Hospital emergency call method, apparatus and device, and medium

Abstract

The invention relates to the technical field of medical calling, and discloses a hospital emergency calling method, device and equipment and a medium, and the method comprises the steps: obtaining the monitoring data of a patient; wherein the monitoring data comprises vital sign data and medical record data; based on the vital sign data and the medical record data, determining the disease severity corresponding to the patient; based on the severity of the illness state, determining a response medical team corresponding to the patient; obtaining the current position of each medical member in the response medical team, and generating response time corresponding to each medical member based on the current position; and sorting from low to high according to the response time, and calling the medical members in sequence until the medical members respond. The system has the beneficial effects of comprehensively evaluating the illness state, accurately positioning the medical personnel, and improving the first-aid efficiency and the medical resource utilization rate.

Description

Technical Field

[0001] The present application relates to the field of medical call technology, and in particular to a hospital emergency call method, device, equipment and medium. Background Art

[0002] The existing emergency call system has problems such as insufficient automation, lack of comprehensive condition judgment, poor positioning accuracy and low call efficiency. Traditional manual calls, fixed equipment alarms and broadcasting systems cannot quickly and accurately dispatch medical staff according to the patient's condition, and cannot accurately locate responders, resulting in extended response time, waste of resources and affected treatment effects.

[0003] Therefore, there is an urgent need for an intelligent system that can comprehensively assess the condition, accurately locate medical staff, and dynamically optimize resource allocation to improve emergency efficiency and medical resource utilization. Summary of the invention

[0004] The present application provides a hospital emergency call method, device, equipment and medium, which solves the technical problems of insufficient automation, lack of comprehensive condition judgment, poor positioning accuracy and low call efficiency, and achieves the technical effect of comprehensively evaluating the condition, accurately locating medical staff, and improving emergency efficiency and medical resource utilization.

[0005] In order to achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, an embodiment of the present application provides a hospital emergency call method, the method comprising: Acquire monitoring data of the patient; wherein the monitoring data includes vital signs data and medical record data; Determine the severity of the patient's condition based on the vital sign data and the medical record data; Based on the severity of the illness, determine the corresponding medical team for the patient; Acquire the current location of each medical member in the responding medical team, and generate the corresponding response time of each medical member based on the current location; The response times are sorted from low to high, and the medical members are called in sequence until they are answered.

[0006] The hospital emergency call method provided in this embodiment can fully understand the patient's health status and intelligently evaluate the severity of the disease by collecting the patient's vital signs data and medical record data in real time, thereby providing accurate decision support for the medical team. According to the severity of the disease, the most suitable medical team is automatically matched and resource allocation is optimized. At the same time, by tracking the location of medical team members in real time and calculating the response time, it is ensured that medical resources can be optimally dispatched, and members with the shortest response time are called for rescue first, ensuring the efficiency and timeliness of the rescue process, and ultimately improving the accuracy and speed of the entire emergency response process.

[0007] Optionally, determining the severity of the illness of the patient based on the vital sign data and the medical record data includes: Extracting vital sign features corresponding to the vital sign data, and extracting medical record features corresponding to the medical record data; Performing weighted fusion on the vital sign features and the medical record features to obtain a comprehensive feature vector; The severity of the illness of the patient is determined according to the comprehensive feature vector.

[0008] This embodiment can provide comprehensive basic data support for the patient's health status by extracting relevant features from vital signs data and medical record data. Then, these features are weighted and fused to form a comprehensive feature vector, which can effectively integrate the key factors in vital signs and medical record information. The comprehensive feature vector is used to assess the severity of the patient's condition, thereby achieving accurate judgment and classification of the condition. Through this weighted fusion method, the complementarity of various types of data can be fully utilized to improve the accuracy and robustness of condition assessment.

[0009] Optionally, the responding medical team includes a rescue team, expert members and department doctors; and determining the responding medical team corresponding to the patient based on the severity of the illness includes: In the case where the severity of the illness is severe, determining the corresponding responding medical team of the patient as the rescue team; In the case where the severity of the illness is moderate, determining that the corresponding responsive medical team of the patient is the expert member; When the severity of the illness is mild, the corresponding responsive medical team for the patient is determined to be the doctor in the department.

[0010] This embodiment can intelligently match and assign medical teams at different levels through real-time assessment of the severity of the patient's condition to ensure rapid response and treatment under different conditions. When the severity of the patient's condition is assessed as severe, it is automatically determined that the rescue team should respond to ensure that high-risk response measures and rescue operations can be quickly taken in emergency situations. When the patient's condition is moderate, the responding medical team will be assigned as expert members who can provide professional diagnosis and treatment plans for complex conditions. When the condition is mild, the responding medical team will be assigned as department doctors to ensure that the patient receives timely but non-emergency routine medical services. Thereby improving the allocation efficiency and response speed of medical resources, thereby improving the timeliness of patient treatment and medical quality.

[0011] Optionally, obtaining the current location of each medical member of the responding medical team includes: Obtaining the coordinate positions of at least three Bluetooth base stations adjacent to any medical member, and the signal strength sent by any medical member to the Bluetooth base stations; Based on the signal strength, determining a base station distance from any medical member to the Bluetooth base station; The current position of any medical member is determined by trilateration according to the base station distance and the coordinate position.

[0012] This embodiment constructs the data foundation required for positioning by acquiring the coordinate position of the Bluetooth base station and the signal strength sent by the medical members. Then the distance from each Bluetooth base station to the medical members is calculated by the signal strength; finally, the precise position of the medical members is finally determined by combining these distances and the base station positions through trilateral measurement. It is then possible to track the precise position of medical members in real time and provide high-precision positioning services in complex environments. Especially in emergency situations, it is possible to quickly determine the location of medical personnel, improve scheduling efficiency and response speed, and optimize the allocation and use of medical resources. This high-precision positioning capability can provide more powerful support for the medical team, effectively improve the ability of medical rescue and emergency response, and ensure the efficient operation of the medical management system.

[0013] Optionally, generating the response time corresponding to each medical member based on the current position includes: Based on the current position, determine the optimal path for any medical member to reach the patient using an optimal path algorithm; According to the optimal path, determining the arrival distance corresponding to any medical member and the number of elevators that need to be passed; The response time corresponding to any one of the medical members is determined according to the arrival distance and the number of elevators.

[0014] This embodiment first compares the current position of the medical member with the patient's position, and uses the optimal path algorithm to calculate the optimal path from the current position of the medical member to the patient's position. This process can ensure that in a complex building structure, the medical member can find the fastest and most direct path to reduce unnecessary time waste. The path planning not only takes into account the actual layout of the space, but also optimizes the medical member's route, thereby improving the rescue efficiency. Then, through the calculation result of the optimal path, the specific distance required for the medical member to reach the patient is further determined, and the number of elevators that may be involved on the path is taken into account. This information can provide an accurate basis for the subsequent response time estimation, especially in multi-story buildings or complex environments that require crossing floors, the use of elevators often becomes a key factor affecting the response time. Finally, the response time required for the medical member to reach the patient is calculated in combination with the determined arrival distance and the number of elevators. Through this response time prediction that comprehensively considers factors such as path length and elevator use, it can provide accurate response time estimates for medical management personnel, so that corresponding resource allocation and scheduling work can be done in advance.

[0015] Optionally, determining the response time corresponding to any one of the medical members according to the arrival distance and the number of elevators includes: Where T is the response time; D is the reach distance; V is the walking speed; n is the number of elevators; T elevator is the elevator waiting time; T additional This is additional processing time.

[0016] Optionally, the step of sorting the response times from low to high and calling the medical members in sequence until they are answered comprises: Sort the response times from low to high to obtain a sorted list; starting the call from the medical member with the lowest response time in the ranked list; When the call result is rejected or the number of calls exceeds a threshold, the next medical member in the sorted list is called until the medical member answers.

[0017] This embodiment obtains a response time sorting list by sorting the response time of each medical member from low to high. This sorting process can ensure that the medical member with the shortest response time is given priority for calling, thereby maximizing the timeliness and efficiency of the rescue and ensuring that the most timely medical support can reach the patient quickly. Then, based on the sorted list, the call is started from the medical member with the lowest response time. It effectively reduces the waste of medical resources, avoids unnecessary delays, and ensures that the medical team can be reasonably scheduled according to the priority of the actual response time, thereby improving the overall rescue response speed. Finally, when the call result is rejected or the number of calls exceeds the threshold, continue to call the next medical member in the sorted list in turn until a response is received. This effectively prevents rescue delays caused by a single member's inability to respond or multiple call failures, ensures that medical scheduling can be continued, and always gets an available medical member to respond, to maximize the smooth completion of the rescue mission.

[0018] In a second aspect, an embodiment of the present application provides a hospital emergency call device, the device comprising: A monitoring data acquisition unit, used to acquire the patient's monitoring data; wherein the monitoring data includes vital sign data and medical record data; a severity determination unit, configured to determine the severity of the condition of the patient based on the vital sign data and the medical record data; A response team determination unit, used for determining a response medical team corresponding to the patient based on the severity of the condition; A response time generating unit, used for acquiring the current position of each medical member in the responding medical team, and generating the response time corresponding to each medical member based on the current position; The medical member calling unit is used to sort the response times from low to high and call the medical members in sequence until they are answered.

[0019] In a third aspect, an embodiment of the present application provides a computer device, including: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the above-mentioned hospital emergency call method by executing the computer instructions.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the hospital emergency call method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A flowchart of a hospital emergency call method provided in an embodiment of the present application; Figure 2 A flowchart of step S3 provided in an embodiment of the present application; Figure 3 A flowchart of step S5 provided in an embodiment of the present application; Figure 4 A flowchart for obtaining the current location of each medical member of a responding medical team provided in an embodiment of the present application; Figure 5 A flowchart of generating a response time corresponding to each medical member based on the current location provided in an embodiment of the present application; Figure 6 A flowchart of step S9 provided in an embodiment of the present application; Figure 7 A block diagram of a hospital emergency call device provided in an embodiment of the present application; Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0024] With the rapid development of the medical industry, especially the increasing demand for efficient and intelligent equipment in the field of emergency treatment, the traditional medical call and emergency response systems have exposed some significant shortcomings, affecting the timeliness and accuracy of the emergency treatment process. Therefore, many hospitals and emergency equipment manufacturers have begun to explore more intelligent solutions to improve response efficiency and treatment effects.

[0025] However, the existing emergency call system still faces some technical bottlenecks and deficiencies, which are specifically manifested in the following aspects: Manual call system: Currently, many hospitals rely on medical staff to make manual calls through telephones, intercoms or buttons. This method has the problems of long response time and low call efficiency. Especially during the golden time for rescue, delays in manual operations may lead to unnecessary waste of time and affect the effect of emergency treatment.

[0026] Fixed equipment alarm system: such as abnormal alarms of bedside alarms or monitoring equipment. The working scope of these systems is usually limited to a single device. When the patient's condition changes, the system cannot make a comprehensive judgment and cannot automatically dispatch the corresponding medical team according to the severity of the condition. For example, if the patient's condition is more complicated, the alarm of a certain physiological indicator alone may not reflect the urgency of the entire condition, thus affecting the effect of treatment.

[0027] Broadcast system: Some hospitals use broadcast messages to send emergency calls to medical staff. However, the limitation of this method is that it cannot accurately locate the actual location of medical staff, resulting in the inability of responders to arrive at the scene in time. Moreover, the broadcast call range is too wide, which can easily lead to too many responders or waste of resources, or even confusion.

[0028] To sum up, the shortcomings are mainly reflected in the following aspects: Insufficient automation: Existing systems often rely on manual operations or single-point alarms, lack automated call processes, and are unable to quickly and accurately dispatch patients based on their conditions.

[0029] Lack of comprehensive condition assessment: Current systems usually issue alarms based on only a single physiological indicator and lack a comprehensive assessment of the patient's overall condition, which may lead to false alarms or missed alarms and affect treatment decisions.

[0030] Poor positioning accuracy: Existing systems cannot accurately locate the location of medical staff, thus affecting the speed and efficiency of response.

[0031] Low call efficiency: The existing system does not implement dynamic hierarchical response, resulting in the call system being unable to dispatch the most appropriate medical personnel in an emergency, resulting in waste of resources or slow response.

[0032] Therefore, there is an urgent need for a more intelligent system that can comprehensively assess the condition, accurately locate medical staff, and dynamically optimize resource allocation to improve emergency efficiency and the utilization of medical resources.

[0033] According to an embodiment of the present application, an embodiment of a hospital emergency call method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] In this embodiment, a hospital emergency call method is provided. Figure 1 A flowchart of a hospital emergency call method provided in an embodiment of the present application, such as Figure 1 As shown, the process includes the following steps: Step S1, obtaining the patient's monitoring data; wherein the monitoring data includes vital sign data and medical record data.

[0035] Specifically, the monitor collects multiple vital signs data output by the monitoring equipment in real time, such as electrocardiogram (ECG), respiration (RESP), body temperature (TEMP), pulse oxygen saturation (SpO2), pulse rate (PR), non-invasive blood pressure (NIBP), heart rate (HR), etc. The medical record data obtained through the doctor's workstation includes the patient's hospitalization medical record, medical course information record, past rescue history and other data.

[0036] Step S3, determining the severity of the patient's condition based on the vital sign data and medical record data.

[0037] Specifically, you can use trained machine learning models (such as random forests, support vector machines, neural networks, etc.), which can automatically learn and predict the severity of the disease based on various features. For example, a continuous severity score can be predicted through regression models (such as linear regression, logistic regression, etc.), or the disease can be divided into different severity levels (such as mild, moderate, and severe) through classification models (such as decision trees, KNN, SVM, etc.). In addition to machine learning models, you can also combine expert experience to assess the disease based on some known medical rules, clinical standards, or diagnostic criteria. For example, experts may have concluded that certain symptoms or signs are highly indicative in specific situations, and these experiences can be converted into rules or thresholds to further judge the severity of the disease.

[0038] Step S5, determining the corresponding medical team for the patient based on the severity of the disease.

[0039] Specifically, according to the severity of the disease, the corresponding medical response team of the patient is determined, including the rescue team, expert members or department doctors. At the same time, the patient's medical record data is automatically linked so that the rescue team can quickly obtain the patient's medical history and current condition, so as to carry out effective emergency treatment. Through this automated response mechanism, it can ensure that quick action is taken when the patient's condition worsens, improve the efficiency and success rate of treatment, and reduce the workload of medical staff.

[0040] Step S7, obtaining the current position of each medical member in the responding medical team, and generating the corresponding response time of each medical member based on the current position.

[0041] Specifically, positioning technologies such as GPS, indoor positioning systems or network-based positioning methods (for example, Wi-Fi positioning, Bluetooth positioning, etc.) are usually used. The embodiment of the present application preferably uses Bluetooth positioning to track the location of each medical member in real time. The purpose of obtaining the real-time location is to understand the distance between each medical member and the patient, so as to effectively evaluate the response time of each member to arrive at the patient site. According to the distance between the location of the medical member and the patient's location, the time required for each member to arrive at the patient site can be calculated. The response time is not only based on the straight-line distance, but may also take into account factors such as floors and elevator waiting. The calculation of the response time can be combined with map data, real-time traffic information, etc. to accurately predict the arrival time.

[0042] Step S9, sorting from low to high according to the response time, calling the medical members in sequence until they are answered.

[0043] Specifically, once the response time of each medical member is obtained, the response time can be sorted from low to high based on the sorting mechanism, and the medical member with the shortest response time can be called first. This location and time-based optimization mechanism can significantly improve rescue efficiency and ensure that the nearest medical personnel can quickly reach the patient site.

[0044] The hospital emergency call method provided in this embodiment can fully understand the patient's health status and intelligently evaluate the severity of the disease by collecting the patient's vital signs data and medical record data in real time, thereby providing accurate decision support for the medical team. According to the severity of the disease, the most suitable medical team is automatically matched and resource allocation is optimized. At the same time, by tracking the location of medical team members in real time and calculating the response time, it is ensured that medical resources can be optimally dispatched, and members with the shortest response time are called for rescue first, ensuring the efficiency and timeliness of the rescue process, and ultimately improving the accuracy and speed of the entire emergency response process.

[0045] Figure 2 The flowchart of step S3 provided in the embodiment of the present application may include the following steps: Step S31, extracting vital sign features corresponding to the vital sign data, and extracting medical record features corresponding to the medical record data.

[0046] Specifically, convolutional neural networks (CNNs) can be used to extract vital signs features, such as the mean, median, and mode of vital signs such as heart rate and blood pressure in a specified time period. Frequency domain characteristics of heart rate, respiration, and other signals can be extracted and analyzed, and time domain signals can be converted into frequency domain signals through Fourier transform to identify specific frequency components. For example, NLP technology can be used to extract keywords and phrases in medical record data and identify features such as diseases, symptoms, and treatment patterns that frequently appear in medical record data.

[0047] Step S33, weighted fusion of vital sign features and medical record features to obtain a comprehensive feature vector.

[0048] Specifically, the vital signs features and medical record features are weighted and fused to obtain a comprehensive feature vector: F=α×X'+β×H, where F is the comprehensive feature vector, X' is the vital signs feature, H is the medical record feature, α is the weight parameter of the vital signs feature, and β is the weight parameter of the medical record feature. α and β can be obtained based on expert knowledge, statistical analysis or machine learning technology, and α is usually greater than β. This comprehensive feature vector method combines real-time vital signs data and historical medical record data, providing more comprehensive data support for subsequent assessment of the severity of the disease.

[0049] For example, the vital signs features need to be normalized first to ensure that different features have the same measure, which is convenient for subsequent weighted fusion. The normalization formula is: Assumption: Heart rate (HR) range is [60,180], given value is 95, .

[0050] The blood oxygen saturation (SpO2) value range is [80,100], and the given value is 90. .

[0051] Systolic blood pressure (SBP) range [90,200], given value 130, .

[0052] Diastolic blood pressure (DBP) ranges from [50,120], with a given value of 85. .

[0053] The normalized vital sign feature X' is: X'=[0.292,0.5,0.364,0.5] The medical record feature H is used directly without normalization: abnormal heart rate (such as heart disease): 1; abnormal lung function (such as pulmonary edema): 0, H = [1,0].

[0054] In order to align with the dimension of the vital sign feature X', the medical record feature H is expanded to H': H'=[1,0,0,0].

[0055] Given α=0.7, β=0.3, calculate each element in each comprehensive feature vector F item by item: F[1]=0.7×X′[1]+0.3×H′[1]=0.7×0.292+0.3×1=0.2044+0.3=0.504 F[2]=0.7×X′[2]+0.3×H′[2]=0.7×0.5+0.3×0=0.35+0=0.35 F[3]=0.7×X′[3]+0.3×H′[3]=0.7×0.364+0.3×0=0.2548+0=0.255 F[4]=0.7×X′[4]+0.3×H′[4]=0.7×0.5+0.3×0=0.35+0=0.35 The final comprehensive feature vector F is: F=[0.504,0.35,0.255,0.35] It should be noted here that for each vital sign feature, only the corresponding medical record feature is fused, rather than evenly distributing all medical record features to all vital sign features. The correspondence between vital sign features and medical record features is based on expert experience or pre-constructed corresponding associations. That is, it is pre-defined that the heart rate (HR) in the vital sign feature is related to heart disease in the medical record feature, so the two need to be weightedly fused. The blood oxygen saturation (SpO2) in the vital sign feature is related to abnormal lung function in the medical record feature, so the two need to be weightedly fused, and so on. This ensures that each comprehensive feature value in the comprehensive feature vector F can accurately reflect the fusion of its corresponding vital sign feature and medical record feature, thereby improving the interpretability and accuracy of the feature.

[0056] Step S35, determining the severity of the patient's illness according to the comprehensive feature vector.

[0057] Specifically, the severity of the disease is divided into 3 levels: Mild: The condition is stable and no special treatment is needed for the time being. Just call the doctor in the corresponding department of the patient for diagnosis and observation.

[0058] Moderate: The condition is at risk of worsening and requires timely monitoring or treatment. This may involve expert consultation, in which case an expert member will need to be called in for diagnosis and observation.

[0059] Severe: Abnormal vital signs, and the rescue team must be called immediately.

[0060] To make judgments based on each element in the comprehensive feature vector, you can use trained machine learning models (such as random forests, support vector machines, neural networks, etc.), which can automatically learn and predict the severity of the disease based on various features. For example, a continuous severity score can be predicted through regression models (such as linear regression, logistic regression, etc.), or the disease can be divided into different severity levels (such as mild, moderate, and severe) through classification models (such as decision trees, KNN, SVM, etc.). In addition to machine learning models, you can also combine expert experience to assess the disease based on some known medical rules, clinical standards, or diagnostic criteria. For example, experts may have concluded that certain symptoms or signs are highly indicative in specific situations, and these experiences can be converted into rules or thresholds to further judge the severity of the disease.

[0061] Continuing with the above example, the corresponding relationship between each comprehensive feature in the comprehensive feature vector F is: F[1]: heart rate feature; F[2]: blood oxygen saturation feature; F[3]: systolic blood pressure feature; F[4]: diastolic blood pressure feature.

[0062] The evaluation criteria set were as follows: the severity of the disease was mild: 0.3≤F[1]≤0.6 (heart rate within the normal range), F[2]≥0.4 (normal blood oxygen), F[3]≥0.3 and F[3]≤0.6 (normal blood pressure); The severity of the disease is moderate: F[1]<0.3 or F[1]>0.6 (low or high heart rate), 0.2≤F[2]<0.4 (slightly low blood oxygen); The severity of the disease is severe: F[2]<0.2 (severely low blood oxygen), F[3]<0.3 (severely low blood pressure), F[1]>0.8 (abnormally fast heart rate).

[0063] According to the above conditions, when the comprehensive feature vector in the comprehensive feature vector exists in the severe range, the severity of the disease is severe; when the comprehensive feature vector does not exist in the severe range but exists in the moderate range, the severity of the disease is moderate; when the comprehensive feature vector only exists in the mild range, the severity of the disease is mild.

[0064] Therefore, the comprehensive feature vector F=[0.504,0.35,0.255,0.35], where F[3]<0.3, means that the severity of the patient's condition is directly judged as severe.

[0065] and Figure 1Compared with the embodiment shown in the figure, this embodiment can provide comprehensive basic data support for the patient's health status by extracting relevant features from vital signs data and medical record data. Then, these features are weighted and fused to form a comprehensive feature vector, which can effectively integrate the key factors in vital signs and medical record information. The comprehensive feature vector is used to assess the severity of the patient's condition, thereby achieving accurate judgment and classification of the condition. Through this weighted fusion method, the complementarity of various types of data can be fully utilized to improve the accuracy and robustness of condition assessment.

[0066] Figure 3 The flowchart of step S5 provided in the embodiment of the present application, the responding medical team includes a rescue team, expert members and department doctors; the process may include the following steps: Step S51, when the severity of the disease is severe, determine that the corresponding responding medical team of the patient is a rescue team.

[0067] Step S53, when the severity of the disease is moderate, determine that the responding medical team corresponding to the patient is an expert member.

[0068] Step S55, when the severity of the disease is mild, determine that the corresponding responding medical team of the patient is the department doctor.

[0069] Specifically, since the severity of the patient's condition is judged to be severe, the corresponding responding medical team should be the rescue team. This means that the emergency rescue process needs to be initiated immediately, and the rescue team needs to be called to provide emergency treatment to the patient. If the severity of the patient's condition is judged to be moderate, the corresponding responding medical team should be expert members. This usually involves situations that require expert consultation, and the expert members will provide further diagnosis and treatment to the patient. If the severity of the patient's condition is judged to be mild, the corresponding responding medical team should be the department doctor. In this case, the patient's condition is relatively stable and does not require emergency treatment, but requires observation and diagnosis by the department doctor.

[0070] and Figure 1Compared with the embodiment shown, this embodiment can intelligently match and assign medical teams at different levels through real-time assessment of the severity of the patient's condition to ensure rapid response and treatment under different conditions. When the severity of the patient's condition is assessed as severe, it is automatically determined that the rescue team should respond to ensure that high-risk response measures and rescue operations can be quickly taken in emergency situations. When the patient's condition is moderate, the responding medical team will be assigned as expert members who can provide professional diagnosis and treatment plans for complex conditions. When the condition is mild, the responding medical team will be assigned as department doctors to ensure that the patient receives timely but non-emergency routine medical services. Thereby improving the allocation efficiency and response speed of medical resources, thereby improving the timeliness of patient treatment and medical quality.

[0071] Figure 4 The flowchart for obtaining the current location of each medical member in the responding medical team provided in the embodiment of the present application may include the following steps: Step S711, obtaining the coordinate positions of at least three Bluetooth base stations adjacent to any medical member, and the signal strength sent by any medical member to the Bluetooth base station.

[0072] Specifically, multiple Bluetooth base stations are deployed on each floor and department of the hospital. These base stations locate the location by receiving signals transmitted from Bluetooth tags (usually mobile phones or special Bluetooth devices) on medical staff. The coordinates of each base station are known, and they interact with the Bluetooth tags of medical staff through Bluetooth technology to obtain the signal strength of medical staff.

[0073] Step S713: determining the base station distance from any medical member to the Bluetooth base station based on the signal strength.

[0074] Signal strength (RSSI value) is an indicator to measure the strength of the received Bluetooth signal. It is usually expressed as a negative value. The larger the value (i.e., the closer to 0), the stronger the signal strength and the closer to the Bluetooth base station. The stronger the base station signal strength, the closer the medical staff is to the base station; conversely, a weaker signal indicates a farther distance. Positioning is performed through the locations of at least three adjacent Bluetooth base stations. The coordinates of the base station are pre-set by the system, which can accurately calibrate the physical location of each base station.

[0075] Specifically, the RSSI distance estimation formula can be used to calculate the distance from the medical member to each Bluetooth base station. The formula is as follows: , where d is the distance (meters), A is the absolute value of the signal strength RSSI when the distance to the Bluetooth device is 1 meter, usually 59, RSSI is the received signal strength, and n is the environmental attenuation factor (usually between 2-4, determined according to the scenario).

[0076] Assume that A=59, n=3, and the signal strength RSSI values ​​are Bluetooth base station 1: -60, Bluetooth base station 2: -65, and Bluetooth base station 3: -75.

[0077] The distance from the medical staff to the Bluetooth base station 1: ; The distance from the medical member to the Bluetooth base station 2: ; The base station distance from the medical member to the Bluetooth base station 3: .

[0078] Step S715, determining the current position of any medical member by trilateration according to the base station distance and coordinate position.

[0079] Specifically, assuming that the coordinate positions of the three Bluetooth base stations are: Bluetooth base station 1 (coordinate x1=0, y1=0), Bluetooth base station 2 (coordinate x2=4, y2=0), Bluetooth base station 3 (coordinate x3=2, y3=4), given that d1=1.08, d2=1.58, d3=3.41, the following set of equations is determined by trilateration: Bluetooth base station 1: Right now Bluetooth Base Station 2: Right now Bluetooth Base Station 3: Right now The final calculated coordinates of the medical member are x=1.834, y=0.275.

[0080] Preferably, the trilateration method may be affected by signal noise and errors in practical applications, resulting in inaccurate positioning results. In order to improve the accuracy and reliability of positioning, the weighted least squares method can be introduced to reduce the impact of noise on the calculation results by assigning different weights to different measurement data. The weights are usually assigned based on the reliability or accuracy of the measurement. By minimizing the weighted sum of squared errors, a more accurate estimate of the device location can be obtained. Kalman filtering can also be used to effectively handle noise and uncertainty in RSSI data to provide smooth and accurate positioning results. By combining these optimization algorithms and techniques, the positioning accuracy and robustness of the trilateration method based on RSSI data can be significantly improved.

[0081] and Figure 1Compared with the embodiment shown, this embodiment constructs the data basis required for positioning by obtaining the coordinate position of the Bluetooth base station and the signal strength sent by the medical member. Then the distance from each Bluetooth base station to the medical member is calculated by the signal strength; finally, the precise position of the medical member is finally determined by combining these distances and the base station position through trilateral measurement. It can then track the precise position of the medical member in real time and provide high-precision positioning services in complex environments. Especially in emergency situations, it can quickly determine the location of medical personnel, improve scheduling efficiency and response speed, and optimize the allocation and use of medical resources. This high-precision positioning capability can provide more powerful support for the medical team, effectively improve the ability of medical rescue and emergency response, and ensure the efficient operation of the medical management system.

[0082] Figure 5 The flowchart provided in the embodiment of the present application for generating the response time corresponding to each medical member based on the current location may include the following steps: Step S731, based on the current position, use the optimal path algorithm to determine the optimal path for any medical member to reach the patient.

[0083] Specifically, the optimal path algorithm can be used to determine the optimal path for any medical member to reach the patient based on the current location and the location where the patient needs to be reached, combined with the hospital's indoor building structure and traffic conditions. The optimal path algorithm includes but is not limited to the Dijkstra algorithm, the A* algorithm, the Rapid Exploration Random Tree (RRT) algorithm, and the D*Lite algorithm.

[0084] For example, the rooms or intersections in a hospital floor are nodes, which constitute the basic unit of a weighted graph. Each node can be regarded as a specific location on the map, for example: Node A: represents the location of medical members. Nodes B and C: represent other key locations or intersections in the hospital. Node D: represents the location of the patient. By connecting these nodes, the network structure of the hospital floor is constructed, and then a path search algorithm such as the Dijkstra algorithm is used to calculate the shortest path from one node to another.

[0085] Step S733: Determine the arrival distance and the number of elevators required to be passed by any medical member according to the optimal path.

[0086] Specifically, according to the optimal path, the number of elevators that need to be passed on the optimal path is analyzed, and the distance that the medical staff needs to walk on the optimal path is calculated. Assume that the optimal path analysis is as follows: If the medical staff is on the 3rd floor and the patient is also on the 3rd floor, there is no need to use the elevator, and the optimal path distance is 50 meters. If the medical staff is on the 2nd floor and the patient is on the 4th floor, then the medical staff needs to use the elevator at least twice (from the 2nd floor to the 3rd floor, and then from the 3rd floor to the 4th floor), and the optimal path distance is 150 meters.

[0087] Step S735, determining the response time corresponding to any medical member according to the arrival distance and the number of elevators.

[0088] In some preferred embodiments, determining the response time corresponding to any medical member according to the arrival distance and the number of elevators includes: Where T is the response time; D is the reach distance; V is the walking speed; n is the number of elevators; T elevator is the elevator waiting time; T additional This is additional processing time.

[0089] Specifically, the walking speed V is based on the average walking speed of an adult, 1.2 m / s, and the additional processing time T additional is 3 seconds, the elevator waiting time T elevator For example, the time required to prepare the equipment needed by the patient or to open the door is 10 seconds. Assuming that the medical member's arrival distance D is 50 meters and the number of elevators passed is 2, the response time calculated according to the above formula is about 65 seconds.

[0090] and Figure 1Compared with the embodiment shown in the figure, this embodiment first compares the current position of the medical member with the patient's position, and uses the optimal path algorithm to calculate the optimal path from the current position of the medical member to the patient's position. This process can ensure that in a complex building structure, the medical member can find the fastest and most direct path to reduce unnecessary time waste. The path planning not only takes into account the actual layout of the space, but also optimizes the route of the medical member, thereby improving the rescue efficiency. Then, through the calculation result of the optimal path, the specific distance required for the medical member to reach the patient is further determined, and the number of elevators that may be involved on the path is taken into account. This information can provide an accurate basis for the subsequent response time estimation, especially in multi-story buildings or complex environments that require crossing floors, the use of elevators often becomes a key factor affecting the response time. Finally, the response time required for the medical member to reach the patient is calculated in combination with the determined arrival distance and the number of elevators. Through this response time prediction that comprehensively considers factors such as path length and elevator use, it is possible to provide accurate response time estimates for medical management personnel, so that corresponding resource allocation and scheduling work can be done in advance.

[0091] Figure 6 The flowchart of step S9 provided in the embodiment of the present application may include the following steps: Step S91, sorting from low to high according to the response time to obtain a sorted list.

[0092] Step S93: Start calling the medical member with the lowest response time in the sorted list.

[0093] Step S95: When the call result is rejected or the number of calls exceeds the threshold, the next medical member in the sorted list is called until the answer is received.

[0094] Specifically, all medical members and their response times are put into a list and sorted from low to high according to the response time. The medical member with the lowest response time is selected from the sorted list, that is, the medical member who can reach the patient first. Then a call is initiated to the medical member, requesting him to go to the patient's location. If the first call is rejected or not responded to, or the number of calls exceeds the preset threshold (for example, 3 consecutive calls are not connected), proceed to the next step. Select the next medical member with a lower response time in the sorted list and initiate a call to him. Continue this process until a medical member answers and accepts the task. Through this process, it can be ensured that the task is assigned to the medical member who responds the fastest, thereby improving the response efficiency and patient care quality in emergency situations.

[0095] and Figure 1Compared with the embodiment shown, this embodiment obtains a response time sorting list by sorting the response time of each medical member from low to high. This sorting process can ensure that the medical member with the shortest response time is given priority for calling, thereby maximizing the timeliness and efficiency of the rescue and ensuring that the most timely medical support can reach the patient quickly. Then, based on the sorting list, the call is started from the medical member with the lowest response time. It effectively reduces the waste of medical resources, avoids unnecessary delays, and ensures that the medical team can be reasonably scheduled according to the priority of the actual response time, thereby improving the overall rescue response speed. Finally, when the call result is rejected or the number of calls exceeds the threshold, the next medical member in the sorting list is called in turn until a response is received. This effectively prevents rescue delays caused by a single member's inability to respond or multiple call failures, ensures that medical dispatch can be continued, and always obtains an available medical member to respond, maximizing the smooth completion of the rescue mission.

[0096] Accordingly, please refer to Figure 7 A block diagram of a hospital emergency call device provided in an embodiment of the present application, the device comprising: The monitoring data acquisition unit 101 is used to acquire the patient's monitoring data; wherein the monitoring data includes vital sign data and medical record data; The severity determination unit 103 is used to determine the severity of the patient's condition based on the vital sign data and the medical record data; A response team determination unit 105 is used to determine a response medical team corresponding to the patient based on the severity of the disease; A response time generating unit 107, used to obtain the current position of each medical member in the responding medical team, and generate a corresponding response time for each medical member based on the current position; The medical member calling unit 109 is used to sort the medical members according to the response time from low to high, and call the medical members in sequence until they are answered.

[0097] In some optional implementations, the severity determination unit 103 includes: Extracting vital sign features corresponding to the vital sign data, and extracting medical record features corresponding to the medical record data; Perform weighted fusion on vital sign features and medical record features to obtain a comprehensive feature vector; According to the comprehensive feature vector, the severity of the patient's condition is determined.

[0098] In some optional implementations, the response medical team includes a rescue team, expert members, and department doctors; the response team determination unit 105 includes: In the case of severe illness, the patient's corresponding response medical team is determined to be the rescue team; In cases where the severity of the illness is moderate, the patient's corresponding response medical team is determined to be a specialist member; In cases where the severity of the illness is mild, the patient's corresponding response medical team is determined to be the department doctor.

[0099] In some optional implementations, obtaining the current location of each medical member in the responding medical team includes: Obtaining the coordinates of at least three Bluetooth base stations adjacent to any medical member, and the signal strength sent by any medical member to the Bluetooth base station; Based on the signal strength, determine the base station distance from any medical member to the Bluetooth base station; The current location of any medical member is determined by trilateration based on the base station distance and coordinate position.

[0100] In some optional implementations, generating a response time corresponding to each medical member based on the current location includes: Based on the current location, the optimal path algorithm is used to determine the optimal path for any medical member to reach the patient; According to the optimal path, determine the corresponding arrival distance of any medical member and the number of elevators that need to be passed; Determine the corresponding response time of any medical member based on the arrival distance and the number of elevators.

[0101] In some optional implementations, determining the response time corresponding to any medical member according to the arrival distance and the number of elevators includes: Where T is the response time; D is the reach distance; V is the walking speed; n is the number of elevators; T elevator is the elevator waiting time; T additional This is additional processing time.

[0102] In some optional implementations, the medical member calling unit 109 includes: Sort by response time from low to high to get a sorted list; Begin calling from the medical member with the lowest response time in the ranked list; When the call result is rejected or the number of calls exceeds the threshold, the next medical member in the sorted list is called until the answer is given.

[0103] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0104] In this embodiment, a hospital emergency call device is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0105] See also Figure 8 , Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0106] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0107] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0108] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0110] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0111] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or is implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0112] The devices or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0113] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0114] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods and devices. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0115] The present application is described with reference to the flowcharts and / or block diagrams of the methods and devices according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0119] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0120] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0121] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A hospital emergency call method, characterized in that: The method comprises: Acquire monitoring data of the patient; wherein the monitoring data includes vital signs data and medical record data; Determine the severity of the patient's condition based on the vital sign data and the medical record data; Based on the severity of the illness, determine the corresponding medical team for the patient; Acquire the current location of each medical member in the responding medical team, and generate the corresponding response time of each medical member based on the current location; The response times are sorted from low to high, and the medical members are called in sequence until they are answered.

2. The method according to claim 1, characterized in that: Determining the severity of the illness of the patient based on the vital sign data and the medical record data includes: Extracting vital sign features corresponding to the vital sign data, and extracting medical record features corresponding to the medical record data; Performing weighted fusion on the vital sign features and the medical record features to obtain a comprehensive feature vector; The severity of the illness of the patient is determined according to the comprehensive feature vector.

3. The method according to claim 1, characterized in that: The responding medical team includes a rescue team, expert members and department doctors; the responding medical team corresponding to the patient is determined based on the severity of the disease, including: In the case where the severity of the illness is severe, determining the corresponding responding medical team of the patient as the rescue team; In the case where the severity of the illness is moderate, determining that the corresponding responsive medical team of the patient is the expert member; When the severity of the illness is mild, the corresponding responsive medical team for the patient is determined to be the doctor in the department.

4. The method according to claim 1, characterized in that: The obtaining of the current location of each medical member of the responding medical team includes: Obtaining the coordinate positions of at least three Bluetooth base stations adjacent to any medical member, and the signal strength sent by any medical member to the Bluetooth base stations; Based on the signal strength, determining a base station distance from any medical member to the Bluetooth base station; The current position of any medical member is determined by trilateration according to the base station distance and the coordinate position.

5. The method according to claim 1, characterized in that The generating the response time corresponding to each medical member based on the current position includes: Based on the current position, determine the optimal path for any medical member to reach the patient using an optimal path algorithm; According to the optimal path, determining the arrival distance corresponding to any medical member and the number of elevators that need to be passed; The response time corresponding to any one of the medical members is determined according to the arrival distance and the number of elevators.

6. The method according to claim 5, characterized in that The determining, according to the arrival distance and the number of elevators, the response time corresponding to any one of the medical members includes: Where T is the response time; D is the reach distance; V is the walking speed; n is the number of elevators; T elevator is the elevator waiting time; T additional This is additional processing time.

7. The method according to claim 1, characterized in that The step of sorting the response times from low to high and calling the medical members in sequence until they are answered comprises: Sort the response times from low to high to obtain a sorted list; starting the call from the medical member with the lowest response time in the ranked list; When the call result is rejected or the number of calls exceeds a threshold, the next medical member in the sorted list is called until the medical member answers.

8. A hospital emergency call device, characterized in that: The device comprises: A monitoring data acquisition unit, used to acquire the patient's monitoring data; wherein the monitoring data includes vital sign data and medical record data; a severity determination unit, configured to determine the severity of the condition of the patient based on the vital sign data and the medical record data; A response team determination unit, used to determine a response medical team corresponding to the patient based on the severity of the condition; A response time generating unit, used for acquiring the current position of each medical member in the responding medical team, and generating the response time corresponding to each medical member based on the current position; The medical member calling unit is used to sort the response times from low to high and call the medical members in sequence until they are answered.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the hospital emergency call method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the hospital emergency call method according to any one of claims 1 to 7.

Images