Monitoring and early warning method and system for intraoperative core body temperature and medium

Abstract

The invention discloses an intraoperative core body temperature monitoring and early warning method and system and a medium, and relates to the related field of medical monitoring and early warning, and the method comprises the following steps: dynamically monitoring to obtain real-time state information of a target user; obtaining a target operation type, and obtaining real-time stage characteristics in combination with the real-time operation stage; extracting real-time anesthesia information, and analyzing the real-time anesthesia information in combination with the target individual information to obtain a body temperature trend index; activating a temperature sensor group in the intelligent earplug, and dynamically monitoring to obtain a real-time ear temperature set; establishing a multi-source data set based on the body temperature trend index and the real-time ear temperature set, and performing collaborative analysis to obtain a real-time predicted core body temperature; if not, early warning of abnormal body temperature is carried out. The technical problems that existing core body temperature monitoring is not timely and inaccurate, and it is difficult to effectively discover body temperature abnormity and conduct early warning are solved, and the technical effects of timely and accurate core body temperature prediction and abnormity early warning are achieved.

Description

Technical Field

[0001] The present application relates to the field of medical monitoring and early warning, and in particular to a method, system and medium for monitoring and early warning of core body temperature during surgery. Background Art

[0002] Accurately monitoring and providing early warning of changes in a patient's core body temperature during surgery is crucial for preventing hypothermia, maintaining physiological homeostasis, and ensuring surgical safety. Currently, the main approach to addressing this issue relies on traditional temperature monitoring methods, such as oral, axillary, or rectal temperature measurement, combined with manual observation and judgment by medical staff. However, this method is limited by the inconvenience of temperature measurement locations, the inefficiency of monitoring frequency, and the subjectivity of manual judgment, resulting in untimely and inaccurate temperature monitoring, making it difficult to detect abnormal temperatures and provide early warnings in a timely and effective manner.

[0003] Among the current related technologies, intraoperative core body temperature monitoring has technical problems such as being untimely and inaccurate, making it difficult to effectively detect abnormal body temperature and issue early warnings. Summary of the Invention

[0004] This application provides a method, system and medium for monitoring and warning of core body temperature during surgery. It adopts dynamic monitoring of the real-time surgical status of the target user, analyzes real-time anesthesia information in combination with the surgical type and stage characteristics, uses smart earplugs to monitor real-time ear temperature, and collaboratively analyzes the body temperature trend index and ear temperature data to predict the core body temperature. If the temperature exceeds the predetermined threshold, an abnormal temperature warning is issued. These technical means achieve the technical effect of timely and accurate prediction of core body temperature and abnormal warning.

[0005] The present application provides a method for monitoring and early warning of core body temperature during surgery, comprising: dynamically monitoring to obtain real-time status information of a target user, wherein the real-time status information includes a real-time surgical stage; obtaining a target surgical type of the target user, and obtaining a real-time stage feature in combination with the real-time surgical stage; extracting real-time anesthesia information from the real-time stage feature, and analyzing the real-time anesthesia information in combination with the target individual information of the target user to obtain a body temperature trend index; activating a temperature sensor group in a smart earplug, and dynamically monitoring the target user's real-time ear temperature set through the temperature sensor group, wherein the smart earplug is fixed to a predetermined ear position of the target user; forming a multi-source data set based on the body temperature trend index and the real-time ear temperature set, and collaboratively analyzing the multi-source data set to obtain a real-time predicted core body temperature; if the real-time predicted core body temperature is not within a predetermined core body temperature threshold, issuing a body temperature abnormality early warning to the target user.

[0006] In a possible implementation, the real-time anesthesia information in the real-time stage feature is extracted, and the real-time anesthesia information is analyzed in combination with the target individual information of the target user to obtain a body temperature trend index, and the following processing is performed: the real-time anesthetic drug type, real-time anesthetic drug amount and real-time anesthesia method in the real-time anesthesia information are extracted, and standardized to form a real-time anesthesia parameter vector; the real-time anesthesia parameter vector is traversed in the anesthesia database to obtain the most similar anesthesia parameter vector; the historical anesthesia depth corresponding to the most similar anesthesia parameter vector is used as the real-time anesthesia depth; the target individual coefficient obtained by analyzing the target individual information is used as the anesthesia calibration feedback coefficient; the anesthesia calibration feedback coefficient and the real-time anesthesia depth are weighted and calculated to obtain the body temperature trend index.

[0007] In a possible implementation, the real-time anesthetic drug type, real-time anesthetic drug amount and real-time anesthesia method in the real-time anesthesia information are extracted and standardized to form a real-time anesthesia parameter vector, and the following processing is performed: an anesthesia vectorization plan is obtained, and the anesthesia vectorization plan includes an anesthetic drug type vectorization plan, an anesthetic drug amount vectorization plan and an anesthesia method vectorization plan; the real-time anesthetic drug type is traversed through multiple tags with anesthetic drug type identification in the anesthetic drug type vectorization plan to obtain a real-time anesthetic drug tag; the real-time anesthetic drug amount is traversed through multiple tags with anesthetic drug amount identification in the anesthetic drug amount vectorization plan to obtain a real-time anesthetic drug amount tag; the real-time anesthesia method is traversed through multiple tags with anesthesia method identification in the anesthesia method vectorization plan to obtain a real-time anesthesia method tag; based on the real-time anesthetic drug tag, the real-time anesthetic drug amount tag and the real-time anesthesia method tag, the real-time anesthesia parameter vector is constructed.

[0008] In a possible implementation, after performing a weighted calculation on the anesthesia calibration feedback coefficient and the real-time anesthesia depth to obtain the body temperature trend index, the following processing is also performed: extracting a real-time environmental feature data set in the real-time status information, wherein the real-time environmental feature data set includes real-time environmental noise; matching the noise calibration feedback coefficient corresponding to the real-time environmental noise, and calibrating and adjusting the body temperature trend index based on the noise calibration feedback coefficient.

[0009] In a possible implementation, the following processing is performed: if the real-time environmental noise is greater than a predetermined noise threshold, the smart sound inlet on the smart earplug is activated, and noise reduction adjustment is performed on the smart earplug through the smart sound inlet.

[0010] In a possible implementation, the temperature sensor group in the smart earplug is activated, and the real-time ear temperature set of the target user is obtained through dynamic monitoring of the temperature sensor group, and the following processing is performed: the first temperature sensor in the temperature sensor group is extracted, and the real-time ear canal temperature is obtained through monitoring by the first temperature sensor; the second temperature sensor in the temperature sensor group is extracted, and the real-time auricle temperature is obtained through monitoring by the second temperature sensor; the real-time ear canal temperature and the real-time auricle temperature constitute the real-time ear temperature set.

[0011] In a possible implementation, the following processing is performed: the real-time status information also includes a real-time vital sign dataset, and the real-time vital sign dataset and the real-time environmental feature dataset are added to the multi-source dataset, wherein the real-time vital sign dataset includes at least real-time heart rate, real-time axillary temperature and real-time blood pressure, and the real-time environmental feature dataset includes at least real-time environmental noise, real-time environmental temperature and real-time environmental humidity.

[0012] In a possible implementation, the following processing is performed: if the real-time predicted core body temperature is not within the predetermined core body temperature threshold, after the target user is given an abnormal temperature warning, it also includes activating an intelligent temperature control device based on the abnormal temperature warning, and performing closed-loop temperature control of the target user through the intelligent temperature control device, wherein the intelligent temperature control device is wirelessly connected to the multi-functional operating table.

[0013] Optionally, the system can be connected to the HIS and hand anesthesia systems to collect information including but not limited to the following: basic patient information such as gender, age, height, and weight; diagnosis (trauma, shock, and other conditions that can lead to abnormal heat distribution due to unstable circulation), medical history (presence of metabolic diseases), preoperative tests (presence of infection, malnutrition), and other medical history and comorbidity information; surgical method (laparotomy, thoracotomy, or minimally invasive surgery), anesthesia method (general anesthesia or spinal anesthesia), time from the start of anesthesia to the start of surgery (length of skin exposed from the start of anesthesia to the sterilization and draping), surgery start time (length of time the body cavity is open), and real-time intraoperative information such as bleeding / urine output, and infusion / transfusion. This creates a multi-source dataset.

[0014] The present application also provides a monitoring and early warning system for core body temperature during surgery, comprising: a real-time status information acquisition module, configured to dynamically monitor and obtain real-time status information of a target user, wherein the real-time status information includes a real-time surgical stage; a real-time stage feature acquisition module, configured to obtain a target surgical type of the target user and obtain a real-time stage feature in combination with the real-time surgical stage; a body temperature trend index acquisition module, configured to extract real-time anesthesia information from the real-time stage feature and analyze the real-time anesthesia information in combination with target individual information of the target user to obtain a body temperature trend index; a real-time ear temperature set acquisition module, configured to activate a temperature sensor group in a smart earplug and dynamically monitor and obtain a real-time ear temperature set of the target user through the temperature sensor group, wherein the smart earplug is fixed to a predetermined ear position of the target user; a real-time predicted core body temperature acquisition module, configured to assemble a multi-source data set based on the body temperature trend index and the real-time ear temperature set, and perform collaborative analysis on the multi-source data set to obtain a real-time predicted core body temperature; and a body temperature abnormality early warning module, configured to issue a body temperature abnormality early warning to the target user if the real-time predicted core body temperature is not within a predetermined core body temperature threshold.

[0015] The present application also provides a computer-readable storage medium, comprising: a computer program stored thereon, which, when executed by a processor, implements a method for monitoring and early warning of core body temperature during surgery.

[0016] The present application proposes a method, system, and medium for monitoring and early warning of intraoperative core body temperature. First, real-time status information of a target user is dynamically monitored, including the real-time surgical stage. The target surgical type of the target user is then acquired and combined with the real-time surgical stage to obtain a real-time stage feature. Real-time anesthesia information is then extracted from the real-time stage feature and analyzed in combination with the target individual information of the target user to obtain a temperature trend index. Simultaneously, a temperature sensor group in a smart earbud is activated and dynamically monitored to obtain a real-time ear temperature set of the target user. The smart earbud is fixed to a predetermined ear position of the target user. A multi-source dataset is then assembled based on the temperature trend index and the real-time ear temperature set, and collaboratively analyzed to obtain a real-time predicted core body temperature. If the real-time predicted core body temperature is not within a predetermined core body temperature threshold, a temperature abnormality warning is issued to the target user. This achieves the technical effect of timely and accurate prediction of core body temperature and abnormality warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 A flowchart of a method for monitoring and early warning of core body temperature during surgery provided in an embodiment of the present application.

[0019] Figure 2 A schematic diagram of the structure of a system for monitoring and early warning of core body temperature during surgery provided in an embodiment of the present application.

[0020] Explanation of the accompanying drawings: real-time status information acquisition module 10, real-time stage feature acquisition module 20, body temperature trend index acquisition module 30, real-time ear temperature set acquisition module 40, real-time predicted core body temperature acquisition module 50, abnormal body temperature warning module 60. DETAILED DESCRIPTION

[0021] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0022] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0023] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0024] The present application embodiment provides a method for monitoring and early warning of core body temperature during surgery, such as Figure 1 As shown, the method includes:

[0025] Step S100 : dynamically monitoring and obtaining real-time status information of the target user, wherein the real-time status information includes a real-time operation stage.

[0026] Specifically, medical monitoring equipment within the operating room (including vital signs monitors and surgical progress recording systems) continuously collects physiological parameters and surgical progress information of the target user (i.e., the surgical patient). Sensors connected to the medical monitoring equipment and a data processing system capture and store the patient's physiological indicators (including heart rate, blood pressure, respiratory rate, etc.) and the current stage of the surgery in real time. The real-time status information refers to comprehensive information about the patient's current physiological state and surgical progress during the surgery. The real-time surgical stage refers to specific steps in the surgical process, such as anesthesia, surgical incision, and suturing.

[0027] Step S200 : obtaining the target surgery type of the target user, and obtaining real-time stage features in combination with the real-time surgery stage.

[0028] Specifically, the system uses the surgical reservation system or the surgical information entered by the doctor to determine the patient's surgical type (such as cardiac surgery, neurosurgery, etc.). By combining the surgical type with the current surgical stage, the system analyzes the unique physiological and surgical characteristics of that stage, such as the depth of anesthesia, blood loss, and surgical site.

[0029] Step S300 : extracting real-time anesthesia information from the real-time stage feature, and analyzing the real-time anesthesia information in combination with the target individual information of the target user to obtain a body temperature trend index.

[0030] Specifically, anesthesia-related data, including anesthetic drug dosage, administration time, and patient response, are filtered from real-time stage characteristics. Anesthesia information is personalized and analyzed, taking into account individual differences such as patient age, weight, and health status. Based on this anesthesia information and individual differences, an algorithm or model is used to derive an index reflecting body temperature trends, which is used to assess the impact of anesthesia on body temperature. The temperature trend index is a key indicator derived through a comprehensive analysis of multiple key information points. It integrates real-time status information from dynamic monitoring, surgery type, real-time stage characteristics, and anesthesia information. Specifically, real-time status information includes the patient's physiological parameters and surgical progress during the surgery, including physiological indicators such as heart rate, blood pressure, and respiratory rate, as well as the current surgical stage (e.g., anesthesia, surgical incision, suturing, etc.). Surgery type and real-time stage characteristics combine the patient's surgery type (e.g., cardiac surgery, neurosurgery, etc.) with physiological and surgical characteristics of the current surgical stage, such as depth of anesthesia, blood loss, and surgical site. Anesthesia information is derived by analyzing the real-time anesthetic drug type, dosage, and administration time, as well as individual patient differences (e.g., age, weight, and health status). The temperature trend index integrates these various information and can more accurately reflect the current temperature change trend of the patient during the operation, providing an important basis for subsequent core temperature prediction and early warning.

[0031] In a possible implementation, the real-time anesthesia information in the real-time stage feature is extracted, and the real-time anesthesia information is analyzed in combination with the target individual information of the target user to obtain a body temperature trend index. Step S300 further includes step S310, extracting the real-time anesthetic drug type, real-time anesthetic drug amount and real-time anesthesia method in the real-time anesthesia information, and standardizing them to form a real-time anesthesia parameter vector. Specifically, real-time data on anesthesia is automatically captured from a medical monitoring device or a surgical record system, including the type of anesthetic drug (such as propofol, fentanyl, etc.), the drug amount (the dose given per unit time) and the anesthesia method (such as general anesthesia, local anesthesia, etc.). The extracted anesthesia information is converted according to a unified standard or format, such as converting the drug amount into a standard unit (milligrams, micrograms, etc.), and converting the anesthesia method into a quantifiable code or label, ultimately forming a consistent and comparable real-time anesthesia parameter vector.

[0032] Step S320, the real-time anesthesia parameter vector is traversed in the anesthesia database to obtain the most similar anesthesia parameter vector. Specifically, the anesthesia database is a database that stores a large number of historical anesthesia cases, each of which contains detailed anesthesia parameters (drug type, drug dosage, anesthesia method) and corresponding anesthesia depth records. Through an algorithm or program, each historical case in the anesthesia database is checked one by one to find the case that is most similar to the current real-time anesthesia parameter vector. That is, the most similar anesthesia parameter vector is the historical anesthesia parameter vector in the anesthesia database that has the smallest difference or the highest similarity to the current real-time anesthesia parameter vector.

[0033] Here's an example: Consider a database of 1,000 historical anesthesia cases using cosine similarity as the similarity metric. For each historical anesthesia parameter vector in the database, calculate the cosine similarity between the current real-time anesthesia parameter vector and each historical anesthesia parameter vector. Store the calculated similarity values ​​in a list and associate them with the corresponding historical anesthesia parameter vectors. Sort the similarity list, select the historical anesthesia parameter vector with the highest similarity, and output information about the most similar anesthesia parameter vector, including the historical case ID, anesthetic drug type, drug dosage, anesthesia method, and anesthesia depth.

[0034] Step S330: Using the historical anesthesia depth corresponding to the most similar anesthesia parameter vector as the real-time anesthesia depth. Specifically, the historical anesthesia depth is the anesthesia depth recorded in the historical case corresponding to the most similar anesthesia parameter vector. Based on the principle of similarity, the historical anesthesia depth is used as an estimate of the current real-time anesthesia depth.

[0035] Step S340 uses the target individual coefficient obtained by analyzing the target individual information as the anesthesia calibration feedback coefficient. Specifically, individual differences in the patient's age, weight, gender, and health status are analyzed, and statistical analysis or machine learning algorithms are used to calculate a coefficient that reflects the impact of these individual differences on the anesthetic effect, namely the target individual coefficient. The target individual coefficient is used as feedback to adjust or calibrate the estimated depth of anesthesia to make it more accurate to the patient's actual condition.

[0036] Step S350 performs a weighted calculation on the anesthesia calibration feedback coefficient and the real-time anesthesia depth to obtain the body temperature trend index. Specifically, the anesthesia calibration feedback coefficient is multiplied by the real-time anesthesia depth (or other forms of combination) to obtain a new value, namely the body temperature trend index. This index integrates the type, amount, and method of anesthetic drugs as well as individual differences of patients to more accurately reflect the current body temperature change trend.

[0037] An example of calculating the temperature trend index is as follows: The current patient's anesthesia information is: Anesthetic drug: Propofol; Anesthetic dose: 100 mg; Anesthesia method: General anesthesia; Personal information: Age 45, Weight 70 kg, Male, In good health. A historical anesthesia database exists, where each case records the anesthetic drug, dose, anesthesia method, as well as the patient's personal information and anesthesia depth. Example historical data is shown in Table 1. Cases with identical anesthetic drug (propofol), dose (100 mg), and anesthesia method (general anesthesia) for the current patient are filtered from the historical database. The filtered data is shown in Table 2.

[0038] Table 1: Historical data

[0039]

[0040]

[0041] Table 2: Screening data

[0042] Case ID age weight gender Health status Depth of anesthesia 1 50 75 male good 45 2 40 65 female good 42 3 45 70 male good 48

[0043] The average depth of anesthesia for the selected historical cases was calculated as follows: historical average depth of anesthesia = (45 + 42 + 48) / 3 = 45. A regression model was trained using the selected historical data to predict depth of anesthesia. Age and weight were normalized, and gender and health status were coded. A linear regression model was used, with the following form: depth of anesthesia = β0 + β1 × age + β2 × weight + β3 × gender + β4 × health status. Through training, the model coefficients β0, β1, β2, β3, and β4 were obtained. This model was used to predict the depth of anesthesia for the current patient, which was 46. The target individual coefficient is the ratio of the predicted depth of anesthesia to the historical average depth of anesthesia: target individual coefficient = predicted depth of anesthesia / historical average depth of anesthesia = 46 / 45 ≈ 1.02. The target individual coefficient was used as the anesthesia calibration feedback coefficient to adjust the real-time depth of anesthesia. The real-time depth of anesthesia was 44, and the temperature trend index = real-time depth of anesthesia × target individual coefficient = 44 × 1.02 = 44.88.

[0044] In one possible implementation, the real-time anesthetic drug type, real-time anesthetic drug amount and real-time anesthesia method in the real-time anesthesia information are extracted and standardized to form a real-time anesthesia parameter vector. Step S310 further includes step S311, obtaining an anesthesia vectorization plan, and the anesthesia vectorization plan includes an anesthetic drug type vectorization plan, an anesthetic drug amount vectorization plan and an anesthesia method vectorization plan. Specifically, the anesthesia vectorization plan is obtained by accessing a database or file pre-stored in a computer system. The anesthesia vectorization plan is a pre-established plan for converting anesthesia information such as anesthetic drug type, anesthetic drug amount and anesthesia method into a vectorized form. This conversion helps the computer process and compare this information.

[0045] In step S312, the real-time anesthetic drug type is traversed through multiple tags with anesthetic drug type identifiers in the anesthetic drug type vectorization plan to obtain a real-time anesthetic drug tag. Specifically, a string matching or hash algorithm is used to match the real-time anesthetic drug type with the anesthetic drug type identifier in the plan (the tag or code used to uniquely identify each anesthetic drug type in the plan). Once a matching anesthetic drug type identifier is found, a corresponding real-time anesthetic drug tag is generated.

[0046] Step S313, the real-time anesthetic drug amount is traversed through multiple tags with anesthetic drug amount identification in the anesthetic drug amount quantization plan to obtain a real-time anesthetic drug amount tag. Specifically, the real-time anesthetic drug amount is converted into the quantitative unit (such as milligrams, grams, etc.) specified in the plan. The converted drug amount is matched with each quantitative interval defined in the plan to find the most appropriate interval tag.

[0047] In step S314, the real-time anesthesia method is traversed through multiple tags with anesthesia method identifiers in the anesthesia method vectorization plan to obtain real-time anesthesia method tags. Specifically, based on the description of the real-time anesthesia method, it is classified into the anesthesia method category defined in the plan, and a corresponding tag is assigned to each classified anesthesia method.

[0048] Step S315: Based on the real-time anesthetic drug label, the real-time anesthetic drug dosage label, and the real-time anesthetic mode label, a real-time anesthesia parameter vector is constructed. Specifically, the real-time anesthetic drug label, the real-time anesthetic drug dosage label, and the real-time anesthetic mode label obtained in steps S312, S313, and S314 are combined into a vector, and the elements in the vector are arranged in the order defined in the plan for subsequent processing and comparison.

[0049] In one possible implementation, after performing a weighted calculation on the anesthesia calibration feedback coefficient and the real-time anesthesia depth to obtain the body temperature trend index, step S300 further includes step S360, extracting a real-time environmental feature data set from the real-time status information, wherein the real-time environmental feature data set includes real-time environmental noise. Specifically, environmental feature data including environmental noise, temperature, humidity, etc. are acquired in real time from the monitoring system of the operating room. Feature data related to real-time environmental noise is screened out from the collected data. Real-time environmental noise refers to the real-time sound intensity level in the operating room, which will affect the patient's anesthesia depth and physiological state.

[0050] Step S370, match the noise calibration feedback coefficient corresponding to the real-time environmental noise, and calibrate and adjust the body temperature trend index based on the noise calibration feedback coefficient. Specifically, according to the level of real-time environmental noise, the corresponding noise calibration feedback coefficient is found in the preset noise calibration coefficient table, and the noise calibration feedback coefficient is used to adjust the body temperature trend index to reflect the impact of environmental noise on body temperature. The noise calibration feedback coefficient found is multiplied by the body temperature trend index to adjust the value of the body temperature trend index. The calibrated and adjusted body temperature trend index is output for subsequent body temperature prediction and early warning analysis. The environmental noise in the operating room is an important factor that may affect the patient's anesthesia depth and physiological state. For example, high noise levels may cause patients to be nervous and anxious, which in turn affects the absorption and metabolism of anesthetic drugs. By monitoring the environmental noise in real time and adjusting the body temperature trend index accordingly, the impact of the patient's surgical environment on their anesthesia state is more comprehensively considered, thereby improving the accuracy of body temperature prediction and early warning.

[0051] In one possible implementation, step S300 further includes step S380, activating the smart sound inlet on the smart earplug if the real-time environmental noise is greater than a predetermined noise threshold, and performing noise reduction adjustment on the smart earplug through the smart sound inlet.

[0052] Specifically, the monitored real-time environmental noise is compared with a preset noise threshold. If the real-time environmental noise is greater than the predetermined noise threshold (the upper limit of the noise level preset according to the operating room environment standard and the patient's comfort), an activation signal is sent to the control module of the smart earplug. After receiving the signal, the smart earplug activates the smart sound inlet through a built-in mechanical structure or electromagnetic device. The smart sound inlet is an adjustable sound inlet channel designed on the smart earplug. The overlap between the sound inlet and the sound emitting hole is controlled by rotating the adjustment plate to achieve a graded noise reduction amount (such as 30%-90%). The smart earplug analyzes the sound entering through the smart sound inlet, processes the analyzed sound using a built-in noise reduction algorithm to reduce or eliminate noise, and outputs the processed sound to the user through the speaker of the smart earplug, while maintaining no impact on the core body temperature monitoring function. In an operating room environment, high noise levels may cause patients to be nervous and anxious, which in turn affects their physiological state, including body temperature and depth of anesthesia. Through the smart sound inlet and noise reduction adjustment functions of the smart earplugs, noise can be automatically reduced or eliminated when the noise exceeds the standard, providing patients with a relatively quiet environment and helping to maintain the accuracy of the smart earplugs in monitoring core body temperature.

[0053] Step S400: activating the temperature sensor group in the smart earplug, and dynamically monitoring the real-time ear temperature set of the target user through the temperature sensor group, wherein the smart earplug is fixed to a predetermined ear position of the target user.

[0054] Specifically, a command is sent to the smart earplug wirelessly to activate its built-in temperature sensor group. The temperature sensor group continuously collects the patient's ear temperature data and transmits it to the data processing system in real time. The continuously collected ear temperature data is organized into a time series data set for subsequent analysis. The smart earplug is a wearable device with a built-in temperature sensor group for monitoring the patient's body temperature. The temperature sensor group is a collection of sensors in the smart earplug for measuring body temperature. The structure of the smart earplug is made of medical silicone material, including an ear hook extension component to ensure a stable wearing, and the ear temperature data is updated every 30 seconds.

[0055] In one possible implementation, the temperature sensor group in the smart earplug is activated, and the real-time ear temperature set of the target user is obtained through dynamic monitoring of the temperature sensor group. Step S400 further includes step S410, extracting the first temperature sensor in the temperature sensor group, and obtaining the real-time ear canal temperature through monitoring of the first temperature sensor. Specifically, the first temperature sensor is selected from the temperature sensor group built into the smart earplug according to a preset number or position identifier. The sensor fits tightly with the ear canal through an elastic seal to reduce the interference of the external environment on temperature monitoring. The elastic seal (such as rubber, polyurethane and other materials) has good elasticity and sealing performance, and can effectively isolate the influence of external noise, vibration and temperature changes on the sensor, ensuring that the monitored temperature data is accurate. Activate the first temperature sensor to start collecting temperature signals in the ear canal, convert the collected temperature signals into digital signals, and store them in a dedicated database of the smart earplug or the monitoring system connected thereto. Among them, the first temperature sensor refers to the temperature sensor in the temperature sensor group that is designated to monitor the ear canal temperature.

[0056] Step S420 extracts the second temperature sensor from the temperature sensor group and uses it to monitor the real-time auricle temperature. Specifically, similar to step S410, this time the second temperature sensor is selected from the temperature sensor group. This sensor is secured to the outside of the smart earbud via an elastic seal, ensuring close contact with the auricle for monitoring auricle temperature. The second temperature sensor is activated and begins collecting temperature signals from the auricle surface. Due to the isolation provided by the elastic seal, the sensor is able to stably monitor changes in auricle temperature.

[0057] In step S430, the real-time ear canal temperature and the real-time auricle temperature constitute the real-time ear temperature set. Specifically, the real-time ear canal temperature and the real-time auricle temperature respectively monitored in steps S410 and S420 are integrated. The integrated data is stored as a whole, that is, the real-time ear temperature set, in the monitoring system for subsequent collaborative analysis of multi-source data sets. Although both the ear canal temperature and the auricle temperature are affected by the ambient temperature and the individual's physiological state, their changing trends and amplitudes are different. By monitoring these two temperature values ​​at the same time and performing subsequent analysis on them as part of the real-time ear temperature set, the core body temperature of the target user can be more accurately assessed.

[0058] Step S500 , constructing a multi-source data set based on the body temperature trend index and the real-time ear temperature set, and performing collaborative analysis on the multi-source data set to obtain a real-time predicted core body temperature.

[0059] Specifically, the temperature trend index and real-time ear temperature data are combined into a comprehensive dataset containing various physiological information. Using machine learning or deep learning algorithms, this multi-source dataset is comprehensively analyzed, taking into account the impact of anesthesia on body temperature, to predict the patient's core temperature. Based on the collaborative analysis results, the patient's current core temperature prediction is output.

[0060] Specifically, the multi-source dataset includes a temperature trend index, real-time ear temperature data, and other relevant features. These features are integrated into a structured dataset for input into the machine learning model. A machine learning model is trained using historical data to predict core body temperature. A random forest model can be used as the machine learning model. The key steps in training are as follows: historical surgical data is collected, including the temperature trend index, ear temperature data, surgical stage, surgical type, individual patient information, and the actual measured core body temperature (as a label). Data is preprocessed, including missing value filling, feature standardization, and encoding of categorical variables (such as surgical type and gender). The historical data is divided into a training set and a validation set. The model is trained using the training set, and hyperparameters are adjusted using the validation set to optimize model performance. The model's prediction accuracy is evaluated using the mean deviation metric, ensuring that the mean deviation is less than ±0.27°C. During the surgery, the temperature trend index, real-time ear temperature data, and other relevant features are input into the trained machine learning model to calculate the patient's core body temperature in real time. For example, it is connected to the HIS system and the hand numbness system to collect information including but not limited to the following: basic information such as patient gender, age, height, and weight; diagnosis (trauma, shock, and other patients with unstable circulation leading to abnormal heat distribution), past medical history (whether there is metabolic disease), preoperative examinations (whether there is infection, malnutrition), and other medical history and comorbidity information; surgical method (laparotomy, thoracotomy, or minimally invasive, etc.), anesthesia method (general anesthesia or intrathecal anesthesia, etc.), time from the start of anesthesia to the start of surgery (the length of time the skin is exposed during the start of anesthesia to the disinfection and laying of the drape), the start time of surgery (the length of time the body cavity is open), bleeding / urine volume, infusion / blood transfusion, and other real-time intraoperative information to form a multi-source data set.

[0061] In a possible implementation, step S500 further includes step S510, wherein the real-time status information also includes a real-time vital sign dataset, and the real-time vital sign dataset and the real-time environmental feature dataset are added to the multi-source dataset, wherein the real-time vital sign dataset includes at least real-time heart rate, real-time axillary temperature and real-time blood pressure, and the real-time environmental feature dataset includes at least real-time environmental noise, real-time environmental temperature and real-time environmental humidity.

[0062] Specifically, building on a multi-source dataset already constructed based on a temperature trend index and real-time ear temperature data, a real-time vital sign dataset and a real-time environmental feature dataset were further added to this multi-source dataset to more comprehensively reflect the patient's intraoperative status, thereby improving the accuracy and reliability of core body temperature prediction. An optical heart rate sensor (integrated in the smart earbud) was used to obtain the patient's heart rate in real time, reflecting their cardiac function and stress response. A wireless temperature sensor was used to measure the patient's axillary temperature in real time. Although axillary temperature is not a direct reflection of core body temperature, it can provide a certain trend of body temperature changes. Forehead temperature was measured using devices such as infrared forehead thermometers. Forehead temperature is also a surface temperature, but it can serve as a quick reference for body temperature fluctuations. Environmental noise monitoring devices (such as noise meters) were used to obtain real-time noise levels in the operating room. Noise can affect the patient's mental state and sleep quality, and thus indirectly affect body temperature. A temperature sensor was used to monitor the temperature in the operating room, as ambient temperature is one of the important factors affecting the patient's body temperature. A hygrometer was used to measure the humidity level in the operating room in real time. Humidity and temperature interact together to influence the patient's body temperature regulation. The real-time vital sign dataset and real-time environmental feature dataset extracted above are integrated with the existing body temperature trend index and real-time ear temperature dataset to form a comprehensive dataset containing more dimensional information, thereby improving the comprehensiveness and accuracy of the multi-source dataset and more effectively predicting the patient's core body temperature.

[0063] Step S600: If the real-time predicted core body temperature is not within the predetermined core body temperature threshold, an abnormal body temperature warning is issued to the target user.

[0064] Specifically, the real-time predicted core body temperature is compared with a predetermined body temperature threshold (a normal body temperature range set according to medical standards and practical experience) to determine whether the body temperature is normal. If the body temperature exceeds the threshold range, the early warning mechanism is triggered, and a warning is issued to the medical staff through sound, light or screen prompts. Based on the early warning information, the medical staff promptly takes measures such as adjusting the room temperature, adjusting the depth of anesthesia, and using thermal insulation equipment to maintain the patient's body temperature within the normal range. The embodiment of the present application adopts the method of dynamically monitoring the real-time surgical status of the target user, analyzing the real-time anesthesia information in combination with the surgical type and stage characteristics, monitoring the real-time ear temperature with smart earplugs, and collaboratively analyzing the body temperature trend index and ear temperature data to predict the core body temperature. If it exceeds the predetermined threshold, an abnormal body temperature warning and other technical means are issued, thereby achieving the technical effect of timely and accurate prediction of the core body temperature and abnormal warning.

[0065] In one possible implementation, the method further includes step S700, after issuing an abnormal temperature warning to the target user if the real-time predicted core body temperature is not within the predetermined core body temperature threshold, it also includes activating an intelligent temperature control device based on the abnormal temperature warning, and performing closed-loop temperature control of the target user through the intelligent temperature control device, wherein the intelligent temperature control device is wirelessly connected to the multi-functional operating table.

[0066] Specifically, if the real-time predicted core temperature is not within the predetermined core temperature threshold, the system will issue a temperature anomaly warning to the target user. Subsequently, based on the temperature anomaly warning, the real-time predicted core temperature data is transmitted via wireless communication to an intelligent temperature control device, which then sends a control signal to activate the device. The intelligent temperature control device, which regulates the patient's temperature, includes devices such as inflatable warming blankets and water-heating blankets. These devices maintain the patient's temperature within a normal range through heating or cooling. Based on the deviation between the real-time predicted core temperature and the predetermined core temperature threshold, the intelligent temperature control device dynamically increases or decreases the heating intensity. For example, if the real-time predicted core temperature is below the threshold, the heating intensity is increased; if it is above the threshold, the heating intensity is decreased or stopped. Heating intensity refers to the power or speed of heating applied by the intelligent temperature control device; the greater the heating intensity, the faster the patient's temperature rises. By monitoring the patient's real-time predicted core body temperature (monitoring), providing feedback based on abnormal temperature warnings (feedback), and dynamically adjusting the heating intensity (regulation) through intelligent temperature control equipment, a closed-loop control system is formed to improve the accuracy and efficiency of temperature management, reduce the possibility of human intervention and errors, and provide strong protection for surgical safety and postoperative recovery.

[0067] In the above, refer to Figure 1 A method for monitoring and warning core body temperature during surgery according to an embodiment of the present invention is described in detail. Figure 2 A monitoring and early warning system for core body temperature during surgery according to an embodiment of the present invention is described.

[0068] According to an embodiment of the present invention, a system for monitoring and warning core body temperature during surgery is designed to address the technical issues of existing intraoperative core body temperature monitoring, which are untimely and inaccurate, and difficult to effectively detect and issue warnings for abnormal body temperature. This system achieves the technical effect of timely and accurate prediction of core body temperature and abnormality warnings. The system includes a real-time status information acquisition module 10, a real-time stage feature acquisition module 20, a body temperature trend index acquisition module 30, a real-time ear temperature set acquisition module 40, a real-time predicted core body temperature acquisition module 50, and a body temperature abnormality warning module 60.

[0069] A real-time status information acquisition module 10 is configured to dynamically monitor and obtain real-time status information of a target user, wherein the real-time status information includes a real-time surgical stage. A real-time stage feature acquisition module 20 is configured to obtain the target surgical type of the target user and obtain a real-time stage feature in combination with the real-time surgical stage. A body temperature trend index acquisition module 30 is configured to extract real-time anesthesia information from the real-time stage feature and analyze the real-time anesthesia information in combination with the target individual information of the target user to obtain a body temperature trend index. A real-time ear temperature set acquisition module 40 is configured to activate a temperature sensor group in a smart earbud and dynamically monitor and obtain a real-time ear temperature set of the target user through the temperature sensor group, wherein the smart earbud is fixed to a predetermined ear position of the target user. A real-time predicted core body temperature acquisition module 50 is configured to assemble a multi-source data set based on the body temperature trend index and the real-time ear temperature set, and perform collaborative analysis on the multi-source data set to obtain a real-time predicted core body temperature. A body temperature abnormality warning module 60 is configured to issue a body temperature abnormality warning to the target user if the real-time predicted core body temperature is not within a predetermined core body temperature threshold.

[0070] Below, the specific configuration of the body temperature trend index acquisition module 30 will be described in detail. As described above, the real-time anesthesia information in the real-time stage feature is extracted, and the real-time anesthesia information is analyzed in combination with the target individual information of the target user to obtain the body temperature trend index. The body temperature trend index acquisition module 30 may further include: a real-time anesthesia parameter vector generation unit for extracting the real-time anesthetic drug type, real-time anesthetic drug amount and real-time anesthesia method in the real-time anesthesia information, and normalizing them to form a real-time anesthesia parameter vector; a database traversal unit for traversing the real-time anesthesia parameter vector in the anesthesia database to obtain the most similar anesthesia parameter vector; a real-time anesthesia depth determination unit for using the historical anesthesia depth corresponding to the most similar anesthesia parameter vector as the real-time anesthesia depth; an anesthesia calibration feedback coefficient acquisition unit for using the target individual coefficient obtained by analyzing the target individual information as the anesthesia calibration feedback coefficient; and a body temperature trend index acquisition unit for performing weighted calculation on the anesthesia calibration feedback coefficient and the real-time anesthesia depth to obtain the body temperature trend index.

[0071] Among them, the real-time anesthetic drug type, real-time anesthetic drug amount and real-time anesthesia method in the real-time anesthesia information are extracted and standardized to form a real-time anesthesia parameter vector. The real-time anesthesia parameter vector generation unit may further include: an anesthesia vectorization plan acquisition subunit for acquiring an anesthesia vectorization plan, the anesthesia vectorization plan including an anesthetic drug type vectorization plan, an anesthetic drug amount vectorization plan and an anesthesia method vectorization plan; a real-time anesthetic drug label acquisition subunit for traversing the real-time anesthetic drug type in multiple labels with anesthetic drug type identification in the anesthetic drug type vectorization plan to obtain a real-time anesthetic drug label; a real-time anesthetic drug amount label acquisition subunit for traversing the real-time anesthetic drug amount in multiple labels with anesthetic drug amount identification in the anesthetic drug amount vectorization plan to obtain a real-time anesthetic drug amount label; a real-time anesthetic method label acquisition subunit for traversing the real-time anesthetic method in multiple labels with anesthetic method identification in the anesthetic method vectorization plan to obtain a real-time anesthetic method label; a real-time anesthesia parameter vector assembly subunit for assembling the real-time anesthesia parameter vector based on the real-time anesthetic drug label, the real-time anesthetic drug amount label and the real-time anesthesia method label.

[0072] Among them, after performing weighted calculation on the anesthesia calibration feedback coefficient and the real-time anesthesia depth to obtain the body temperature trend index, the body temperature trend index acquisition module 30 can further include: a real-time environmental feature data set extraction unit for extracting the real-time environmental feature data set in the real-time status information, wherein the real-time environmental feature data set includes real-time environmental noise; a body temperature trend index calibration unit for matching the noise calibration feedback coefficient corresponding to the real-time environmental noise, and calibrating and adjusting the body temperature trend index based on the noise calibration feedback coefficient.

[0073] Among them, the body temperature trend index acquisition module 30 can further include: a noise reduction adjustment unit is used to activate the smart sound inlet on the smart earplug if the real-time environmental noise is greater than a predetermined noise threshold, and perform noise reduction adjustment on the smart earplug through the smart sound inlet.

[0074] The specific configuration of the real-time ear temperature set acquisition module 40 will be described in detail below. As described above, the temperature sensor group in the smart earplug is activated, and the real-time ear temperature set of the target user is obtained through dynamic monitoring of the temperature sensor group. The real-time ear temperature set acquisition module 40 may further include: a real-time ear canal temperature acquisition unit for extracting the first temperature sensor in the temperature sensor group and obtaining the real-time ear canal temperature through monitoring of the first temperature sensor; a real-time auricle temperature acquisition unit for extracting the second temperature sensor in the temperature sensor group and obtaining the real-time auricle temperature through monitoring of the second temperature sensor; and a real-time ear temperature set formation unit for combining the real-time ear canal temperature and the real-time auricle temperature into the real-time ear temperature set.

[0075] The specific configuration of the real-time predicted core body temperature acquisition module 50 will be described in detail below. As described above, the real-time predicted core body temperature acquisition module 50 may further include: a multi-source dataset assembly unit configured to include the real-time status information in a real-time vital sign dataset, and to add the real-time vital sign dataset and the real-time environmental characteristic dataset to the multi-source dataset, wherein the real-time vital sign dataset includes at least real-time heart rate, real-time axillary temperature, and real-time blood pressure, and the real-time environmental characteristic dataset includes at least real-time environmental noise, real-time environmental temperature, and real-time environmental humidity.

[0076] The system may further include: a body temperature closed-loop control module for activating an intelligent temperature control device based on the abnormal body temperature warning after issuing an abnormal body temperature warning to the target user if the real-time predicted core body temperature is not within the predetermined core body temperature threshold, and performing closed-loop body temperature control of the target user through the intelligent temperature control device, wherein the intelligent temperature control device is wirelessly connected to the multi-functional operating table.

[0077] An intraoperative core body temperature monitoring and early warning system provided by an embodiment of the present invention can execute an intraoperative core body temperature monitoring and early warning method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0078] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0079] Based on the foregoing embodiments, an embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method described in any of the foregoing embodiments can be implemented.

[0080] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for monitoring and early warning of core body temperature during surgery, characterized in that: include: Dynamic monitoring obtains real-time status information of the target user, wherein the real-time status information includes the real-time operation stage; Acquire the target surgery type of the target user, and obtain real-time stage features in combination with the real-time surgery stage; extracting real-time anesthesia information from the real-time stage feature, and analyzing the real-time anesthesia information in combination with the target individual information of the target user to obtain a body temperature trend index; activating a temperature sensor group in a smart earplug, and dynamically monitoring and obtaining a real-time ear temperature set of the target user through the temperature sensor group, wherein the smart earplug is fixed to a predetermined ear position of the target user; Building a multi-source data set based on the body temperature trend index and the real-time ear temperature set, and collaboratively analyzing the multi-source data set to obtain a real-time predicted core body temperature; If the real-time predicted core body temperature is not within the predetermined core body temperature threshold, an abnormal body temperature warning is issued to the target user.

2. The method for monitoring and early warning of core body temperature during surgery according to claim 1, characterized in that: Extracting real-time anesthesia information from the real-time stage feature and analyzing the real-time anesthesia information in combination with the target individual information of the target user to obtain a body temperature trend index, including: extracting the real-time anesthetic drug type, real-time anesthetic drug amount, and real-time anesthetic method from the real-time anesthesia information, and normalizing them to form a real-time anesthesia parameter vector; Traversing the real-time anesthesia parameter vector in the anesthesia database to obtain the most similar anesthesia parameter vector; Using the historical anesthesia depth corresponding to the most similar anesthesia parameter vector as the real-time anesthesia depth; using a target individual coefficient obtained by analyzing the target individual information as an anesthesia calibration feedback coefficient; The anesthesia calibration feedback coefficient and the real-time anesthesia depth are weightedly calculated to obtain the body temperature trend index.

3. The method for monitoring and early warning of core body temperature during surgery according to claim 2, characterized in that: Extracting the real-time anesthetic drug type, real-time anesthetic drug amount, and real-time anesthetic mode from the real-time anesthesia information, and normalizing them to form a real-time anesthesia parameter vector, including: Obtaining a vectorized anesthesia plan, wherein the vectorized anesthesia plan includes a vectorized plan of anesthetic drug type, a vectorized plan of anesthetic drug amount, and a vectorized plan of anesthesia method; Traversing the real-time anesthetic drug type among multiple labels with anesthetic drug type identifiers in the anesthetic drug type vectorization plan to obtain a real-time anesthetic drug label; Traversing the real-time anesthetic drug amount among a plurality of tags with anesthetic drug amount identifiers in the anesthetic drug amount quantization plan to obtain a real-time anesthetic drug amount tag; Traversing the real-time anesthesia mode among multiple labels with anesthesia mode identifiers in the anesthesia mode vectorization plan to obtain a real-time anesthesia mode label; The real-time anesthesia parameter vector is constructed based on the real-time anesthetic drug label, the real-time anesthetic drug amount label, and the real-time anesthesia method label.

4. The method for monitoring and early warning of core body temperature during surgery according to claim 2, characterized in that: After performing weighted calculation on the anesthesia calibration feedback coefficient and the real-time anesthesia depth to obtain the body temperature trend index, the method further includes: Extracting a real-time environmental feature data set from the real-time status information, wherein the real-time environmental feature data set includes real-time environmental noise; A noise calibration feedback coefficient corresponding to the real-time environmental noise is matched, and the body temperature trend index is calibrated and adjusted based on the noise calibration feedback coefficient.

5. The method for monitoring and early warning of core body temperature during surgery according to claim 4, characterized in that: If the real-time environmental noise is greater than a predetermined noise threshold, the smart sound inlet on the smart earplug is activated, and noise reduction adjustment is performed on the smart earplug through the smart sound inlet.

6. The method for monitoring and early warning of core body temperature during surgery according to claim 1, characterized in that: Activating the temperature sensor group in the smart earplug and dynamically monitoring the target user's real-time ear temperature set through the temperature sensor group includes: Extracting a first temperature sensor from the temperature sensor group, and obtaining real-time ear canal temperature through monitoring by the first temperature sensor; Extracting a second temperature sensor from the temperature sensor group, and obtaining a real-time auricle temperature through monitoring by the second temperature sensor; The real-time ear canal temperature and the real-time auricle temperature constitute the real-time ear temperature set.

7. The method for monitoring and early warning of core body temperature during surgery according to claim 4, characterized in that: The real-time status information also includes a real-time vital sign data set, and the real-time vital sign data set and the real-time environmental feature data set are added to the multi-source data set, wherein the real-time vital sign data set includes at least real-time heart rate, real-time axillary temperature and real-time blood pressure, and the real-time environmental feature data set includes at least real-time environmental noise, real-time environmental temperature and real-time environmental humidity.

8. The method for monitoring and early warning of core body temperature during surgery according to claim 1, characterized in that: If the real-time predicted core body temperature is not within the predetermined core body temperature threshold, after issuing an abnormal temperature warning to the target user, it also includes activating an intelligent temperature control device according to the abnormal temperature warning, and performing closed-loop temperature control of the target user through the intelligent temperature control device, wherein the intelligent temperature control device is wirelessly connected to the multi-functional operating table.

9. A monitoring and early warning system for core body temperature during surgery, characterized in that: The system is used to implement the intraoperative core body temperature monitoring and early warning method according to any one of claims 1 to 8, and the system comprises: A real-time status information acquisition module is used to dynamically monitor and obtain the real-time status information of the target user, wherein the real-time status information includes the real-time operation stage; A real-time stage feature acquisition module is used to acquire the target surgery type of the target user and obtain the real-time stage feature in combination with the real-time surgery stage; a body temperature trend index acquisition module, configured to extract the real-time anesthesia information from the real-time stage feature, and analyze the real-time anesthesia information in combination with the target individual information of the target user to obtain a body temperature trend index; a real-time ear temperature set acquisition module, configured to activate a temperature sensor group in a smart earplug and dynamically monitor and obtain the real-time ear temperature set of the target user through the temperature sensor group, wherein the smart earplug is fixed to a predetermined ear position of the target user; a real-time predicted core body temperature acquisition module, configured to construct a multi-source data set based on the body temperature trend index and the real-time ear temperature set, and perform collaborative analysis on the multi-source data set to obtain a real-time predicted core body temperature; The abnormal body temperature warning module is used to issue an abnormal body temperature warning to the target user if the real-time predicted core body temperature is not within the predetermined core body temperature threshold.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a method for monitoring and warning core body temperature during surgery as described in any one of claims 1 to 8 is implemented.

Images