Control method and system of portable multifunctional emergency first-aid kit
By constructing and optimizing life vectors and global state vectors, and combining multidimensional vital signs and environmental data, risk labels are generated and emergency rescue tools are automatically inferred. This solves the problems of delayed response and misuse of portable emergency rescue devices in high-risk scenarios, and realizes efficient and accurate emergency supplies allocation and intelligent decision-making.
Patent Information
- Application Number
- CN202511184780.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-22
- Publication Date
- 2025-11-14
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing portable emergency medical equipment struggles to quickly and accurately identify patient conditions, and its resistance to disturbances and response delays in the face of multi-source risk coupling changes result in insufficient personalization, precision, and efficiency in emergency response. In particular, in high-risk emergency scenarios, misuse of supplies, delayed deployment, or mismatch of interventions are prone to occur.
By constructing optimized life vectors and global state vectors, and combining multidimensional vital signs and environmental data, risk labels are generated. Then, intelligent judgment mechanisms and predictive models are used to automate reasoning, enabling precise matching and rapid dispatch of emergency medical tools.
It improves the accuracy of characterizing and judging the evolution trend of patients' life risks, enhances anti-interference and perception discrimination capabilities, ensures efficient and reasonable allocation of emergency supplies, and significantly improves the intelligent decision-making ability and operational efficiency of portable first aid kits.
Smart Images
Figure CN120938733A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of emergency medical equipment control technology, specifically to a control method and system for a portable multifunctional emergency first aid kit. Background Technology
[0002] With the widespread application of multifunctional portable emergency medical equipment, how to quickly and accurately identify the patient's condition and rationally allocate emergency resources in emergency treatment scenarios has become a key direction for the intelligent development of emergency medical systems.
[0003] Traditional first aid kits mostly operate in a linear manner of "collection-discrimination-response". Their core relies on the vital signs data at the current moment to determine the status, which makes it difficult to effectively capture the evolution trend of the patient's vital signs over time, and their adaptability to external treatment environment factors is limited. Although some systems have multiple sensor inputs, their data fusion capabilities are insufficient and their status representation structure is simple, resulting in poor anti-interference ability and response delay when facing multi-source risk coupling changes.
[0004] Furthermore, existing resource allocation methods are mostly based on fixed mapping or manual intervention strategies, failing to form a tool response mechanism that links with the patient's status in real time. Under the influence of multi-faceted changes in patients and sudden changes in the environment, existing solutions cannot guarantee the personalization, accuracy, and efficiency of emergency response. Especially in high-risk emergency scenarios, problems such as misuse of resources, delayed deployment, or intervention mismatch are more likely to occur, thereby affecting the overall treatment effectiveness of outdoor emergency care. Summary of the Invention
[0005] To address the aforementioned technical problems, this invention provides a control method and system for a portable multifunctional emergency first aid kit, wherein...
[0006] A control method for a portable multifunctional emergency first aid kit, the method comprising:
[0007] The system acquires multidimensional vital data of the patient at time t and time t-1 using a first aid kit, constructs a real-time vital vector and historical vital state, and optimizes the vector based on the real-time vital vector and historical vital vector to obtain an optimized vital vector.
[0008] Acquire multidimensional environmental data at time t to construct an environmental state vector, and generate a global state vector based on the environmental state vector and the optimized life vector;
[0009] The risk labels of patients in the current environment are obtained through global status, and the risk labels include high-risk labels, medium-risk labels, low-risk labels and stable labels;
[0010] The risk label and its corresponding global state vector are input into a predetermined first aid kit usage tool prediction model to obtain the corresponding first aid tool to light up as a prompt.
[0011] Furthermore, the multidimensional vital data includes heart rate, blood pressure, blood oxygen saturation, body temperature, respiratory rate, and pupil images.
[0012] Furthermore, the logic for obtaining the optimized state vector is as follows:
[0013] Let the real-time life vector S(t) = [H t B t P t M t ];in,
[0014] t≥0, where H t B t P t M t These are the heart rate, blood pressure, blood oxygen saturation, and body temperature at time t, respectively.
[0015] The optimized state vector is obtained by calculating the real-time life vector S(t).
[0016] Furthermore, the logic for obtaining the optimization factor λ is as follows:
[0017] Based on respiratory rate and pupil images at time t and t-1, respiratory rate change values and pupil difference maps were obtained. The respiratory rate change values and pupil difference maps, among which...
[0018] The change in respiratory rate is obtained by calculating the difference between the respiratory rates at time t and time t-1; and,
[0019] The pupil difference map is obtained by performing an absolute difference operation on the pixel dimension on the preprocessed pupil images at time t and time t-1.
[0020] Pupil difference diagrams are used to reflect changes in the pupil area;
[0021] The respiratory rate and pupil difference map are input into the established optimization factor analysis model to predict the optimization factor at time t+1.
[0022] Furthermore, the construction logic of the optimized factor analysis model is as follows:
[0023] Historical optimization factor analysis data is obtained and divided into a model training set and a model test set. The historical optimization factor analysis data includes respiratory rate change values, pupil difference maps, and the corresponding optimization factor λ for the next time step.
[0024] Construct the first regression network by taking the respiratory rate change value and pupil difference map in the model training set as the input of the regression network and taking the optimization factor λ corresponding to the next time step in the model training set as the output of the regression network to obtain the first initial regression network.
[0025] The first initial regression network was validated using the model test set. The first initial regression network with a first test error less than or equal to the preset first error was output as the optimized factor analysis model.
[0026] Furthermore, the multidimensional environmental data includes the temperature, humidity, and concentration of harmful gases at the treatment site.
[0027] Furthermore, the steps for generating the global state vector include:
[0028] The environment state vector and the optimized life vector are concatenated to construct the global state vector.
[0029] Furthermore, the logic for obtaining the risk label is as follows:
[0030] If there are 5 types of data in the global state vector that are not within the predetermined threshold range, they are marked as high-risk.
[0031] If there are 3 types of data in the global state vector that are not within the predetermined threshold range, they are marked as medium-risk.
[0032] If there is one type of data in the global state vector that is not within the predetermined threshold range, it is marked as a low-risk label;
[0033] If all data within the global state vector are within a predetermined threshold range, they are marked as stable.
[0034] Furthermore, the construction logic of the first aid kit tool prediction model is as follows:
[0035] Historical tool usage prediction data is obtained and divided into a tool prediction training set and a tool prediction test set. The historical tool usage prediction data includes risk labels, global state vector S(t), and the corresponding tool to be used at the next moment.
[0036] Construct a second regression network by taking the risk labels predicted by the tool in the training set and the corresponding global state vector S(t) as the input of the second regression network, and taking the tool predictions of the next time step in the training set as the output of the second regression network to generate the second initial regression network.
[0037] The second regression network is validated using the tool's prediction training set. The output of the second regression network is less than or equal to the second test error, and it is used as a tool prediction model in the first aid kit.
[0038] A control system for a portable multifunctional emergency first aid kit, used to execute the control method for any one of the portable multifunctional emergency first aid kits, the system comprising:
[0039] The first data processing module is used to acquire multidimensional life data of the patient at time t and time t-1 through the first aid kit, construct real-time life vector and historical life status, and perform vector optimization based on real-time life vector and historical life vector to obtain optimized life vector;
[0040] The second data processing module is used to acquire multidimensional environmental data at time t, to construct an environmental state vector, and to generate a global state vector based on the environmental state vector and the optimized life vector.
[0041] The label classification module is used to obtain the patient's risk label in the current environment through the global state vector. The risk label includes high-risk label, medium-risk label, low-risk label and stable label.
[0042] The tool prediction module is used to input the risk label and its corresponding global state vector into the predetermined first aid kit tool prediction model to obtain the corresponding first aid tool to light up as a prompt.
[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0044] This invention introduces an optimized mechanism for constructing life vectors and global state vectors, enabling patients' vital signs and their environmental states to form a unified dynamic expression system. This allows for the accurate characterization and identification of the evolution trend of life risks. Compared to traditional processing methods that rely on current vital sign data, this solution has stronger state stability and anti-interference capabilities. It also improves the ability to perceive and distinguish individual fluctuations and environmental coupling risks, providing more timely and accurate data for subsequent emergency response.
[0045] Furthermore, by constructing an intelligent judgment mechanism oriented towards risk labels and combining it with a predictive model to automate the reasoning of tool responses, this invention achieves accurate matching and rapid scheduling of emergency resources. Under multi-dimensional state-driven label classification, it ensures reduced human intervention in high-pressure emergency rescue scenarios, completes efficient and reasonable emergency supplies requisition, and significantly improves the intelligent decision-making capability and operational efficiency of portable first aid kits. Attached Figure Description
[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.
[0047] Figure 1 A flowchart of a control method for a portable multifunctional emergency first aid kit provided in Embodiment 1 of the present invention;
[0048] Figure 2 This is a block diagram of the control system of a portable multifunctional emergency first aid kit provided in Embodiment 2 of the present invention. Detailed Implementation
[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0050] Example 1
[0051] Please see Figure 1 As shown in the figure, this embodiment discloses a control method for a portable multifunctional emergency first aid kit, the method comprising:
[0052] S110: Obtain multidimensional life data of the patient at time t and time t-1 through the first aid kit, construct real-time life vector S(t) and historical state life S(t-1), and optimize the vector based on real-time life vector S(t) and historical life vector S(t-1) to obtain optimized life vector Sy(t);
[0053] Specifically, the multidimensional vital data includes heart rate, blood pressure, blood oxygen saturation, body temperature, respiratory rate, and pupil images:
[0054] It should be noted that the multidimensional life data is acquired through various vital sign acquisition devices installed in the first aid kit. These devices include, but are not limited to, electrocardiogram monitors, electronic blood pressure monitors, finger pulse oximeters, infrared thermometers, electronic thermometers, and finger vital sign scanners.
[0055] Specifically, the logic for obtaining the optimized state vector Sy(t) is as follows:
[0056] Let the real-time life vector S(t) = [H t B t P t M t ];in,
[0057] t≥0, where H t B t P t M tThese are the heart rate, blood pressure, blood oxygen saturation, and body temperature at time t, respectively.
[0058] Similarly, let S(t-1) = [H t-1 B t-1 P t-1 M t-1 ];
[0059] The optimized state vector Sy(t) is calculated using the following formula:
[0060] Sy(t)=λ×S(t-1)+(1-λ)×S(t);
[0061] Output the optimized state vector Sy(t) after calculation, where Sy(t) = [Hy t By t Py t My t ];
[0062] Wherein, λ is the optimization factor, λ∈(0,1), and λ is obtained through the optimization factor analysis model;
[0063] Specifically, the logic for obtaining the optimization factor λ is as follows:
[0064] Based on respiratory rate and pupil images at time t and t-1, respiratory rate change values and pupil difference maps were obtained. The respiratory rate change values and pupil difference maps, among which...
[0065] The change in respiratory rate is obtained by calculating the difference between the respiratory rates at time t and time t-1; and,
[0066] The pupil difference map is obtained by performing an absolute difference operation on the pixel dimension on the preprocessed pupil images at time t and time t-1.
[0067] Pupil difference diagrams are used to reflect changes in the pupil area;
[0068] The respiratory rate and pupil difference map are input into the established optimization factor analysis model to predict the optimization factor at time t+1.
[0069] It should be noted that the respiratory rate change value can be positive or negative, that is, the absolute value of the respiratory rate change value is not processed, so as to ensure that the sign of the value can be used to determine whether the respiratory rate change is accelerating or slowing down.
[0070] Specifically, the construction logic of the optimized factor analysis model is as follows:
[0071] Historical optimization factor analysis data is obtained and divided into a model training set and a model test set. The historical optimization factor analysis data includes respiratory rate change values, pupil difference maps, and the corresponding optimization factor λ for the next time step.
[0072] Construct the first regression network by taking the respiratory rate change value and pupil difference map in the model training set as the input of the regression network and taking the optimization factor λ corresponding to the next time step in the model training set as the output of the regression network to obtain the first initial regression network.
[0073] The first initial regression network was validated using the model test set. The first initial regression network with a first test error less than or equal to the preset first error was output as the optimized factor analysis model.
[0074] It should be noted that the optimized factor analysis model includes, but is not limited to, convolutional neural networks (CNN), multilayer perceptrons (MLP), convolutional fusion regression networks, two-branch multimodal regression networks, and time-series prediction networks based on Transformer. The first test error is set by the experimenters.
[0075] In this step, by fusing the multidimensional vital sign vectors at consecutive times t and t-1, and generating an optimized vital sign vector Sy(t) based on a dynamic optimization factor λ, the short-term fluctuations of vital signs are effectively smoothed, the stability of the state and the ability to identify changing trends are enhanced, and misjudgment due to single-point anomalies is avoided.
[0076] Most existing methods assess vital signs at a single moment, which cannot effectively filter out short-term noise at the emergency scene. This step introduces an adaptive optimization factor λ based on changes in respiratory rate and pupil image to achieve data fusion and dynamic trend perception, improve the accuracy of vital sign identification, reduce the false judgment rate, and have better real-time responsiveness and anti-interference ability.
[0077] S120: Obtain multidimensional environmental data at time t to construct an environmental state vector E(t), and generate a global state vector S(t) based on the environmental state vector and the optimized life vector Sy(t).
[0078] Specifically, the multidimensional environmental data includes the temperature of the treatment site, the humidity of the treatment site, and the concentration of harmful gases at the treatment site;
[0079] It should be noted that the above environmental data can be collected in real time by an environmental sensing device installed on the outside or side of the first aid kit. The environmental sensing device includes, but is not limited to: a digital temperature sensor (such as DS18B20) for collecting ambient temperature data; a digital humidity sensor (such as DHT22 or SHT35) for collecting ambient relative humidity; and a harmful gas detection module (such as a gas sensor based on MQ-135, CCS811 or NDIR technology) for detecting the concentration of harmful gases such as CO, NH3, and HCHO in the air.
[0080] Specifically, the steps for generating the global state vector S(t) include:
[0081] Let the environment state vector be E(t) = [A t U t L t ];in,
[0082] A t U t L t These are the temperature, humidity, and concentration of harmful gases at the treatment site, respectively.
[0083] Concatenate the environment state vector Sy(t) and the optimized life vector Sy(t) to construct the global state vector S(t):
[0084] S(t)=[Sy(t);E(t)]; where,
[0085] The semicolon ";" is a concatenation symbol.
[0086] Traditional emergency care plans rely solely on single vital sign data for risk assessment, neglecting the impact of environmental factors on emergency strategies. This step introduces multidimensional environmental data to construct a global state vector, enabling unified modeling of patient vital signs and external environmental information. This significantly improves the accuracy of risk perception and enhances the adaptability of the first aid kit to complex rescue scenarios.
[0087] S130, obtain the patient's risk label in the current environment through the global state vector S(t), the risk label includes high-risk label, intermediate-risk label, low-risk label and stable label;
[0088] Specifically, the logic for obtaining the risk label is as follows:
[0089] If there are 5 types of data in the global state vector S(t) that are not within the predetermined threshold range, they are marked as high-risk labels;
[0090] If there are three types of data in the global state vector S(t) that are not within the predetermined threshold range, they are marked as medium-risk.
[0091] If there is a class of data in the global state vector S(t) that is not within the predetermined threshold range, it is marked as a low-risk label;
[0092] If all data in the global state vector S(t) are within a predetermined threshold range, then it is marked as a stable label;
[0093] Existing methods are based on single indicators or simple threshold comparisons and lack the ability to collaboratively evaluate multi-source heterogeneous data. This step uses a multi-dimensional fusion global state vector S(t) to classify risks, resulting in more accurate judgments and more effective guidance for emergency response decisions. It is suitable for emergency response scenes with rapidly changing data and complex environments.
[0094] S140, input the risk label and the corresponding global state vector S(t) into the predetermined first aid kit usage tool prediction model to obtain the corresponding first aid tool to light up the prompt;
[0095] It should be noted that the light prompts are activated by indicator lights located at the bottom of each compartment of the first aid kit.
[0096] Specifically, the construction logic of the first aid kit tool prediction model is as follows:
[0097] Historical tool usage prediction data is obtained and divided into a tool prediction training set and a tool prediction test set. The historical tool usage prediction data includes risk labels, global state vector S(t), and the corresponding tool to be used at the next moment.
[0098] Construct a second regression network by taking the risk labels predicted by the tool in the training set and the corresponding global state vector S(t) as the input of the second regression network, and taking the tool predictions of the next time step in the training set as the output of the second regression network to generate the second initial regression network.
[0099] The second regression network is validated by using the tool to predict the training set. The output of the second regression network is less than or equal to the second test error. This second regression network is then used as a first aid kit to predict the model.
[0100] It should be noted that the tool prediction model used in the first aid kit includes, but is not limited to, convolutional neural networks (CNN), multilayer perceptrons (MLP), convolutional fusion regression networks, two-branch multimodal regression networks, and Transformer-based temporal prediction networks. The second test error is set by the experimenters.
[0101] Currently, most emergency medical equipment relies on doctors' manual judgment and experience to select emergency supplies, which carries the risk of judgment delays and misselection. This step establishes an intelligent tool prediction model based on multimodal data, which can automatically push emergency tool prompts, achieve accurate and efficient auxiliary decision-making, reduce the probability of human misjudgment, and improve the success rate of emergency care.
[0102] Example 2
[0103] Please see Figure 2 As shown, based on a unified inventive concept, this embodiment discloses a control system for a portable multifunctional emergency first aid kit, the system comprising:
[0104] The first data processing module S210 is used to acquire multidimensional life data of the patient at time t and time t-1 through the first aid kit, construct a real-time life vector S(t) and a historical state life S(t-1), and perform vector optimization based on the real-time life vector S(t) and the historical life vector S(t-1) to obtain an optimized life vector Sy(t).
[0105] The second data processing module S220 is used to acquire multidimensional environmental data at time t to construct an environmental state vector, and generate a global state vector S(t) based on the environmental state vector and the optimized life vector.
[0106] The label classification module S230 is used to obtain the patient's risk label in the current environment through the global state vector S(t), and the risk label includes high-risk label, medium-risk label, low-risk label and stable label;
[0107] The tool prediction module S240 is used to input the risk label and the corresponding global state vector S(t) into the predetermined first aid kit tool prediction model to obtain the corresponding first aid tool to light up.
[0108] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.
[0109] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0110] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0111] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only for the control method and system of a portable multifunctional emergency first aid kit. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.
[0112] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0113] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0114] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
[0115] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A control method for a portable multifunctional emergency first aid kit, characterized in that, The method includes: The system acquires multidimensional vital data of the patient at time t and time t-1 using a first aid kit, constructs a real-time vital vector and historical vital state, and optimizes the vector based on the real-time vital vector and historical vital vector to obtain an optimized vital vector. Acquire multidimensional environmental data at time t to construct an environmental state vector, and generate a global state vector based on the environmental state vector and the optimized life vector; The risk labels of patients in the current environment are obtained through global status, and the risk labels include high-risk labels, medium-risk labels, low-risk labels and stable labels; The risk label and its corresponding global state vector are input into a predetermined first aid kit usage tool prediction model to obtain the corresponding first aid tool to light up as a prompt.
2. The control method for a portable multifunctional emergency first aid kit according to claim 1, characterized in that, The multidimensional vital data includes heart rate, blood pressure, blood oxygen saturation, body temperature, respiratory rate, and pupil images.
3. The control method for a portable multifunctional emergency first aid kit according to claim 2, characterized in that, The logic for obtaining the optimized state vector is as follows: Let the real-time life vector S(t) = [H t B t P t M t ];in, t≥0, where H t B t P t M t These are the heart rate, blood pressure, blood oxygen saturation, and body temperature at time t, respectively. The optimized state vector is obtained by calculating the real-time life vector S(t).
4. The control method for a portable multifunctional emergency first aid kit according to claim 3, characterized in that, The logic for obtaining the optimization factor λ is as follows: Based on respiratory rate and pupil images at time t and t-1, respiratory rate change values and pupil difference maps were obtained. The respiratory rate change values and pupil difference maps, among which... The change in respiratory rate is obtained by calculating the difference between the respiratory rates at time t and time t-1; and, The pupil difference map is obtained by performing an absolute difference operation on the pixel dimension on the preprocessed pupil images at time t and time t-1. Pupil difference diagrams are used to reflect changes in the pupil area; The respiratory rate and pupil difference map are input into the established optimization factor analysis model to predict the optimization factor at time t+1.
5. The control method for a portable multifunctional emergency first aid kit according to claim 4, characterized in that, The construction logic of the optimized factor analysis model is as follows: Historical optimization factor analysis data is obtained and divided into a model training set and a model test set. The historical optimization factor analysis data includes respiratory rate change values, pupil difference maps, and the corresponding optimization factor λ for the next time step. Construct the first regression network by taking the respiratory rate change value and pupil difference map in the model training set as the input of the regression network and taking the optimization factor λ corresponding to the next time step in the model training set as the output of the regression network to obtain the first initial regression network. The first initial regression network was validated using the model test set. The first initial regression network with a first test error less than or equal to the preset first error was output as the optimized factor analysis model.
6. The control method for a portable multifunctional emergency first aid kit according to claim 5, characterized in that, The multidimensional environmental data includes the temperature, humidity, and concentration of harmful gases at the treatment site.
7. The control method for a portable multifunctional emergency first aid kit according to claim 6, characterized in that, The steps for generating the global state vector include: The environment state vector and the optimized life vector are concatenated to construct the global state vector.
8. The control method for a portable multifunctional emergency first aid kit according to claim 7, characterized in that, The logic for obtaining the risk label is as follows: If there are 5 types of data in the global state vector that are not within the predetermined threshold range, they are marked as high-risk. If there are 3 types of data in the global state vector that are not within the predetermined threshold range, they are marked as medium-risk. If there is one type of data in the global state vector that is not within the predetermined threshold range, it is marked as a low-risk label; If all data within the global state vector are within a predetermined threshold range, they are marked as stable.
9. The control method for a portable multifunctional emergency first aid kit according to claim 8, characterized in that, The construction logic of the first aid kit tool prediction model is as follows: Historical tool usage prediction data is obtained and divided into a tool prediction training set and a tool prediction test set. The historical tool usage prediction data includes risk labels, global state vector S(t), and the corresponding tool to be used at the next moment. Construct a second regression network by taking the risk labels predicted by the tool in the training set and the corresponding global state vector S(t) as the input of the second regression network, and taking the tool predictions of the next time step in the training set as the output of the second regression network to generate the second initial regression network. The second regression network is validated using the tool's prediction training set. The output of the second regression network is less than or equal to the second test error, and it is used as a tool prediction model in the first aid kit.
10. A control system for a portable multifunctional emergency first aid kit, used to execute the control method for a portable multifunctional emergency first aid kit according to any one of claims 1-9, characterized in that, The system includes: The first data processing module is used to acquire multidimensional life data of the patient at time t and time t-1 through the first aid kit, construct real-time life vector and historical life status, and perform vector optimization based on real-time life vector and historical life vector to obtain optimized life vector; The second data processing module is used to acquire multidimensional environmental data at time t, to construct an environmental state vector, and to generate a global state vector based on the environmental state vector and the optimized life vector. The label classification module is used to obtain the patient's risk label in the current environment through the global state vector. The risk label includes high-risk label, medium-risk label, low-risk label and stable label. The tool prediction module is used to input the risk label and its corresponding global state vector into the predetermined first aid kit tool prediction model to obtain the corresponding first aid tool to light up as a prompt.