometric recognition technologies, such as entering a username and password, to confirm the user's identity. According to the recognized user identity, the integrated machine device is started. Different users will have different configurations and requirements. Therefore, the device will provide personalized services according to the user's identity after recognizing the user. When the identity is confirmed, based on the identity recognition result, the case data and irrigation reaction records of the user are read from the database. Among them, the case data includes the user's health status, past medical history, such as nasal diseases, surgical history, etc., and other relevant case information; the irrigation reaction record is the reaction data of the user when using the device in the past, such as the effect after nasal irrigation and the user's comfort level. In this way, the data reading module can provide necessary information support for the device to ensure that the device can make personalized nasal irrigation decisions according to the health status and historical reactions of different users.

[0016] A real-time interaction module 20, configured to perform data interaction with a real-time monitoring device, and obtain a user nasal cavity data set, where the user nasal cavity data set includes nasal cavity resistance sensing data and nasal cavity temperature and humidity data.

[0017] The real-time interaction module interacts with real-time monitoring devices in the device, such as sensors or other monitoring devices, to obtain relevant data of the user in real time. These monitoring devices can continuously collect data and feedback it to the real-time interaction module. Among them, the nasal cavity resistance sensing data reflects the air flow resistance inside the user's nasal cavity, usually measured by sensors in the nasal cavity. The air flow resistance of the nasal cavity can help evaluate the nasal cavity ventilation condition, such as whether there is nasal congestion and other problems; the nasal cavity temperature and humidity data reflects the temperature and humidity conditions inside the user's nasal cavity. Temperature and humidity are crucial for nasal cavity health and can provide some information about the nasal cavity environment to help evaluate whether there are problems such as dryness, inflammation or other nasal cavity health problems. Through the real-time interaction module, the device can dynamically monitor the user's nasal cavity condition and make appropriate adjustments according to the real-time data to ensure the effect and safety of the nasal irrigation process.

[0018] The decision-making module 30 is configured to receive the user case data, the irrigation response record, and the user nasal cavity dataset, generate a historical weight factor according to the temporal concentration degree of the user case data, establish irrigation constraints based on the irrigation response record, and then make an irrigation control decision according to the historical weight factor, the user case data, and the user nasal cavity dataset, and establish a decision result.

[0019] The decision-making module first receives data inputs from other modules, specifically including user case data, irrigation response records, and user nasal cavity datasets. Then, it analyzes the temporal concentration degree of the user case data. The temporal concentration degree refers to the distribution and regularity of the user case data in time, evaluating whether there are periodic or specific time patterns in the data. Through the analysis of the temporal concentration degree, it can be determined which data have a more important impact at specific time points. Based on the temporal concentration degree, the decision-making module generates a historical weight factor, which can reflect the weights of the case data at different time nodes. The role of the historical weight factor is to adjust the influence of various data during the nasal irrigation process, so that when making irrigation decisions, more attention can be paid to certain key time periods or historical events. Establish irrigation constraints based on the irrigation response record, which means setting some limiting conditions, such as the maximum irrigation intensity, the maximum liquid volume, etc., according to the user's past responses, to avoid possible discomfort or adverse reactions.

[0020] Combining the historical weight factor, the user's case data, the user nasal cavity dataset, and the irrigation constraints, the decision-making module makes an irrigation control decision. This step is to intelligently adjust parameters such as the irrigation intensity, liquid flow rate, and irrigation liquid volume according to all the collected data to ensure that the irrigation process is most suitable for the user's nasal cavity. This process will ensure the personalization and efficiency of the nasal irrigation plan according to the user's individual differences, past nasal irrigation responses, and current nasal health status.

[0021] Finally, the decision-making module outputs a decision result, which contains the specific control parameters and steps to be followed during the nasal irrigation process, and provides them to the negative pressure control module or other execution modules of the device to perform the actual nasal irrigation operation. In summary, the role of the decision-making module is to integrate various data, analyze and judge the user's personalized needs, so as to provide a precise control plan for the nasal irrigation process and ensure the nasal irrigation effect and the user's safety.

[0022] The negative pressure control module 40 is configured to configure the negative pressure intensity, liquid flow rate, and irrigation liquid volume according to the decision result and perform negative pressure nasal cavity cleaning.

[0023] The negative pressure control module first receives the decision result from the decision-making module and configures the appropriate negative pressure intensity according to the decision result. The negative pressure intensity refers to the suction force generated by the device, which is usually adjusted according to the user's nasal conditions and health status. For example, if the user's nasal cavity is more sensitive or has nasal inflammation, a lower negative pressure intensity will be selected; if the nasal ventilation is poor, the negative pressure intensity needs to be increased to achieve the cleaning effect. The negative pressure control module sets the liquid flow rate according to the decision result. The adjustment of the liquid flow rate helps to ensure that the irrigation fluid can enter the nasal cavity evenly and be effectively cleaned. For example, too fast a flow rate may cause excessive impact of the liquid on the nasal cavity, resulting in discomfort; too slow a flow rate may affect the cleaning effect. According to the decision result, the negative pressure control module also controls the total amount of the irrigation fluid. Too much liquid may cause overflow or discomfort, while too little liquid may not be sufficient to clean the nasal cavity. Therefore, the amount of the irrigation fluid will be reasonably configured according to the user's nasal conditions and nasal irrigation needs.

[0024] After the configuration is completed, the negative pressure control module starts to execute the actual negative pressure nasal cavity cleaning process. At this time, the device starts the negative pressure suction according to the predetermined parameters, including the negative pressure intensity, the liquid flow rate, and the amount of the irrigation fluid, and flushes the cleaning fluid through the nasal cavity. The negative pressure suction helps to suck out the dirt, mucus and other substances in the nasal cavity to achieve the purpose of cleaning the nasal cavity. In summary, the role of the negative pressure control module is to accurately control the negative pressure intensity, the liquid flow rate, and the amount of the irrigation fluid according to the personalized nasal irrigation plan generated by the decision-making module to perform the negative pressure nasal cavity cleaning and ensure the effectiveness, safety and comfort of the entire nasal irrigation process.

[0025] In addition, the medical self-service negative pressure nasal irrigation machine also includes an atomization module. The atomization module uses ultrasonic technology to convert the liquid medicine or physiological saline into tiny particles, which can penetrate deep into the user's nasal cavity to provide a soothing effect. The atomization module includes an ultrasonic atomizer and an atomization liquid medicine bin. Among them, the ultrasonic atomizer uses ultrasonic frequency to convert the liquid into tiny atomized particles, and the particle size is usually between 1 and 5 microns to ensure that the medicine can effectively reach the deep part of the nasal cavity; the atomization liquid medicine bin is used to store the liquid medicine or physiological saline to be atomized, supporting the user to add it according to needs to ensure the flexibility and convenience of use. The atomization module can automatically adjust the atomization amount and time according to the personalized plan generated by the intelligent evaluation system to ensure the accuracy and personalization of atomization. Moreover, the user can directly operate the atomization module through the touch screen to select the atomization parameters and monitor the atomization process, increasing the flexibility of atomization.

[0026] Combined with the medical self-service negative pressure nasal irrigation machine, the addition of the atomization module not only enriches the functions of the device, enabling it to provide a more comprehensive nasal cavity care plan, but also increases the flexibility of atomization. Through this integrated design, users can complete nasal cavity evaluation, negative pressure nasal irrigation and atomization on the same device, achieving efficient and safe nasal cavity care.

[0027] Furthermore, as Figure 2 shown, the decision-making module 30 includes:

[0028] A data time-series sorting module 31, configured to perform time-series sorting on the user case data to establish a data time-series sorting result; a data volume analysis module 32, configured to perform richness analysis on the user case data to establish a data richness analysis result; a zero-point concentration evaluation module 33, configured to perform time-series concentration analysis on the data time-series sorting result after setting the current time node as the time-series zero point to establish a time-series concentration degree, and generate a historical weight factor according to the time-series concentration degree and the data richness analysis result.

[0029] The case data of a user often changes over time. For example, changes in certain health indicators or symptoms. The time-series sorting module sorts these case data in chronological order to ensure that each data point has a correct timestamp for better analysis and processing. The sorted data forms an ordered data time-series sorting result, which helps to evaluate the changing patterns of the user's health status at different time points.

[0030] The richness of case data reflects the comprehensiveness and detail level of the data. A high data richness means that the collected case information is more detailed, covering more health indicators, symptoms, nasal irrigation records, etc.; while a low data richness may lack some important information, affecting the accuracy and analysis effect of the data. Analyzing the richness of user case data specifically involves performing data integrity checks, including checking whether there are missing key fields or indicators in the case data. For example, whether basic information such as the user's age, symptoms, and past medical history is complete; data volume evaluation. The user's case data should contain a sufficient sample size to generate meaningful analysis results. If the case data is too small, the data set will be marked as insufficient in data volume. After the richness analysis is completed, a data richness analysis result is established.

[0031] The time-series zero point refers to taking the current time node as the reference point. Generally, time-series analysis relies on the time order of data. The zero-point concentration evaluation module selects the current time node as the reference point for analysis. The time order of all data will be adjusted relative to this time node. At this time, the timestamps of other data will be offset or normalized with this node as the reference point. This approach helps to concentrate the data within a time frame for subsequent analysis and processing.

[0032] When the time nodes of the data are unified, the zero-point centralized evaluation module performs a temporal concentration analysis on the sorted data. Temporal concentration reflects whether the data is concentrated on the time axis, that is, the distribution of the data within a specific time period. For example, if the data fluctuates greatly within a certain period, it indicates that the nasal irrigation reaction changes significantly during that period; while the period with relatively stable data reflects the stability of the state. The evaluation of temporal concentration helps to identify which time periods of the data are more influential in the decision-making process, especially those time periods with relatively drastic state changes or strong reactions.

[0033] Generate historical weight factors based on the analysis results of temporal concentration and data richness. Specifically, through the analysis of temporal concentration, it can be judged which time periods of the data are more valuable for reference. For example, if there are significant changes in the user's condition or reaction within a certain time period, higher weights will be assigned to the data in that time period. In this way, in the nasal irrigation decision-making process, the time periods with greater influence will be given higher priorities; the analysis of data richness can judge which data is relatively complete and which data is scarce or unreliable. In the calculation of weight factors, the parts with higher data richness will be assigned greater weights, so as to ensure that the decision is based on more complete and reliable information.

[0034] By analyzing temporal concentration and data richness, the zero-point centralized evaluation module provides more accurate historical weight factors for the decision-making module. Based on the historical weight factors, the nasal irrigation plan can be adjusted or the nasal irrigation strategy can be optimized.

[0035] Furthermore, the decision-making module 30 further includes:

[0036] A fitting module, which is used to perform nasal cavity state fitting based on the user case data and establish a nasal cavity state fitting result; a weighted decision-making module, which is used to perform weighted calculation on the nasal cavity state fitting result according to the historical weight factors, then perform data fusion with the user nasal cavity data set, extract key features according to the data fusion result, synchronize the key features to the decision-making channel to execute the irrigation decision, and establish a decision result.

[0037] The fitting module establishes a mathematical model applicable to the nasal cavity health state based on the user case data, which can be completed through regression analysis. The purpose is to simulate the change trend of the user's nasal cavity state as accurately as possible. Through the fitting algorithm, infer the user's current nasal cavity health state from the existing case data. For example, by analyzing symptom changes, examination results such as nasal cavity resistance, temperature and humidity, etc., and the nasal irrigation history to speculate on the user's nasal cavity condition. Through the fitting process, a nasal cavity state fitting result is generated, which includes various aspects of the user's nasal cavity health condition, such as the degree of nasal congestion, humidity regulation, airflow resistance, etc., and can provide a quantitative analysis of the current nasal cavity state.

[0038] The weighted decision-making module receives historical weight factors, which represent the influence degrees of the user's nasal cavity data in different time periods. According to these factors, the fitting result of the nasal cavity state is weighted and adjusted. For example, if the concentration of healthy data in a certain time period is relatively high, indicating that the data in this time period has a greater impact on the decision-making, then the data in this time period will occupy a greater proportion in the weighted calculation to ensure that the prediction of nasal cavity health is more accurate and meets the actual requirements.

[0039] The fitting result after weighted calculation is fused with the user's nasal cavity data set collected in real time. Data fusion synthesizes multiple data sources to improve the accuracy of prediction and decision-making. For example, the user's nasal cavity data set includes the temperature, humidity and resistance data of the nasal cavity monitored in real time. Combining these data with the predicted nasal cavity health state through the fitting model helps to generate a more accurate decision-making input.

[0040] Based on the data fusion, key features are extracted from the fused data. These features are the factors most relevant to the user's current nasal cavity health state, such as nasal cavity resistance, humidity change, air flow state, etc.

[0041] The key features are synchronized to the decision-making channel to execute the irrigation decision, that is, the next nasal irrigation measure is determined according to the extracted key features. Specifically, the irrigation decision will adjust parameters such as irrigation intensity, liquid flow rate, and irrigation liquid volume based on the user's current nasal cavity state and the predicted health change trend to ensure that the nasal irrigation plan is personalized and effective, and finally generate a decision result, which includes a personalized nasal cavity cleaning plan, such as negative pressure setting, liquid flow rate, and liquid medicine volume. These decisions will be transmitted to the negative pressure control module for actual execution of negative pressure nasal cavity irrigation.

[0042] Furthermore, in the weighted decision-making module 30, extracting key features according to the data fusion result includes:

[0043] Calculating the feature importance degrees for the data fusion result respectively to establish an importance degree identification set; using the importance degree identification set as the initial population, where each importance degree identification is an individual in the population; setting a random function, randomly removing individuals in the initial population through the random function, and calculating the fitness of the population after removing the individuals; performing evolutionary iteration of the population according to the population fitness, and extracting key features according to the evolutionary iteration result.

[0044] Calculate the feature importance for the data fusion results respectively. Specifically, by analyzing the correlation between each feature and the target variable (such as the nasal cavity health status), the importance of the feature is evaluated; evaluate the contribution of each feature to the prediction target. If a feature is highly correlated with the target variable (such as the nasal cavity irrigation effect), then this feature is determined to have a high importance. Through evaluation, each feature will obtain an importance score, generating an importance identification set. The importance score is usually represented in numerical form, indicating the contribution size of this feature in data fusion. The feature with a higher score has a greater impact on the result.

[0045] Use the importance identification set as the initial population. The importance identification of each feature becomes an individual in the population. These individuals represent the importance of different features in the data fusion result. In this way, the individuals in the population can cover all possible feature combinations, providing diversity for subsequent evolution.

[0046] Set a random function. The random function randomly removes some individuals from the initial population with a certain probability. Each individual has a certain probability of being removed. The process of removing individuals increases the diversity of exploring the feature space. After removing individuals, recalculate the fitness of the remaining population. Fitness is a measure of the contribution of the feature combination to the target prediction effect. The fitness evaluation criteria usually include the impact on the model performance after removing the feature. If the model performance does not decrease significantly after removing a certain feature, it indicates that this feature is not important in the model. Otherwise, it means that this feature is important.

[0047] After fitness evaluation, select the most dominant individuals in the population to participate in the next round of crossover and mutation operations. This step is the selection step in the genetic algorithm, aiming to retain and strengthen those excellent features. In the genetic algorithm, crossover and mutation operations are used to generate new individuals to explore a wider range of feature combinations. The crossover operation generates new individuals by exchanging the features of different individuals, while the mutation operation ensures the diversity of the population through small random changes, thus avoiding falling into local optimal solutions. After multiple rounds of evolutionary iterations, the fitness of the population gradually increases, and the feature combination becomes more and more accurate. Eventually, the optimal feature combination is obtained, making the performance of the model reach the optimal. The key features obtained through the evolutionary process include the features that are most important for nasal cavity health prediction. These features are selected according to their importance, fitness, and contribution to the model prediction effect.

[0048] Furthermore, the performing of the evolutionary iteration of the population according to the population fitness includes:

[0049] Determine whether the population fitness meets the expected fitness threshold; if the population fitness meets the expected fitness threshold, record the fitness change value of the current iteration, and then continue to perform random individual removal; when the fitness cannot meet the expected fitness threshold during any evolutionary iteration process, generate a termination instruction, stop this round of iterative search according to the termination instruction, and record the current fitness value and the number of eliminated individuals; perform iterative backtracking based on all the fitness change values, and re - perform evolutionary iteration according to the iterative backtracking result; perform screening based on the current fitness values and the number of eliminated individuals in multiple rounds of evolutionary iteration, and establish the evolutionary iteration result.

[0050] In each iteration process, calculate the fitness of the population according to the performance of the population, and compare the calculated fitness with the preset expected fitness threshold, which is determined during the algorithm design and used to measure whether the population has been sufficiently adapted to the model requirements.

[0051] If the population fitness reaches or exceeds the preset threshold, record the fitness change value of this iteration. This change value is used to analyze the change trend of the population fitness and evaluate the effect of feature optimization. After recording the fitness change value, if the fitness is still increasing or remaining stable, continue to perform random individual removal and other evolutionary operations, such as crossover and mutation, to further optimize the population.

[0052] When the population fitness fails to reach the preset threshold continuously for multiple times during evolutionary iteration, or the fitness decreases, it indicates that the current feature combination or strategy needs to be re - evaluated. At this time, generate a termination instruction to indicate the algorithm to stop further iterative search, which is to avoid ineffective calculations and resource waste, especially when more iterations are unlikely to significantly improve the fitness. When stopping the iteration, record the fitness value of the current population, which helps to analyze and adjust the parameters or strategies of the genetic algorithm in the follow - up. At the same time, record the number of individuals eliminated due to insufficient fitness. These information are used to understand the dynamic changes of the population and the optimization strategy.

[0053] Based on all the fitness change values recorded during the previous iteration process, perform backtracking on the past iterative decisions. By backtracking the previous iterative steps, those features that may have been prematurely eliminated or not fully considered can be re - evaluated and adjusted, which helps to discover more effective feature combinations, especially when the fitness improvement is not obvious or the progress is slow. Analyze the performance of the feature combination after each iteration using the recorded fitness change values. If it is found that the fitness change trend after a certain iteration point does not meet the expectation, such as the fitness suddenly drops, consider restarting the iteration from this point.

[0054] Based on the results of backtracking analysis, a suitable iteration starting point is selected. For example, if the fitness improvement is most significant after a certain round of iteration, that point may be chosen as the new iteration starting point, and the evolutionary operations, including steps such as crossover, mutation, and individual selection, are restarted from the selected starting point in order to achieve a better fitness result.

[0055] After performing multiple rounds of evolutionary iteration, the feature set is screened and optimized according to the fitness value and the number of eliminations in each round. Specifically, the fitness data in multiple rounds of iteration is analyzed to identify which iterations have produced the feature combinations with the highest fitness value. Considering the number of eliminations, it is evaluated which features are frequently retained or eliminated in multiple iterations to judge the stability and importance of the features. The most effective feature combinations are screened out from the data of multiple rounds of iteration, especially those features that show high fitness and stable performance in most iterations. An evolutionary iteration result is established based on the screened feature set for further flushing decision-making.

[0056] Furthermore, the all-in-one machine includes:

[0057] A flushing fitting module for establishing a flushing fitting result according to the decision result and the user's nasal cavity dataset; a real-time feedback module for reading the real-time monitoring data of the real-time monitoring device to establish a real-time monitoring feedback; a self-optimization module for taking the flushing fitting result as the target node, performing a follow-up fitting of the real-time monitoring feedback to establish a follow-up feedback, and performing self-optimization of the cleaning of the all-in-one machine according to the follow-up feedback.

[0058] The flushing fitting module, based on the decision result, including parameters such as the pressure, temperature, liquid medicine type, and amount of flushing, as well as the user's nasal cavity dataset, such as data on nasal cavity shape, size, and historical blockage conditions, establishes a fitting result of the flushing scheme through data analysis and model calculation. The purpose is to provide an optimized nasal cavity flushing scheme for individual users to improve the nasal washing effect and user comfort.

[0059] The real-time monitoring device includes various sensors, such as a pressure sensor, a temperature sensor, etc. The real-time feedback module reads data from the real-time monitoring device, monitors various parameters during the nasal cavity flushing process in real time, analyzes these real-time data, such as whether the pressure and temperature are within the set range, whether the user has any discomfort reactions, etc., and forms a real-time monitoring feedback.

[0060] The self-optimizing module sets the irrigation fitting result as the target, continuously compares the real-time monitoring data with the target parameters, and makes adjustments if there are any deviations. This method ensures that nasal irrigation is always carried out according to the optimal plan, and automatically adjusts the irrigation parameters such as pressure, temperature, and liquid medicine flow rate based on the result of following the fitting. For example, if it is monitored that the actual pressure is lower than the target pressure, the pressure will be automatically increased. This automated and intelligent design not only improves the effectiveness of nasal irrigation but also increases the user's comfort and satisfaction.

[0061] Furthermore, the all-in-one machine further includes:

[0062] A user feedback module for receiving the user's real-time response feedback; a compensation module for generating decision optimization data based on the real-time response feedback and performing decision result optimization compensation according to the decision optimization data.

[0063] Users can input their feelings and feedback in real time through interfaces such as touchscreens or mobile applications. This can be regarding the nasal irrigation pressure, temperature sensation, discomfort level, or other related feelings. The user feedback module receives these real-time response feedbacks to facilitate understanding of the user experience and identify possible problems.

[0064] Based on the user's feedback, the compensation module analyzes the feedback content and generates optimization data. For example, if most users report feeling discomfort at a specific pressure setting, it will recommend reducing the default pressure setting. According to the generated decision optimization data, relevant nasal irrigation parameters such as pressure, temperature, or liquid medicine volume are automatically adjusted. These adjustments are dynamic and can take effect immediately during the user's next nasal irrigation, ensuring continuous improvement of the user experience. This optimization process forms a feedback loop, and the system continuously self-adjusts and optimizes according to the user's latest feedback, thus ensuring that the nasal irrigation plan always remains up-to-date and most suitable for the user.

[0065] Furthermore, the all-in-one machine includes:

[0066] An early warning module for triggering and discriminating monitoring anomalies based on the real-time monitoring feedback and reporting an anomaly early warning according to the triggering discrimination result.

[0067] The early warning module analyzes the real-time monitoring feedback, such as pressure, temperature, or other key indicators, to determine whether there are any readings beyond the normal range. When an abnormal situation is identified, an early warning signal is immediately triggered to notify the user or system administrator for necessary inspections or interventions. This early warning module is a key part of the system's security monitoring, ensuring that a rapid response can be made when potential dangers or abnormal situations occur.

[0068] Furthermore, the all-in-one machine includes:

[0069] An early warning supervision module is used to identify the early warning response for the abnormal early warning. If there is no early warning response within a preset window, after the warning level of the abnormal early warning is increased, a neighborhood early warning is established, and an early warning is reported according to the neighborhood early warning.

[0070] The early warning supervision module identifies the early warning response for the abnormal early warning. That is, when an abnormality is detected and the early warning is triggered, the early warning supervision module starts to monitor the early warning response situation, including checking whether the system administrator or user has viewed, confirmed, or processed the early warning. If within a preset time window, such as within 1 minute or 3 minutes, the early warning does not receive any response, the early warning level will be automatically increased. Increasing the early warning level usually means increasing the urgency and visibility of the early warning. For example, upgrading from a general warning to a serious warning, which may trigger additional notification processes, such as sending text messages or emails to higher-level system administrators or security responsible persons. After the early warning level is increased, a neighborhood early warning is established and reported more widely. The neighborhood early warning refers to expanding the scope of the early warning notification. This approach aims to ensure that necessary security measures are implemented by increasing the coverage and participants of the early warning.

[0071] Furthermore, the all-in-one machine includes:

[0072] A display screen is used to match a guiding animation according to the identity recognition result and conduct user operation guidance based on the guiding animation.

[0073] The display screen is used to show the user the guiding animation matched according to the identity recognition result. First, the user's identity is recognized, and then according to the recognition result, the most suitable operation guiding animation for the user is selected. For example, different users may require different levels of guidance. New users, compared to old users, need more detailed step-by-step displays. The display screen shows the animation, explaining in detail how to operate the device, including safety warnings, operation steps, and optimized usage methods, etc., to ensure that users can use the device safely and effectively.

[0074] In summary, the medical self-service negative pressure nasal washing all-in-one machine provided by the embodiments of the present application has the following technical effects:

[0075] The data reading module can automatically load the user's case history and previous irrigation responses by activating the device and identifying the user, which are used for analyzing and improving future nasal irrigation plans, ensuring the continuity and optimization of nasal irrigation, and ensuring the personalization of the nasal irrigation plan. The real-time interaction module ensures that the device can receive the user's nasal cavity data set in real time, including nasal cavity resistance and temperature and humidity data, through the data interaction function with the real-time monitoring device. The collected data is used to monitor the nasal irrigation process in real time and make immediate adjustments to the irrigation parameters, improving the adaptability and effectiveness of nasal irrigation. The decision-making module generates historical weight factors by analyzing the temporal concentration of the user's case data, which helps to prioritize the most relevant and influential historical data in new nasal irrigation decisions. The irrigation response records of the user are used to establish irrigation constraints, ensuring that the plan conforms to the individual responses of the user in terms of safety and effectiveness. The decision-making module makes decisions by integrating historical weight factors, case data, and real-time nasal cavity data, and formulates the most suitable irrigation plan for the current user status. The negative pressure control module automatically configures the negative pressure intensity, liquid flow rate, and irrigation fluid volume according to the decision result to meet different requirements, ensuring the comfort and effectiveness during nasal irrigation, achieving efficient and safe nasal cavity cleaning, reducing discomfort during nasal irrigation, and enhancing the user experience.

[0076] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A medical self-service negative pressure nasal irrigation integrated machine, characterized in that, The all-in-one machine includes: A data reading module, which is used to perform user identity recognition after being activated by the user, start the all-in-one machine according to the identity recognition result, and read the user's case data and flushing reaction records based on the identity recognition result; A real-time interaction module, which is used to perform data interaction with a real-time monitoring device to obtain a user nasal cavity dataset, and the user nasal cavity dataset includes nasal cavity resistance sensing data and nasal cavity temperature and humidity data; A decision-making module, which is used to generate a historical weight factor according to the time series concentration degree of the user case data after receiving the user case data, the flushing reaction record, and the user nasal cavity dataset, establish a flushing constraint based on the flushing reaction record, and perform a flushing control decision according to the historical weight factor, the user case data, and the user nasal cavity dataset, and establish a decision result; A negative pressure control module, which is used to configure the negative pressure intensity, liquid flow rate, and flushing liquid volume according to the decision result and perform negative pressure nasal cavity cleaning.

2. The medical self-service negative-pressure nasal irrigation integrated machine according to claim 1, wherein The decision-making module includes: A data time series sorting module, which is used to sort the user case data in time series and establish a data time series sorting result; A data volume analysis module, which is used to perform a richness analysis of the user case data and establish a data richness analysis result; A zero-point concentration evaluation module, which is used to set the current time node as the time series zero point, perform a time series concentration analysis of the data time series sorting result, establish a time series concentration degree, and generate a historical weight factor according to the time series concentration degree and the data richness analysis result.

3. The medical self-service negative pressure nasal irrigation integrated machine according to claim 2, wherein, The decision-making module further includes: A fitting module, which is used to perform nasal cavity state fitting based on the user case data and establish a nasal cavity state fitting result; A weighted decision-making module, which is used to perform weighted calculation on the nasal cavity state fitting result according to the historical weight factor, perform data fusion with the user nasal cavity dataset, extract key features according to the data fusion result, synchronize the key features to the decision-making channel to perform a flushing decision, and establish a decision result.

4. The medical self-service negative-pressure nasal irrigation integrated machine according to claim 3, wherein In the weighted decision-making module, extracting key features according to the data fusion result includes: Calculating the feature importance degree of the data fusion result respectively to establish an importance degree identification set; Using the importance degree identification set as the initial population, where each importance degree identification is an individual in the population; Setting a random function, and performing random individual removal of the initial population through the random function and calculating the fitness of the population after removing the individuals; Performing evolutionary iteration of the population according to the population fitness, and extracting key features according to the evolutionary iteration result.

5. The medical self-service negative-pressure nasal washing integrated machine according to claim 4, wherein, The performing evolutionary iteration of the population according to the population fitness includes: Judging whether the population fitness meets the expected fitness threshold; If the population fitness meets the expected fitness threshold, record the fitness change value of the current iteration and continue to perform random individual removal; When the fitness cannot meet the expected fitness threshold during any evolutionary iteration process, generate a termination instruction, stop this round of iterative search according to the termination instruction, and record the current fitness value and the number of eliminated individuals; Performing iterative backtracking according to all the fitness change values, and re-performing evolutionary iteration according to the iterative backtracking result; Filter according to the current fitness value and the number of eliminations in multiple rounds of evolutionary iteration to establish the evolutionary iteration result.

6. The medical self-service negative-pressure nasal irrigation integrated machine according to claim 1, wherein, The all-in-one machine includes: A flushing fitting module, configured to establish a flushing fitting result according to the decision result and the user nasal cavity data set; A real-time feedback module, configured to read the real-time monitoring data of the real-time monitoring device and establish a real-time monitoring feedback; A self-optimization module, configured to use the flushing fitting result as a target node, perform a follow-up fitting of the real-time monitoring feedback, establish a follow-up feedback, and perform a cleaning self-optimization of the all-in-one machine according to the follow-up feedback.

7. The medical self-service negative-pressure nasal irrigation integrated machine according to claim 6, wherein, The all-in-one machine further includes: A user feedback module, configured to receive the real-time response feedback of the user; A compensation module, configured to generate decision optimization data according to the real-time response feedback and perform decision result optimization compensation according to the decision optimization data.

8. The medical self-service negative pressure nasal irrigation integrated machine according to claim 6, wherein The all-in-one machine includes: An early warning module, configured to perform a trigger discrimination of monitoring anomalies according to the real-time monitoring feedback and report an anomaly early warning according to the trigger discrimination result.

9. The medical self-service negative-pressure nasal irrigation integrated machine according to claim 8, wherein, The all-in-one machine includes: An early warning supervision module, configured to perform an early warning response recognition of the anomaly early warning. If there is no early warning response within a preset window, after raising the early warning level of the anomaly early warning, establish a neighborhood early warning and report the early warning according to the neighborhood early warning.

10. The medical self-service negative-pressure nasal irrigation integrated machine according to claim 1, wherein The all-in-one machine includes: A display screen, configured to match a guidance animation according to the identity recognition result and perform user operation guidance based on the guidance animation.

Images