Intelligent erbium laser therapeutic instrument

Abstract

The application relates to the technical field of intelligent device control, and particularly discloses an intelligent laser treatment instrument, a method thereof comprising the following steps: a feedback signal module: determining real-time operation data and real-time physiological data; a man-machine interaction module: determining input instructions of the intelligent laser treatment instrument, and displaying the real-time operation data and the real-time physiological data; a main control board module: acquiring a plurality of historical operation data and a plurality of historical physiological data, determining a risk physiological parameter set and a related treatment parameter vector of each physiological parameter in the risk physiological parameter set; and a control signal module: generating and executing real-time control instructions to realize real-time control of the intelligent laser treatment instrument. Real-time double monitoring of device operation and patient physiological state, personalized and accurate configuration of parameters, prospective prediction of treatment risks, deep analysis of parameter correlation, accurate and personalized adjustment of treatment schemes, multi-parameter collaborative optimization, and improvement of treatment safety and accuracy can be realized.

Description

Technical Field

[0001] This invention relates to the field of intelligent device control technology, and in particular to an intelligent erbium laser therapy device. Background Technology

[0002] Early erbium laser therapy devices had limited functionality, relying mainly on medical staff to manually set treatment parameters based on experience, lacking real-time monitoring of equipment operation and patient physiological responses. With advancements in laser technology, some devices have begun to offer basic parameter adjustment functions; however, monitoring methods are limited, only displaying basic operating parameters and failing to effectively assess the patient's physiological state, posing certain safety risks during treatment.

[0003] Currently, with the development of artificial intelligence, although some laser therapy devices have introduced simple sensors for data collection, their data processing and analysis capabilities are insufficient. They cannot fully utilize historical and real-time data for in-depth analysis, making it difficult to accurately identify risks during treatment or achieve intelligent dynamic adjustment of treatment parameters. Significant room for improvement remains in terms of intelligence, precision, and safety, making it difficult to meet the needs of personalized medicine.

[0004] Therefore, this invention proposes an intelligent erbium laser therapy device. Summary of the Invention

[0005] This invention provides an intelligent erbium laser therapy device. Based on acquired treatment needs and basic data, the device's input commands are determined. Combining real-time operational data, real-time physiological data, all historical operational data, and all historical physiological data, a set of risk physiological parameters and a related treatment parameter vector for each physiological parameter within this set are determined. Real-time control commands are then generated and executed, enabling real-time control of the intelligent erbium laser therapy device. This allows for real-time dual monitoring of device operation and patient physiological status, as well as personalized and precise parameter configuration. It enables proactive prediction of treatment risks and in-depth analysis of parameter correlations, allowing for precise and personalized adjustments to treatment plans. Multi-parameter synergistic optimization further enhances treatment safety and accuracy.

[0006] This invention provides an intelligent erbium laser therapy device, comprising:

[0007] Feedback signal module: Real-time monitoring of the operating status of the intelligent erbium laser therapy device to determine real-time operating data, and real-time monitoring of the physiological status of the patient's treatment area to determine real-time physiological data;

[0008] Human-computer interaction module: Acquires the patient's treatment needs and basic data, determines the input commands of the intelligent erbium laser therapy device, and displays the real-time operating data of the intelligent erbium laser therapy device and the real-time physiological data of the patient's treatment area;

[0009] Main control board module: acquires multiple historical operational data and multiple historical physiological data, analyzes real-time operational data, real-time physiological data, all historical physiological data and all historical operational data, and determines the set of risk physiological parameters and the relevant treatment parameter vector for each physiological parameter in the set of risk physiological parameters;

[0010] Control signal module: Based on real-time operating data, risk physiological parameter set, and related treatment parameter vectors of all physiological parameters in the risk physiological parameter set, generate real-time control commands and execute real-time control commands to realize the real-time control of the intelligent erbium laser therapy device.

[0011] Preferably, a smart erbium laser therapy device includes a feedback signal module comprising:

[0012] Real-time operation data unit: Based on the real-time output value of each treatment parameter of the intelligent erbium laser therapy instrument at the current time point, the real-time operation data is determined based on the real-time output value of all treatment parameters of the intelligent erbium laser therapy instrument;

[0013] Real-time physiological data unit: Based on the real-time monitoring of multiple physiological parameters of the patient's treatment area at the current time point by the second sensor group, real-time physiological data is determined based on the real-time parameter values ​​of all physiological parameters of the patient's treatment area.

[0014] Preferably, an intelligent erbium laser therapy device includes a human-computer interaction module, comprising:

[0015] Basic data unit: The intelligent erbium laser therapy device acquires the patient's basic data, which includes at least the patient's name, gender, age, skin type, and allergy history;

[0016] Judgment Unit: Acquires the patient's treatment needs, determines the patient's treatment mode and treatment area based on the patient's treatment needs, and determines whether skin matching is required;

[0017] Patient Skin Type Unit: Determine if the patient's skin type in the patient's basic data is empty. If it is empty, retrieve the patient's skin information, determine the patient's skin type based on the patient's skin type, and update the patient's basic data.

[0018] Preferably, a smart erbium laser therapy device, including a human-computer interaction module, further includes:

[0019] First initial treatment parameter data unit: If the patient needs skin matching, the patient's initial treatment parameter data is determined based on the patient's skin type and skin preset parameter library in the patient's basic data. The initial treatment parameter data includes the initial parameter values ​​and treatment parameter ranges of multiple treatment parameters.

[0020] Second initial treatment parameter data unit: If the patient does not need skin matching, the initial treatment parameter data of the patient is determined based on the patient's treatment mode and mode preset parameter library. The initial treatment parameter data includes the initial parameter values ​​and treatment parameter ranges of multiple treatment parameters.

[0021] Input command unit: Based on the patient's treatment mode and the initial parameter values ​​of all treatment parameters in the initial treatment parameter data, determine the input command of the intelligent erbium laser therapy device.

[0022] Preferably, a smart erbium laser therapy device includes a main control board module comprising:

[0023] Acquisition Unit: Acquires historical operational data and historical physiological data for a specified number of historical time points prior to the current time point. The historical operational data includes the historical output values ​​of all treatment parameters at the corresponding historical time point, and the historical physiological data includes the historical parameter values ​​of all physiological parameters at the corresponding historical time point.

[0024] Risk physiological parameter set unit: The set of risk physiological parameters is determined based on real-time physiological data and all historical physiological data;

[0025] Relevant treatment parameter vector unit: Based on real-time operation data, all historical operation data, and the risk physiological parameter set, calculate the comprehensive correlation value between each physiological parameter and each treatment parameter in the risk physiological parameter set, and determine the relevant treatment parameter vector for each physiological parameter in the physiological parameter set.

[0026] Preferably, a smart erbium laser therapy device includes a risk physiological parameter collection unit, comprising:

[0027] Physiological parameter image subunit: Based on the real-time parameter value of each physiological parameter in the real-time physiological data at the current time point and the historical parameter value of each physiological parameter in the historical physiological data at all historical time points, a physiological parameter image is drawn for each physiological parameter. The horizontal axis of the physiological parameter image represents the current time point and all historical time points, and the vertical axis of the physiological parameter image represents the real-time parameter value or historical parameter value of the corresponding physiological parameter.

[0028] Predicted parameter value subunit: The physiological parameter image of each physiological parameter is input into the prediction model, and the predicted parameter value of each physiological parameter at the next time point is determined based on the output of the prediction model;

[0029] Risk Physiological Parameter Set Subunit: Obtain the physiological parameter range of each physiological parameter in the real-time physiological data, and determine the risk physiological parameter set based on the predicted parameter values ​​of all physiological parameters at the next time point from the current time point and the physiological parameter range.

[0030] Preferably, an intelligent erbium laser therapy device includes a related treatment parameter vector unit, comprising:

[0031] The computational subunit calculates the time-lag correlation value, cumulative correlation value, and cumulative trend consistency of each physiological parameter and each treatment parameter in the risk physiological parameter set, based on the set of risk physiological parameters, real-time operational data at the current time point, historical operational data at all historical time points before the current time point, and historical physiological data.

[0032] Comprehensive correlation value subunit: Based on the time lag correlation value, cumulative correlation value, and cumulative trend consistency of each physiological parameter and each treatment parameter in the risk physiological parameter set, calculate the comprehensive correlation value of each physiological parameter and each treatment parameter in the risk physiological parameter set;

[0033] Relevant treatment parameter vector subunit: Sort the comprehensive correlation values ​​of each physiological parameter and all treatment parameters in the risk physiological parameter set from largest to smallest, select the treatment parameters corresponding to the first preset number of comprehensive correlation values ​​of each physiological parameter in the risk physiological parameter set after sorting, and determine the relevant treatment parameter vector of each physiological parameter in the risk physiological parameter set.

[0034] Preferably, a smart erbium laser therapy device includes a control signal module comprising:

[0035] Risk physiological parameter vector unit: Based on all physiological parameters in the risk physiological parameter set, sort them according to their corresponding risk levels to determine the risk physiological parameter vector;

[0036] Real-time control instruction unit: Inputs real-time running data, risk physiological parameter vector, and related treatment parameter vector of each physiological parameter in the risk physiological parameter set into the control model, and determines real-time control instructions based on the output of the control model. The real-time control instructions include multiple real-time control sub-instructions.

[0037] Execution Unit: Input each real-time control sub-instruction in the real-time control command to the corresponding execution unit, execute all real-time control sub-instructions, and realize the real-time control of the intelligent erbium laser therapy device.

[0038] The beneficial effects of this invention compared to existing technologies are as follows: Based on the acquired treatment needs and basic data, the input commands for the intelligent erbium laser therapy device are determined. Combining real-time operating data, real-time physiological data, all historical operating data, and all historical physiological data, a set of risk physiological parameters and the relevant treatment parameter vectors for each physiological parameter in the risk physiological parameter set are determined. Real-time control commands are generated and executed, achieving real-time control of the intelligent erbium laser therapy device. This enables real-time dual monitoring of device operation and patient physiological state, as well as personalized and precise parameter configuration. It allows for proactive prediction of treatment risks and in-depth analysis of parameter correlations, enabling precise and personalized adjustments to treatment plans, achieving multi-parameter collaborative optimization, improving treatment safety and accuracy, and becoming an important application scenario for artificial intelligence.

[0039] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0040] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0041] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0042] Figure 1 This is a schematic diagram of an intelligent erbium laser therapy device according to an embodiment of the present invention. Detailed Implementation

[0043] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention. Example 1:

[0044] This invention provides an intelligent erbium laser therapy device, referenced Figure 1 ,include:

[0045] Feedback signal module: Real-time monitoring of the operating status of the intelligent erbium laser therapy device to determine real-time operating data, and real-time monitoring of the physiological status of the patient's treatment area to determine real-time physiological data;

[0046] Human-computer interaction module: Acquires the patient's treatment needs and basic data, determines the input commands of the intelligent erbium laser therapy device, and displays the real-time operating data of the intelligent erbium laser therapy device and the real-time physiological data of the patient's treatment area;

[0047] Main control board module: acquires multiple historical operational data and multiple historical physiological data, analyzes real-time operational data, real-time physiological data, all historical physiological data and all historical operational data, and determines the set of risk physiological parameters and the relevant treatment parameter vector for each physiological parameter in the set of risk physiological parameters;

[0048] Control signal module: Based on real-time operating data, risk physiological parameter set, and related treatment parameter vectors of all physiological parameters in the risk physiological parameter set, generate real-time control commands and execute real-time control commands to realize the real-time control of the intelligent erbium laser therapy device.

[0049] In this embodiment, the feedback signal module monitors the operating status of the intelligent erbium laser therapy device in real time through various built-in sensors. Simultaneously, it monitors the physiological state of the patient's treatment area in real time using a second set of dedicated sensors.

[0050] In this embodiment, the human-computer interaction module serves as a "bridge" for communication between medical staff and the treatment device. Based on the collected information and combined with the device's built-in parameter setting rules, it determines the input commands for the intelligent erbium laser therapy device, such as setting appropriate parameters like laser energy, pulse frequency, and treatment time for different treatment needs and patient conditions. Regarding information output, this module displays real-time operating data of the intelligent erbium laser therapy device and real-time physiological data of the patient's treatment area through an intuitive interface, allowing medical staff to easily monitor the device's operation and the patient's physiological responses, and to make timely adjustments and decisions regarding the treatment process.

[0051] In this embodiment, the main control board module first acquires operational and physiological data from multiple historical time points. Then, it performs in-depth mining and analysis on the real-time operational data, real-time physiological data, historical physiological data, and historical operational data. Through trend analysis, it identifies physiological parameters that exceed the normal range or pose potential risks, forming a set of risk physiological parameters. Next, it performs correlation analysis to find the relevant treatment parameter vectors corresponding to each physiological parameter in the risk physiological parameter set, clarifying which treatment parameters are closely related to each risk physiological parameter and the degree of correlation between them.

[0052] In this embodiment, the control signal module generates real-time control commands based on real-time operating data, a set of risk physiological parameters, and relevant treatment parameter vectors for all physiological parameters within the risk physiological parameter set, through a control model. These commands cover precise adjustments to control parameters of equipment components such as the laser emission module and cooling system. For example, when a patient's skin temperature is found to be too high (a risk physiological parameter) and highly correlated with laser energy (relevant treatment parameter vector), the control signal module generates real-time control commands to reduce laser energy and increase the power of the cooling system. Subsequently, these commands are sent to the corresponding execution units for execution, achieving real-time dynamic adjustment of the intelligent erbium laser therapy device and ensuring the safe and effective conduct of the treatment process.

[0053] The beneficial effects of the above technology are as follows: Based on the acquired treatment needs and basic data, the input commands for the intelligent erbium laser therapy device are determined. Combining real-time operating data, real-time physiological data, all historical operating data, and all historical physiological data, a set of risk physiological parameters and the relevant treatment parameter vectors for each physiological parameter in the risk physiological parameter set are determined. Real-time control commands are generated and executed, achieving real-time control of the intelligent erbium laser therapy device. This enables real-time dual monitoring of device operation and patient physiological status, as well as personalized and precise parameter configuration. It allows for proactive prediction of treatment risks and in-depth analysis of parameter correlations, enabling precise and personalized adjustments to treatment plans, and achieving multi-parameter synergistic optimization, thus improving treatment safety and accuracy. Example 2:

[0054] Based on Example 1, a smart erbium laser therapy device includes a feedback signal module, comprising:

[0055] Real-time operation data unit: Based on the real-time output value of each treatment parameter of the intelligent erbium laser therapy instrument at the current time point, the real-time operation data is determined based on the real-time output value of all treatment parameters of the intelligent erbium laser therapy instrument;

[0056] Real-time physiological data unit: Based on the real-time monitoring of multiple physiological parameters of the patient's treatment area at the current time point by the second sensor group, real-time physiological data is determined based on the real-time parameter values ​​of all physiological parameters of the patient's treatment area.

[0057] In this embodiment, the first sensor group may include an optical power sensor to monitor the actual output power of the laser, a pulse frequency sensor to monitor the emission frequency of the laser pulse, a spot size sensor to monitor the actual size of the laser spot, a time counter to monitor the laser emission time, a cooling system sensor to monitor the operating status of the cooling system, including coolant temperature and flow rate, and a voltage and current sensor to monitor the power supply voltage and current of the device.

[0058] In this embodiment, the second sensor group may include a temperature sensor to monitor the temperature of the treatment area, a reflected light intensity sensor to monitor the intensity of laser light reflected from the treatment area, an optical sensor (such as a CCD / CMOS camera) to monitor tissue reactions in the treatment area, such as color changes, edema, bleeding, etc., a humidity sensor to monitor the humidity of the treatment area, and a Doppler blood flow sensor to monitor the blood flow in the treatment area, etc.

[0059] In this embodiment, the treatment parameters may include laser power, pulse frequency, emission time, cooling system status, power supply voltage and current, etc.

[0060] In this embodiment, physiological parameters may include reflected light intensity, tissue reaction, humidity, blood flow, tissue temperature, light spot uniformity, treatment depth, etc.

[0061] In this embodiment,

[0062] The beneficial effects of the above technologies are: real-time monitoring of the operating status of the intelligent erbium laser therapy device to determine real-time operating data, real-time monitoring of the physiological state of the patient's treatment area to determine real-time physiological data, and providing data support for determining the set of risk physiological parameters and the related treatment parameter vectors of each physiological parameter in the set of risk physiological parameters. Example 3:

[0063] Based on Example 1, a smart erbium laser therapy device includes a human-computer interaction module, comprising:

[0064] Basic data unit: The intelligent erbium laser therapy device acquires the patient's basic data, which includes at least the patient's name, gender, age, skin type, and allergy history;

[0065] Judgment Unit: Acquires the patient's treatment needs, determines the patient's treatment mode and treatment area based on the patient's treatment needs, and determines whether skin matching is required;

[0066] Patient Skin Type Unit: Determine if the patient's skin type in the patient's basic data is empty. If it is empty, retrieve the patient's skin information, determine the patient's skin type based on the patient's skin type, and update the patient's basic data.

[0067] In this embodiment, the basic data unit serves as the core entry point for the intelligent erbium laser therapy device to acquire basic patient information, undertaking the crucial task of reading patient data. Before the patient receives treatment, medical staff manually input the patient's basic data through a human-computer interaction interface (such as a touchscreen, operation panel, etc.), or directly retrieve relevant information from the hospital's electronic medical record system or database and transmit it to the basic data unit.

[0068] In this embodiment, the judgment unit first interacts with medical staff through the human-computer interaction module to obtain the patient's treatment needs. Based on the patient's condition, symptoms, and treatment goals, the medical staff selects appropriate treatment options on the device's interface, such as skin rejuvenation, scar repair, or acne treatment. This selection information is then transmitted to the judgment unit.

[0069] In this embodiment, the treatment needs may include acne scars, skin aging, wrinkles, pigmentation, cervical surgery, nasal surgery in the Department of Otolaryngology, periodontal treatment, or stone treatment in the Department of Urology.

[0070] In this embodiment, the treatment modes include ablative treatment, non-ablative treatment, fractional therapy, pulse therapy, and continuous wave therapy.

[0071] In this embodiment, treatment needs include skin abrasion, skin rejuvenation and phototherapy, periodontal treatment, teeth whitening, urinary tract stone treatment, benign prostatic hyperplasia treatment, and corneal surgery.

[0072] In this embodiment, the intelligent erbium laser therapy device can read the patient's basic information via RFID or NFC.

[0073] In this embodiment, the patient's skin type can be classified according to skin texture (oily, dry, normal, combination, and sensitive, etc.); or it can be classified according to the skin's photosensitivity (Fitzpatrick classification includes types I to VI).

[0074] In this embodiment, the need for skin matching is determined based on the patient's treatment needs. For example, if the type of skin treatment a patient undergoes during skin resurfacing, skin rejuvenation, or phototherapy directly affects the effectiveness and safety of laser treatment, then skin matching is required. However, non-skin-related treatments such as periodontal treatment, teeth whitening, and urinary tract stone treatment do not require skin matching.

[0075] In this embodiment, based on the acquired treatment needs, the judgment unit determines a suitable treatment mode for the patient using a built-in treatment plan knowledge base and algorithm. Simultaneously, the judgment unit also determines the treatment area based on the treatment needs and the patient's specific condition. Medical personnel can specify the area to be treated by drawing or selecting a preset area on the device's interface. After receiving this information, the judgment unit clarifies the scope and boundaries of the treatment area.

[0076] In this embodiment, the patient skin type unit first checks if the patient skin type field in the patient's basic data is empty. If the field is empty, it indicates that the patient's skin type information is missing. Upon detecting missing skin type information, the patient skin type unit triggers a skin information acquisition process. This can be achieved in two ways: one is by prompting medical staff to manually input the patient's skin type information, which can be determined by observing the patient's skin and inquiring about the patient's condition; the other is by acquiring skin information through the device's built-in skin detection function, such as using spectral analysis technology or image recognition technology to detect the patient's skin and analyze indicators such as sebum secretion, moisture content, and stratum corneum thickness to determine the patient's skin type. Once accurate skin type information is obtained, the patient skin type unit updates it to the patient's basic data to ensure the completeness and accuracy of the patient's basic information.

[0077] The beneficial effects of the above technologies are: obtaining patients' treatment needs and basic data, enabling comprehensive collection and precise management of patients' basic information, and providing a reliable information foundation and decision support for personalized and safe laser treatment. Example 4:

[0078] Based on Example 3, a smart erbium laser therapy device, including a human-computer interaction module, further includes:

[0079] First initial treatment parameter data unit: If the patient needs skin matching, the patient's initial treatment parameter data is determined based on the patient's skin type and skin preset parameter library in the patient's basic data. The initial treatment parameter data includes the initial parameter values ​​and treatment parameter ranges of multiple treatment parameters.

[0080] Second initial treatment parameter data unit: If the patient does not need skin matching, the initial treatment parameter data of the patient is determined based on the patient's treatment mode and mode preset parameter library. The initial treatment parameter data includes the initial parameter values ​​and treatment parameter ranges of multiple treatment parameters.

[0081] Input command unit: Based on the patient's treatment mode and the initial parameter values ​​of all treatment parameters in the initial treatment parameter data, determine the input command of the intelligent erbium laser therapy device.

[0082] In this embodiment, when the judgment unit determines that the patient needs skin matching, it uses the skin type in the patient's basic data as the core basis and connects to a preset skin parameter library. This library pre-stores a large amount of clinical research data and practical experience summaries for various skin types. Taking dry skin as an example, the library may record suitable laser energy ranges of 1.5-2.5 J / cm² and pulse frequencies of 10-15 Hz. By matching the patient's skin type with the data in the library, initial parameter values ​​for multiple treatment parameters suitable for the patient's skin type are selected, such as setting the initial laser energy value to 2.0 J / cm² and the initial pulse width value to 10 ms. At the same time, a reasonable range for each treatment parameter is determined, such as a laser energy range of 1.8-2.2 J / cm². The determination of these parameters and ranges considers both the common characteristics of skin types and leaves room for subsequent fine-tuning of parameters based on the patient's specific response.

[0083] In this embodiment, if the determination unit determines that the patient does not require skin matching, the second initial treatment parameter data unit is activated. In this scenario, the determination of treatment parameters mainly revolves around the patient's treatment mode. Different treatment modes correspond to different pathological needs and treatment goals. For example, the skin beauty mode aims to improve skin tone and texture, while the acne treatment mode focuses on killing Propionibacterium acnes and regulating sebum secretion.

[0084] In this embodiment, the mode preset parameter library integrates standard treatment plans and parameter combinations for various treatment modes. Taking scar repair treatment mode as an example, the library contains parameter settings suitable for different scar types (such as hypertrophic scars and atrophic scars). When a patient selects a scar repair treatment mode, the unit selects appropriate initial treatment parameter data from it. For example, for hypertrophic scars, the initial laser energy value may be determined to be 3.0 J / cm², and the pulse frequency to be 8 Hz. At the same time, the treatment parameter range is given, such as the laser energy being adjustable between 2.8 and 3.2 J / cm². Through precise docking with the mode preset parameter library, the second initial treatment parameter data unit can quickly and accurately configure initial treatment parameters for a specific treatment mode, improving the efficiency of treatment plan formulation, while ensuring that the parameter settings comply with the clinical norms and requirements of the treatment mode.

[0085] In this embodiment, the input command unit, as a key output link of the human-computer interaction module, determines the input commands for the intelligent erbium laser therapy device based on the patient's treatment mode and the initial parameter values ​​of all treatment parameters in the initial treatment parameter data. It integrates the treatment mode information with the specific initial parameter values ​​to form a complete and explicit set of commands. For example, if the patient's treatment mode is acne treatment, and the initial laser energy value in the initial treatment parameter data is 2.2 J / cm² and the pulse frequency is 12 Hz, the input command unit will convert this information into signals and command formats recognizable by the device. For instance, through digital encoding or a specific communication protocol, it will send the command to the main control board module of the therapy device to set the laser energy to 2.2 J / cm² and the pulse frequency to 12 Hz.

[0086] The beneficial effects of the above technologies are: by determining the input instructions of the intelligent erbium laser therapy device, personalized and precise configuration of treatment parameters can be achieved, thereby improving the safety and effectiveness of treatment. Example 5:

[0087] Based on Example 4, a smart erbium laser therapy device, including a main control board module, comprises:

[0088] Acquisition Unit: Acquires historical operational data and historical physiological data for a specified number of historical time points prior to the current time point. The historical operational data includes the historical output values ​​of all treatment parameters at the corresponding historical time point, and the historical physiological data includes the historical parameter values ​​of all physiological parameters at the corresponding historical time point.

[0089] Risk physiological parameter set unit: The set of risk physiological parameters is determined based on real-time physiological data and all historical physiological data;

[0090] Relevant treatment parameter vector unit: Based on real-time operation data, all historical operation data, and the risk physiological parameter set, calculate the comprehensive correlation value between each physiological parameter and each treatment parameter in the risk physiological parameter set, and determine the relevant treatment parameter vector for each physiological parameter in the physiological parameter set.

[0091] In this embodiment, the acquisition unit serves as the data entry point for the main control board module. Following preset rules, it actively retrieves data from the device's data storage module or an external database for a specified number of historical time points prior to the current time. The specified number is flexible and can be adjusted based on factors such as the complexity of the treatment process and the frequency of data changes. For example, for simple cosmetic skin treatments, data from the most recent 10 historical time points during the current treatment process might be retrieved; while for complex scar repair treatments, data from the most recent 30 historical time points during the current treatment process may need to be retrieved to ensure sufficiently rich information is obtained.

[0092] In this embodiment, the historical operational data encompasses the historical output values ​​of all treatment parameters of the intelligent erbium laser therapy device at the corresponding historical time point, including laser energy, pulse frequency, pulse width, and cooling system parameters. This data records the device's operating status before the current time during the current treatment process. The historical physiological data includes the historical parameter values ​​of all physiological parameters of the patient at the corresponding historical time point, such as skin temperature, tissue impedance, and blood oxygen saturation, providing a clear view of the patient's physiological responses before the current time during the current treatment process.

[0093] The beneficial effects of the above technologies are as follows: acquiring multiple historical operational data and multiple historical physiological data, analyzing real-time operational data, real-time physiological data, all historical physiological data and all historical operational data, determining the set of risk physiological parameters and the related treatment parameter vectors of each physiological parameter in the set of risk physiological parameters, can realize the forward prediction of treatment risks and the in-depth analysis of parameter correlations, providing core support for intelligent adjustment of treatment plans and improving treatment safety and accuracy. Example 6:

[0094] Based on Example 5, a smart erbium laser therapy device, including a risk physiological parameter collection unit, comprises:

[0095] Physiological parameter image subunit: Based on the real-time parameter value of each physiological parameter in the real-time physiological data at the current time point and the historical parameter value of each physiological parameter in the historical physiological data at all historical time points, a physiological parameter image is drawn for each physiological parameter. The horizontal axis of the physiological parameter image represents the current time point and all historical time points, and the vertical axis of the physiological parameter image represents the real-time parameter value or historical parameter value of the corresponding physiological parameter.

[0096] Predicted parameter value subunit: The physiological parameter image of each physiological parameter is input into the prediction model, and the predicted parameter value of each physiological parameter at the next time point is determined based on the output of the prediction model;

[0097] Risk Physiological Parameter Set Subunit: Obtain the physiological parameter range of each physiological parameter in the real-time physiological data, and determine the risk physiological parameter set based on the predicted parameter values ​​of all physiological parameters at the next time point from the current time point and the physiological parameter range.

[0098] In this embodiment, the physiological parameter image subunit collects the real-time parameter values ​​of each physiological parameter from the real-time physiological data at the current time point, and simultaneously acquires the historical parameter values ​​of each physiological parameter from the historical physiological data at all historical time points. It integrates this data, using time as the horizontal axis to encompass the current time point and all historical time points, thus reflecting changes over time; and using the real-time or historical parameter values ​​of the corresponding physiological parameters as the vertical axis to form data points. For example, for the physiological parameter of skin temperature, it maps the temperature values ​​at different time points to the corresponding coordinates of those time points.

[0099] In this embodiment, the parameter prediction subunit takes a physiological parameter image as input, which contains information on the changes of physiological parameters over time. The prediction model is built based on a large amount of historical data and specialized algorithms, such as machine learning algorithms and time series analysis algorithms. Taking machine learning algorithms as an example, the model learns from historical physiological parameter images and extracts features and patterns. For example, by analyzing the temperature change trend and fluctuation range in skin temperature images, the model can identify the patterns and trends of parameter changes. Based on the input physiological parameter image and the learned patterns and rules, the model predicts the predicted parameter value of each physiological parameter at the next time point. For example, based on the historical trend of skin temperature changes and the current changes, the model predicts the skin temperature value at the next time point.

[0100] In this embodiment, within the risk physiological parameter set subunit: the calculation formula for determining the risk physiological parameter set based on the predicted parameter values ​​of all physiological parameters at the current time point and the range of physiological parameters at the next time point can be expressed as:

[0101] ;

[0102] ;

[0103] ;

[0104] in, This represents the predicted value of the i-th physiological parameter at the next time point after the current time point t. This represents the lower limit of the range of the i-th physiological parameter. This represents the upper limit of the range of physiological parameters for the i-th physiological parameter. This represents the deviation of the predicted parameter value of the i-th physiological parameter at the next time point from the current time point t, based on the range of the physiological parameter. This represents the risk level of the i-th physiological parameter, where HD and MD represent the upper and lower limits of deviation, respectively. Let represent the i-th physiological parameter, and RS represent the set of risk physiological parameters.

[0105] In this embodiment, the upper limit of deviation and the lower limit of deviation can be 0.3 and 0.1, respectively.

[0106] The beneficial effects of the above technologies are as follows: by determining the set of risk physiological parameters based on real-time physiological data and all historical physiological data, it is possible to analyze the trend of physiological parameter changes and predict risks, providing strong support for treatment safety and plan adjustment. Example 7:

[0107] Based on Example 6, a smart erbium laser therapy device, including a related treatment parameter vector unit, comprises:

[0108] The computational subunit calculates the time-lag correlation value, cumulative correlation value, and cumulative trend consistency of each physiological parameter and each treatment parameter in the risk physiological parameter set, based on the set of risk physiological parameters, real-time operational data at the current time point, historical operational data at all historical time points before the current time point, and historical physiological data.

[0109] Comprehensive correlation value subunit: Based on the time lag correlation value, cumulative correlation value, and cumulative trend consistency of each physiological parameter and each treatment parameter in the risk physiological parameter set, calculate the comprehensive correlation value of each physiological parameter and each treatment parameter in the risk physiological parameter set;

[0110] Relevant treatment parameter vector subunit: Sort the comprehensive correlation values ​​of each physiological parameter and all treatment parameters in the risk physiological parameter set from largest to smallest, select the treatment parameters corresponding to the first preset number of comprehensive correlation values ​​of each physiological parameter in the risk physiological parameter set after sorting, and determine the relevant treatment parameter vector of each physiological parameter in the risk physiological parameter set.

[0111] In this embodiment, the calculation subunit: based on the risk physiological parameter set, real-time operational data at the current time point, historical operational data from all historical time points prior to the current time point, and historical physiological data, calculates the time lag correlation value, cumulative correlation value, and cumulative trend consistency of each physiological parameter and each treatment parameter in the risk physiological parameter set, and calculates the comprehensive correlation value of each physiological parameter and each treatment parameter in the risk physiological parameter set. The calculation formula can be expressed as:

[0112] ;

[0113] ;

[0114] ;

[0115] ;

[0116] ;

[0117] ;

[0118] in, The i-th physiological parameter and the j-th therapeutic parameter are based on time delay. The time-delay correlation value, Indicates time delay, This represents the maximum time-lag correlation value between the i-th physiological parameter and the j-th treatment parameter, 0. N1 represents the specified quantity. This represents the historical parameter value of the i-th physiological parameter in the historical physiological data at the k-th historical time point. This represents the average historical parameter value of the i-th physiological parameter from the real-time physiological data at the current time point and the historical physiological data from a specified number of historical time points prior to the current time point. Represents the pre-delay at the k-th historical time point. The historical output value of the j-th treatment parameter in the historical operation data of each historical time point. This represents the average historical output value of the j-th treatment parameter from the real-time operating data at the current time point and the historical operating data from a specified number of historical time points prior to the current time point, where γ represents the time decay factor. This represents the real-time value of the i-th physiological parameter at the current time point t. Indicates the time delay before the current time point t. The historical output value of the j-th treatment parameter in the historical operation data of each historical time point. This represents the cumulative correlation value between the i-th physiological parameter and the j-th treatment parameter based on the maximum time lag correlation value. This represents the historical output value of the j-th treatment parameter in the historical operation data at the a-th historical time point. This represents the cumulative first historical output value of the k-th historical time point based on the time lag corresponding to the maximum time lag correlation value and the j-th treatment parameter among all historical physiological data. This represents the time lag corresponding to the maximum time lag correlation value at the current time point and all historical time points, as well as the historical average cumulative value of the j-th treatment parameter in all historical physiological data. This represents the cumulative second historical output value at the current time point, based on the time lag corresponding to the maximum time lag correlation value and the j-th treatment parameter from all historical physiological data. This indicates the consistency of the cumulative trend of the time lags corresponding to the maximum time lag correlation values ​​of the i-th physiological parameter and the j-th treatment parameter, where sign(X) represents the positive or negative value of X. This represents the time delay corresponding to the maximum time delay correlation value between the i-th physiological parameter and the j-th treatment parameter.

[0119] In this embodiment, for example: When the result is positive, =+1, When the result is negative, =-1.

[0120] In this embodiment, the comprehensive correlation value subunit calculates the comprehensive correlation value of each physiological parameter and each treatment parameter in the risk physiological parameter set based on the time lag correlation value, cumulative correlation value, and cumulative trend consistency. The calculation formula can be expressed as follows:

[0121] ;

[0122] in, The i-th physiological parameter and the j-th therapeutic parameter are based on time delay. The comprehensive correlation value, W1 represents the risk adjustment coefficient, and W2 represents the time-lag correlation weight and the cumulative correlation weight, respectively.

[0123] In this embodiment, the comprehensive correlation values ​​of each risk physiological parameter with all treatment parameters are sorted in descending order, and a preset number (e.g., 3-5) of treatment parameters are selected. For example, for the risk physiological parameter of skin temperature, if the comprehensive correlation values ​​of laser energy, pulse frequency, and cooling water flow rate rank in the top three, they are selected.

[0124] The beneficial effects of the above technologies are as follows: Based on real-time operation data, all historical operation data, and the set of risk physiological parameters, the comprehensive correlation value of each physiological parameter and each treatment parameter in the set of risk physiological parameters is calculated, and the relevant treatment parameter vector of each physiological parameter in the set of physiological parameters is determined. This can accurately capture the dynamic interaction between treatment parameters and physiological parameters, customize parameter control combinations for each risk physiological parameter, realize precise and personalized adjustment of treatment plans, and improve treatment safety and effectiveness. Example 8:

[0125] Based on Example 1, a smart erbium laser therapy device includes a control signal module comprising:

[0126] Risk physiological parameter vector unit: Based on all physiological parameters in the risk physiological parameter set, sort them according to their corresponding risk levels to determine the risk physiological parameter vector;

[0127] Real-time control instruction unit: Inputs real-time running data, risk physiological parameter vector, and related treatment parameter vector of each physiological parameter in the risk physiological parameter set into the control model, and determines real-time control instructions based on the output of the control model. The real-time control instructions include multiple real-time control sub-instructions.

[0128] Execution Unit: Input each real-time control sub-instruction in the real-time control command to the corresponding execution unit, execute all real-time control sub-instructions, and realize the real-time control of the intelligent erbium laser therapy device.

[0129] In this embodiment, physiological parameters are sorted in descending order according to risk level to construct a risk physiological parameter vector.

[0130] In this embodiment, the control model performs feature extraction and nonlinear mapping on the input data to generate real-time control instructions. Each real-time control sub-instruction includes the treatment parameter to be adjusted, the target value, the adjustment step size, and the execution priority.

[0131] In this embodiment, the control model can adopt a hierarchical hybrid control architecture, consisting of an input fusion layer, a dynamic decision layer, and a safety constraint layer. The input layer receives real-time running data, risk physiological parameter vectors, and related treatment parameter vectors. It first performs spatiotemporal alignment and normalization of multi-source data to construct a multi-dimensional feature tensor. The dynamic decision layer includes parallel control submodules: 1) a steady-state regulator based on fuzzy PID, which dynamically adjusts the proportional-integral-derivative coefficients according to the risk deviation for core parameters such as energy and pulse width to achieve rapid error convergence; 2) an event-driven compensator, which learns the temporal correlation patterns of physiological parameters and treatment parameters in historical risk events through an LSTM network, predicts potential risk inflection points, and generates feedforward compensation instructions; 3) a reinforcement learning optimizer, which explores the Pareto optimal solution for treatment parameter combinations online. The safety constraint layer introduces a two-layer verification mechanism: the primary verification uses a rule engine (such as IF-THEN logic) to hard limit the output range, and the secondary verification uses a support vector machine (SVM) dynamic classifier to determine whether the instruction combination falls within the confidence interval of the historical safety database, implementing circuit breaking or degradation for abnormal instructions. The final output consists of multiple multi-dimensional real-time control sub-instructions, each with a timestamp and a safety confidence tag. These sub-instructions are sent to the actuators via the CAN bus according to priority, ensuring that the instruction response delay is less than 20ms, while also meeting the real-time and fault-tolerant requirements of IEC62304 for medical device control systems.

[0132] In this embodiment, the execution unit can send real-time control sub-instructions to each execution unit via the CAN bus. A priority scheduling algorithm is adopted, with high-priority instructions (such as emergency cooling) preemptively executed to ensure that critical parameters are adjusted first.

[0133] The beneficial effects of the above technologies are as follows: real-time control commands are generated based on real-time operating data, a set of risk physiological parameters, and the relevant treatment parameter vectors of all physiological parameters in the set of risk physiological parameters. Executing these real-time control commands enables real-time control of the intelligent erbium laser therapy device, which can achieve risk-level response and multi-parameter collaborative optimization, thereby improving treatment safety and accuracy.

[0134] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart erbium laser therapy device, characterized in that, include: Feedback signal module: Real-time monitoring of the operating status of the intelligent erbium laser therapy device to determine real-time operating data, and real-time monitoring of the physiological status of the patient's treatment area to determine real-time physiological data; Human-computer interaction module: Acquires the patient's treatment needs and basic data, determines the input commands of the intelligent erbium laser therapy device, and displays the real-time operating data of the intelligent erbium laser therapy device and the real-time physiological data of the patient's treatment area; Main control board module: acquires multiple historical operational data and multiple historical physiological data, analyzes real-time operational data, real-time physiological data, all historical physiological data and all historical operational data, and determines the set of risk physiological parameters and the relevant treatment parameter vector for each physiological parameter in the set of risk physiological parameters; Control signal module: Based on real-time operating data, risk physiological parameter set, and related treatment parameter vectors of all physiological parameters in the risk physiological parameter set, it generates real-time control commands and executes the real-time control commands to realize the real-time control of the intelligent erbium laser therapy device; The main control board module includes: Risk physiological parameter set unit: The set of risk physiological parameters is determined based on real-time physiological data and all historical physiological data; The risk physiological parameter set unit includes: Physiological parameter image subunit: Based on the real-time parameter value of each physiological parameter in the real-time physiological data at the current time point and the historical parameter value of each physiological parameter in the historical physiological data at all historical time points, a physiological parameter image is drawn for each physiological parameter. The horizontal axis of the physiological parameter image represents the current time point and all historical time points, and the vertical axis of the physiological parameter image represents the real-time parameter value or historical parameter value of the corresponding physiological parameter. Predicted parameter value subunit: The physiological parameter image of each physiological parameter is input into the prediction model, and the predicted parameter value of each physiological parameter at the next time point is determined based on the output of the prediction model; Risk Physiological Parameter Set Subunit: Obtain the physiological parameter range of each physiological parameter in the real-time physiological data, and determine the risk physiological parameter set based on the predicted parameter values ​​of all physiological parameters at the next time point from the current time point and the physiological parameter range.

2. The intelligent erbium laser therapy device according to claim 1, characterized in that, The feedback signal module includes: Real-time operation data unit: Based on the real-time output value of each treatment parameter of the intelligent erbium laser therapy instrument at the current time point, the real-time operation data is determined based on the real-time output value of all treatment parameters of the intelligent erbium laser therapy instrument; Real-time physiological data unit: Based on the real-time monitoring of multiple physiological parameters of the patient's treatment area at the current time point by the second sensor group, real-time physiological data is determined based on the real-time parameter values ​​of all physiological parameters of the patient's treatment area.

3. The intelligent erbium laser therapy device according to claim 1, characterized in that, The human-computer interaction module includes: Basic data unit: The intelligent erbium laser therapy device acquires the patient's basic data, which includes at least the patient's name, gender, age, skin type, and allergy history; Judgment Unit: Acquires the patient's treatment needs, determines the patient's treatment mode and treatment area based on the patient's treatment needs, and determines whether skin matching is required; Patient Skin Type Unit: Determine if the patient's skin type in the patient's basic data is empty. If it is empty, retrieve the patient's skin information, determine the patient's skin type based on the patient's skin type, and update the patient's basic data.

4. The intelligent erbium laser therapy device according to claim 3, characterized in that, The human-computer interaction module also includes: First initial treatment parameter data unit: If the patient needs skin matching, the patient's initial treatment parameter data is determined based on the patient's skin type and skin preset parameter library in the patient's basic data. The initial treatment parameter data includes the initial parameter values ​​and treatment parameter ranges of multiple treatment parameters. Second initial treatment parameter data unit: If the patient does not need skin matching, the initial treatment parameter data of the patient is determined based on the patient's treatment mode and mode preset parameter library. The initial treatment parameter data includes the initial parameter values ​​and treatment parameter ranges of multiple treatment parameters. Input command unit: Based on the patient's treatment mode and the initial parameter values ​​of all treatment parameters in the initial treatment parameter data, determine the input command of the intelligent erbium laser therapy device.

5. The intelligent erbium laser therapy device according to claim 4, characterized in that, The main control board module includes: Acquisition Unit: Acquires historical operational data and historical physiological data for a specified number of historical time points prior to the current time point. The historical operational data includes the historical output values ​​of all treatment parameters at the corresponding historical time point, and the historical physiological data includes the historical parameter values ​​of all physiological parameters at the corresponding historical time point. Relevant treatment parameter vector unit: Based on real-time operation data, all historical operation data, and the risk physiological parameter set, calculate the comprehensive correlation value between each physiological parameter and each treatment parameter in the risk physiological parameter set, and determine the relevant treatment parameter vector for each physiological parameter in the physiological parameter set.

6. The intelligent erbium laser therapy device according to claim 5, characterized in that, Relevant treatment parameter vector units, including: Calculation subunit: Based on the risk physiological parameter set, real-time operation data at the current time point, historical operation data at all historical time points before the current time point, and historical physiological data, calculate the time lag correlation value, cumulative correlation value, and cumulative trend consistency of each physiological parameter and each treatment parameter in the risk physiological parameter set; Comprehensive correlation value subunit: Based on the time lag correlation value, cumulative correlation value, and cumulative trend consistency of each physiological parameter and each treatment parameter in the risk physiological parameter set, calculate the comprehensive correlation value of each physiological parameter and each treatment parameter in the risk physiological parameter set; Relevant treatment parameter vector subunit: Sort the comprehensive correlation values ​​of each physiological parameter and all treatment parameters in the risk physiological parameter set from largest to smallest, select the treatment parameters corresponding to the first preset number of comprehensive correlation values ​​of each physiological parameter in the risk physiological parameter set after sorting, and determine the relevant treatment parameter vector of each physiological parameter in the risk physiological parameter set.

7. The intelligent erbium laser therapy device according to claim 1, characterized in that, The control signal module includes: Risk physiological parameter vector unit: Based on all physiological parameters in the risk physiological parameter set, sort them according to their corresponding risk levels to determine the risk physiological parameter vector; Real-time control instruction unit: Inputs real-time running data, risk physiological parameter vector, and related treatment parameter vector of each physiological parameter in the risk physiological parameter set into the control model, and determines real-time control instructions based on the output of the control model. The real-time control instructions include multiple real-time control sub-instructions. Execution Unit: Input each real-time control sub-instruction in the real-time control command to the corresponding execution unit, execute all real-time control sub-instructions, and realize the real-time control of the intelligent erbium laser therapy device.

Images