System, method and equipment for optimizing control parameters of suction in airway

Abstract

The invention discloses an in-airway suction control parameter optimization processing system, method and equipment, and relates to the technical field of data processing. Airway images are collected, airway suction tasks are determined, airway three-dimensional reconstruction is carried out, discretization surface element processing is executed, airway geometric shapes are constructed, suction constraint conditions are introduced, and in allusion to the airway suction tasks, three-dimensional reconstruction is carried out. According to the flow field suction state, first-order surface element optimization based on the airway geometry is executed, second-order back-stepping optimization is executed according to airway suction parameters, a parameter sequence of the complete suction cycle is determined, and airway suction control and feedback tracking adjustment are conducted in response to an aspirator. The method and device are used for solving the technical problems that in the prior art, optimization guidance is carried out according to documents and cases, the parameter self-adaptive adjustment capacity of existing airway suction control is insufficient, and the suction efficiency is limited, and the self-adaptive degree of airway suction parameters can be effectively improved so as to guarantee the suction efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a system, method and device for optimizing airway aspiration control parameters. Background Art

[0002] Airway aspiration aims to remove secretions in the patient's airway and ensure unobstructed breathing. At present, existing airway aspiration systems mainly rely on fixed parameter settings, lack real-time feedback adjustment for individual patients, and are prone to mismatched aspiration parameters, leading to secondary injuries such as airway mucosal injury, hypoxemia, and atelectasis caused by negative pressure. In addition, during the traditional airway aspiration operation, medical staff mainly rely on experience to adjust the aspiration intensity, duration, and intubation position, resulting in unstable aspiration effects and difficulty in achieving precise control.

[0003] Currently, in the aspect of airway aspiration, a complete parameter optimization system has not been formed, and literature cases have not been effectively utilized for intervention optimization. Therefore, how to provide optimization guidance through evidence-based literature cases to solve the technical problems of insufficient parameter adaptive adjustment ability and limited aspiration efficiency in existing airway aspiration control. Summary of the Invention

[0004] This application provides a system, method and device for optimizing airway aspiration control parameters, which are used to solve the technical problems of how to provide optimization guidance through evidence-based literature cases to solve the insufficient parameter adaptive adjustment ability and limited aspiration efficiency in existing airway aspiration control.

[0005] In view of the above problems, this application provides a system, method and device for optimizing airway aspiration control parameters.

[0006] In a first aspect, this application provides a system for optimizing airway aspiration control parameters. The system includes: a construction module, configured to collect airway images, determine airway aspiration tasks, perform three-dimensional reconstruction of the airway, and construct an airway geometry by performing discretized surface element processing, where the vertices of the airway geometry correspond to the singular points of the surface elements; a condition introduction module, configured to introduce aspiration constraint conditions, where the aspiration constraint conditions include aspiration methods and user state elements; an optimization module, configured to perform first-order surface element optimization based on the airway geometry and second-order inverse optimization for airway aspiration parameters for the airway aspiration task according to the aspiration constraint conditions, to determine a parameter sequence for the entire aspiration cycle, where optimization guidance is provided through evidence-based cases; an aspiration control module, configured to perform airway aspiration control and feedback tracking adjustment in response to the parameter sequence by an aspirator.

[0007] Second aspect, the present application provides a method for optimizing airway aspiration control parameters, the method comprising: acquiring airway images, determining an airway aspiration task, and performing three-dimensional reconstruction of the airway. By performing discretized panel processing, an airway geometry is constructed, wherein the vertices of the airway geometry correspond to panel singularities; introducing aspiration constraint conditions, wherein the aspiration constraint conditions include an aspiration mode and user state elements; for the airway aspiration task, according to the aspiration constraint conditions, for the flow field aspiration state, performing first-order panel optimization based on the airway geometry, and performing second-order inverse optimization for airway aspiration parameters to determine a parameter sequence for the entire aspiration cycle, wherein optimization guidance is carried out through case-based evidence; the parameter sequence responds to the aspirator to perform airway aspiration control and feedback tracking adjustment.

[0008] Third aspect, the present application provides an electronic device, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the system described in the first aspect when executing the computer program.

[0009] One or more technical solutions provided in the present application have at least the following technical effects or advantages: A method for optimizing airway aspiration control parameters provided in an embodiment of the present application acquires airway images, determines an airway aspiration task, and performs three-dimensional reconstruction of the airway. By performing discretized panel processing, an airway geometry is constructed, and aspiration constraint conditions are introduced, including an aspiration mode and user state elements; for the airway aspiration task, according to the aspiration constraint conditions, for the flow field aspiration state, performing first-order panel optimization based on the airway geometry, and performing second-order inverse optimization for airway aspiration parameters to determine a parameter sequence for the entire aspiration cycle, wherein optimization guidance is carried out through case-based evidence; the parameter sequence responds to the aspirator to perform airway aspiration control and feedback tracking adjustment. It is used to solve the technical problem in the prior art of how to carry out optimization guidance through case-based evidence in the literature to solve the insufficient parameter adaptive adjustment ability of the existing airway aspiration control and the limited aspiration efficiency, and can effectively improve the adaptability of airway aspiration parameters to ensure the aspiration efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a schematic flowchart of a method for optimizing airway aspiration control parameters provided by the present application; Figure 2 It is a schematic structural diagram of a system for optimizing airway aspiration control parameters provided by the present application; Figure 3 It is a schematic structural diagram of an electronic device provided by the present application.

[0011] Description of reference numerals: construction module 11, condition introduction module 12, optimization module 13, suction control module 14, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. Detailed implementation

[0012] This application provides an airway suction control parameter optimization processing system, method and device, which collects airway images, determines airway suction tasks, and performs three-dimensional airway reconstruction. By performing discretized panel processing, an airway geometry is constructed, and suction constraint conditions are introduced. For the airway suction task and the flow field suction state, first-order panel optimization based on the airway geometry is performed, and second-order inverse inference optimization is performed on airway suction parameters to determine the parameter sequence of the entire suction cycle. In response to the suction device, airway suction control and feedback tracking adjustment are performed. It is used to solve the technical problem in the prior art of how to perform optimization guidance through evidence-based literature cases to solve the insufficient parameter adaptive adjustment ability of existing airway suction control and limited suction efficiency.

[0013] Embodiment 1: As Figure 1 shown, this application provides an airway suction control parameter optimization processing method, and the method includes: S1: Collect airway images, determine airway suction tasks, and perform three-dimensional airway reconstruction. By performing discretized panel processing, an airway geometry is constructed, where the vertices of the airway geometry correspond to panel singularities.

[0014] In the embodiment of this application, the airway images can be sourced from CT (Computed Tomography), MRI (Magnetic Resonance Imaging) or other medical imaging devices. The acquired image data should have sufficient resolution and slice thickness to ensure the accuracy of subsequent reconstruction. Preferably, the airway images can be collected using a multi-view scanning method to ensure complete coverage of the target area and reduce information loss during the reconstruction process.

[0015] After obtaining the airway images, determine the airway suction tasks according to the airway state represented by the images. The determination of the airway suction tasks is usually based on the suction requirements of the airway state. For example, the suction targets and distribution positions in the airway. In this step, preferably, the respiratory dynamics parameters of the patient, such as airflow resistance and airway pressure difference, can be combined to accurately identify the airway areas that need to be suctioned and provide input conditions for subsequent optimization.

[0016] Subsequently, based on the airway image data, three-dimensional airway reconstruction is performed to obtain an airway structure model that can be used for computational analysis. The three-dimensional reconstruction can adopt image segmentation and reconstruction algorithms. First, threshold segmentation is performed on the original image data to distinguish the airway from the surrounding tissues. Then, methods such as region growing and level set are used to further refine the airway contour, and geometric reconstruction based on the airway contour is performed to generate a three-dimensional structure model. The result of this three-dimensional reconstruction can be used as the basis for subsequent calculations.

[0017] After completing the three-dimensional reconstruction, discretized surface element processing is performed on the three-dimensional airway model to construct an airway geometry that can be used for numerical calculations. Discretized surface element processing refers to converting the continuous airway surface into a discrete surface element grid. In a feasible embodiment, methods such as Delaunay triangulation, Voronoi segmentation, or tetrahedral mesh generation can be used to ensure uniform mesh division and accurate representation of the airway's geometric features. For example, in areas of airway stenosis or bifurcation, the mesh density can be appropriately increased to enhance the calculation accuracy, while in areas where the airway is relatively smooth, larger surface elements can be used to reduce the computational burden.

[0018] In the discretized surface element processing, surface element singular points need to be set, and it is ensured that the vertices of the airway geometry correspond to the surface element singular points. A surface element singular point refers to a characteristic point in the airway surface mesh. Each mesh is assigned a surface element singular point, which is used to characterize the local flow field characteristics of the mesh. According to the number of surface element meshes, the number of vertices of the airway geometry is determined, and a polyhedron is constructed as the airway geometry, which can provide a mathematical basis for subsequent optimization and adjustment, making the attraction control more targeted and accurate.

[0019] Furthermore, when performing the discretized surface element processing, step S1 of this application includes: Obtain the reconstructed airway. According to the airway structure, perform discretized mesh division on the airway surface to determine the surface element meshes; for the surface element meshes, set surface element singular points, where the surface element meshes and the surface element singular points are in one-to-one correspondence, and the surface element singular points characterize the flow field state characteristics of the corresponding airway surface element meshes; map the surface element meshes and the surface element singular points as the surface element processing result.

[0020] In the embodiment of this application, obtaining the reconstructed airway means obtaining a three-dimensional model containing the complete airway structure on the basis of the previous three-dimensional reconstruction. After obtaining the reconstructed airway, discretized mesh division is performed on the airway surface according to the airway structure to form a discrete model suitable for numerical calculations. Discretized mesh division refers to dividing the continuous airway surface into finite surface elements, thereby constructing a computational mesh for calculating the flow field characteristics. Usually, methods such as Delaunay triangulation, Voronoi diagram segmentation, or tetrahedral mesh generation can be used.

[0021] Preferably, for airway regions with complex geometric features, such as stenosis segments, curved segments, and bifurcation sites, the grid density can be appropriately increased to enhance local calculation accuracy. In relatively smooth or regular airway regions, larger surface elements can be used to reduce the computational amount. The rationality of the discretized grid directly affects the reliability of the optimization of the attraction parameters. Therefore, adaptive grid division needs to be carried out according to the characteristics of the airway structure.

[0022] For the surface element grid, surface element singular points are set, where the surface element grid corresponds one-to-one with the surface element singular points. The surface element singular point refers to the key point used to characterize the state characteristics of the local flow field. Under standard conditions, the center of the surface element is usually selected.

[0023] In a feasible embodiment, grid intersection points or the positions of surface elements where the flow field changes violently can be used. For example, at the airway bifurcation, due to the splitting of the airflow, the velocity gradient increases. The center of the surface element near the bifurcation point can be set as the surface element singular point; in the airway stenosis segment, due to the increase in the pressure gradient, the center of the typical cross-section of the stenosis segment can also be selected as the surface element singular point. The setting of the surface element singular point helps to accurately describe the local flow state of the airway and provides the necessary flow field information for the optimization of the attraction control parameters.

[0024] Finally, map the surface element grid and the surface element singular points as the surface element processing result. The mapping operation means establishing a one-to-one mapping relationship on the already divided surface element grid based on its corresponding surface element singular points, so that the surface element singular points can effectively characterize the flow field characteristics of this region. For example, during the numerical calculation process, the surface element singular points can be used as the characteristic nodes for the analysis of the airway flow field, characterizing characteristics such as the flow velocity, flow direction, and pressure of the attracting flow field, and performing subsequent optimization calculations. Through the construction of this mapping relationship, it can be ensured that all surface element grids have corresponding flow field state characteristics, so that the flow field characteristics of the entire airway geometry are accurately described, providing a computational basis for the formulation of subsequent attraction optimization strategies.

[0025] Furthermore, step S1 of the present application includes: constructing the airway geometry according to the surface element processing result; Among them, the construction method includes: for the airway attraction task, locating the attracting medium, where the attracting medium is marked with medium characteristics and airway positions; traversing the surface element grid to determine the number of vertices; locating the key surface element grids based on the attracting medium and setting the first weight, where the weighting is performed based on the medium characteristics; constructing the airway geometry with the number of vertices and the first weight.

[0026] In the embodiment of the present application, constructing the airway geometry according to the surface element processing result means respectively assigning a geometric vertex to each surface element singular point, delimiting the space with the characteristic range of each surface element singular point, and constructing a polyhedron, that is, converting it into a data optimization problem. To support subsequent attraction optimization calculations and the formulation of control strategies.

[0027] Among them, the construction method includes: First, for the airway suction task, locate the suction medium. The airway suction task refers to the specific suction target determined based on the patient's airway condition, secretion distribution, suction requirements, etc., such as clearing mucus in the upper airway or reducing airway resistance. The suction medium refers to the target to be suctioned, such as airway secretions, etc. Different physical characteristics of the suction medium correspond to different suction parameter control standards, such as density, viscosity, etc.

[0028] After locating the suction medium, traverse the surface element grid to determine the number of vertices of the airway geometry. The surface element grid is a surface structure composed of multiple discretized surface element units, and the number of its vertices determines the complexity of the airway geometry. For each surface element grid, determine a vertex respectively to represent the state based on the flow field suction requirement in the follow-up, so as to determine the number of vertices.

[0029] Subsequently, locate the key surface element grid based on the suction medium and set the first weight. The key surface element grid refers to the grid area where there is a suction medium during the suction operation. For the key surface element, set the first weight to represent the importance of this surface element for the overall flow field suction. The setting of the first weight can be weighted according to the characteristics of the suction medium. For example, for a suction medium with high density and relatively high viscosity, its suction difficulty is greater, and the corresponding weighted value is larger. Therefore, the weight of the corresponding key surface element should be appropriately increased to enhance the influence on the local flow field behavior.

[0030] Finally, construct the airway geometry with the number of vertices and the first weight. Specifically, construct a polyhedron according to the number of vertices. Each vertex of the polyhedron represents the flow field state of each surface element grid, determine the airway geometry, and through matching, based on the first weight, identify the airway geometry. Through the above steps, it is converted into a mathematical optimization problem, laying a foundation for subsequent suction parameter optimization and control strategy implementation.

[0031] S2: Introduce suction constraint conditions, where the suction constraint conditions include suction methods and user state elements.

[0032] In the embodiment of the present application, by introducing suction constraint conditions, it is ensured that the airway suction process meets specific application requirements and realizes optimized control. The suction constraint conditions refer to the restrictive conditions that need to be met when performing the airway suction task, so as to avoid having an adverse impact on the patient's physiological state while ensuring the suction effect.

[0033] Among them, the suction constraint conditions include the suction method and user state factors. The suction method refers to the suction operation mode adopted for different clinical needs, mainly including open airway suction and closed airway suction. Open airway suction means that when the patient's airway is connected to the external environment, an external negative pressure device is used to remove secretions. For example, after tracheal intubation or tracheotomy, open suction can be used to clean the secretions in the airway. In contrast, closed airway suction is performed within a sealed pipeline system and is applicable to mechanically ventilated patients to reduce the fluctuation of airway pressure during ventilation and lower the infection risk. The choice of suction method directly affects the setting of suction parameters. For example, open suction usually requires a larger negative pressure to quickly remove secretions, while closed suction needs to consider maintaining stable airway pressure to avoid interfering with the patient's respiratory function.

[0034] User state factors refer to the physiological state of the patient during suction, such as multiple key indicators including the spontaneous breathing mode, airway resistance level, lung compliance, and oxygenation status. For example, for patients with spontaneous breathing, it is necessary to consider the airway patency and respiratory drive to avoid airway collapse or hypoxemia caused by excessive negative pressure during suction. The determination of user state factors can be based on real-time monitoring data, including parameters such as respiratory rate, tidal volume, blood oxygen saturation, and peak airway pressure. For example, in a state of high airway resistance, the suction negative pressure can be appropriately reduced and the suction time can be extended to reduce the risk of airway collapse, while in the case of low lung compliance, the suction timing needs to be optimized to avoid excessive alveolar collapse.

[0035] By comprehensively considering the suction method and user state factors, suction constraint conditions for different application scenarios can be formed, providing a guiding basis for subsequent optimization of suction parameters. The setting of suction constraint conditions needs to combine clinical evidence-based data and individual physiological characteristics to ensure that the suction process can effectively remove airway secretions while minimizing the impact on the patient's respiratory function, achieving precise and individualized airway suction control.

[0036] Furthermore, step S2 of this application includes: The suction method is open airway suction or closed airway suction; according to the suction method, the airway suction requirements under the characteristics of the suction method are explored; according to the airway suction requirements, the first suction constraint condition is determined.

[0037] The suction method is open airway suction or closed airway suction. For the characteristics of different suction methods, corresponding suction control strategies are set to ensure that the suction process can effectively remove airway secretions while minimizing the impact on the patient's respiratory function.

[0038] Among them, open airway suction refers to the process in which the airway is in a connected state with the external environment during suction. Usually, by briefly opening the breathing circuit, the suction tube is directly in contact with the patient's airway, so that secretions can be discharged by the action of negative pressure. The characteristic of this method is relatively high suction efficiency, which can quickly remove secretions and is suitable for patients with acute secretory obstruction or those who need intermittent airway clearance. However, since the airway is briefly exposed to the atmospheric environment during open suction, it may cause a sudden drop in airway pressure, which in turn leads to transient hypoxemia or alveolar collapse. Therefore, in the open suction mode, it is necessary to focus on the suction negative pressure intensity, suction time and the patient's oxygenation status to ensure the safety and effectiveness of the suction process.

[0039] In contrast, closed airway suction refers to the suction operation carried out within a closed breathing circuit. The suction tube is connected to the ventilator tube and enters the airway through a closed interface to prevent the entry of external air during suction. This method is suitable for patients receiving mechanical ventilation, which can maintain positive airway pressure during suction, reduce the pressure fluctuation in the breathing circuit, lower the risk of infection, and maintain the continuity of ventilation. However, since the airway is always in a closed state during closed suction, the suction operation may cause a transient increase in ventilation resistance or airway pressure changes. Therefore, in the closed suction mode, it is necessary to comprehensively consider the suction timing, airway pressure compensation mechanism and ventilation synchrony to optimize the stability and safety of the suction process.

[0040] Based on the characteristics of the above suction methods, it is necessary to further explore the airway suction requirements under each suction mode. The airway suction requirements refer to the specific technical conditions that need to be met to ensure the safety and effectiveness of the suction operation under different suction modes. Exemplarily, it may include elements such as suction flow rate, negative pressure range, suction frequency, airway ventilation status and physiological adaptability. For example, in the open suction mode, it is necessary to ensure sufficient oxygen reserve in the patient before the suction operation. The pre-oxygenation method can be used to improve the oxygenation level. At the same time, the duration of each single suction should be strictly controlled, generally not exceeding 15 seconds, to reduce the risk of hypoxemia. In the closed suction mode, it is necessary to synchronously monitor the peak airway pressure and the ventilator pressure compensation situation to prevent the suction operation from causing ventilation imbalance, and an automatic negative pressure adjustment mechanism can be used to reduce the interference with mechanical ventilation.

[0041] According to the airway suction requirements, determine the first suction constraint condition. The first suction constraint condition refers to the preliminary technical limitations that need to be met during the suction operation to ensure that the suction process meets the requirements of safety, stability, and individualization. For example, for the open suction mode, the first suction constraint conditions may include the maximum negative pressure limit (such as -100 mmHg to -200 mmHg), the single suction time limit (such as ≤15 seconds), and the minimum oxygen saturation threshold (such as ≥90%), to ensure that the patient maintains sufficient oxygen supply during the suction process. For the closed suction mode, the first suction constraint conditions may include the ventilator synchronous trigger time window (such as the inhalation-exhalation ratio controlled within 1:2) and the suction negative pressure gradient control (such as the negative pressure rise time ≥2 seconds), to reduce the interference of suction on the ventilation mode. By setting the above constraint conditions, the suction process can be effectively optimized, the refinement level of airway management can be improved, and the risk of suction-related complications can be reduced.

[0042] S3: For the airway suction task, according to the suction constraint conditions, perform first-order panel optimization based on the airway geometry for the flow field suction state, and perform second-order inverse inference optimization for the airway suction parameters to determine the parameter sequence of the entire suction cycle, where optimization guidance is carried out through case-based evidence.

[0043] In the embodiments of the present application, for the airway suction task, to ensure the accuracy and stability of the suction process, it is necessary to optimize the airway suction control strategy according to the preset suction constraint conditions. The airway suction task refers to implementing a suction operation to remove airway secretions and ensure airway patency based on the patient's individual physiological state, combined with the accumulation of airway secretions and ventilation requirements. The suction constraint conditions are the technical limitation parameters that need to be met during the suction task, including key elements such as the suction method, negative pressure intensity, hydrodynamic characteristics, and patient physiological adaptability, aiming to balance the suction effect and physiological safety and avoid airway damage or ventilation disorders caused by excessive suction or improper control.

[0044] On the premise of meeting the suction constraint conditions, it is necessary to perform first-order panel optimization based on the airway geometry for the flow field suction state. The flow field suction state refers to the dynamic evolution of the airflow distribution, pressure gradient, and vortex structure in the airway during the suction process, which directly affects the suction efficiency and airway ventilation function. The airway geometry is used to characterize the flow field state of each panel, and its morphological characteristics determine the distribution of the flow field in the airway and the suction effect.

[0045] To optimize the suction flow field, make the suction negative pressure evenly distributed, reduce turbulence and vortex effects, and improve the suction efficiency, a first-order panel optimization method needs to be adopted. First-order panel optimization refers to taking the local flow field state of each panel grid as the target, and through iterative adjustment, adjusting the spatial geometric distribution of the vertices, which is equivalent to adjusting the suction state of the local flow field, so as to perform iterative adjustment of different local flow field states to determine the optimal comprehensive flow field state that can meet the airway suction requirements. The flow field is processed in the form of mathematical optimization. During this process, the case-based evidence method can be used, that is, based on a large amount of clinical data and literature reviews as support, to assist in making decisions on the adjustment direction of optimization, so as to determine the flow field effect that needs to be achieved under suction control.

[0046] After completing the optimization of the suction state of the flow field, further perform second-order inverse optimization on the airway suction parameters to determine the parameter sequence of the entire suction cycle. The airway suction parameters include pneumatic parameters (such as suction negative pressure, air flow velocity), suction time limit, intubation position, etc. Second-order inverse optimization refers to, based on the flow field optimization result, that is, the optimal flow field suction state that meets the airway suction requirements, reverse-deriving the optimal suction parameter configuration to achieve this suction state, so that it can meet the best hydrodynamic conditions at different suction stages. Further perform timing integration to determine the parameter sequence of the entire suction cycle.

[0047] For example, in the initial stage of suction, to reduce the sudden drop in airway pressure, a lower initial negative pressure can be set, and through progressive negative pressure adjustment, the target suction intensity can be gradually reached; in the end stage of suction, to prevent airway collapse caused by residual airflow disorder, a slow-release negative pressure strategy can be adopted to make the suction process end smoothly. In addition, if during the suction process, the parameter changes at certain time nodes are too drastic (that is, there are parameter jumps at the changing nodes), then further perform parameter jump smoothing processing to ensure the continuity and stability of the suction process.

[0048] Through the gradual implementation of the above optimization strategies, accurate, efficient and individualized airway suction control is finally achieved, improving the safety and effectiveness of the suction operation.

[0049] Further, perform first-order panel optimization based on the airway geometry. Step S3 of this application includes: Taking double-order optimization as the underlying logic, determining sample data through case-based evidence, and driving the training optimization processor; assisting the optimization processor to determine the first initial complex for the airway geometry, where it is determined based on the first initial suction flow field of each panel singularity; setting an iterative operation method, which at least includes reflection - contraction - expansion - reconstruction methods; randomly selecting from the iterative operation method to iteratively adjust the first initial complex, and preferentially determining the target complex, where the target complex represents the flow field state of airway suction for each panel grid, and is the first suction time node based on the entire suction cycle.

[0050] In the optimization process of airway suction control parameters, a two-stage optimization is used as the underlying logic. By constructing a two-layer progressive optimization structure, precise suction control is achieved. Among them, the two-stage optimization refers to a step-by-step optimization method that first performs flow field optimization (the first-stage optimization) and then parameter inverse deduction (the second-stage optimization) to ensure the stability and adaptability of the suction process. To ensure the reliability of the optimization model, it is first necessary to determine the sample data based on the case-based evidence method. The case-based evidence method refers to taking the combination of previous clinical suction cases and literature reviews as the basis.

[0051] Preferably, a control group and an experimental group can be used for calibration analysis, which can effectively improve the representativeness of the samples. Extract a representative suction data set to form the training samples of the optimization model. By constructing multiple groups of sample data, the adaptability of the optimization model can be effectively improved, enabling it to provide precise optimization solutions for different airway morphologies and suction requirements.

[0052] After determining the sample data, drive the training optimization processor to perform optimization calculations. The optimization processor is a computing unit used to calculate airway suction parameters, and its core function is to perform hydrodynamic analysis and parameter optimization based on the input sample data. When the optimization processor performs optimization calculations, it first determines the first initial complex for the airway geometry. Specifically, the first initial complex refers to the initial flow field state generated by the optimization processor at the beginning of the optimization. This flow field state is determined based on the first initial suction flow field of each panel singularity, that is, any geometric shape that satisfies the suction constraint conditions based on the airway geometry. Each geometric vertex represents the flow field state of each panel area, including parameters such as local flow velocity, pressure distribution, and vortex intensity. Therefore, by calculating the initial flow field state of each panel singularity, the first initial complex can be constructed, providing a reference benchmark for subsequent optimization iterations.

[0053] After determining the first initial complex, it is necessary to set the iterative operation method to optimize and adjust the initial complex. The iterative operation method refers to a calculation strategy that gradually adjusts the initial complex based on mathematical optimization methods, which at least includes the reflection-shrinkage-expansion-reconstruction method. The reflection method refers to, for a local abnormal flow field area, by adjusting the flow boundary of the panel singularity, making the airflow reflect back to a reasonable flow field distribution; the shrinkage method refers to when a region with large flow field disturbances is found, by reducing the local flow intensity, making the suction process more stable; the expansion method is for the situation of uneven flow field distribution, by expanding the flow field boundary, making the negative pressure distribution more uniform; the reconstruction method refers to, after multiple rounds of optimization adjustments, re-adjusting the overall flow field structure to ensure the final realization of the optimization goal.

[0054] After setting the iterative operation mode, the first initial complex is iteratively adjusted by randomly selecting according to the iterative operation mode to gradually optimize the attracting flow field state. Random selection means that when performing iterative optimization, instead of calculating according to a fixed optimization method, different optimization methods are randomly selected for dynamic adjustment to enhance the global convergence of optimization. Through multiple rounds of iterative adjustment, the target complex can be determined by selecting the best. Among them, the target complex characterizes the airway attracting flow field state of each panel grid, that is, through the optimized flow field distribution, the attracting effect reaches the best state.

[0055] Among them, through the method of sample training, the attracting effect based on the flow field state is used for calibration and selection judgment.

[0056] Finally, the target complex, as the optimization result, can be used to determine the flow field state based on the first attracting time node in the entire attracting cycle, that is, at the first key time point of the attracting process, to provide the optimal hydrodynamic configuration to ensure the stability and efficiency of the attracting process.

[0057] Further, when iteratively adjusting the first initial complex, step S3 of this application includes: Identify the first weight identifier and determine the adjustment collision priority; according to the adjustment collision priority, perform iterative adjustment constraints; among them, single-step iteration is performed by randomly finite element adjustment based on the vertices of the first initial complex. Among them, before performing iterative adjustment, it also includes: limiting the geometric feasible region with the attracting constraint condition; performing iterative adjustment limitation with the geometric feasible region.

[0058] During the optimization process, to ensure the stability and convergence of iterative calculation, it is necessary to first identify the first weight identifier and determine the adjustment collision priority accordingly. Among them, the first weight identifier refers to the weight parameter assigned to different panel grids or attracting media in the optimization calculation, and this weight is used to characterize the importance of each region and the priority of optimization adjustment. For example, if there are more attracting targets and stronger adhesion in a certain grid, that is, the attracting difficulty is greater, its weight value can be appropriately increased so that it is given priority in optimization.

[0059] By identifying the first weight identifier, the key regions that need to be optimized first can be distinguished, ensuring that the focus of the optimization calculation is on the core parts that affect the stability and efficiency of the attracting flow field. After identifying the first weight identifier, according to the adjustment collision priority, iterative adjustment constraints are executed. Among them, the adjustment collision priority refers to determining the optimization order of flow field impact, eddy current interference, and negative pressure attraction intensity change based on the weight parameters of each panel during the optimization iteration to avoid local instability or calculation divergence during the optimization process.

[0060] During the optimization iteration adjustment process, single-step iteration is performed with random finite element adjustment based on the vertices of the first initial complex. Among them, the vertices of the first initial complex refer to the discretized geometric points that constitute the initial attracting flow field state, and these vertices determine the shape and boundary conditions of the flow field. Random finite element adjustment means that during the optimization process, the attracting flow field is dynamically adjusted by combining the finite element method, and the adjustment area is randomly selected, such as randomly determining the adjusted vertices, that is, the surface element grid; randomly determining the adjustment quantity, etc. Single-step iteration refers to a single optimization iteration, and each adjustment is based on the finite element method to enhance the convergence and robustness of the optimization calculation. By performing single-step iteration of random finite element adjustment, the gradual convergence of the optimization process can be ensured, and the attracting flow field can tend to the optimal solution during stable adjustment.

[0061] Before performing iterative adjustment, it is also necessary to define the geometric feasible region based on the attracting constraint conditions. The attracting constraint conditions refer to the physical and physiological boundary conditions that need to be observed during the optimization process, such as the morphological constraints of the inner wall of the airway, the safety threshold of the attracting negative pressure, and the feasible flow range of the flow field. The geometric feasible region refers to the allowable geometric adjustment range in the optimization calculation, and this range is determined by the airway shape, the action area of the attracting medium, and the distribution of the negative pressure field. By defining the geometric feasible region, it can be ensured that the optimization adjustment does not exceed the physical feasible range, and the risk of attracting failure or injury caused by excessive adjustment can be avoided.

[0062] After defining the geometric feasible region, iterative adjustment limitation is performed with the geometric feasible region, that is, during the optimization calculation, all parameter adjustments need to meet the boundary conditions of the geometric feasible region. Through iterative adjustment limitation, that is, during the optimization process, in order to prevent the calculation from deviating from the reasonable solution space, the adjustment process needs to be constrained so that the optimization calculation is always within the feasible range. By defining the iterative adjustment range, the stability of the optimization calculation can be ensured, so that the finally obtained attracting parameters and flow field distribution conform to physical reality and attracting requirements, and the precise optimization of the airway attracting process can be realized.

[0063] Furthermore, second-order inverse push optimization is performed on the airway attracting parameters. Step S3 of this application includes: Determine the airway attracting parameters. Among them, the airway attracting parameters at least include pneumatic parameters, attracting time limit, and intubation position. The pneumatic parameters at least include pneumatic velocity and pneumatic negative pressure; for the target complex, perform inverse push of the airway attracting parameters to determine the parameter sequence based on the attracting time limit; Among them, if there is a parameter jump at the change node of the parameter sequence, it also includes: performing parameter jump smoothing processing on the change node.

[0064] In the parameter optimization process of airway suction control, it is first necessary to determine the airway suction parameters. Airway suction parameters refer to the key physical parameters that need to be adjusted during the airway suction process. These parameters directly affect the optimization and implementation of the suction effect. For example, the control parameters of the suction device. The airway suction parameters at least include pneumatic parameters, suction time limit, and intubation position. Among them, pneumatic parameters refer to the parameters related to fluid dynamics, including pneumatic velocity and pneumatic negative pressure. Pneumatic velocity refers to the flow velocity of the air flow in the airway, and its magnitude determines the intensity of the suction effect. Pneumatic negative pressure refers to the negative pressure value generated by the suction device. Controlling the magnitude of the negative pressure can adjust the suction ability of the flow field in the airway to ensure the effect of airway cleaning. The suction time limit refers to the time limit of the airway suction operation, and its setting needs to ensure that the airway is cleaned within an effective time without causing too much discomfort to the patient. The intubation position refers to the insertion position of the suction tube, which has an important impact on the air flow in the airway and the cleaning effect.

[0065] After determining the airway suction parameters, it is necessary to perform inverse deduction of the airway suction parameters for the target composite shape. The target composite shape refers to the suction flow field state after optimization and adjustment, that is, the flow field state that can achieve the best suction effect. This state characterizes the ideal flow field distribution required for airway suction operations under specific airway morphologies and suction conditions.

[0066] Inverse deduction of airway suction parameters means to reverse calculate the airway suction control parameters that can achieve this flow field state through the known target composite shape. Through inverse deduction calculation, accurate parameter settings can be provided for the suction operation to ensure the efficiency and stability of airway suction in practical applications.

[0067] When performing inverse deduction of airway suction parameters, the influence of the suction time limit is mainly considered. Based on the suction time limit, a corresponding parameter sequence is constructed to ensure the best airway cleaning effect within the specified time. The parameter sequence refers to the dynamic adjustment strategy of pneumatic velocity, pneumatic negative pressure, and other suction parameters changing with time during the suction process. By setting a reasonable parameter sequence, a smooth transition of the suction process can be ensured and the predetermined suction effect can be achieved.

[0068] In a feasible embodiment, based on the control mechanism of the suction device, the conversion relationship between parameters and effects is determined, and recursive analysis is carried out based on this.

[0069] However, during the process of generating the parameter sequence, divergence nodes may occur. A divergence node refers to a point in the parameter sequence where the change is relatively drastic. These nodes are usually caused by parameter jumps, that is, at certain moments, the attracting parameters change significantly. If these parameter jumps are not effectively smoothed, it may lead to instability during the attracting process or discontinuity of the effect. Therefore, when determining the parameter sequence, if there are parameter jumps, the divergence nodes should be processed for parameter jump smoothing to make them smoother and avoid the adverse effects brought by sharp changes to the attracting process. Exemplarily, it is achieved by adjusting the parameter jump scale to multi-step parameter adjustment. Through this processing, the stable transition of the parameter sequence can be ensured, thereby realizing the stability and efficiency of the airway suction process.

[0070] S4: The parameter sequence responds to the suction device to perform airway suction control and feedback tracking adjustment.

[0071] Furthermore, for performing airway suction control and feedback tracking adjustment, step S4 of the present application includes: Collect user physiological indicators along with airway suction control, and synchronously perform airway image acquisition to determine the suction state; perform feedback adjustment management of airway suction control according to the user physiological indicators and the suction state.

[0072] In the practical application of airway suction control, the parameter sequence responds to the suction device to perform airway suction control and feedback tracking adjustment. The suction device refers to the device used to perform the airway suction task, which automatically adjusts the suction operation according to the preset parameter sequence, including adjusting parameters such as pneumatic speed and pneumatic negative pressure. The suction device controls the suction flow field in the airway in real time according to these parameters and makes real-time adjustments according to the feedback information to ensure the optimization of the airway cleaning effect. Feedback tracking adjustment means that the system monitors various physiological parameters and flow field states in the airway suction process in real time and timely adjusts the operation of the suction device to make the suction process more accurate and adaptable to the needs of the patient.

[0073] Furthermore, performing airway suction control and feedback tracking adjustment includes collecting user physiological indicators along with airway suction control and synchronously performing airway image acquisition to determine the suction state. Collecting user physiological indicators means that during the airway suction process, the physiological parameters of the patient, such as heart rate, blood oxygen saturation, respiratory rate, etc., are monitored in real time to evaluate the impact of airway suction on the patient's physiological state. Airway image acquisition is to obtain the image information inside the airway through image acquisition devices such as endoscopes or CT scans to monitor the cleaning effect and suction state of the airway in real time. These physiological indicators and image information provide a feedback basis for the suction device, enabling it to dynamically adjust the operation parameters during the suction process.

[0074] Furthermore, by analyzing the collected physiological data and airway imaging data, it is evaluated whether the current suction state meets the expected goal. If it is found that the suction effect is not ideal, the system will adjust the parameters of the suction device based on the feedback data for real-time optimization. For example, if a decrease in the patient's blood oxygen saturation is detected, the system may adjust the negative pressure or pneumatic speed of the suction device to reduce the suction intensity to prevent discomfort caused by over-suction. Through continuous feedback tracking and adjustment, it is ensured that the airway suction process is always carried out within a safe and effective range, thereby improving the treatment effect and reducing the occurrence of complications.

[0075] An airway suction control parameter optimization processing method provided by this application has the following technical effects: 1. By collecting airway images and performing three-dimensional reconstruction of the airway, combined with discrete surface element processing to construct the airway geometry. Through surface element processing for airway region division, targeted optimization decisions can be made for different airway region states. By constructing the airway geometry, the airway flow field optimization problem is converted into a mathematical optimization problem, that is, the flow field characteristics of the airway are converted into discrete numerical data, which is convenient for further optimization and adjustment of the flow field.

[0076] 2. According to the suction method, combined with the physiological state elements of the user, suction constraint conditions are set. By dynamically setting the suction conditions, the suction process can be adjusted in real time according to the specific situation of the patient, improving the personalization and adaptability of the treatment.

[0077] 3. Using a two-stage optimization method, based on the airway geometry and flow field state, through first-order surface element optimization and second-order inverse optimization, the parameter sequence of the entire suction cycle is determined. That is, first, the flow field state that can achieve the best suction effect is determined through optimization analysis, and then the corresponding suction control parameters are inversely deduced based on this flow field state. Under complex airway structures and flow field conditions, the best suction control strategy can be achieved through an optimization algorithm to ensure the efficiency and safety of airway cleaning. At the same time, through case-based evidence-guided training, the reliability and practical feasibility of the optimization process are further improved.

[0078] 4. By real-time collecting the user's physiological indicators and airway images, monitoring the suction state, and dynamically adjusting the suction control according to the feedback data. Precise control can be achieved during the suction process, enabling the suction operation to be optimized in a timely manner according to the patient's physiological response, thereby minimizing discomfort and complications to the greatest extent and improving the treatment effect.

[0079] Embodiment 2: Based on the same inventive concept as the airway suction control parameter optimization processing method in the foregoing embodiment, as Figure 2 shown, this application provides an airway suction control parameter optimization processing system, and the system includes: The building module 11 is used to collect airway images, determine airway aspiration tasks, and perform three-dimensional airway reconstruction. By performing discretized surface element processing, an airway geometry is constructed, where the vertices of the airway geometry correspond to the singularities of the surface elements. The condition introduction module 12 is used to introduce aspiration constraint conditions, where the aspiration constraint conditions include the aspiration method and user state elements. The optimization module 13 is used for the airway aspiration task. According to the aspiration constraint conditions, for the flow field aspiration state, perform first-order surface element optimization based on the airway geometry, and perform second-order inverse deduction optimization for airway aspiration parameters to determine the parameter sequence of the entire aspiration cycle, where optimization guidance is carried out through case evidence-based. The aspiration control module 14 is used to respond to the aspirator with the parameter sequence for airway aspiration control and feedback tracking adjustment.

[0080] Furthermore, the building module 11 includes: The division module is used to obtain the reconstructed airway, discretize the airway surface into grids according to the airway structure to determine the surface element grids; the setting module is used to set surface element singularities for the surface element grids, where the surface element grids and the surface element singularities are in one-to-one correspondence, and the surface element singularities represent the flow field state characteristics of the corresponding airway surface element grids; the mapping module is used to map the surface element grids and the surface element singularities as the surface element processing results.

[0081] Furthermore, the building module 11 includes: The sub-building module is used to construct the airway geometry based on the surface element processing results. Among them, the sub-building module also includes a construction method, including the following steps: for the airway aspiration task, locate the aspiration medium, where the aspiration medium is marked with medium characteristics and airway positions; traverse the surface element grids to determine the number of vertices; locate the key surface element grids based on the aspiration medium and set the first weight, where the weight is assigned based on the medium characteristics; construct the airway geometry with the number of vertices and the first weight.

[0082] Furthermore, the condition introduction module 12 includes: the aspiration method is open airway aspiration or closed airway aspiration; the mining module is used to mine the airway aspiration requirements under the characteristics of the method according to the aspiration method; the condition determination module is used to determine the first aspiration constraint condition according to the airway aspiration requirements.

[0083] Furthermore, the optimization module 13 includes: A training module, which is used to take double - order optimization as the underlying logic, determine sample data through case - based evidence, and drive the training optimization processor; An initial determination module, which is used to assist the optimization processor to determine a first initial complex for the airway geometry, where the determination is made based on the first initial attracting flow field of the singular points of each surface element; An iterative setting module, which is used to set the iterative operation mode, where at least the reflection - contraction - expansion - reconstruction mode is included; An iterative adjustment module, which is used to iteratively adjust the first initial complex in a randomly selected manner according to the iterative operation mode, and preferentially determine the target complex, where the target complex represents the flow field state of the airway attraction of each surface element grid and is the first attraction time node based on the entire attracting cycle.

[0084] Further, the iterative adjustment module includes: A priority determination module, which is used to identify the first weight identifier and determine the adjustment collision priority; An adjustment constraint module, which is used to perform iterative adjustment constraints according to the adjustment collision priority; where single - step iteration is performed based on the random finite - element adjustment of the vertices of the first initial complex. Wherein, before performing iterative adjustment, the following steps are further included: Limiting the geometric feasible region with the attracting constraint condition; Performing iterative adjustment limitation with the geometric feasible region.

[0085] Further, the optimization module 13 includes: A parameter determination module, which is used to determine airway attraction parameters, where the airway attraction parameters at least include aerodynamic parameters, attraction time limit, intubation position, and the aerodynamic parameters at least include aerodynamic velocity and aerodynamic negative pressure; A parameter inverse - deduction module, which is used to perform airway attraction parameter inverse - deduction for the target complex and determine the parameter sequence based on the attraction time limit. Wherein, if there is a parameter jump at the changing node of the parameter sequence, the following steps are further included: Performing parameter jump smoothing processing on the changing node.

[0086] Further, the attraction control module 14 includes: An acquisition module, which is used to collect user physiological indicators during airway attraction control and synchronously collect airway images to determine the attraction state; A feedback module, which is used to perform feedback adjustment management of airway attraction control according to the user physiological indicators and the attraction state.

[0087] Embodiment 3: Based on the same inventive concept as the airway internal attraction control parameter optimization processing method in Embodiment 1 above, the present application also provides an electronic device, including: at least one processor, and a memory communicatively connected to the at least one processor.

[0088] Among them, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of any one of the methods described in the above-mentioned Embodiment 1. As Figure 3 As shown, the bus architecture is represented by bus 300, and bus 300 may include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and a memory represented by memory 304 together. Bus 300 may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and thus will not be further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0089] Through the foregoing detailed description of a method for optimizing airway suction control parameters in this specification, those skilled in the art can clearly know a system, method, and device for optimizing airway suction control parameters in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0090] 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 obvious 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 these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An airway suction control parameter optimization processing system, characterized in that: The system comprises: A construction module is used to collect airway images, determine airway suction tasks, and perform airway three-dimensional reconstruction, and construct airway geometry by performing discretization surface element processing, wherein the vertices of the airway geometry correspond to the surface element singularities; A condition introduction module, used to introduce attraction constraint conditions, wherein the attraction constraint conditions include attraction mode and user status elements; An optimization module is used for performing first-order panel optimization based on the airway geometry and second-order inverse optimization on airway suction parameters for the airway suction task according to the suction constraint conditions and the flow field suction state, and determining the parameter sequence of the full suction cycle, wherein the optimization is guided by case-based evidence; The suction control module is used for performing airway suction control and feedback tracking adjustment in response to the parameter sequence of the suction device.

2. The airway suction control parameter optimization processing system according to claim 1, characterized in that: The building blocks include: A partitioning module is used to obtain the reconstructed airway, discretize the airway surface into grids according to the airway structure, and determine the facet grid; A setting module, used for setting a panel singularity for the panel grid, wherein the panel grid corresponds to the panel singularity one-to-one, and the panel singularity represents the flow field state characteristics of the corresponding airway panel grid; A mapping module is used to map the facet grid and the facet singular point as a facet processing result.

3. The airway suction control parameter optimization processing system according to claim 2, characterized in that: The building blocks include: A sub-construction module, used for constructing the airway geometry according to the facet processing result; The sub-construction module further includes a construction method, including the following steps: For the airway suction task, positioning a suction medium, wherein the suction medium is marked with medium characteristics and airway position; Traversing the panel grid to determine the number of vertices; Positioning a key facet grid based on the attraction medium, and setting a first weight, wherein the weighting is performed based on medium characteristics; The airway geometry is constructed using the number of vertices and the first weight.

4. The airway suction control parameter optimization processing system according to claim 1, characterized in that: The condition introduction module includes: The suction method is suction in an open airway or suction in a closed airway; A mining module for mining airway suction requirements under the characteristics of the suction mode according to the suction mode; The condition determination module is used to determine the first suction constraint condition according to the airway suction requirement.

5. The airway suction control parameter optimization processing system according to claim 1, characterized in that: The optimization module comprises: The training module is used to determine sample data through case-based evidence based on the dual-stage optimization as the underlying logic, and drive the training optimization processor; An initial determination module, used to assist the optimization processor in determining a first initial composite shape for the airway geometry, wherein the determination is performed based on a first initial suction flow field of each surface element singular point; An iteration setting module, used to set an iteration operation mode, which at least includes a reflection-contraction-expansion-reconstruction mode; The iterative adjustment module is used to iteratively adjust the first initial composite shape by random selection in the iterative operation mode, and determine the target composite shape by optimization, wherein the target composite shape represents the flow field state of airway suction of each facet grid, and is the first suction time node based on the full suction cycle.

6. The airway suction control parameter optimization processing system according to claim 5, characterized in that: The iterative adjustment module comprises: A priority determination module, used to identify the first weight identifier and determine and adjust the collision priority; An adjustment constraint module, used for iteratively adjusting constraints according to the adjustment collision priority; In which, a single-step iteration is performed based on random finite element adjustment of the vertices of the first initial composite shape, Before iterative adjustment, the following steps are also included: Using the attraction constraint condition, a geometrically feasible domain is limited; The geometric feasible domain is used to perform iterative adjustment and limitation.

7. The airway suction control parameter optimization processing system according to claim 5, characterized in that: The optimization module comprises: A parameter determination module, used to determine airway suction parameters, wherein the airway suction parameters at least include pneumatic parameters, suction time limit, and intubation position, and the pneumatic parameters at least include pneumatic speed and pneumatic negative pressure; A parameter inversion module, used for inverting airway suction parameters for the target complex shape, and determining a parameter sequence based on the suction time limit; If there is a parameter transition at the trending node of the parameter sequence, the method further includes the following steps: A parameter transition smoothing process is performed on the trend-changing node.

8. The airway suction control parameter optimization processing system according to claim 1, characterized in that: The attraction control module comprises: The acquisition module is used to collect the user's physiological indicators along with the airway suction control, and synchronously collect airway images to determine the suction state; The feedback module is used to perform feedback adjustment management of airway suction control according to the user's physiological indicators and the suction state.

9. A method for optimizing airway suction control parameters, characterized in that: The method is implemented by an airway suction control parameter optimization processing system according to any one of claims 1 to 8, comprising: Acquire airway images, determine airway suction tasks, and perform three-dimensional reconstruction of the airway, and construct airway geometry by performing discretization surface element processing, wherein the vertices of the airway geometry correspond to the surface element singularities; Introducing attraction constraints, wherein the attraction constraints include attraction methods and user status elements; For the airway suction task, according to the suction constraint conditions and the flow field suction state, a first-order facet optimization based on the airway geometry is performed, and a second-order inverse optimization is performed on the airway suction parameters to determine the parameter sequence of the entire suction cycle, wherein the optimization is guided by case-based evidence; The parameter sequence is responsive to the aspirator to perform airway aspiration control and feedback tracking adjustment.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the airway suction control parameter optimization processing system according to any one of claims 1 to 8 are implemented.

Images