Nanoscale sleep-aiding substance targeted delivery method and device based on individual metabolic characteristics

Abstract

The invention relates to the technical field of sleep aiding, in particular to a nanoscale sleep aiding substance targeted delivery method and device based on individual metabolic characteristics. The method includes: receiving a metabolic feature set extracted from exhaled breath of a user; inputting the metabolic feature set into a sleep recognition model, and when a recognition result of sleep disorder output by the sleep recognition model is received, screening key features from the metabolic feature set based on the feature relation graph and generating a key feature list; generating a sleep-aiding substance proportion based on the key feature list, and controlling a sleep-aiding substance blending module to blend sleep-aiding substances based on the sleep-aiding substance proportion; a current user image of the user is obtained, delivery parameters are determined based on the current user image, when it is monitored that the user inhales, the delivery device is controlled to spray out the sleep aiding substance according to the delivery parameters, and the delivery parameters comprise the delivery angle and the delivery dosage. According to the application, sleep-aiding substance differential delivery can be carried out according to different individual metabolic characteristics.

Description

Technical Field

[0001] This application relates to the technical field of sleep aids, and in particular to a method and device for targeted delivery of nano-scale sleep aid substances based on individual metabolic characteristics. Background Art

[0002] In modern society, sleep disorders have become a common health problem, and external sleep aids have become a solution.

[0003] Related technologies achieve sleep aid through oral medications or spray devices. The spray device releases liquid or gaseous sleep aid substances through a nozzle. However, both of these methods adopt a fixed formula and a population average dose mode, ignoring the differences in the demand for sleep aid substances caused by different individual metabolic characteristics, and ultimately resulting in sub-optimal sleep aid effects. Summary of the Invention

[0004] To solve the problem that the prior art cannot perform differential delivery of sleep aid substances according to different individual metabolic characteristics, this application provides a method and device for targeted delivery of nano-scale sleep aid substances based on individual metabolic characteristics.

[0005] In a first aspect, this application provides a method for targeted delivery of nano-scale sleep aid substances based on individual metabolic characteristics, adopting the following technical solution: A method for targeted delivery of nano-scale sleep aid substances based on individual metabolic characteristics, comprising: Receiving a metabolic feature set extracted from the exhaled gas of a user; Inputting the metabolic feature set into a sleep recognition model. When receiving an identification result of sleep disorder output by the sleep recognition model, screening key features from the metabolic feature set based on a feature relationship graph and generating a key feature list; Generating a sleep aid substance formulation based on the key feature list, and controlling a sleep aid substance preparation module to prepare a sleep aid substance based on the sleep aid substance formulation; Obtaining the current user image of the user, determining delivery parameters based on the current user image, and when it is monitored that the user inhales, controlling a delivery device to spray the sleep aid substance according to the delivery parameters, where the delivery parameters include a delivery angle and a delivery dose.

[0006] By adopting the above technical solution, extracting the metabolic feature set of the user's exhaled gas and inputting it into the sleep recognition model, sleep disorders can be accurately identified. Based on the feature relationship graph, key features are screened to generate a list, realizing the localization of the core intervention target from the root of the metabolic network. According to the key feature list and the preset mapping relationship, a personalized sleep aid substance ratio is generated to solve the problem that the traditional fixed formula cannot respond to individual metabolic differences. Using the user's current image to construct a three-dimensional model to determine the delivery angle and dose, combined with the inhalation trigger mechanism, the nano-level sleep aid substance reaches the target area at a precise angle and compensatory dose, improving the delivery efficiency and bioavailability. Through the personalized ratio driven by metabolic features and the precise delivery synchronized with the respiratory cycle, the present application significantly enhances the pertinence and effectiveness of the sleep aid effect, reducing substance loss and side effects.

[0007] In a preferred example, the present application can be further configured as: The method further includes: Obtaining historical exhalation data and extracting a historical metabolic feature set from the historical exhalation data; Analyzing the causal relationship between every two features in the historical metabolic feature set, where the causal relationship includes direct causal relationship and indirect causal relationship; Calculating the causal strength between every two features with the causal relationship, where the causal strength includes direct causal strength and indirect causal strength; Constructing the feature relationship graph based on the causal relationship and the causal strength.

[0008] By adopting the above technical solution, collecting historical exhalation data and extracting the metabolic feature set provides a data basis for analyzing the causal relationship between features. Analyzing the direct and indirect causal relationships between features can reveal the interaction paths of features in the metabolic network. Calculating the causal strength to quantify the degree of feature influence converts the causal relationship from qualitative description to quantitative analysis. Finally, the constructed feature relationship graph presents the causal association and strength of metabolic features in a structured form.

[0009] In a preferred example, the present application can be further configured as: The screening of key features from the metabolic feature set based on the feature relationship graph and generating a key feature list includes: Determining the degree of influence of each feature in the metabolic feature set on the presence of the sleep disorder as the first index; Based on the feature relationship graph, determining the primary features from the metabolic feature set as the key features, where the primary features represent the features of the superior nodes that do not have direct connections to the corresponding nodes in the feature relationship graph; Based on the feature relationship graph, taking the features that have a direct causal relationship with the target primary feature as secondary features, and calculating the second index of the target primary feature based on the direct causal index between the secondary features and the target primary feature, where the target primary feature is any one of the primary features; Based on the characteristic relationship graph, the characteristics that have an indirect causal relationship with the target primary characteristic are used as the tertiary characteristics, and the third index of the target primary characteristic is calculated based on the indirect causal index between the tertiary characteristics and the target primary characteristic; Based on the first index, the second index, and the third index, calculate the key index of the target primary characteristic; Arrange each primary characteristic in descending order according to the key index to obtain the key characteristic list.

[0010] By adopting the above technical solution, calculate the direct influence degree (the first index) of each characteristic on sleep disorder to clarify the basic role of a single characteristic; locate the primary characteristics without upstream nodes based on the characteristic relationship graph to lock the root key characteristics of the metabolic network; combine the directly causally associated characteristics (secondary characteristics) and indirectly causally associated characteristics (tertiary characteristics) of the primary characteristics, calculate the second index and the third index respectively, and comprehensively measure the conduction effect of direct and indirect influences; finally, calculate the key index by multi-index weighting and sort it to generate a key characteristic list focusing on the core intervention targets, so that the selected key characteristics can not only reflect the direct inducement of sleep disorder but also reflect the global influence of the metabolic network.

[0011] In a preferred example, the present application can be further configured as: generating the sleep aid substance ratio based on the key characteristic list, including: Extract the mapping relationship between the metabolic characteristics and the sleep aid substance ratio, and the mapping relationship includes the mapping relationship between the standard metabolic characteristics and the standard sleep aid substance ratio; Compare the target key characteristic with the standard metabolic characteristics, determine the adjustment method of each sleep aid substance corresponding to the target key characteristic based on the comparison result and the mapping relationship, and combine the target key characteristic and the adjustment method of a sleep aid substance into an adjustment vector to obtain a number of adjustment vectors corresponding to the target key characteristic, where the target key characteristic is any key characteristic in the key characteristic list; Divide the adjustment vectors corresponding to all the key characteristics in the key characteristic list into multiple adjustment groups according to the type of sleep aid substance, and determine the adjustment polarity of each adjustment group, where the adjustment polarity includes co-directional adjustment and reverse adjustment; Based on the key characteristic list and the adjustment polarity, determine the target adjustment method of the sleep aid substance corresponding to each adjustment group, and adjust the standard sleep aid substance ratio based on the target adjustment method of each adjustment group to obtain the sleep aid substance ratio.

[0012] By adopting the above technical solutions, a standard mapping relationship between metabolic characteristics and sleep aid substances is established, providing a benchmark rule for personalized proportioning; the key characteristics are compared with the standard characteristics to generate an adjustment vector, realizing an accurate mapping from metabolic abnormalities to substance adjustments; grouping by substance type and determining the adjustment polarity to solve the adjustment conflicts of multiple characteristics on the same substance; determining the target adjustment method based on the polarity and key index, dynamically balancing the co-directional or reverse adjustment requirements, ensuring that the proportioning not only responds to individual metabolic differences but also avoids conflicts in the interactions between substances.

[0013] In a preferred example of the present application, it can be further configured as: taking any adjustment group as the target adjustment group, and taking any adjustment vector in the target adjustment group as the target adjustment vector; Determining the target adjustment method of the sleep aid substance corresponding to the target adjustment group based on the key characteristic list and the adjustment polarity, including: When the adjustment polarity of the target adjustment group is the co-directional adjustment, calculating an adjustment index based on the key index of the key characteristics in the target adjustment vector and the adjustment method of the sleep aid substance; determining, from the target adjustment group, an adjustment vector with the largest adjustment index as the target adjustment method of the sleep aid substance corresponding to the target adjustment group; When the adjustment polarity of the target adjustment group is the reverse adjustment, calculating an adjustment index based on the key index of the key characteristics in the target adjustment vector and the adjustment method of the sleep aid substance; determining the first adjustment vector with the largest adjustment index and the second adjustment vector with the smallest adjustment index from the target adjustment group, and synthesizing the first adjustment vector and the second adjustment vector to obtain the target adjustment method of the sleep aid substance corresponding to the target adjustment group.

[0014] By adopting the above technical solutions, during co-directional adjustment, the adjustment index is calculated based on the key index and the adjustment method, and the adjustment vector with the largest index is selected as the target method to ensure that the dominant adjustment requirements of the core characteristics are implemented first; during reverse adjustment, by determining the vectors with the largest and smallest adjustment indexes and comprehensively balancing, the invalidation of the proportioning caused by conflicting adjustments is avoided.

[0015] In a preferred example of the present application, it can be further configured as: the determining the delivery parameters based on the current user image includes: Performing three-dimensional modeling based on the current user image, and identifying the target delivery area of the user based on the three-dimensional modeling; Determining the relative position relationship between the delivery device and the target delivery area, and determining the delivery angle based on the relative position relationship; Determining the delivery distance based on the relative position relationship, and calculating the delivery dose based on the delivery distance and the delivery mapping relationship, where the delivery mapping relationship is the mapping relationship between the delivery distance and the loss degree of the sleep aid substance.

[0016] By adopting the above technical solution, the delivery angle is calculated based on the relative position between the device and the target area, so that the nanoparticle ejection path is directly aligned with the target area, avoiding non-targeted loss; the dose is dynamically adjusted according to the delivery distance and loss mapping relationship to compensate for the material loss during long-distance transmission, significantly improving the delivery efficiency and bioavailability, and reducing the attenuation of the intervention effect caused by distance deviation or angle deviation.

[0017] In a second aspect, the present application provides a nanoscale sleep aid substance targeted delivery device based on individual metabolic characteristics, adopting the following technical solution: A nanoscale sleep aid substance targeted delivery device based on individual metabolic characteristics, comprising: a sleep aid substance preparation module, a delivery device, and an electronic device; The sleep aid substance preparation module is configured to receive a preparation instruction containing the proportion of the sleep aid substance sent by the electronic device, and prepare the sleep aid substance based on the preparation instruction; The delivery device, connected to the sleep aid substance preparation module, is configured to receive a delivery instruction containing delivery parameters sent by the electronic device, and deliver the sleep aid substance to the user based on the delivery instruction; The electronic device is configured to execute the nanoscale sleep aid substance targeted delivery method based on individual metabolic characteristics as described in any item of the first aspect.

[0018] In a preferred example, the present application can be further configured as: the device further comprises: a pressure sensor and a gas sensor; The pressure sensor is configured to monitor the breathing state of the user, and the breathing state includes inhalation and exhalation; The gas sensor is configured to capture the exhaled gas of the user and extract a metabolic feature set and send it to the electronic device when the pressure sensor monitors the user's exhalation.

[0019] In a preferred example, the present application can be further configured as: the electronic device includes: One or more processors; A memory; At least one application program, wherein at least one application program is stored in the memory and configured to be executed by at least one processor, and the at least one application program is configured to: execute the nanoscale sleep aid substance targeted delivery method based on individual metabolic characteristics as described in any item of the first aspect.

[0020] In summary, the present application includes the following beneficial technical effects: By extracting the metabolic feature set of the user's exhaled gas and inputting it into the sleep recognition model, this application can accurately identify sleep disorders, screen key features based on the feature relationship graph to generate a list, and achieve the localization of core intervention targets from the root of the metabolic network; generate personalized sleep aid substance ratios according to the key feature list and the preset mapping relationship to solve the problem that traditional fixed formulas cannot respond to individual metabolic differences; use the user's current image to construct a three-dimensional model to determine the delivery angle and dose, and combine with the inhalation trigger mechanism to make the nano-level sleep aid substances reach the target area directly at a precise angle and compensatory dose, improving the delivery efficiency and bioavailability. Through the personalized ratio driven by metabolic features and the precise delivery synchronized with the respiratory cycle, this application significantly enhances the pertinence and effectiveness of the sleep aid effect, reducing substance loss and side effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 FIG. is a schematic structural diagram of a nano-level sleep aid substance targeted delivery device based on individual metabolic characteristics provided by an embodiment of the present application; Figure 2 FIG. is a schematic flowchart of a nano-level sleep aid substance targeted delivery method based on individual metabolic characteristics provided by an embodiment of the present application; Figure 3 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The following will further describe the present application in detail with reference to the attached Figure 1 to the attached Figure 3 drawings.

[0023] This specific embodiment is only an interpretation of the present application and does not limit the present application. Those skilled in the art can make modifications without creative contributions to this embodiment after reading this specification, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art without making creative efforts based on the embodiments of the present application belong to the scope of protection of the present application.

[0025] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0026] It should be noted that in the optional embodiments of the present application, for relevant data such as object information, when the embodiments in the present application are applied to specific products or technologies, object permission or consent is required, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions. That is to say, if the embodiments in the present application involve data related to an object, it needs to be obtained under the authorization and consent of the object, the authorization and consent of relevant departments, and compliance with relevant laws, regulations, and standards of the country and region. In the embodiments, if personal information is involved, the acquisition of all personal information requires the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained, and the embodiments also need to be implemented under the authorization and consent of the object.

[0027] An embodiment of the present application provides a nanoscale sleep aid substance targeted delivery device based on individual metabolic characteristics, such as Figure 1 shown. The device includes: a sleep aid substance preparation module, a delivery device, a pressure sensor, a gas sensor, and an electronic device. The sleep aid substance preparation module, the delivery device, the pressure sensor, and the gas sensor can be integrated on a device housing, and the electronic device can be connected to it in a wired or wireless manner.

[0028] Specifically, the pressure sensor is used to monitor the user's breathing state, and the breathing state includes inhalation and exhalation. The gas sensor is used to capture the user's exhaled gas and extract a metabolic feature set and send it to the electronic device when the pressure sensor monitors the user's exhalation. The electronic device analyzes the metabolic feature set to obtain the proportion of the sleep aid substance and generates a preparation instruction. The sleep aid substance preparation module is used to receive the preparation instruction sent by the electronic device and prepare the sleep aid substance based on the preparation instruction. When the pressure sensor monitors the user's inhalation, the electronic device generates a delivery instruction to the delivery device. The delivery device is connected to the sleep aid substance preparation module and is used to receive the delivery instruction sent by the electronic device and deliver the sleep aid substance to the user.

[0029] An embodiment of the present application provides a nanoscale sleep aid substance targeted delivery method based on individual metabolic characteristics, such as Figure 2 shown. In the method provided in the embodiments of the present application, it is executed by an electronic device, and the electronic device can be a server or a terminal device. Among them, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected through wired or wireless communication methods. The embodiments of the present application do not limit this. The method includes step S201-step S204, where: S201. Receive the metabolic feature set extracted from the user's exhaled gas.

[0030] Specifically, a gas sampling probe is provided on the gas sensor. When the pressure sensor detects the user's exhalation, the gas sampling probe collects the user's exhaled gas. The gas sensor can be a gas chromatography-mass spectrometry (GC-MS) sensor, which integrates a miniaturized GC-MS module (detection limit 0.1 ppb) to capture 17 pressure hormone metabolic markers (such as cortisol, adrenaline) in the user's exhaled gas in real time. The concentrations of various pressure hormone metabolic markers constitute the metabolic feature set.

[0031] S202. Input the metabolic feature set into the sleep recognition model. When receiving the recognition result of sleep disorder output by the sleep recognition model, screen key features from the metabolic feature set based on the feature relationship graph and generate a key feature list.

[0032] Specifically, the sleep recognition model can be a machine learning classifier or a deep learning model, which can be trained using historical features. The historical features are labeled as "normal sleep" and "with sleep disorder", and "with sleep disorder" can be further labeled as different levels of sleep disorder, which is not limited in this embodiment. Then, the model is trained using the labeled historical features.

[0033] Pre-analyze the historical metabolic feature set, use the causal inference algorithm to analyze the causal relationship between metabolic features, and construct a directed acyclic graph as the feature relationship graph. The nodes in the graph represent metabolic features, the edges represent causal relationships, the arrow direction is the feature influence direction, and the edge weight is the causal strength. The key features are the features that have a great impact on sleep disorder. The features earlier in the key feature list indicate a greater impact on sleep disorder.

[0034] S203. Generate the sleep aid substance ratio based on the key feature list, and control the sleep aid substance dispensing module to dispense the sleep aid substance based on the sleep aid substance ratio.

[0035] Specifically, construct a database that stores the mapping relationship between metabolic features and sleep aid substances. The mapping relationship includes the mapping relationship between standard metabolic features and standard sleep aid substance ratios, as well as the corresponding rules for adjusting the sleep aid substance ratio for abnormal metabolic features. For example, for every unit increase in cortisol compared to the standard metabolic feature, the ratio of the corresponding GABA increases by A content.

[0036] Compare the key features in the key feature list with the standard metabolic features, adjust the standard sleep aid substance ratio based on the comparison result to obtain the sleep aid substance ratio suitable for the user, and the electronic device sends an instruction to the sleep aid substance dispensing module.

[0037] The sleep aid substance formulation module can use the electrostatic adsorption method to wrap the sleep aid substance in a mesoporous silica carrier (pore size 5 nm), and coat a temperature-sensitive hydrogel (LCST = 34°C) and personalized fragrance molecules (such as lavender or cedar essential oil) through microfluidic technology to achieve targeted sustained release triggered by the nasal mucosa. The sleep aid substance formulation module internally integrates a microfluidic chip (channel width 200 μm), and regulates the mixing ratio of reactants through electroosmotic flow to complete the continuous synthesis from raw materials to encapsulated microparticles (time-consuming <3 minutes).

[0038] S204. Obtain the current user image of the user, determine the delivery parameters based on the current user image, and when it is detected that the user inhales, control the delivery device to spray the sleep aid substance according to the delivery parameters, where the delivery parameters include the delivery angle and the delivery dose.

[0039] Specifically, the current user image is obtained by taking a facial image of the user with the built-in camera of the device, a three-dimensional model of the user's face is constructed using computer vision algorithms, the target delivery area (such as the nasal cavity entrance or the olfactory mucosa) is located, and the relative position relationship between the center point coordinates of the target delivery area and the nozzle position coordinates of the delivery device is calculated. The delivery angle and the delivery distance are determined based on the relative position relationship, and then the delivery dose is determined according to the delivery distance. The respiratory rhythm is monitored using a pressure sensor, and the spray is triggered only at the beginning of inhalation to avoid drug waste during the exhalation phase.

[0040] An array of piezoelectric brakes is provided inside the delivery device. Using PZT-5H piezoelectric ceramic chips (displacement accuracy ±0.5 μm), the microcavity diaphragm is driven to generate high-frequency vibrations (20 kHz), atomizing the nanoparticles into 1-3 μm aerosols (particle size CV <5%). The atomization output is monitored by a MEMS flow sensor (range 0-0.1 ml, accuracy ±0.5%), and the piezoelectric voltage is corrected in real time in combination with the PID algorithm to ensure that the single injection dose error ≤ 0.01 ml.

[0041] In this embodiment, by extracting the metabolic feature set of the user's exhaled gas and inputting it into the sleep recognition model, sleep disorders can be accurately identified, key features are screened based on the feature relationship graph to generate a list, and the core intervention targets are located from the root of the metabolic network; according to the key feature list and the preset mapping relationship, a personalized sleep aid substance ratio is generated to solve the problem that traditional fixed formulas cannot respond to individual metabolic differences; a three-dimensional model is constructed using the user's current image to determine the delivery angle and dose, combined with the inhalation trigger mechanism, so that the nanoscale sleep aid substance reaches the target area directly at a precise angle and a compensated dose, improving the delivery efficiency and bioavailability. Through the personalized ratio driven by metabolic features and the precise delivery synchronized with the respiratory cycle, the present application significantly enhances the pertinence and effectiveness of the sleep aid effect, and reduces substance loss and side effects.

[0042] A possible implementation manner of the embodiment of the present application, the method further includes: Obtain historical exhalation data and extract a historical metabolic feature set from the historical exhalation data; Analyze the causal relationships between every two features in the historical metabolic feature set, where the causal relationships include direct causal relationships and indirect causal relationships; Calculate the causal strength between every two features with causal relationships, where the causal strength includes direct causal strength and indirect causal strength; Construct a feature relationship graph based on the causal relationships and causal strength.

[0043] In this embodiment, the Granger causality test algorithm can be used to analyze the direct causal relationships between features. Among the already identified direct causal relationships, traverse all paths with a length of at least 2 (such as A→B→C), and determine whether the path is connected and there is no conflicting evidence (such as no reverse causal relationship A←B). If there is no connected and conflicting evidence, it is determined that there is an indirect causal relationship between feature A and feature C.

[0044] Calculate the direct causal strength between every two features with direct causal relationships. The linear regression model can be established using the regression coefficient method, and the regression coefficient is used as the direct causal strength; the standardized effect size algorithm can also be used to calculate the ratio of the mean difference of feature B before and after the intervention of feature A to the combined standard deviation as the direct causal strength.

[0045] Furthermore, for indirect causal relationships, the product of the direct causal strengths on the path is used as the indirect causal strength. For example, for A→B→C, the direct causal relationship of A→B is β1, and the direct causal relationship of B→C is β2, then the indirect causal strength of A→C is β1×β2.

[0046] Each metabolic feature corresponds to a node, and the feature name is marked on the node. The direct causal relationship is represented by an edge with an arrow, and the edge weight is the direct causal strength. The indirect causal relationship is represented by a dotted arrow edge, and the weight is the indirect causal strength, and finally a feature relationship graph is obtained.

[0047] In this embodiment, the collection of historical exhalation data to extract the metabolic feature set provides a data basis for analyzing the causal relationships between features; analyzing the direct and indirect causal relationships between features can reveal the paths of interaction between features in the metabolic network; calculating the causal strength quantifies the degree of feature influence, turning the causal relationship from qualitative description to quantitative analysis; finally, the constructed feature relationship graph presents the causal association and strength of metabolic features in a structured form.

[0048] A possible implementation manner of the embodiment of the present application is to screen key features from the metabolic feature set based on the feature relationship graph and generate a list of key features, including: Determine the degree of influence of each feature pair in the metabolic feature set on the presence of sleep disorders as the first index; Determine the primary features from the metabolic feature set based on the feature relationship graph as the key features. The primary features represent the features for which there are no superior nodes corresponding to the nodes in the feature relationship graph; Based on the feature relationship graph, take the features that have a direct causal relationship with the target primary feature as secondary features, and calculate the second index of the target primary feature based on the direct causal index between the secondary features and the target primary feature and the number of features of the secondary features. The target primary feature is any one of the primary features; Based on the feature relationship graph, take the features that have an indirect causal relationship with the target primary feature as tertiary features, and calculate the third index of the target primary feature based on the indirect causal index between the tertiary features and the target primary feature and the number of features of the tertiary features; Based on the first index, the second index, and the third index, calculate the key index of the target primary feature; Arrange each primary feature in descending order according to the key index to obtain the key feature list.

[0049] In this embodiment, based on the historical metabolic feature set, through statistical methods (such as logistic regression, random forest) or machine learning models (such as neural networks) training, calculate the influence coefficient of each feature, and normalize it as the first index.

[0050] Traverse all nodes in the feature relationship graph, and filter out the nodes with an in-degree of 0 (i.e., the nodes without arrows pointing to them) as primary features. The secondary features are the nodes directly pointed to by the primary nodes in the feature relationship graph. Calculate the sum (or average value) of the direct causal strengths of each secondary feature that has a direct causal relationship with the target primary feature as the second index, and calculate the sum (or average value) of the indirect causal strengths of each tertiary feature that has an indirect causal relationship with the target primary feature as the third index.

[0051] Based on the preset weights, perform a weighted sum of the first index, the second index, and the third index to obtain the key index of the target primary feature.

[0052] In this embodiment, by calculating the direct influence degree (the first index) of each feature on sleep disorder, the basic role of a single feature is clarified; based on the feature relationship graph, locate the primary features without upstream nodes to lock the root key features of the metabolic network; combine the directly causally associated features (secondary features) and indirectly causally associated features (tertiary features) of the primary features, calculate the second index and the third index respectively, and comprehensively measure the conduction effect of direct and indirect influences; finally, calculate the key index by multi-index weighting and sort to generate a key feature list focusing on the core intervention targets, so that the selected key features can not only reflect the direct inducement of sleep disorder, but also reflect the global influence of the metabolic network.

[0053] A possible implementation manner of the embodiment of the present application is to generate a sleep aid substance ratio based on the key feature list, including: Extracting the mapping relationship between metabolic characteristics and sleep-inducing substance ratios, including the mapping relationship between standard metabolic characteristics and standard sleep-inducing substance ratios; Compare the target key feature with the standard metabolic feature, determine the adjustment method of each sleep-inducing substance corresponding to the target key feature based on the comparison result and the mapping relationship, combine the target key feature and the adjustment method of a sleep-inducing substance into an adjustment vector to obtain several adjustment vectors corresponding to the target key feature, where the target key feature is any key feature in the key feature list; Divide the adjustment vectors corresponding to all key features in the key feature list into multiple adjustment groups according to the type of sleep-aiding substance, and determine the adjustment polarity of each adjustment group, which includes same-direction adjustment and reverse adjustment; The target adjustment method of the sleep-aiding substance corresponding to each adjustment group is determined based on the key feature list and the adjustment polarity, and the standard sleep-aiding substance ratio is adjusted based on the target adjustment method of each adjustment group to obtain the sleep-aiding substance ratio.

[0054] In this example, based on clinical research, normal ranges for various metabolic characteristics are pre-set as standard metabolic characteristics, and the basic ratios of sleep-inducing substances corresponding to these normal ranges are defined as standard substance ratios. Rules for adjusting abnormal metabolic characteristics and sleep-inducing substances are established. For example, if cortisol is elevated above the upper limit of the standard range, a1: GABA + b1 (inhibits cortisol synthesis), melatonin - c1 (avoids cortisol antagonism); if tryptophan is depressed above the lower limit of the standard range, a2: 5-hydroxytryptophan + b2 (supplements precursors), vitamin B6 + c2 (promotes conversion), where a1 and a2 are used as unit concentrations.

[0055] Each key feature is compared to the corresponding standard metabolic feature range to identify abnormal key features. Based on the mapping relationship, several adjustment vectors (feature-sleep-enhancing substance adjustment pairs) are generated for each abnormal key feature, with one adjustment vector corresponding to each sleep-enhancing substance. If key feature A is abnormally elevated and the mapping relationship corresponds to sleep-enhancing substances A, B, and C, three adjustment vectors corresponding to sleep-enhancing substances A, B, and C are generated.

[0056] For key feature A and sleep-inducing substance A, the adjustment range of sleep-inducing substance A corresponding to a unit increase in key feature A (denoted as aA) in the mapping relationship is represented as bA (positive or negative). Calculate the difference between key feature A and the upper limit of the standard range of feature A. The result of calculating the difference / aA×bA is used as the adjustment method in the adjustment vector corresponding to sleep-inducing substance A. A negative result indicates that the proportion of sleep-inducing substance A needs to be reduced, while a positive result indicates that the proportion of sleep-inducing substance A needs to be increased. Referring to the above steps, a corresponding adjustment vector is generated for each sleep-inducing substance corresponding to each abnormal key feature. The adjustment vector includes: feature name, sleep-inducing substance type, and the corresponding adjustment direction and adjustment range. The adjustment direction can be either increase or decrease.

[0057] The adjustment vectors for all abnormal key features are grouped by sleep-inducing substance type, such as the "5-hydroxytryptophan group" and the "GABA group." Same-direction adjustment means that all adjustment vectors within the adjustment group are adjusted in the same direction (e.g., all increase or all decrease). Opposite-direction adjustment means that the adjustment directions for the same sleep-inducing substance within the adjustment group are contradictory (simultaneous increase and decrease). For example, if one feature requires an increase in melatonin, while another requires a decrease, then the polarity of this group is opposite.

[0058] This embodiment provides benchmark rules for personalized matching by establishing a standard mapping relationship between metabolic characteristics and sleep-inducing substances; compares key characteristics with standard characteristics to generate adjustment vectors, achieving precise mapping from metabolic abnormalities to substance adjustments; groups substances by type and determines adjustment polarity to resolve adjustment conflicts for the same substance with multiple characteristics; determines the target adjustment method based on polarity and key indexes, dynamically balancing the need for same-direction or opposite-direction adjustments, and ensuring that matching responds to individual metabolic differences while avoiding conflicts between substances.

[0059] In a possible implementation of the embodiment of the present application, any adjustment group is used as a target adjustment group, and any adjustment vector in the target adjustment group is used as a target adjustment vector; Based on the key feature list and adjustment polarity, the target adjustment method for the sleep-inducing substance corresponding to the target adjustment group is determined, including: When the adjustment polarity of the target adjustment group is in the same direction, the adjustment index is calculated based on the key index of the key feature in the target adjustment vector and the adjustment method of the sleep-inducing substance; and the adjustment vector with the largest adjustment index is determined from the target adjustment group as the target adjustment method of the sleep-inducing substance corresponding to the target adjustment group. When the adjustment polarity of the target adjustment group is reverse adjustment, the adjustment index is calculated based on the key index of the key feature in the target adjustment vector and the adjustment method of the sleep-inducing substance; the first adjustment vector with the largest adjustment index and the second adjustment vector with the smallest adjustment index are determined from the target adjustment group, and the target adjustment method of the sleep-inducing substance corresponding to the target adjustment group is obtained by combining the first adjustment vector and the second adjustment vector.

[0060] In this embodiment, when the adjustment polarity of the target adjustment group is the same-direction adjustment, calculate the product of the key index of the key feature in the target adjustment vector and the adjustment method (adjustment amplitude) of the sleep aid substance as the adjustment index, where the adjustment amplitude includes positive and negative signs.

[0061] When the adjustment polarity of the target adjustment group is the reverse adjustment, calculate the product of the key index of the key feature in the target adjustment vector and the adjustment method (adjustment amplitude) of the sleep aid substance as the adjustment index. Since there are adjustment vectors with both positive and negative adjustment amplitudes in the reverse adjustment group and the key index is positive, the calculated adjustment index also includes both positive and negative numbers. The adjustment method (adjustment amplitude) in the first adjustment vector with the largest adjustment index is to increase the content of the sleep aid substance, and the adjustment method (adjustment amplitude) in the second adjustment vector with the smallest adjustment index is to decrease the content of the sleep aid substance. Take the sum of the adjustment methods (adjustment amplitudes) of the first adjustment vector and the second adjustment vector as the target adjustment method of the sleep aid substance corresponding to the target adjustment group.

[0062] In this embodiment, during the same-direction adjustment, calculate the adjustment index based on the key index and the adjustment method, and select the adjustment vector with the largest index as the target method to ensure that the dominant adjustment requirements of the core features are implemented first; during the reverse adjustment, determine the vectors with the largest and smallest adjustment indices and comprehensively balance them to avoid the ratio failure caused by contradictory adjustments.

[0063] A possible implementation manner of the embodiment of the present application is to determine the delivery parameters based on the current user image, including: Perform three-dimensional modeling based on the current user image, and identify the target delivery area of the user based on the three-dimensional modeling; Determine the relative position relationship between the delivery device and the target delivery area, and determine the delivery angle based on the relative position relationship; Determine the delivery distance based on the relative position relationship, calculate the delivery dose based on the delivery distance and the delivery mapping relationship, and the delivery mapping relationship is the mapping relationship between the delivery distance and the loss degree of the sleep aid substance.

[0064] In this embodiment, measure the loss rate of the sleep aid substance at different delivery distances through experiments, and establish a distance-loss curve. For example, when the delivery distance does not exceed 5 cm, the corresponding loss rate is 5%, and when the delivery distance is 10 cm, the corresponding loss rate is 15%, etc., calculate 1 / (1 - loss rate) as the compensation coefficient corresponding to the delivery distance.

[0065] Take the dose expected to be ingested by the user as the standard dose, determine the loss rate corresponding to the delivery distance, calculate the compensation coefficient, and take the product of the standard dose and the compensation coefficient as the delivery dose.

[0066] In this embodiment, the delivery angle is calculated based on the relative position between the device and the target area, so that the nanoparticle ejection path is directly aligned with the target area, avoiding non-targeted loss; the dose is dynamically adjusted according to the delivery distance and loss mapping relationship to compensate for the material loss during long-distance transmission, significantly improving the delivery efficiency and bioavailability, and reducing the attenuation of the intervention effect caused by distance deviation or angle deviation.

[0067] An electronic device is provided in an embodiment of the present application, as Figure 3 shown Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0068] The processor 301 may be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor 301 may also be a combination that implements computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0069] The bus 302 may include a path for transmitting information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 3 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0070] The memory 303 can be a ROM (Read Only Memory), or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions. It can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0071] The memory 303 is used to store the application program code for executing the solution of this application, and is controlled by the processor 301 for execution. The processor 301 is used to execute the application program code stored in the memory 303 to implement the content shown in the foregoing embodiments of the method for targeted delivery of nanoscale sleep aid substances based on individual metabolic characteristics.

[0072] Figure 3 The illustrated electronic device is only an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0073] The embodiments of this application provide a computer-readable storage medium on which a computer program is stored. When it runs on a computer, it enables the computer to execute the content shown in the foregoing embodiments of the method for targeted delivery of nanoscale sleep aid substances based on individual metabolic characteristics.

[0074] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limitation, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0075] An embodiment of the present application provides a computer program product, including a computer program, which when executed by a processor, implements the content shown in the foregoing embodiment of the method for targeted delivery of nanoscale sleep aids based on individual metabolic characteristics.

[0076] The above are only partial embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A nanoscale targeted delivery method of sleep aid substances based on individual metabolic characteristics, characterized in that, Including: Receiving a set of metabolic features extracted from the exhaled gas of a user; Inputting the set of metabolic features into a sleep recognition model. When receiving the recognition result of sleep disorder output by the sleep recognition model, screening key features from the set of metabolic features based on a feature relationship graph and generating a list of key features; Generating a sleep aid substance ratio based on the list of key features, and controlling a sleep aid substance dispensing module to dispense a sleep aid substance based on the sleep aid substance ratio; Obtaining a current user image of the user, determining a delivery parameter based on the current user image, and when it is monitored that the user inhales, controlling a delivery device to eject the sleep aid substance according to the delivery parameter, where the delivery parameter includes a delivery angle and a delivery dose.

2. The method for targeted delivery of nano-scale sleep aid substances based on individual metabolic characteristics according to claim 1, wherein The method further includes: Obtaining historical exhalation data, and extracting a set of historical metabolic features from the historical exhalation data; Analyzing the causal relationship between every two features in the set of historical metabolic features, where the causal relationship includes a direct causal relationship and an indirect causal relationship; Calculating the causal strength between every two features having the causal relationship, where the causal strength includes a direct causal strength and an indirect causal strength; Constructing the feature relationship graph based on the causal relationship and the causal strength.

3. The method for targeted delivery of nano-scale sleep aid substances based on individual metabolic characteristics according to claim 1, characterized in that, The screening of key features from the set of metabolic features based on the feature relationship graph and generating a list of key features includes: Determining the influence degree of each feature in the set of metabolic features on the presence of the sleep disorder as a first index; Determining first-level features from the set of metabolic features based on the feature relationship graph as the key features, where the first-level features represent features of the superior nodes corresponding to the nodes in the feature relationship graph that do not have direct connections; Taking the features having a direct causal relationship with a target first-level feature as second-level features based on the feature relationship graph, and calculating a second index of the target first-level feature based on the direct causal index between the second-level features and the target first-level feature, where the target first-level feature is any one of the first-level features; Taking the features having an indirect causal relationship with the target first-level feature as third-level features based on the feature relationship graph, and calculating a third index of the target first-level feature based on the indirect causal index between the third-level features and the target first-level feature; Calculating a key index of the target first-level feature based on the first index, the second index, and the third index; Arranging each of the first-level features in descending order according to the key index to obtain the list of key features.

4. The method for targeted delivery of nanoscale sleep aid substances based on individual metabolic characteristics according to claim 1, characterized in that The generating of the sleep aid substance ratio based on the list of key features includes: Extracting the mapping relationship between metabolic features and sleep aid substance ratios, where the mapping relationship includes the mapping relationship between standard metabolic features and standard sleep aid substance ratios; Comparing a target key feature with the standard metabolic features, determining the adjustment method of each sleep aid substance corresponding to the target key feature based on the comparison result and the mapping relationship, and combining the target key feature and the adjustment method of a sleep aid substance into an adjustment vector to obtain a plurality of adjustment vectors corresponding to the target key feature, where the target key feature is any key feature in the list of key features; Divide the adjustment vectors corresponding to all key features in the key feature list into multiple adjustment groups according to the types of sleep aid substances, and determine the adjustment polarity of each adjustment group. The adjustment polarity includes co-directional adjustment and reverse adjustment. Based on the key feature list and the adjustment polarity, determine the target adjustment method of the sleep aid substance corresponding to each adjustment group, and adjust the standard sleep aid substance ratio based on the target adjustment method of each adjustment group to obtain the sleep aid substance ratio.

5. According to the nano-level sleep aid substance targeted delivery method based on individual metabolic characteristics described in claim 4, take any adjustment group as the target adjustment group, and take any adjustment vector in the target adjustment group as the target adjustment vector. Determining the target adjustment method of the sleep aid substance corresponding to the target adjustment group based on the key feature list and the adjustment polarity includes: When the adjustment polarity of the target adjustment group is the co-directional adjustment, calculate the adjustment index based on the key index of the key feature in the target adjustment vector and the adjustment method of the sleep aid substance; determine an adjustment vector with the largest adjustment index in the target adjustment group as the target adjustment method of the sleep aid substance corresponding to the target adjustment group. When the adjustment polarity of the target adjustment group is the reverse adjustment, calculate the adjustment index based on the key index of the key feature in the target adjustment vector and the adjustment method of the sleep aid substance; determine the first adjustment vector with the largest adjustment index and the second adjustment vector with the smallest adjustment index in the target adjustment group, and synthesize the first adjustment vector and the second adjustment vector to obtain the target adjustment method of the sleep aid substance corresponding to the target adjustment group.

6. The method for targeted delivery of nanoscale sleep aid substances based on individual metabolic characteristics according to claim 1, wherein The determining the delivery parameters based on the current user image includes: Perform three-dimensional modeling based on the current user image, and identify the target delivery area of the user based on the three-dimensional modeling. Determine the relative position relationship between the delivery device and the target delivery area, and determine the delivery angle based on the relative position relationship. Determine the delivery distance based on the relative position relationship, and calculate the delivery dose based on the delivery distance and the delivery mapping relationship. The delivery mapping relationship is the mapping relationship between the delivery distance and the loss degree of the sleep aid substance.

7. A nanoscale targeted delivery device for sleep-aiding substances based on individual metabolic characteristics, characterized in that, Includes: A sleep aid substance preparation module, a delivery device, and an electronic device; The sleep aid substance preparation module is configured to receive a preparation instruction including the sleep aid substance ratio sent by the electronic device, and prepare the sleep aid substance based on the preparation instruction. The delivery device is connected to the sleep aid substance preparation module, and is configured to receive a delivery instruction including delivery parameters sent by the electronic device, and deliver the sleep aid substance to the user based on the delivery instruction. The electronic device is configured to execute the nano-level sleep aid substance targeted delivery method based on individual metabolic characteristics described in any one of claims 1-6.

8. The nano-level sleep aid substance targeted delivery device based on individual metabolic characteristics according to claim 7, characterized in that, The device further includes: a pressure sensor and a gas sensor; The pressure sensor is configured to monitor the breathing state of the user, and the breathing state includes inhalation and exhalation. The gas sensor is configured to capture the exhaled gas of the user and extract the metabolic feature set and send it to the electronic device when the pressure sensor monitors that the user exhales.

9. The nano-level sleep aid substance targeted delivery device based on individual metabolic characteristics according to claim 7, characterized in that, The electronic device includes: At least one processor; A memory; At least one application program, where at least one application program is stored in the memory and configured to be executed by at least one processor, and the at least one application program is configured to: execute the method for targeted delivery of nanoscale sleep aid substances based on individual metabolic characteristics according to any one of claims 1-6.

Images