Hemodialysis auxiliary nursing system and method

Abstract

The invention relates to the field of intelligent auxiliary nursing, and particularly discloses a hemodialysis auxiliary nursing system and method.The hemodialysis auxiliary nursing method comprises the steps that firstly, a temperature and humidity information collection module obtains humidity and temperature data in a dialysis area through sensing equipment; the blood pressure influence parameter module analyzes the influence of the data on the blood pressure of the patient to obtain blood pressure influence parameters, and then the dialysis influence parameter calculation module obtains dialysis influence parameters. Meanwhile, the comfort level parameter calculation module evaluates the influence of the environmental factors on the comfort level of the patient, and comfort level perception influence parameters are obtained. The proportion calculation module determines the environmental comfort influence proportion by analyzing the perceptual image array of the patient. Finally, the scheme generation module synthesizes all parameters and formulates an optimal auxiliary nursing scheme. According to the scheme, personalized and precise nursing scheme optimization is achieved, and the stability of the dialysis effect and the comfort degree of a patient are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent assisted nursing, and more specifically, to a hemodialysis assisted nursing system and method. Background Art

[0002] As a common kidney replacement therapy, hemodialysis is mainly for patients with renal failure. By means of dialysis equipment to simulate kidney function, through principles such as diffusion and convection, it removes the metabolic wastes accumulated in the patient's body, such as creatinine and urea nitrogen, as well as excess water, to maintain the stability of the body's internal environment. However, traditional nursing often ignores the influence of environmental factors such as temperature and humidity on dialysis effect and patient comfort, resulting in unstable nursing quality.

[0003] For this reason, the existing patent CN118762796A proposes an intelligent hemodialysis assisted nursing method and system based on dynamic environment perception. It uses sensing devices to collect arrays of humidity and temperature information at multiple sensing points in the dialysis area. By analyzing the influence of these information on the blood pressure of dialysis patients, it obtains blood pressure influence parameters and classifies them as dialysis influence parameters; at the same time, it conducts comfort influence analysis to obtain perceived comfort influence parameters. Then, it collects the array of patient perception images, analyzes and obtains the actual comfort influence parameters, and further calculates the environmental comfort influence ratio. Finally, it optimizes the assisted nursing plan by integrating the above parameters, determines the optimal temperature and humidity adjustment plan for the dialysis environment, thus solving the problems of traditional nursing ignoring environmental factors and individual differences and realizing personalized nursing optimization.

[0004] In the existing patent, the calculation of blood pressure influence parameters is based on the static input arrays of humidity and temperature information, without modeling the continuous changes in the time dimension. This method ignores the cumulative effect and lag influence of environmental parameter fluctuations (such as sudden temperature rise or slow temperature drop) on blood pressure, resulting in the inability to accurately capture the influence of dynamic changes on the patient's blood pressure. In addition, relying only on a simple regression model to learn feature associations makes it difficult to represent complex cross-modal spatio-temporal interaction mechanisms, such as the combined effect of a local high-temperature area and a neighboring high-humidity area on blood pressure. This limitation makes the prediction results show low robustness and accuracy in the face of a changing actual environment.

[0005] Therefore, an optimized hemodialysis assisted nursing plan is desired. Summary of the Invention

[0006] To solve the above technical problems, this application is proposed.

[0007] According to one aspect of this application, a hemodialysis assisted nursing system is provided, which includes:

[0008] A temperature and humidity information acquisition module for collecting an array of humidity information and an array of temperature information in the hemodialysis area through sensing devices;

[0009] A blood pressure influence parameter module, configured to perform an analysis of the influence of blood pressure on the humidity information array and the temperature information array based on a dialysis patient to obtain a blood pressure influence parameter, wherein the blood pressure influence parameter module is configured to: perform a temperature-humidity spatio-temporal interaction chain reasoning analysis based on time domain features on the humidity information array and the temperature information array to obtain the blood pressure influence parameter;

[0010] A dialysis influence parameter calculation module, configured to obtain a dialysis influence parameter based on the blood pressure influence parameter;

[0011] A comfort parameter calculation module, configured to perform an analysis of the influence of comfort on the humidity information array and the temperature information array based on a dialysis patient to obtain a comfort perception influence parameter;

[0012] A ratio calculation module, configured to obtain a perception image array of the dialysis patient and perform an analysis of the environmental comfort on the perception image array to obtain an environmental comfort influence ratio;

[0013] A scheme generation module, configured to obtain an optimal assisted care scheme based on the dialysis influence parameter, the comfort perception influence parameter, and the environmental comfort influence ratio.

[0014] According to another aspect of the present application, there is provided a method for assisting hemodialysis care, including:

[0015] Collecting a humidity information array and a temperature information array in a hemodialysis area through a sensing device;

[0016] Performing an analysis of the influence of blood pressure on the humidity information array and the temperature information array based on a dialysis patient to obtain a blood pressure influence parameter, including: performing a temperature-humidity spatio-temporal interaction chain reasoning analysis based on time domain features on the humidity information array and the temperature information array to obtain the blood pressure influence parameter;

[0017] Obtaining a dialysis influence parameter based on the blood pressure influence parameter;

[0018] Performing an analysis of the influence of comfort on the humidity information array and the temperature information array based on a dialysis patient to obtain a comfort perception influence parameter;

[0019] Obtaining a perception image array of the dialysis patient and performing an analysis of the environmental comfort on the perception image array to obtain an environmental comfort influence ratio;

[0020] Obtaining an optimal assisted care scheme based on the dialysis influence parameter, the comfort perception influence parameter, and the environmental comfort influence ratio.

[0021] Compared with the prior art, a hemodialysis assisted nursing system and method provided by the present application first uses a sensing device in the temperature and humidity information acquisition module to obtain humidity and temperature data in the dialysis area. The blood pressure influence parameter module analyzes the influence of these data on the patient's blood pressure to obtain blood pressure influence parameters, and then the dialysis influence parameter calculation module obtains dialysis influence parameters. At the same time, the comfort parameter calculation module evaluates the influence of these environmental factors on the patient's comfort to obtain a comfort perception influence parameter. The ratio calculation module then determines the environmental comfort influence ratio by analyzing the patient's perception image array. Finally, the scheme generation module synthesizes all parameters to formulate an optimal assisted nursing scheme. This scheme realizes the optimization of personalized and precise nursing schemes, improving the stability of dialysis effect and the comfort of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present application will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0023] Figure 1 It is a block diagram of a hemodialysis assisted nursing system according to an embodiment of the present application.

[0024] Figure 2 It is a block diagram of the blood pressure influence parameter module in the hemodialysis assisted nursing system according to an embodiment of the present application.

[0025] Figure 3 It is a block diagram of the temperature-humidity spatio-temporal interaction unit in the hemodialysis assisted nursing system according to an embodiment of the present application.

[0026] Figure 4 It is a flowchart of a hemodialysis assisted nursing method according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0028] It should be noted that in this application, all actions of acquiring signals, information, or data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining authorization from the owner of the corresponding device.

[0029] In view of the problems in the above-mentioned background technology, this application proposes a hemodialysis assisted nursing system. Figure 1 It is a block diagram of a hemodialysis assisted nursing system according to an embodiment of this application. Specifically, as Figure 1 shown, the hemodialysis assisted nursing system 100 according to an embodiment of this application includes: a temperature and humidity information acquisition module 110, configured to acquire a humidity information array and a temperature information array in the hemodialysis area through a sensing device; a blood pressure influence parameter module 120, configured to perform a blood pressure influence analysis on the humidity information array and the temperature information array based on a hemodialysis patient to obtain a blood pressure influence parameter; a dialysis influence parameter calculation module 130, configured to obtain a dialysis influence parameter based on the blood pressure influence parameter; a comfort parameter calculation module 140, configured to perform a comfort influence analysis on the humidity information array and the temperature information array based on a hemodialysis patient to obtain a comfort perception influence parameter; a ratio calculation module 150, configured to acquire a perception image array of the hemodialysis patient and perform an environmental comfort analysis on it to obtain an environmental comfort influence ratio; a scheme generation module 160, configured to obtain an optimal assisted nursing scheme based on the dialysis influence parameter, the comfort perception influence parameter, and the environmental comfort influence ratio.

[0030] In an embodiment of this application, the temperature and humidity information acquisition module 110 is configured to acquire a humidity information array and a temperature information array in the hemodialysis area through a sensing device. In particular, the sensing device includes a sensor array configured at multiple sensing points around the dialysis position. It should be understood that the humidity information array is a set of humidity data at multiple sensing points around the dialysis position, and the temperature information array is a set of temperature data at multiple sensing points around the dialysis position. The temperature and humidity in the dialysis environment are in dynamic change, and relying only on the data of a single sensing point cannot accurately reflect the overall environmental condition. In an actual dialysis scenario, there are differences in the feelings and reactions of different parts of the patient's body to temperature and humidity. The layout of multiple sensing points can collect data from multiple dimensions, covering the temperature and humidity conditions of various areas around the patient, so as to obtain more comprehensive and accurate environmental information.

[0031] The specific implementation process is as follows: In the hemodialysis area, multiple sensing points will be carefully set around the dialysis position. The layout of these sensing points is scientifically planned and distributed at key positions such as near the patient's head and limbs. At each sensing point, a sensor array composed of a high-precision temperature sensor and a humidity sensor is configured. These sensors are like sensitive "environmental antennas" that can capture the temperature and humidity changes at the location in real time and accurately.

[0032] When dialysis begins, the sensor array enters the working state and continuously collects temperature and humidity data at each sensing point. The temperature data collected at numerous sensing points converge to form a temperature information array, which details the temperature distribution in different areas of the dialysis environment, such as whether the temperature in the patient's head area is stable and whether there are differences in temperature near the limbs. Similarly, the humidity data sets of each sensing point constitute a humidity information array, providing detailed information on humidity changes in the dialysis environment, such as whether the humidity fluctuates within an appropriate range and whether there are areas with excessively high or low humidity.

[0033] These humidity information arrays and temperature information arrays collected in real time are quickly transmitted to the subsequent data processing system. They provide essential basic data for key processes such as blood pressure impact analysis and comfort impact analysis. Through this multi-point sensing layout and precise data collection method, the system can sensitively capture minor changes in the dialysis environment, laying a data foundation for accurately adjusting the temperature and humidity in the dialysis environment later, improving the dialysis effect and comfort of patients, and ensuring that the entire hemodialysis assistance nursing process is more scientific and effective.

[0034] In the embodiment of the present application, the blood pressure impact parameter module 120 is used to perform a blood pressure impact analysis on the humidity information array and the temperature information array based on dialysis patients to obtain blood pressure impact parameters. Specifically, in the embodiment of the present application, the blood pressure impact parameter module is used to: perform a temperature-humidity spatio-temporal interaction chain reasoning analysis based on time domain features on the humidity information array and the temperature information array to obtain the blood pressure impact parameters. Correspondingly, environmental factors (such as temperature and humidity) can affect the dialysis effect, and blood pressure is an important indicator reflecting the dialysis effect and the patient's physical condition. Changes in temperature and humidity can affect the body's physiological functions. Dialysis patients are more vulnerable and more sensitive to environmental changes. Humidity may affect the body's water metabolism, and temperature can affect the constriction and dilation of blood vessels, thereby affecting blood pressure. Different temperature-humidity combinations have different effects on the patient's blood pressure. Therefore, it is necessary to analyze the impact of the humidity information array and the temperature information array on the blood pressure of dialysis patients.

[0035] Therefore, in view of the technical problems in the above-mentioned background art, the technical concept of this application is to first perform dynamic time-series modeling on each sensing point in the temperature and humidity information array to capture the trend change characteristics of the temperature and humidity at each sensing point in the time dimension (such as the cumulative effect of a slow temperature drop or the lag response of a sudden humidity increase). On this basis, a local interactive chain reasoning mechanism is constructed to model the cross-modal coupling relationship between temperature and humidity parameters in the spatio-temporal intertwined feature space (for example, the dynamic effect of the synergistic effect between a high-temperature area and a neighboring high-humidity area on vasoconstriction), and the non-linear action law between local areas is mined layer by layer through an interactive encoder with chain transmission. Finally, the spatio-temporal collaborative interactive coding vector is decoded into a comprehensive parameter reflecting the blood pressure fluctuation risk. This solution effectively solves the problems of missing trend response and ignoring local interaction in traditional static modeling by capturing the spatio-temporal evolution law of temperature and humidity parameters and their non-linear collaborative mechanism, enabling the blood pressure impact prediction to reflect the lag effect and regional synergy in the dynamic fluctuation of environmental parameters, thereby enhancing the adaptability of the auxiliary nursing plan to complex environmental changes.

[0036] Figure 2 The block diagram of the blood pressure impact parameter module in the hemodialysis auxiliary nursing system according to an embodiment of the present application. Specifically, as Figure 2 shown, the blood pressure impact parameter module 120 includes: a humidity information time-series encoding unit 121 for performing time-series analysis on each humidity row vector in the humidity information array to obtain a set of single-point humidity time-series correlation feature encoding vectors; a temperature information time-series encoding unit 122 for performing time-series analysis on each temperature row vector in the temperature information array to obtain a set of single-point temperature time-series correlation feature encoding vectors; a temperature-humidity spatio-temporal interaction unit 123 for performing temperature-humidity spatio-temporal interactive chain reasoning on the set of single-point humidity time-series correlation feature encoding vectors and the set of single-point temperature time-series correlation feature encoding vectors to obtain a temperature-humidity spatio-temporal collaborative interactive coding vector; and a temperature-humidity spatio-temporal interaction feature decoding unit 124 for performing feature decoding on the temperature-humidity spatio-temporal collaborative interactive coding vector to obtain the blood pressure impact parameter.

[0037] Specifically, in the embodiment of the present application, the humidity information time series encoding unit 121 is configured to: perform time series analysis based on a bidirectional recurrent network on each humidity row vector in the humidity information array to obtain a set of single-point humidity time series correlation feature encoding vectors. It should be understood that considering the significant time series correlation of the impact of dynamic changes in environmental humidity on the physiological state of patients. Dialysis treatment usually lasts for several hours, and the humidity fluctuations in the area where the patient is located (such as local humidity sudden increase / slow decrease caused by equipment heat dissipation, body fluid evaporation, or air conditioner operation) will have a cumulative effect or lag impact on vascular tone through skin microcirculation and the respiratory system. For example, the continuous decrease in humidity at a certain sensing point in the first half of dialysis may exacerbate vasoconstriction through skin water loss, and this process requires a two-way analysis combining historical trends and potential future changes. Traditional unidirectional time series modeling can only capture the correlation in a single direction (such as from the past to the current), and cannot characterize the evolution law of humidity parameters on the complete time axis (such as the predictability of current humidity changes on subsequent trends), resulting in difficulty in predicting the dynamic association between humidity parameters and blood pressure fluctuations in real-time monitoring scenarios. Based on this, the present application performs time series analysis based on a bidirectional recurrent network on each humidity row vector in the humidity information array to obtain a set of single-point humidity time series correlation feature encoding vectors. Specifically, through a bidirectional network structure, the context dependence of humidity parameters is extracted from both the forward (from the past to the current) and backward (from the future to the current) dimensions simultaneously. Specifically, the forward layer captures the driving mechanism of historical humidity changes on the current state (such as the cumulative effect of continuous three-hour humidity slow decrease on vasoconstriction), and the backward layer learns the potential impact of the current humidity value on future trends (such as a sudden increase in current humidity may indicate an accelerated subsequent evaporation rate). By fusing the features in both directions through a bidirectional gating mechanism, the single-point humidity time series correlation feature encoding vector of each monitoring point is finally generated, completely characterizing the dynamic evolution law of humidity parameters in the time dimension and its potential causal chain with blood pressure fluctuations.

[0038] Specifically, in the embodiment of the present application, the temperature information time series encoding unit 122 is configured to: perform time series analysis based on a bidirectional recurrent network on each temperature row vector in the temperature information array to obtain a set of single-point temperature time series correlation feature encoding vectors. Correspondingly, considering that the dynamic change of the ambient temperature has significant time series dependence on the regulation of the patient's cardiovascular system. Temperature fluctuations in the dialysis area (such as local temperature sudden rise / slow decline caused by equipment heat generation, air-conditioning regulation, or patient body surface heat dissipation) will affect the vasomotor state of the peripheral blood vessels through heat radiation and conduction mechanisms, and then cause delayed or cumulative abnormalities in blood pressure. For example, the continuous rise in temperature at a certain sensing point during the middle stage of dialysis may cause blood vessel dilation, but this physiological effect may not appear until several minutes after the temperature reaches the peak, and its influence degree is closely related to the temperature change rate and historical trend. Traditional unidirectional time series modeling can only extract unidirectional evolution features of temperature parameters (such as linear correlation from the past to the present), but cannot capture the bidirectional correlation of temperature parameters on the complete time axis (such as the predictive nature of the current temperature value on future trends), resulting in limited analytical ability for the complex causal chain between temperature dynamic changes and blood pressure responses. Based on this, in the technical solution of the present application, perform time series analysis based on a bidirectional recurrent network on each temperature row vector in the temperature information array to obtain the non-linear evolution law of temperature parameters in the time dimension, and obtain a set of single-point temperature time series correlation feature encoding vectors.

[0039] Specifically, the temperature-humidity spatio-temporal interaction unit 123 is configured to perform temperature-humidity spatio-temporal interaction chain reasoning on the set of single-point humidity time-series correlation feature encoding vectors and the set of single-point temperature time-series correlation feature encoding vectors to obtain temperature-humidity spatio-temporal collaborative interaction encoding vectors. Furthermore, considering that the influence of environmental temperature and humidity parameters on the patient's blood pressure is not an isolated action in the time or space dimension, but a complex process of spatio-temporal dynamic coupling. The temperature and humidity distributions at different monitoring points within the dialysis area have spatial heterogeneity (such as higher temperature in the area near the dialysis equipment and changing humidity gradient on the patient's body surface), and the temporal fluctuations of local temperature and humidity parameters (such as a gradual increase in temperature in a certain area accompanied by a sudden drop in humidity in the adjacent area) will generate cross-modal collaborative effects through heat conduction and evaporation effects. For example, a high-temperature area accelerates the evaporation of moisture on the patient's body surface, resulting in a decrease in local humidity, while a high-humidity environment may inhibit the heat dissipation efficiency and further exacerbate the stimulation of temperature on blood vessels. Existing technologies use static or single-modal analysis and cannot capture such cross-temporal and cross-modal non-linear coupling mechanisms, leading to significant biases in the assessment of blood pressure fluctuation risks. Traditional global interaction models are difficult to analyze the causal association network hidden in the temperature and humidity fields because they ignore the chain effect transmission between local regions. Based on this, the present application performs temperature-humidity spatio-temporal interaction chain reasoning on the set of single-point humidity time-series correlation feature encoding vectors and the set of single-point temperature time-series correlation feature encoding vectors to obtain temperature-humidity spatio-temporal collaborative interaction encoding vectors.

[0040] Figure 3 It is a block diagram of the temperature-humidity spatio-temporal interaction unit in the hemodialysis-assisted nursing system according to an embodiment of the present application. Specifically, as Figure 3 shown, the temperature-humidity spatio-temporal interaction unit 123 includes: a temperature-humidity single-point time-series feature interaction sub-unit 1231, configured to perform single-point time-series feature interaction on each group of corresponding single-point humidity time-series correlation feature encoding vectors and single-point temperature time-series correlation feature encoding vectors in the set of single-point humidity time-series correlation feature encoding vectors and the set of single-point temperature time-series correlation feature encoding vectors to obtain a set of temperature-humidity local time-series feature interaction encoding vectors; a temperature-humidity single-point time-series feature cross-modal collaborative sub-unit 1232, configured to perform cross-modal chain attention spatio-temporal collaborative encoding on the set of temperature-humidity local time-series feature interaction encoding vectors to obtain the temperature-humidity spatio-temporal collaborative interaction encoding vectors.

[0041] Specifically, the temperature-humidity single-point time-series feature interaction sub-unit 1231 is configured to perform single-point time-series feature interaction on each group of corresponding single-point humidity time-series correlation feature encoding vectors and single-point temperature time-series correlation feature encoding vectors in the set of single-point humidity time-series correlation feature encoding vectors and the set of single-point temperature time-series correlation feature encoding vectors to obtain a set of temperature-humidity local time-series feature interaction encoding vectors. This process is represented by the formula:

[0042] X = {x1, x2,..., x i ,..., x n}

[0043] Y = {y1, y2,..., y i ,..., y n}

[0044]

[0045] where X is a set of single-point humidity time-series correlation feature encoding vectors, Y is a set of single-point temperature time-series correlation feature encoding vectors, x1, x2, x i and x n are the 1st, 2nd, ith, and nth single-point humidity time-series correlation feature encoding vectors in the set of single-point humidity time-series correlation feature encoding vectors respectively, y1, y2, y i and y n are the 1st, 2nd, ith, and nth single-point temperature time-series correlation feature encoding vectors in the set of single-point temperature time-series correlation feature encoding vectors respectively, n is the number of vectors in X and Y, and X and Y have the same length, ⊙ is dot product by position, is addition by position, is subtraction by position, concat{·; ·; ·} is a concatenation operation, W i is the ith local time-series feature interaction weight matrix in the set of local time-series feature interaction weight matrices, b i is the ith local time-series feature interaction bias vector in the set of local time-series feature interaction bias vectors, v i is the ith temperature-humidity local time-series feature interaction encoding vector in the set of temperature-humidity local time-series feature interaction encoding vectors.

[0046] It should be understood that the co-evolution of the temperature and humidity parameters in the microenvironment where the patient is located in the time dimension is inseparably related to physiological regulation. The increase in temperature at a certain sensing point within the dialysis area may accelerate the evaporation of body surface moisture, resulting in a decrease in local humidity, and the humidity change may in turn affect the heat exchange efficiency in the opposite direction, forming a dynamically coupled temperature-humidity action chain. If the temperature and humidity parameters are analyzed independently or simply superimposed, the non-linear cooperative mechanism between the two within the same spatio-temporal unit is ignored (such as the superimposed effect of high temperature and low humidity may exacerbate the blood vessel constriction rate). Especially in the middle and late stages of dialysis, the change in the patient's body fluid balance state makes the temporal interaction of local temperature and humidity parameters (such as the slow decrease in humidity following a sudden increase in temperature) have a compound impact on blood pressure fluctuations. Therefore, in this application, the single-point humidity temporal correlation feature coding vector and the single-point temperature temporal correlation feature coding vector corresponding to each group are respectively subjected to single-point temporal feature interaction to obtain a set of temperature-humidity local temporal feature interaction coding vectors reflecting the dynamic coupling relationship between temperature and humidity within the local spatio-temporal unit.

[0047] Specifically, in the embodiment of this application, the temperature-humidity single-point temporal feature cross-modal cooperative subunit includes: a chained attention weight calculation secondary subunit, configured to determine the cross-modal interaction chained attention weights of each temperature-humidity local temporal feature interaction coding vector based on the feature distribution characteristics of each temperature-humidity local temporal feature interaction coding vector in the set of temperature-humidity local temporal feature interaction coding vectors to obtain a set of temperature-humidity local temporal feature cross-modal interaction chained attention weights; a temperature-humidity interaction feature modulation secondary subunit, configured to perform weighted modulation on the set of temperature-humidity local temporal feature interaction coding vectors based on the set of temperature-humidity local temporal feature cross-modal interaction chained attention weights to obtain a set of temperature-humidity local temporal feature interaction modulation coding vectors; and a temperature-humidity interaction feature temporal reasoning secondary subunit, configured to input the set of temperature-humidity local temporal feature interaction modulation coding vectors into a temporal reasoning device based on a forward LSTM model to obtain the temperature-humidity spatio-temporal cooperative interaction coding vector.

[0048] Specifically, the chained attention weight calculation secondary subunit is configured to determine the cross-modal interaction chained attention weights of each temperature-humidity local temporal feature interaction coding vector based on the feature distribution characteristics of each temperature-humidity local temporal feature interaction coding vector in the set of temperature-humidity local temporal feature interaction coding vectors to obtain a set of temperature-humidity local temporal feature cross-modal interaction chained attention weights. This process is represented by the formula:

[0049]

[0050] where, v iis the i-th temperature-humidity local temporal feature interaction coding vector in the set of temperature-humidity local temporal feature interaction coding vectors, v i,j is the i j-th eigenvalue in v 2 ||·|| i is for calculating the square of the Euclidean norm of the vector, L is the number of eigenvalues in v i is the i-th temperature-humidity local temporal feature cross-modal interaction chained attention weight in the set of temperature-humidity local temporal feature cross-modal interaction chained attention weights.

[0051] Correspondingly, due to the significant differences in the impact of temperature and humidity interactions in different space-time on blood pressure fluctuations. For example, the co-variation of temperature and humidity in the trunk area of the patient may directly act on the cardiovascular system through the core body temperature regulation mechanism, while the temperature and humidity interaction in the foot area may have a lagging effect due to microcirculation differences. If equal weights are assigned to all local interactions, the dominant role of the interaction characteristics in key physiologically sensitive areas (such as the synergistic effect of sudden changes in temperature and adjacent humidity in the carotid artery area) in the overall blood pressure fluctuation is ignored. Based on this, in the technical solution of this application, based on the characteristic distribution characteristics of each temperature-humidity local temporal feature interaction coding vector, the cross-modal interaction chained attention weights of each temperature-humidity local temporal feature interaction coding vector are determined to obtain a set of temperature-humidity local temporal feature cross-modal interaction chained attention weights. In this way, the attention to interaction units with strong physiological relevance (such as the dangerous signal with continuous high variance in the body surface temperature and humidity interaction of the patient) can be strengthened, and the interference of non-critical areas or noise (such as the stable fluctuation in the equipment heat dissipation area far from the patient) can be suppressed.

[0052] More specifically, in the embodiment of this application, the temperature-humidity interaction feature modulation secondary subunit is used for:

[0053] Performing weight correction based on interaction rule deconstruction on the set of temperature-humidity local temporal feature cross-modal interaction chained attention weights to obtain a set of temperature-humidity local temporal feature cross-modal interaction chained attention corrected weights. This process is expressed by the formula:

[0054]

[0055] a′ i =(ω a ×ξ i +ω b ×ζ i )a i

[0056] where x iis the i-th single-point humidity time-series correlation feature encoding vector in the set of single-point humidity time-series correlation feature encoding vectors, y i is the i-th single-point temperature time-series correlation feature encoding vector in the set of single-point temperature time-series correlation feature encoding vectors, a i is the i-th temperature-humidity local time-series feature cross-modal interaction chain attention weight in the set of temperature-humidity local time-series feature cross-modal interaction chain attention weights, α i is the i-th temperature-humidity local time-series feature linear displacement intensity in the set of temperature-humidity local time-series feature linear displacement intensities, β i is the i-th temperature-humidity local time-series feature displacement difference intensity in the set of temperature-humidity local time-series feature displacement difference intensities, γ i is the i-th temperature-humidity local time-series feature oscillation coupling intensity in the set of temperature-humidity local time-series feature oscillation coupling intensities, ln is the logarithmic function value with the natural constant e as the base, ξ i is the i-th temperature-humidity local time-series feature period dimension dynamic correction factor in the set of temperature-humidity local time-series feature period dimension dynamic correction factors, ζ i is the i-th temperature-humidity local time-series feature period phase auxiliary modulation term in the set of temperature-humidity local time-series feature period phase auxiliary modulation terms, ω a and ω b are ξ i and ζ i corresponding weight coefficients respectively, a′ i is the i-th temperature-humidity local time-series feature cross-modal interaction chain attention correction weight in the set of temperature-humidity local time-series feature cross-modal interaction chain attention correction weights;

[0057] Based on the set of the temperature-humidity local time-series feature cross-modal interaction chain attention correction weights, perform weighted modulation on the set of the temperature-humidity local time-series feature interaction encoding vectors to obtain the set of the temperature-humidity local time-series feature interaction modulation encoding vectors, and this process is expressed by the formula as:

[0058] I i =a′ i ·v i

[0059] I={I1,I2,...,I i ,...,I n}

[0060] where, v i is the i-th temperature-humidity local time-series feature interaction encoding vector in the set of temperature-humidity local time-series feature interaction encoding vectors, a′ iis the i-th temperature-humidity local temporal feature cross-modal interaction chained attention correction weight in the set of temperature-humidity local temporal feature cross-modal interaction chained attention correction weights, I1, I2, I i and I n are the 1st, 2nd, i-th, and n-th temperature-humidity local temporal feature interaction modulation coding vectors in the set of temperature-humidity local temporal feature interaction modulation coding vectors respectively, and I is the set of temperature-humidity local temporal feature interaction modulation coding vectors.

[0061] Specifically, when calculating each temperature-humidity local temporal feature interaction coding vector, the interaction feature between the corresponding single-point humidity temporal correlation feature coding vector and the single-point temperature temporal correlation feature coding vector needs to be introduced, such as x i ⊙y i , and so on. These operations essentially correspond to different interaction rules, thus forming differential regional constraint couplings in the interaction space.

[0062] To enhance the influence of the rule dynamic gain on the temperature-humidity local temporal feature cross-modal interaction chained attention weight, the weight needs to be corrected based on the spatial efficiency deconstruction of the interaction rules. Specifically, and can be regarded as linear displacement effects (i.e., the gradient direction is consistent with the spatial interaction direction), while x i ⊙y i corresponds to the oscillatory coupling response (the gradient direction is orthogonal to the spatial interaction direction). By analyzing the statistics of different action vectors (such as γ i =||x i ⊙y i || 2 ), it can be found that the oscillatory coupling response will induce regional periodic dynamic features in the direction of the linear displacement effect, and the corresponding temperature-humidity local temporal feature period dimension dynamic correction factor can be expressed as:

[0063]

[0064] where, α i +β i as a linear localization representation, indicating that the intensity of the oscillatory coupling response increases with the expansion of the linear displacement effect on the logarithmic scale.

[0065] At the same time, the oscillatory coupling response will also cause a phase shift of the linear displacement effect, thereby generating a temperature-humidity local temporal feature period phase auxiliary modulation term:

[0066] Finally, the original cross-modal interaction chain attention weight a of the temperature-humidity local temporal features is corrected by the weighted sum of the above two items i : a' i =(ω a ×ξ i +ω b ×ζ i )a i

[0067] By distinguishing the action mechanisms of different interaction rules within the spatial constraint rule framework, this method significantly improves the modeling accuracy of regional constraint coupling correlation in the interaction space, thereby optimizing the calculation robustness of the cross-modal interaction chain attention weight of the temperature-humidity local temporal features.

[0068] After that, based on the set of corrected weights of the cross-modal interaction chain attention of the temperature-humidity local temporal features, the set of temperature-humidity local temporal feature interaction encoding vectors is weighted and modulated to obtain the set of temperature-humidity local temporal feature interaction modulation encoding vectors. For each spatio-temporal interaction encoding vector, the feature amplitude is scaled according to its attention correction weight value: high-weight vectors (such as the interaction mode of continuous high temperature in the torso area and slow decrease in humidity) enhance their contribution through feature channel amplification, while low-weight vectors (such as the stable and unchanged temperature-humidity interaction in the distal area of the device) reduce their interference through feature suppression. During the modulation process, the attention correction weight and the channel dimension of the interaction encoding vector are element-wise multiplied to retain the spatial distribution pattern of key interaction features (such as the abnormal waveform of sudden increase in patient's back temperature accompanied by sudden decrease in humidity), while filtering out the noise patterns weakly correlated with blood pressure fluctuations (such as the periodic temperature-humidity oscillation around the fixed bracket of the dialysis chair). The modulated feature set not only maintains the spatio-temporal topological structure but also highlights the interaction hot regions with high physiological relevance.

[0069] Specifically, the temperature-humidity interaction feature temporal inference secondary subunit is used to input the set of temperature-humidity local temporal feature interaction modulation encoding vectors into a temporal inference engine based on a forward LSTM model to obtain the temperature-humidity spatio-temporal collaborative interaction encoding vector, and this process is represented by the formula:

[0070]

[0071] where I is the set of temperature-humidity local temporal feature interaction modulation encoding vectors, is the forward LSTM encoding, and v f is the temperature-humidity spatio-temporal collaborative interaction encoding vector.

[0072] Finally, input the set of the temperature-humidity local temporal feature interaction modulation coding vectors into a temporal reasoning engine based on a forward LSTM model to obtain the temperature-humidity spatio-temporal collaborative interaction coding vectors. That is, when the memory cells of the LSTM process the modulation coding vectors one by one, new features (such as abnormal pulse signals of the temperature-humidity interaction in the dorsal hand area) are screened by the input gate, historical irrelevant information (such as the early interaction features of the stable torso) is eliminated by the forget gate, and the output gate controls the contribution degree of the current state to the global reasoning. As the sequence progresses, the model gradually accumulates spatio-temporal memories of cross-region interactions (such as the conduction path of rising foot temperature → calf humidity response → thigh vasoconstriction), and finally fuses in the hidden state to form a high-order coding vector representing the collaborative effect of temperature and humidity during the entire treatment cycle.

[0073] Specifically, the temperature-humidity spatio-temporal interaction feature decoding unit 124 is configured to perform feature decoding on the temperature-humidity spatio-temporal collaborative interaction coding vectors to obtain the blood pressure influence parameters. Specifically, in the embodiment of the present application, the temperature-humidity spatio-temporal interaction feature decoding unit is configured to: use a blood pressure influence analyzer based on a decoder to perform feature decoding on the temperature-humidity spatio-temporal collaborative interaction coding vectors to obtain the blood pressure influence parameters. That is, the temperature-humidity spatio-temporal collaborative interaction coding vectors are obtained through complex spatio-temporal interaction chain reasoning analysis, and their forms and features are for facilitating the model to capture and process the spatio-temporal information of temperature and humidity, but they are not intuitive for directly representing the blood pressure influence parameters. It is necessary to convert them into a parameter form that can directly reflect the blood pressure influence through a decoder, so as to realize the mapping from the complex coding space to the blood pressure influence parameter space with practical significance. Specifically, the blood pressure influence analyzer based on the decoder can deeply mine the blood pressure-related information hidden in the temperature-humidity spatio-temporal collaborative interaction coding vectors. The decoder can learn the potential relationships between different features in the coding vectors and the blood pressure influence, and present these potential relationships in the form of blood pressure influence parameters through the decoding process, thereby revealing the specific influence mechanism of the temperature and humidity in the dialysis environment on the patient's blood pressure.

[0074] Use a blood pressure influence analyzer based on a decoder to perform feature decoding on the coding vectors. This blood pressure influence analyzer is specially trained, and its training data comes from a large amount of historical hemodialysis data. During the training process, the analyzer learns the internal connection between the temperature-humidity spatio-temporal collaborative interaction coding vectors and the blood pressure influence parameters. When the current temperature-humidity spatio-temporal collaborative interaction coding vectors are input, the analyzer will perform decoding operations on the vectors according to the patterns and rules learned before. It will extract the feature information related to the blood pressure influence from the vectors, and through the internal calculation logic, convert these features into specific blood pressure influence parameters.

[0075] For example, the analyzer may, based on the changing trends of temperature at different times and positions in the coding vector, as well as the interaction relationship with humidity, and in combination with the experience in historical data, determine the degree of impact that the current environment may have on the patient's blood pressure, and finally output a quantified blood pressure impact parameter. This parameter can intuitively reflect the potential impact of temperature and humidity factors in the current dialysis environment on the patient's blood pressure, providing an important basis for subsequent evaluation of dialysis impact and formulation of nursing plans.

[0076] In the embodiment of the present application, the dialysis impact parameter calculation module 130 is used to obtain a dialysis impact parameter based on the blood pressure impact parameter. It should be understood that although the blood pressure impact parameter can reflect the effect of the temperature and humidity environment on the blood pressure of dialysis patients, the dialysis process is a complex physiological process affected by various factors comprehensively, and blood pressure is only one of the key aspects. Merely focusing on the blood pressure impact is not sufficient to comprehensively measure the effectiveness and safety of the entire dialysis process. By further obtaining a dialysis impact parameter based on the blood pressure impact parameter, the role of the blood pressure factor in the entire dialysis process can be comprehensively considered, combined with other potentially influential factors, to more comprehensively and accurately evaluate the overall impact of environmental factors on the dialysis effect.

[0077] Specifically as follows: First, screen and collect from a large amount of historical hemodialysis data to obtain a sample humidity information array set and a sample temperature information array set. These data cover the environmental temperature and humidity conditions in many different dialysis scenarios, providing a rich variety of samples for subsequent analysis. At the same time, in combination with the corresponding blood pressure test data, according to the parameters of blood pressure changes therein, carefully label to obtain a sample blood pressure impact parameter set, which details the specific quantified data of the impact on the blood pressure of dialysis patients in different temperature and humidity environments.

[0078] Next, use these collected and labeled data and adopt machine learning algorithms such as neural networks or random forests to train the environmental blood pressure impact analysis channel. During the training process, the algorithm continuously learns the complex internal relationship between humidity, temperature and blood pressure changes. After repeated iteration and optimization with a large amount of data, the environmental blood pressure impact analysis channel is enabled to have the ability to accurately predict the potential impact of environmental factors on blood pressure. Then, input the humidity information array and temperature information array collected in real time in the current dialysis environment into the trained environmental blood pressure impact analysis channel, and through the operation and analysis of this channel, obtain the blood pressure impact parameters under the current environmental conditions, which quantitatively describe the potential impact degree of the current environment on the patient's blood pressure.

[0079] To further obtain dialysis impact parameters, it is also necessary to collect a set of sample dialysis impact parameters from historical hemodialysis data again. These parameter sets are obtained through in-depth analysis of historical dialysis data and contain key indicators such as dialysis clearance rate and electrolyte balance, which reflect the specific impacts of different dialysis environmental conditions on dialysis effects. Then, the previously obtained set of sample blood pressure impact parameters is combined with the collected set of sample dialysis impact parameters to construct a dialysis impact classification channel. This channel is like an intelligent classifier that can accurately classify different blood pressure impact parameters into corresponding dialysis effect categories, helping medical staff clearly identify which dialysis impact parameters are significantly affected by environmental factors under different environmental conditions.

[0080] Finally, the current blood pressure impact parameters obtained through the environmental blood pressure impact analysis channel are input into the dialysis impact classification channel. Based on the previously learned rules and models, the dialysis impact classification channel classifies the input blood pressure impact parameters and finally outputs dialysis impact parameters. These dialysis impact parameters accurately evaluate the specific impacts on dialysis effects under the current environmental conditions, providing a scientific and reliable basis for formulating and optimizing auxiliary nursing plans in the follow-up, helping medical staff adjust nursing strategies according to actual situations, and improving the treatment effect of hemodialysis and the comfort of patients.

[0081] In the embodiment of the present application, the comfort parameter calculation module 140 is used to perform a comfort impact analysis on the humidity information array and the temperature information array based on dialysis patients to obtain comfort perception impact parameters. Correspondingly, since traditional hemodialysis care often ignores the impact of environmental factors on patients' comfort, and the comfort of patients during dialysis is crucial. Humidity and temperature are important environmental factors affecting comfort. Different patients have different sensitivities to changes in temperature and humidity, and changes in temperature and humidity will bring different comfort experiences to patients. To make up for the deficiencies of traditional care and fully consider individual differences, it is necessary to analyze the impact of temperature and humidity on comfort to obtain comfort perception impact parameters, so as to deeply understand the relationship between environmental factors and comfort.

[0082] To implement this process, the first step is to collect a large number of data records of patients in the hemodialysis environment. These records cover detailed environmental data of different dialysis periods and different patients, and sample humidity information array sets and sample temperature information array sets are selected from them to comprehensively reflect the diverse environmental temperature and humidity conditions during dialysis. At the same time, collect the comfort inquiry data of patients during the same period. These data are the intuitive subjective feedback of patients on the comfort of the current dialysis environment. The environmental data and the comfort inquiry data are matched one by one, and according to specific annotation rules, a set of sample comfort perception impact parameters is obtained through annotation, so that the data set contains both environmental characteristic information and associated comfort impact information, providing solid data support for subsequent analysis.

[0083] After completing data collection and annotation, machine learning algorithms such as support vector machines, decision trees, or deep learning models are used to train the perception comfort impact analysis channel. In the training stage, the algorithm deeply mines and learns from the sample humidity information array set, the sample temperature information array set, and the sample comfort perception impact parameter set, and analyzes the intricate relationship between humidity, temperature, and patient comfort. Through repeated training and verification with a large amount of sample data, the model parameters are continuously optimized to improve the prediction accuracy and generalization ability of the perception comfort impact analysis channel, ensuring that it can accurately identify the potential impact of temperature and humidity on patient comfort under different environmental conditions and adapt to various dialysis environments and patient individual differences.

[0084] When the perception comfort impact analysis channel is trained and reaches the expected performance, it enters the actual application stage. The real-time collected humidity information array and temperature information array are input into the trained perception comfort impact analysis channel. Based on the previously learned relationship model between environmental temperature and humidity and comfort, this channel automatically calculates and analyzes the input data. Through a series of complex calculation processes, it outputs the comfort perception impact parameters corresponding to the current environmental temperature and humidity. These parameters accurately describe the specific impact degree of the current dialysis environment on patient comfort in a quantitative form. For example, the higher the value, the greater the positive impact of the environment on patient comfort, and vice versa.

[0085] In the embodiment of the present application, the ratio calculation module 150 is used to obtain the perception image array of the dialysis patient and perform environmental comfort analysis on it to obtain the environmental comfort impact ratio. It should be understood that the comfort analysis based only on humidity and temperature information has limitations and is difficult to comprehensively reflect the true comfort status of patients. The comfort of patients is affected by a variety of factors. In addition to environmental temperature and humidity, it also includes their own psychological state, health status, etc. The perception image can capture external features such as the patient's expression, body posture, and skin condition, which can intuitively reflect their comfort. Combining the comfort perception impact parameters predicted based on environmental temperature and humidity with the actual comfort impact parameters obtained from image analysis can more comprehensively and accurately evaluate the proportion of environmental factors in the overall comfort of patients and make up for the deficiencies of a single analysis method.

[0086] The specific implementation process is as follows: At multiple perception points in the hemodialysis area, devices such as cameras or image sensors are deployed to collect the perception image array of dialysis patients. The settings of these perception points are carefully planned and distributed in positions that can comprehensively capture the patient's state, ensuring that the obtained perception image array can cover various visual features of the patient during dialysis, such as expression, body posture, skin condition, and blood vessel color. These real-time image data provide intuitive external visible clues for subsequent analysis of the patient's comfort.

[0087] Next, we extract the patient comfort analysis data from the historical data, and based on this data, we collect a set of sample perception images. This set covers the image states of patients at different comfort levels and is rich in diversity. For each sample perception image, we carefully annotate it in combination with the corresponding patient comfort situation, so as to obtain the set of parameters affecting the sample's actual comfort. This step closely links the patient's subjective comfort perception with the objective performance in the image, providing a key data foundation for subsequent training models.

[0088] Afterwards, the actual comfort impact analysis channel was trained with the help of a convolutional neural network (CNN) using a set of sample perception images and a set of sample actual comfort impact parameters. As a powerful deep learning model, CNN has unique advantages in the field of image recognition and analysis. Through repeated training of a large amount of sample data, CNN can automatically extract and learn key features in the image, and gradually master the complex mapping relationship between image features and actual comfort impact factors. After sufficient training and optimization, the actual comfort impact analysis channel has the ability to accurately identify the factors affecting the patient's actual comfort.

[0089] After the model training is completed, the trained actual comfort impact analysis channel is used to identify and analyze the currently acquired perception image array. This channel processes multiple perception images in the perception image array one by one to generate multiple actual comfort impact analysis results. Based on these analysis results, through a specific calculation method, various factors are comprehensively considered, and finally the actual comfort impact parameter of the current dialysis patient is calculated. This parameter is an objective assessment of the patient's actual comfort status in the current dialysis environment, reflecting the actual level of the patient's physiological and psychological comfort.

[0090] At the same time, the comfort impact analysis of the humidity information array and the temperature information array has been carried out before, and the comfort perception impact parameters have been obtained. At this time, by calculating the ratio of the comfort perception impact parameter to the actual comfort impact parameter, the environmental comfort impact ratio can be obtained. This ratio is a key indicator to measure the impact of the dialysis environment on the patient's comfort. When the ratio is small, it means that the patient's comfort is relatively less affected by environmental factors, and is more likely to be determined by other factors such as psychological state or health status; on the contrary, if the ratio is large, it means that environmental factors are the main reason affecting the patient's comfort. In the subsequent optimization of the nursing plan, it is necessary to focus on adjusting the dialysis environment, such as adjusting the temperature and humidity, to improve the patient's dialysis comfort and optimize the entire nursing process.

[0091] In the embodiment of the present application, the solution generation module 160 is configured to obtain an optimal assisted nursing solution based on the dialysis influence parameter, the comfort perception influence parameter, and the environmental comfort influence ratio. Correspondingly, in hemodialysis care, a single parameter cannot comprehensively reflect the patient's needs and dialysis status. The dialysis influence parameter reflects the effect of the environment on the dialysis effect, the comfort perception influence parameter reflects the influence of temperature and humidity on the patient's subjective feelings, and the environmental comfort influence ratio measures the proportion of environmental factors in the overall comfort. By integrating these parameters, comprehensive information can be obtained from multiple aspects such as dialysis effect, patient comfort, and environmental impact, providing a basis for formulating a more accurate and effective nursing plan and avoiding the one-sidedness of making decisions based on a single factor.

[0092] The specific implementation process is as follows: First, an assisted nursing function is constructed based on the above three key parameters. The function expression is:

[0093]

[0094] where ANF represents the nursing fitness, which is used to measure the quality of the nursing plan; ω1 and ω2 are the dialysis weight and the comfort weight respectively, and the sum of the two is 1. Their role is to balance the importance of dialysis effect and patient comfort in the nursing plan; AFF n is the dialysis influence parameter of the environmental characteristic information array after nursing according to the assisted nursing plan, and AFF b is the currently obtained dialysis influence parameter; K s is the environmental comfort influence ratio; CFF n is the comfort perception influence parameter of the environmental characteristic information array after nursing according to the assisted nursing plan, and CFF b is the currently obtained comfort perception influence parameter. This function organically combines the three parameters and aims to maximize the nursing fitness, providing a quantitative basis for subsequent optimization of the nursing plan. In particular, after constructing the assisted nursing plan space and generating a specific plan, based on the temperature and humidity adjustment settings in the plan, an analysis and classification of the blood pressure influence on dialysis patients are carried out, and finally this parameter is obtained. Taking the generated first assisted nursing plan as an example, the plan includes a first temperature adjustment plan and a first humidity adjustment plan. Based on this, relevant analysis is carried out on dialysis patients, and the parameter used to measure the dialysis effect is the "dialysis influence parameter of the environmental characteristic information array after nursing according to the assisted nursing plan" (in this case, it is the first dialysis influence parameter). It is a quantitative index that can intuitively show the influence of the environment on dialysis under the current nursing plan.

[0095] Next, obtain the temperature adjustment range and humidity adjustment range of the hemodialysis environment, and construct an auxiliary nursing plan space based on these two ranges. This space contains all possible combinations of temperature and humidity adjustments, and these combinations form the set of nursing plans available for selection in the system optimization process. Randomly generate a first auxiliary nursing plan within the auxiliary nursing plan space. This plan includes a first temperature adjustment plan and a first humidity adjustment plan. Analyze and classify the blood pressure impact on dialysis patients according to this plan to obtain the first dialysis impact parameter. At the same time, conduct a comfort impact analysis to obtain the first comfort perception impact parameter. Then, substitute the first dialysis impact parameter, the first comfort perception impact parameter, and the known environmental comfort impact ratio into the auxiliary nursing function to calculate the first nursing fitness, which reflects the comprehensive performance of this plan in balancing dialysis effects and patient comfort.

[0096] Subsequently, make appropriate adjustments to the first temperature adjustment plan and the first humidity adjustment plan to generate a second auxiliary nursing plan. Repeat the above analysis and calculation process, that is, conduct a blood pressure impact analysis and a comfort impact analysis on the second auxiliary nursing plan, substitute the corresponding parameters into the auxiliary nursing function after obtaining them, and calculate the second nursing fitness. Then, compare the first nursing fitness and the second nursing fitness. If the second nursing fitness is greater than the first nursing fitness, directly retain the second auxiliary nursing plan; if the second nursing fitness is not greater than the first nursing fitness, calculate the ratio of the two, and combine it with the environmental comfort impact ratio to calculate the retention probability. For example, multiply the ratio by the environmental comfort impact ratio to obtain the retention probability, and then compare a random number generated within 0 - 1 with the retention probability to decide whether to retain the first dialysis impact parameter and the corresponding first auxiliary nursing plan, or the second dialysis impact parameter and the second auxiliary nursing plan. This method not only considers the fitness difference of the plan itself but also takes into account the importance of environmental comfort to the patient experience, enhancing the scientific nature and overall situation of the optimization process.

[0097] Finally, based on the retained auxiliary nursing plan, continue to make adjustments and iterative optimizations within the auxiliary nursing plan space according to the auxiliary nursing function. Continuously change the temperature adjustment plan and the humidity adjustment plan, recalculate the nursing fitness, and continue this process until the nursing fitness no longer improves and reaches a convergence state. At this time, the plan with the maximum nursing fitness output is the optimal auxiliary nursing plan, which includes the optimal temperature adjustment plan and the optimal humidity adjustment plan in the dialysis environment, can provide the best auxiliary nursing service for patients, and effectively improve the dialysis effect and patient comfort. In particular, since this step is not the focus of this application, no specific description is provided. For details, please refer to the existing patent CN118762796A.

[0098] In summary, the hemodialysis assisted care system 100 according to the embodiments of the present application is elucidated. First, the temperature and humidity information acquisition module uses sensing devices to obtain the humidity and temperature data in the dialysis area. The blood pressure influence parameter module analyzes the influence of these data on the patient's blood pressure to obtain blood pressure influence parameters, and then the dialysis influence parameter calculation module obtains dialysis influence parameters. At the same time, the comfort parameter calculation module evaluates the influence of these environmental factors on the patient's comfort to obtain comfort perception influence parameters. The ratio calculation module determines the environmental comfort influence ratio by analyzing the patient's perception image array. Finally, the solution generation module synthesizes all parameters to formulate the best assisted care solution. This solution realizes the optimization of personalized and precise care solutions, improving the stability of dialysis effects and the comfort of patients.

[0099] As described above, the hemodialysis assisted care system 100 according to the embodiments of the present application can be implemented in various wireless terminals, such as a server with a hemodialysis assisted care algorithm. In a possible implementation manner, the hemodialysis assisted care system 100 according to the embodiments of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the hemodialysis assisted care system 100 can be a software module in the operating system of the wireless terminal, or can be an application program developed for the wireless terminal; of course, the hemodialysis assisted care system 100 can also be one of the numerous hardware modules of the wireless terminal.

[0100] Alternatively, in another example, the hemodialysis assisted care system 100 and the wireless terminal can also be separate devices, and the hemodialysis assisted care system 100 can be connected to the wireless terminal through a wired and / or wireless network and transmit interaction information in accordance with a predefined data format.

[0101] Figure 4 It is a flowchart of the hemodialysis assisted care method according to the embodiments of the present application. As Figure 4As shown, the hemodialysis assisted nursing method according to an embodiment of the present application includes: S110, collecting a humidity information array and a temperature information array in the hemodialysis area through a sensing device; S120, performing an analysis of the influence on the blood pressure of a dialysis patient on the humidity information array and the temperature information array to obtain a blood pressure influence parameter, including: performing a temperature-humidity spatio-temporal interaction chain reasoning analysis based on time domain features on the humidity information array and the temperature information array to obtain the blood pressure influence parameter; S130, obtaining a dialysis influence parameter based on the blood pressure influence parameter; S140, performing an analysis of the influence on the comfort of a dialysis patient on the humidity information array and the temperature information array to obtain a comfort perception influence parameter; S150, obtaining a perception image array of the dialysis patient and performing an environmental comfort analysis on it to obtain an environmental comfort influence ratio; S160, obtaining an optimal assisted nursing plan based on the dialysis influence parameter, the comfort perception influence parameter, and the environmental comfort influence ratio.

[0102] Here, those skilled in the art can understand that the specific operations of each step in the above hemodialysis assisted nursing method have been introduced in detail in the description of the Figures 1 to 3 hemodialysis assisted nursing system above, and therefore, the repeated description thereof will be omitted.

[0103] The above specific embodiments have further elaborated on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A hemodialysis assisted nursing system, characterized in that, Including: A temperature and humidity information acquisition module for collecting a humidity information array and a temperature information array within a hemodialysis area through a sensing device; A blood pressure impact parameter module for performing a blood pressure impact analysis on the humidity information array and the temperature information array based on a hemodialysis patient to obtain a blood pressure impact parameter, wherein the blood pressure impact parameter module is used to: perform a temperature-humidity spatio-temporal interaction chain reasoning analysis on the humidity information array and the temperature information array based on time-domain features to obtain the blood pressure impact parameter; A dialysis impact parameter calculation module for obtaining a dialysis impact parameter based on the blood pressure impact parameter; A comfort parameter calculation module for performing a comfort impact analysis on the humidity information array and the temperature information array based on a hemodialysis patient to obtain a comfort perception impact parameter; A ratio calculation module for obtaining a perception image array of the hemodialysis patient and performing an environmental comfort analysis on it to obtain an environmental comfort impact ratio; A solution generation module for obtaining an optimal auxiliary care solution based on the dialysis impact parameter, the comfort perception impact parameter, and the environmental comfort impact ratio.

2. The hemodialysis assistance nursing system according to claim 1, wherein The blood pressure impact parameter module includes: A humidity information time series encoding unit for performing a time series analysis on each humidity row vector in the humidity information array to obtain a set of single-point humidity time series correlation feature encoding vectors; A temperature information time series encoding unit for performing a time series analysis on each temperature row vector in the temperature information array to obtain a set of single-point temperature time series correlation feature encoding vectors; A temperature-humidity spatio-temporal interaction unit for performing a temperature-humidity spatio-temporal interaction chain reasoning on the set of single-point humidity time series correlation feature encoding vectors and the set of single-point temperature time series correlation feature encoding vectors to obtain a temperature-humidity spatio-temporal collaborative interaction encoding vector; A temperature-humidity spatio-temporal interaction feature decoding unit for performing feature decoding on the temperature-humidity spatio-temporal collaborative interaction encoding vector to obtain the blood pressure impact parameter.

3. The hemodialysis assistance nursing system according to claim 2, wherein The humidity information time series encoding unit is used to: perform a time series analysis on each humidity row vector in the humidity information array based on a bidirectional recurrent network to obtain the set of single-point humidity time series correlation feature encoding vectors.

4. The hemodialysis-assisted nursing system according to claim 3, wherein The temperature information time series encoding unit is used to: perform the time series analysis based on the bidirectional recurrent network on each temperature row vector in the temperature information array to obtain the set of single-point temperature time series correlation feature encoding vectors.

5. The hemodialysis assisted care system according to claim 2, characterized in that, The temperature-humidity spatio-temporal interaction unit includes: A temperature and humidity single-point time series feature interaction sub-unit for respectively performing single-point time series feature interactions on each group of corresponding single-point humidity time series correlation feature encoding vectors and single-point temperature time series correlation feature encoding vectors in the set of single-point humidity time series correlation feature encoding vectors and the set of single-point temperature time series correlation feature encoding vectors to obtain a set of temperature-humidity local time series feature interaction encoding vectors; The temperature-humidity single-point time-series feature cross-modal collaborative subunit is used to perform cross-modal chained attention spatio-temporal collaborative encoding on the set of temperature-humidity local time-series feature interaction encoding vectors to obtain the temperature-humidity spatio-temporal collaborative interaction encoding vectors.

6. The hemodialysis assistance nursing system according to claim 5, wherein, The temperature-humidity single-point time-series feature cross-modal collaborative subunit includes: The chained attention weight calculation secondary subunit is used to determine the cross-modal interaction chained attention weights of each temperature-humidity local time-series feature interaction encoding vector based on the feature distribution characteristics of each temperature-humidity local time-series feature interaction encoding vector in the set of temperature-humidity local time-series feature interaction encoding vectors to obtain a set of temperature-humidity local time-series feature cross-modal interaction chained attention weights; The temperature-humidity interaction feature modulation secondary subunit is used to perform weighted modulation on the set of temperature-humidity local time-series feature interaction encoding vectors based on the set of temperature-humidity local time-series feature cross-modal interaction chained attention weights to obtain a set of temperature-humidity local time-series feature interaction modulation encoding vectors; The temperature-humidity interaction feature time-series reasoning secondary subunit is used to input the set of temperature-humidity local time-series feature interaction modulation encoding vectors into a time-series reasoner based on a forward LSTM model to obtain the temperature-humidity spatio-temporal collaborative interaction encoding vectors.

7. The hemodialysis assisted nursing system according to claim 6, characterized in that, The temperature-humidity interaction feature modulation secondary subunit is used to: Perform weight correction based on interaction rule deconstruction on the set of temperature-humidity local time-series feature cross-modal interaction chained attention weights to obtain a set of temperature-humidity local time-series feature cross-modal interaction chained attention corrected weights; Perform weighted modulation on the set of temperature-humidity local time-series feature interaction encoding vectors based on the set of temperature-humidity local time-series feature cross-modal interaction chained attention corrected weights to obtain the set of temperature-humidity local time-series feature interaction modulation encoding vectors.

8. The hemodialysis assistance nursing system according to claim 7, characterized in that, The temperature-humidity spatio-temporal interaction feature decoding unit is used to: Use a blood pressure impact analyzer based on a decoder to perform feature decoding on the temperature-humidity spatio-temporal collaborative interaction encoding vectors to obtain the blood pressure impact parameters.

9. A blood dialysis assisted nursing method, characterized in that, It includes: Collect a humidity information array and a temperature information array in the hemodialysis area through a sensing device; Perform blood pressure impact analysis on the humidity information array and the temperature information array based on hemodialysis patients to obtain blood pressure impact parameters, including: Perform temperature-humidity spatio-temporal interaction chained reasoning analysis based on time-domain features on the humidity information array and the temperature information array to obtain the blood pressure impact parameters; Obtain dialysis impact parameters based on the blood pressure impact parameters; Perform comfort impact analysis on the humidity information array and the temperature information array based on hemodialysis patients to obtain comfort perception impact parameters; Obtain the perception image array of the hemodialysis patient and perform environmental comfort analysis on it to obtain the environmental comfort impact ratio; Obtain the optimal assisted care plan based on the dialysis impact parameters, the comfort perception impact parameters, and the environmental comfort impact ratio.

Images