First-aid data intelligent management sharing platform based on Internet of Things

Abstract

The invention relates to the technical field of data management, in particular to a first-aid data intelligent management sharing platform based on the Internet of Things. The acquisition module is used for acquiring a target first-aid data set of a target first-aid demander, a historical first-aid data set of a historical first-aid demander and a to-be-matched hospital set of the target first-aid demander; and the second acquisition module is used for acquiring the target matching degree corresponding to each hospital in the to-be-selected hospital set, and taking the hospital corresponding to the maximum target matching degree as the emergency treatment matching hospital of the target emergency treatment demander. And the probability that the first-aid demander cannot obtain effective first aid within the optimal treatment time can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and particularly relates to an intelligent management and sharing platform for first-aid data based on the Internet of Things. Background Art

[0002] With the rapid development of the Internet of Things, people's requirements for first aid are also increasing day by day. Therefore, the first-aid data management and sharing platform has emerged as the times require. The first-aid data management and sharing platform is a system that can realize the collection, transmission, analysis, and collaborative management of first-aid whole-process data by integrating technologies such as the Internet of Things, big data, and 5G communication. In the current pre-hospital first-aid system in the first-aid data management and sharing platform, generally, the hospital for the first-aid requester is determined based on the principle of proximity. That is, after the first-aid requester dials the first-aid call, the dispatching center usually gives priority to dispatching the ambulance of the nearest first-aid station to the first-aid requester to shorten the response time. If the vehicle at the nearest station is busy (such as on a mission), the second-nearest available vehicle will be dispatched. Then, a preliminary diagnosis will be made on the condition of the first-aid requester, and the first-aid requester will be sent to the nearest hospital with the ability to treat according to the diagnosis result. However, the factors considered in this way of selecting a hospital for the first-aid requester are relatively single, that is, only the distance between the first-aid requester's location and the hospital is considered, and other factors such as the first-aid resources of the hospital to be sent to or the first-aid contradiction in the hospital to be sent to are not considered. As a result, the risk that the first-aid requester cannot receive effective first aid within the best treatment time may be increased, and even the situation that the first-aid requester is in life danger due to delayed treatment may occur. Therefore, how to match the emergency hospital for the first-aid requester to reduce the probability that the first-aid requester cannot receive effective first aid within the best treatment time has become an urgent problem to be solved. Summary of the Invention

[0003] In order to solve the above problems, the present invention provides an intelligent management and sharing platform for first-aid data based on the Internet of Things, and the specific technical solution adopted is as follows:

[0004] An embodiment of the present invention provides an intelligent management and sharing platform for first-aid data based on the Internet of Things. The intelligent management and sharing platform for first-aid data based on the Internet of Things includes:

[0005] A first acquisition module, configured to acquire a target first-aid data set of a target first-aid requester, a historical first-aid data set of a historical first-aid requester, and a set of hospitals to be matched for the target first-aid requester;

[0006] The second acquisition module is used to obtain the influence degree values ​​of different emergency data types according to the historical emergency data set, obtain the risk level value of the target emergency needer according to the influence degree values ​​of the different emergency data types and the target emergency data set, obtain the target matching degree corresponding to each hospital in the set of hospitals to be selected according to the time from the location of the target emergency needer to each hospital in the set of hospitals to be selected, the medical resource occupancy rate of each hospital in the set of hospitals to be selected and the risk level value of the target emergency needer, and use the hospital corresponding to the maximum target matching degree as the emergency matching hospital for the target emergency needer.

[0007] Beneficial effects: The present invention includes a first acquisition module, which is used to acquire a target emergency data set of a target emergency demander, a historical emergency data set of a historical emergency demander, and a set of hospitals to be matched for the target emergency demander; a second acquisition module, which is used to obtain the influence degree values ​​of different emergency data types according to the historical emergency data set, obtain the risk level value of the target emergency demander according to the influence degree values ​​of different emergency data types and the target emergency data set, obtain the target matching degree corresponding to each hospital in the set of hospitals to be selected according to the time from the location of the target emergency demander to each hospital in the set of hospitals to be selected, the medical resource occupancy rate of each hospital in the set of hospitals to be selected, and the risk level value of the target emergency demander, and use the hospital corresponding to the maximum target matching degree as the emergency matching hospital for the target emergency demander. The present invention combines multiple factors to analyze the target matching degree corresponding to each hospital, and then determines the emergency matching hospital for the target emergency demander according to the size of the target matching degree corresponding to each hospital, which can reduce the probability that the emergency demander cannot get effective emergency treatment within the optimal treatment time as much as possible, that is, the present invention can increase the probability that the emergency demander can get effective emergency treatment within the optimal treatment time. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0009] Figure 1 The present invention is a structural block diagram of an intelligent management and sharing platform for emergency data based on the Internet of Things. DETAILED DESCRIPTION

[0010] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art belong to the scope protected by the embodiments of the present invention.

[0011] 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 invention belongs.

[0012] This embodiment provides an intelligent management and sharing platform for first aid data based on the Internet of Things, which is described in detail as follows:

[0013] As Figure 1 shown, an intelligent management and sharing platform for first aid data based on the Internet of Things provided in this embodiment includes:

[0014] A first acquisition module 01, configured to acquire a target first aid data set of a target first aid requester, a historical first aid data set of a historical first aid requester, and a set of hospitals to be matched for the target first aid requester.

[0015] Since the pre - hospital emergency system in the current first - aid data management and sharing platform only considers a single factor when matching an emergency hospital for a first - aid requester or determining the hospital to which the first - aid requester should be sent, that is, only the distance between the location of the first - aid requester and the hospital is considered, without considering other factors such as the first - aid resources of the hospital to be sent to or the occurrence of first - aid contradictions in the hospital to be sent to. This may increase the risk that the first - aid requester cannot receive effective first - aid within the best treatment time, and even lead to the situation that the first - aid requester is in life - threatening danger due to delayed treatment. In order to increase the probability that the first - aid requester can receive effective first - aid within the best treatment time and reduce the mortality rate of the first - aid requester, in this embodiment, the risk level value of the first - aid requester will be obtained through data fusion based on the deviation degree of the first - aid data of the first - aid requester from the normal range and the influence weight of different first - aid data types. Then, by analyzing the distance between the hospital and the first - aid requester, the occupancy situation of medical resources in the hospital, and the risk of medical contradictions, the matching degree between the first - aid requester and different hospitals or the preference degree of the hospital will be determined. Based on the size of the preference degree, the hospital where the first - aid requester should go for first - aid will be recommended or the emergency matching hospital for the first - aid requester will be obtained based on the size of the preference degree. In addition, usually, the pre - hospital emergency system in the intelligent management and sharing platform of first - aid data will include information about hospitals, community clinics, and township health centers in a city. When the pre - hospital emergency system receives an emergency call or information from a first - aid requester, it immediately locates the current position of the first - aid requester, notifies the emergency dispatch center to dispatch the nearest emergency vehicle to the location of the first - aid requester, arranges for an emergency doctor to arrive at the emergency scene with the ambulance to conduct a preliminary diagnosis and treatment of the patient. And the pre - hospital emergency system has the function of matching or recommending a hospital with the ability to treat for the first - aid requester, that is, the pre - hospital emergency platform has the function of matching an emergency hospital for the first - aid requester. The main purpose of this embodiment is to optimize the process of the pre - hospital emergency system for matching an emergency hospital for the first - aid requester or making a hospital recommendation. And in this embodiment, the recommended or matched emergency hospital for the first - aid requester is the best first - aid hospital or the hospital for medical treatment that the first - aid requester should go to. That is, the first - aid requester going to the emergency matching hospital corresponding to the first - aid requester for first - aid will reduce the risk that the first - aid requester cannot receive effective first - aid within the best treatment time, and also reduce the probability that the first - aid requester is in life - threatening danger due to delayed treatment.

[0016] In this embodiment, for the convenience of understanding, the process of matching an emergency hospital for an emergency responder whose emergency hospital has not been determined or the process of matching an emergency hospital will be described. The emergency responder whose emergency hospital has not been determined is denoted as the target emergency responder. An emergency responder refers to an individual who requires emergency medical intervention due to sudden acute and critical illnesses (such as myocardial infarction, severe trauma) or accidental injuries (such as drowning, poisoning). Its core feature is the existence of a life-threatening emergency state, and it is necessary to immediately initiate a professional medical rescue process. It is also an individual who seeks emergency medical assistance by calling an emergency number (such as 120). Additionally, a pre-hospital emergency system whose service coverage area includes the location of the target emergency responder when seeking emergency medical assistance is obtained and denoted as the pre-hospital emergency system to be analyzed.

[0017] Then, the target first-aid data set of the target first-aid requester is obtained. The first-aid data in the target first-aid data set is such that after the ambulance arrives at the location of the target first-aid requester, the on-board medical staff will monitor the first-aid data of the target first-aid requester. When the on-board medical staff monitors the first-aid data of the target first-aid requester, the first-aid data of different first-aid data types monitored all belong to the first-aid data in the target first-aid data set. And in this embodiment, the types of first-aid data monitored by the on-board medical staff include but are not limited to body temperature data, blood pressure data, heart rate data, respiratory rate data, blood glucose data, etc. The first-aid data such as body temperature data, blood pressure data, heart rate data, respiratory rate data, blood glucose data, etc. is collected by networked devices or networked instruments. For example, heart rate data can be monitored and collected by a networked electrocardiograph. Then, the set of all first-aid data types monitored after the ambulance arrives at the location of the target first-aid requester is recorded as the target first-aid data set. For example, after the ambulance arrives at the location of the target first-aid requester, when the on-board medical staff monitors the first-aid data of the target first-aid requester, the first-aid data monitored includes blood pressure data, heart rate data, and respiratory rate data. Then the target first-aid data set consists of the blood pressure data, heart rate data, and respiratory rate data of the target first-aid requester, and the monitored first-aid data will be uploaded to the pre-hospital first-aid system to be analyzed. In addition, after the ambulance arrives at the location of the target first-aid requester, the first-aid data of the same first-aid data type may be monitored multiple times. When this situation occurs, in this embodiment, only the average value is used as the first-aid data of the target first-aid requester. For example, if the systolic blood pressure is collected three times after the ambulance arrives at the location of the target first-aid requester, the first time the systolic blood pressure is collected is 95 mmHg, the second time is 105 mmHg, and the third time is 100 mmHg. Then at this time, 100 mmHg is used as one of the first-aid data for constructing the target first-aid data set. The location of the target first-aid requester refers to the location of the target first-aid person obtained by the emergency dispatch center when receiving the first-aid information of the target first-aid requester.

[0018] After obtaining the target first-aid data set of the target first-aid requester, all first-aid requesters served by the pre-hospital first-aid system to be analyzed before receiving the first-aid call of the target first-aid requester are obtained from the platform database, and are all recorded as historical first-aid requesters. And these historical first-aid requesters are all first-aid requesters who have been treated in the emergency hospital, that is, historical first-aid requesters refer to first-aid requesters who have been picked up by the ambulance and sent to the hospital for treatment; then the first-aid data sets of each historical first-aid requester are obtained from the platform database, and are recorded as the historical first-aid data sets of the first-aid requesters. The historical first-aid data sets of the historical first-aid requesters are mainly used to obtain the influence degree values of different types of first-aid data in the follow-up. And the acquisition method of the first-aid data in the historical first-aid data sets of the historical first-aid requesters is the same as that of the first-aid data in the target first-aid data set of the target first-aid requester, so it will not be described in detail.

[0019] Immediately afterwards, continue to obtain the set of hospitals to be matched for the target first-aid requester, and the set of hospitals to be matched is composed of all hospitals in the area where the target first-aid requester is located that have the ability to receive the target first-aid requester; that is, after the ambulance arrives at the location of the target first-aid requester, the preliminary diagnosis results of the accompanying medical staff are input into the pre-hospital first-aid system to be analyzed. In the area covered by the pre-hospital first-aid system to be analyzed, all hospitals that have the ability to receive the target first-aid requester are screened out. Then, in the area covered by the pre-hospital first-aid system to be analyzed, the set constructed by all the screened-out hospitals that have the ability to receive the target first-aid requester is the set of hospitals to be matched for the target first-aid requester. Or based on the obtained target first-aid data set of the target first-aid requester, the pre-hospital first-aid system to be analyzed can initially diagnose the condition of the target first-aid requester. Based on the condition of the target first-aid requester initially diagnosed by the pre-hospital first-aid system to be analyzed, all hospitals that have the ability to receive the target first-aid requester can also be screened out in the area covered by the pre-hospital first-aid system to be analyzed. Then, the set constructed by all the screened-out hospitals that have the ability to receive the target first-aid requester is also the set of hospitals to be matched for the target first-aid requester. For example, if the preliminary diagnosis result of the accompanying medical staff is that the target first-aid requester has burns, and in the area covered by the pre-hospital first-aid system to be analyzed, only Hospital A1, Hospital A2, and Hospital A3 receive and treat burns, then the set of hospitals to be matched for the target first-aid requester at this time is composed of Hospital A1, Hospital A2, and Hospital A3. Subsequently, the emergency matching hospital for the target first-aid requester will be screened out from the set of hospitals to be matched for the target first-aid requester.

[0020] The second acquisition module 02 is configured to obtain the influence degree values of different first-aid data types according to the historical first-aid data set, obtain the risk level value of the target first-aid requester according to the influence degree values of different first-aid data types and the target first-aid data set, and obtain the corresponding target matching degree of each hospital in the to-be-selected hospital set according to the time from the location of the target first-aid requester to each hospital in the to-be-selected hospital set, the occupancy rate of medical resources of each hospital in the to-be-selected hospital set, and the risk level value of the target first-aid requester, and use the hospital corresponding to the maximum target matching degree as the emergency matching hospital of the target first-aid requester.

[0021] In this embodiment, next, the influence degree values of different first-aid data types will be obtained according to the historical first-aid data set. Moreover, the changes shown by the first-aid data of different conditions are different. Therefore, the influence degrees of different types of first-aid data on the patient's life are different. In the subsequent part of this embodiment, statistical analysis will be performed based on the first-aid data of some known historical first-aid requesters and the lethality risk or lethality rate of the diseases diagnosed by the historical first-aid requesters to obtain the influence degree of different first-aid data types on the life safety of the first-aid requesters, that is, the influence degree value. The influence degree value is an important parameter for accurately evaluating the risk level value of the target first-aid requester later. Then, the specific process of obtaining the influence degree values of different first-aid data types is as follows:

[0022] First, count all the first-aid data types that appear in all the historical first-aid data sets, and in all the historical first-aid data sets, divide the first-aid data belonging to the same first-aid data type into the same set to obtain the to-be-screened sets corresponding to different first-aid data types. That is, the types of first-aid data in the to-be-screened sets are the same, but they come from different historical first-aid data sets. For example, if there are 3 historical first-aid requesters, the first-aid data set of the first historical first-aid requester consists of blood pressure data and heart rate data, the first-aid data set of the second historical first-aid requester consists of body temperature data, respiratory rate data, and heart rate data, and the first-aid data set of the third historical first-aid requester consists of body temperature data and respiratory rate data. Then, the first-aid data types that appear at this time include blood pressure data, heart rate data, body temperature data, and respiratory rate data. At this time, the to-be-screened set corresponding to the respiratory rate data type consists of two respiratory rate data, and these two respiratory rate data come from the second historical first-aid requester and the third historical first-aid requester respectively. Then, the respiratory rate data type at this time consists of the second historical first-aid requester and the third historical first-aid requester.

[0023] Then, according to the normal value ranges corresponding to different first aid data types, the deviation degrees of each first aid data in the set to be screened are obtained. The set reconstructed from all the first aid data with non-zero deviation degrees in the set to be screened corresponding to different first aid data types is denoted as the set to be analyzed corresponding to the corresponding first aid data type, and each first aid data in the set to be analyzed is denoted as the data to be analyzed. Then, according to the set to be analyzed and the historical first aid demanders to which the data to be analyzed in the set to be analyzed belong, the reference weight values and lethality risk coefficients corresponding to the data to be analyzed in the set to be analyzed are obtained, and the product of the reference weight value corresponding to each data to be analyzed in the set to be analyzed and the lethality risk coefficient corresponding to the corresponding data to be analyzed is calculated and denoted as the weighted lethality risk coefficient corresponding to the corresponding data to be analyzed. The sum of the weighted lethality risk coefficients corresponding to all the data to be analyzed in the set to be analyzed corresponding to different first aid data types is obtained and used as the comprehensive weighted lethality risk coefficient corresponding to the corresponding first aid data type. The weighted lethality risk coefficients of different first aid data types are normalized respectively, and the normalization result is denoted as the influence degree value corresponding to the corresponding first aid data type. The larger the influence degree value of the first aid data type, the greater the influence degree of the corresponding first aid data type on the patient's life safety, and the more the deviation degree of the first aid data belonging to the first aid data type needs to be referred to when evaluating the risk level value of the target first aid demander later; the process of normalizing the comprehensive weighted lethality risk coefficients of different first aid data types is as follows: first, obtain the cumulative result of the comprehensive weighted lethality risk coefficients of all first aid data types, and use the ratio of the comprehensive weighted lethality risk coefficient of different first aid data types to the cumulative result of the comprehensive weighted lethality risk coefficients of all first aid data types as the influence degree value corresponding to the corresponding first aid data type. The cumulative result of the comprehensive weighted lethality risk coefficients of all first aid data types is the basis for normalizing the comprehensive weighted lethality risk coefficients of different first aid data types.

[0024] In this embodiment, the specific process of obtaining the deviation degree of each first aid data in the set to be screened according to the normal value range corresponding to different first aid data types is as follows: For any first aid data a in any set to be screened: Obtain the first aid data type corresponding to the first aid data a, and denote it as first aid data type A. Obtain the normal value range corresponding to the first aid data type A, and denote the maximum value and the minimum value in the normal value range corresponding to the first aid data type A as the maximum normal value and the minimum normal value corresponding to the first aid data type A respectively. Obtain the difference between the maximum value and the minimum value in the normal value range corresponding to the first aid data type A, and denote it as the extreme difference. Then, determine whether the first aid data a belongs to the normal value range corresponding to the first aid data type A. If so, take 0 as the deviation degree of the first aid data a. Otherwise, continue to determine whether the first aid data a is greater than the maximum normal value corresponding to the first aid data type A. If so, take the ratio of the result of subtracting the maximum normal value corresponding to the first aid data type A from the first aid data a to the extreme difference as the deviation degree of the first aid data a. Otherwise, continue to determine whether the first aid data a is less than the minimum normal value corresponding to the first aid data type A. If so, take the ratio of the result of subtracting the first aid data a from the minimum normal value corresponding to the first aid data type A to the extreme difference as the deviation degree of the first aid data a. That is, if the first aid data a is greater than the maximum normal value corresponding to the first aid data type A, the deviation degree of the first aid data a is If the first aid data a is less than the maximum normal value corresponding to the first aid data type A, the deviation degree of the first aid data a is where D is the extreme difference, X a is the value of the first aid data a, X max is the maximum normal value corresponding to the first aid data type A, X min is the minimum normal value corresponding to the first aid data type A; in addition, the normal value range corresponding to different first aid data types needs to be determined according to the first aid data type. For example, if the first aid data type A is systolic blood pressure, then the normal value range corresponding to the first aid data type A is [90 mmHg, 139 mmHg].

[0025] In this embodiment, the specific process of obtaining the reference weight value and the lethal risk coefficient corresponding to each analyzed data in the analyzed set according to the analyzed set and the historical first aid requesters to which the analyzed data in the analyzed set belong is as follows:

[0026] For any analyzed data f in the analyzed set corresponding to any first aid data type F:

[0027] First, obtain the historical first-aid requester to which the data f to be analyzed belongs, and denote it as the first-aid requester V. Denote the sets to be analyzed corresponding to other first-aid data types except the set to be analyzed corresponding to the first-aid data type F as feature sets, and denote all the first-aid data in the historical first-aid data set of the first-aid requester V as feature data. In all the feature sets, obtain the number of feature sets containing the feature data, and denote it as the frequency characterization value of the historical first-aid requester to which the data f to be analyzed belongs.

[0028] Then, normalize the frequency characterization value of the historical first-aid requester to which the data f to be analyzed belongs, and denote the normalized result as the correlation degree of the data f to be analyzed. That is, the correlation degree of the data f to be analyzed is where M is the number of types of first-aid data types that appear in all the historical first-aid data sets, m is the frequency characterization value of the historical first-aid requester to which the data f to be analyzed belongs, and M is used to normalize the frequency characterization value. In addition, the larger the frequency characterization value, the more it indicates that the lethality of the disease diagnosed by the first-aid requester V is more likely to be affected by various factors or the correlation degree between the data f to be analyzed and other types of first-aid data is greater. Then, the smaller the reference weight value or importance of the data f to be analyzed obtained subsequently. And the smaller the reference weight value of the data f to be analyzed, the smaller the participation degree of the lethality risk coefficient corresponding to the data f to be analyzed when calculating the influence degree values of different first-aid data types. The lethality risk coefficient corresponding to the data f to be analyzed can reflect the magnitude of the lethality of the disease related to the data f to be analyzed.

[0029] After that, obtain the sum of the correlation degree of the data f to be analyzed and a preset first constant, and denote it as the correlation characterization value of the data f to be analyzed. Obtain the cumulative sum of the correlation characterization values of all the data to be analyzed in the set to be analyzed corresponding to the first aid data type F, and denote it as the comprehensive correlation characterization value of the first aid data type F. After that, obtain the ratio of the comprehensive correlation characterization value of the first aid data type F to the correlation characterization value of the data f to be analyzed, and denote it as the first ratio of the data f to be analyzed. Then, perform normalization processing on the first ratio of the data f to be analyzed, and denote the result of the normalization processing as the reference weight value of the data f to be analyzed. The method for obtaining the correlation characterization values of all the data to be analyzed in the set to be analyzed corresponding to the first aid data type F is the same as the method for obtaining the correlation characterization value of the data f to be analyzed. Additionally, the process of performing normalization processing on the first ratio of the data f to be analyzed is as follows: obtain the cumulative sum of the first ratios of all the data to be analyzed in the set to be analyzed corresponding to the first aid data type F, and denote it as the comprehensive ratio. Use the ratio of the first ratio of the data f to be analyzed to the comprehensive ratio as the result of the normalization processing of the first ratio of the data f to be analyzed or as the reference weight value of the data f to be analyzed. In this embodiment, the preset first constant needs to be set according to the actual situation. For example, in this embodiment, it is set to 1. The purpose of adding the preset first constant is to prevent the denominator from being 0 when calculating the ratio.

[0030] Immediately obtain all types of diseases diagnosed for the first-aid requester V from the emergency medical record of the first-aid requester V, and denote the set constructed by all types of diseases diagnosed for the first-aid requester V as the diagnosed disease set of the first-aid requester V; then, in the diagnosed disease set of the first-aid requester V, obtain the diseases related to the data f to be analyzed, and denote them as the diseases related to the data f to be analyzed. Then, obtain the lethality rate of the diseases related to the data f to be analyzed, and use the lethality rate of the diseases related to the data f to be analyzed as the lethality risk coefficient of the data f to be analyzed. The lethality rates of different types of diseases mainly come from the data statistically collected by public health institutions, academic research platforms, health statistics departments, and hospital historical medical records, etc.; and if the data f to be analyzed is obtained by monitoring a certain historical first-aid requester, then denote this historical first-aid requester as the historical first-aid requester to which the data f to be analyzed belongs; in addition, in the diagnosed disease set of the first-aid requester V, the number of types of diseases related to the data f to be analyzed may be greater than 1 or 0. Therefore, when the number of types of diseases related to the data f to be analyzed is greater than 1, use the average value of the lethality rates of all diseases related to the data f to be analyzed obtained in the diagnosed disease set of the first-aid requester V as the lethality risk coefficient of the data f to be analyzed. When the number of types of diseases related to the data f to be analyzed is 0, then use 0 as the lethality risk coefficient of the data f to be analyzed; for example, if a certain type of disease can cause a change in a certain first-aid data, it indicates that the corresponding first-aid data is related to the disease. For example, if the data f to be analyzed is the respiratory rate data, and the diagnosed disease of the first-aid requester V is acute asthma, and acute asthma will cause the patient's respiratory rate to increase compensatorily, that is, acute asthma will affect the respiratory rate, then it is determined that acute asthma is related to the respiratory rate. And research shows that the lethality rate of acute asthma is approximately 1%, so the lethality risk coefficient of this historical data is 1% at this time. And if the data f to be analyzed is the body temperature data, and the diagnosed disease of the first-aid requester V is still acute asthma, and acute asthma patients usually do not cause changes in the body temperature data of the corresponding patients, so it is determined that acute asthma is not related to the body temperature data. Then, the lethality risk coefficient of the data f to be analyzed at this time is 0.

[0031] After obtaining the influence degree values of different first-aid data types, the risk level value of the target first-aid recipient is obtained according to the influence degree values of different first-aid data types and the target first-aid data set. The specific obtaining process is as follows: First, each first-aid data in the first-aid data set of the target first-aid recipient is recorded as the first data, and the deviation degree of each first data is obtained. The obtaining method of the deviation degree of the first data is the same as the obtaining method of the deviation degree of the above-mentioned first-aid data a. The larger the value of the deviation degree, the greater the difference between the corresponding first-aid data and the normal physical sign data, and the greater the participation degree in evaluating the risk level value or the first-aid risk coefficient of the target first-aid recipient in the subsequent process; then, the product of the deviation degree of each first data and the influence degree value of the first-aid data type to which the corresponding first data belongs is obtained, and is recorded as the weighted deviation degree of the corresponding first data. The sum of the weighted deviation degrees of all the first data in the target first-aid data set is recorded as the first-aid risk coefficient of the target first-aid recipient. The larger the first-aid risk coefficient of the target first-aid recipient, the more critical the patient's condition, the shorter the required first-aid time, and the need to be sent to the hospital for first-aid as soon as possible, otherwise there will be life-threatening risks; immediately afterwards, the value range of the first-aid risk coefficient is obtained and recorded as the target value range, and then the target value range is divided to obtain each sub-value range corresponding to the target value range, and the risk level values corresponding to each sub-value range corresponding to the target value range are assigned in turn. Finally, the risk level value corresponding to the sub-value range to which the first-aid risk coefficient of the target first-aid recipient belongs is used as the risk level value of the target first-aid recipient.

[0032] And in this embodiment, the specific process of dividing the target value range to obtain each sub-value range corresponding to the target value range and assigning the risk level values corresponding to each sub-value range corresponding to the target value range in turn is as follows: The target value range is evenly divided into H equal parts, and each equal part obtained by the division is recorded as the sub-value range corresponding to the target value range. Then, all the obtained sub-value ranges are sorted according to the order of the sub-value ranges in the target value range to obtain a sub-value range sequence. The risk level value of the h-th sub-value range in the sub-value range sequence is assigned as h, that is, the value of the g-th sub-value range in the sub-value range sequence is less than the value of the (g + 1)-th sub-value range in the sub-value range sequence, but greater than the value of the (g - 1)-th sub-value range in the sub-value range sequence, where g is greater than 1; in addition, since there will be no overly obvious changes in the physical health of the first-aid recipient when the first-aid risk coefficient changes within a small range, while there are obvious differences in physical health when it changes within a large range, this embodiment divides the target value range into 10 levels according to a length of 0.1. That is, in this embodiment, the value range of the first-aid risk coefficient is [0, 1], that is, the target value range is [0, 1]. Then, when divided into 10 levels according to a length of 0.1, the obtained sub-value range sequence is {[0, 0.1], (0.1, 0.2], (0.2, 0.3]…(0.9, 1.0]}.

[0033] Therefore, through the above process, the risk level value of the target first-aid requester can be obtained in this embodiment. After obtaining the risk level value of the target first-aid requester, the target first-aid requester needs to be sent to a doctor as soon as possible; under normal circumstances, it will be preferentially sent to the nearest hospital that can treat the condition of the target first-aid requester. However, since medical resources are public resources and are within the scope of a city, medical conflicts may occur. That is, when multiple patients need to be sent to the same hospital, the hospital cannot receive all of them. If only the distance between the first-aid requester and the hospital is used to select the receiving first-aid patients, it may lead to the risk of missing the best first-aid time for the critically ill first-aid requesters who are not received due to the long time to go to other hospitals, thus resulting in life-threatening. Therefore, multi-dimensional considerations are needed to match the emergency hospital for the first-aid requester; so in this embodiment, next, according to multiple factors such as the time for the target first-aid requester to reach each hospital in the set of hospitals to be selected from the location of the target first-aid requester, the occupancy rate of medical resources of each hospital in the set of hospitals to be selected, and the risk level value of the target first-aid requester, the corresponding target matching degree of each hospital in the set of hospitals to be selected is obtained. And the greater the target matching degree, the greater the probability that the target first-aid requester will be sent to this hospital for first-aid to improve the probability of the first-aid requester receiving effective first-aid within the best treatment time, that is, the greater the target matching degree, the greater the probability that the corresponding hospital is the emergency matching hospital for the target first-aid requester. Then, in this embodiment, the specific process of obtaining the corresponding target matching degree of each hospital in the set of hospitals to be selected is as follows:

[0034] First, obtain the location of the target first-aid requester obtained by the emergency dispatch center when receiving the first-aid information of the target first-aid requester, and record it as the starting location; then, after the ambulance arrives at the starting location, obtain the expected time for the ambulance to travel from the starting location to each hospital in the set of hospitals to be selected on the Internet of Things navigation system, and record the expected time for the ambulance to travel from the starting location to each hospital in the set of hospitals to be selected as the time characterization value of the corresponding hospital; then, obtain the cumulative value of the time characterization values of all hospitals in the set of hospitals to be selected, and record it as the comprehensive time characterization value. Record the ratio of the comprehensive time characterization value to the time characterization value of any hospital in the set of hospitals to be selected as the distance index value of the corresponding hospital, and record the normalized value of each hospital's distance index value as the distance score value of the corresponding hospital; that is, the expression of the distance score value of the j-th hospital in the set of hospitals to be selected is: Among them, S j is the distance score value of the j-th hospital in the set of hospitals to be selected, T j is the distance index value of the j-th hospital, J is the total number of hospitals in the set of hospitals to be selected, and t j is the time characterization value of the j-th hospital in the set of hospitals to be selected.

[0035] Immediately when the ambulance arrives at the starting position, obtain the number of idle ambulances in each hospital in the set of hospitals to be selected, the number of in-hospital patients in each hospital, and the equipment occupancy rate in each hospital through the hospital information system, the emergency center dispatching system, etc. Then, based on the number of idle ambulances in each hospital in the set of hospitals to be selected, the number of in-hospital patients in the hospital, and the equipment occupancy rate in the hospital, obtain the medical resource characterization value corresponding to each hospital in the set of hospitals to be selected; then obtain the set of historical emergency requesters corresponding to each hospital in the set of hospitals to be selected and the risk level values of each historical emergency requester in the set of historical emergency requesters corresponding to each hospital. The set of historical emergency requesters corresponding to any hospital consists of all emergency requesters received by the corresponding hospital within a preset recent historical time period. The method for obtaining the risk level value of a historical emergency requester is the same as the method for obtaining the risk level value of a target emergency requester; and since most hospitals generally conduct a statistical inpatient medical record quality inspection and review once a month, in this embodiment, the month before the target moment is used as the preset recent historical time period, and the target moment is the moment when the emergency dispatch center receives the emergency information of the target emergency requester.

[0036] After that, based on the set of historical emergency requesters corresponding to each hospital in the set of hospitals to be selected and the risk level values of each historical emergency requester in the set of historical emergency requesters corresponding to each hospital, obtain the medical conflict risk characterization value corresponding to each hospital in the set of hospitals to be selected. Immediately, based on the distance score value of each hospital in the set of hospitals to be selected, the medical conflict risk characterization value corresponding to each hospital, and the medical resource characterization value corresponding to each hospital, obtain the target preference degree corresponding to each hospital in the set of hospitals to be selected.

[0037] In this embodiment, the specific process of obtaining the medical resource characterization value corresponding to each hospital in the set of hospitals to be selected based on the number of idle ambulances in each hospital in the set of hospitals to be selected, the number of in-hospital patients in the hospital, and the equipment occupancy rate in the hospital is as follows: For any hospital k in the set of hospitals to be selected: Obtain the reciprocal of the result obtained by adding the number of idle ambulances in hospital k to a preset first constant, and denote it as the first characteristic value. Obtain the ratio of the number of in-hospital patients in hospital k to the maximum number of patients that hospital k can accommodate, and denote it as the second characteristic value. Denote the equipment occupancy rate in hospital k as the third characteristic value. Obtain the weighted sum value of the first characteristic value, the second characteristic value, and the third characteristic value, and denote it as the medical resource characterization value corresponding to hospital k; and in this embodiment, the specific calculation expression of the medical resource characterization value corresponding to hospital k is:

[0038]

[0039] where, Z kis the medical resource representation value corresponding to hospital k, w1 is the first weight value, w2 is the second weight value, w 31 is the third weight value, N k is the number of idle ambulances in hospital k, M1 K is the number of in-patient patients in hospital k, M0 K is the maximum number of patients that hospital k can accommodate, P K is the equipment occupancy rate in hospital k; when N k is smaller, M1 K is larger, P K is larger, it indicates that the medical resources of hospital k are relatively scarce at this time. On the contrary, when N k is larger, M1 K is smaller, P K is smaller, it indicates that the medical resources of hospital k are relatively abundant at this time; and since sufficient real-time medical resources are required for first aid treatment, otherwise the waiting time for medical resources may also affect the first aid result. Therefore, the situation of hospital medical resources also needs to be considered when matching emergency hospitals. For example, if an emergency requester needs to use a certain large-scale instrument, such as a magnetic resonance imaging device, etc., but there are only a small number of devices in the hospital. If the medical device is occupied at the current moment, it cannot be used for the first aid patient immediately, and at this time, it is necessary to wait for the device to be released before use, but the waiting time is uncertain, which is likely to cause the patient to die without timely treatment; at the same time, since there may be too many patients already received in the hospital, when there are emergency patients, the time for the hospital to carry out medical resource scheduling becomes longer, such as medical device scheduling, doctor scheduling, bed scheduling, etc., which may all affect the patient's first aid time. At the same time, when there are too many patients in the hospital, the emergency green channel of the hospital may be occupied, and the channel smoothness is reduced, etc. Therefore, whether the medical first aid resources of the hospital are abundant is also one of the influencing factors affecting the first aid result. In addition, in specific applications, the implementer needs to set the first weight value, the second weight value, and the third weight value according to the actual situation. And since medical device resources are more important and are related to whether first aid can be directly carried out after arriving at the hospital, in this embodiment, both the first weight value and the second weight value are set to 0.2, and the third weight value is set to 0.6.

[0040] In this embodiment, the specific process of obtaining the medical contradiction risk representation value corresponding to each hospital in the set of hospitals to be selected according to the set of historical emergency requesters corresponding to each hospital in the set of hospitals to be selected and the risk level values of each historical emergency requester in the set of historical emergency requesters corresponding to each hospital is as follows:

[0041] For any hospital K: First, denote the set of risk level values of each historical emergency requester in the set of historical emergency requesters corresponding to hospital K as the risk level value set. Take the mode in the risk level value set as the comparison risk level value. Denote the result of subtracting the risk level value of the target emergency requester from the comparison risk level value as the risk level difference. Take Max(0, D) as the first index value, where Max() is the maximum value function and D is the risk level difference. The larger the first index value, the greater the probability that the situation of affecting more serious emergency requesters received later due to receiving the target emergency requester occurs. Then, obtain the location of the historical emergency requester when the emergency dispatch center receives the emergency information of the historical emergency requester, and denote it as the emergency location of the corresponding historical emergency requester. After that, in the set of historical emergency requesters corresponding to hospital K, obtain the set of all historical emergency requesters whose emergency locations are within the preset neighborhood range of hospital K, and denote it as the first set. Then, denote the set of all historical emergency requesters in the first set that are greater than the risk level value of the target emergency requester as the second set, and obtain the ratio of the number of historical emergency requesters in the second set to the number of historical emergency requesters in the first set and denote it as the second index value. The larger the second index value, the greater the probability that there are emergency requesters with risk level values higher than the target emergency patient around hospital K. And in specific applications, the implementer needs to set the preset neighborhood range of hospital K according to the hospital's plan or the distance between hospitals. For example, in this embodiment, the preset neighborhood range of hospital K can be within a five-kilometer range of hospital K. After that, obtain the moment when the emergency dispatch center receives the emergency information of the historical emergency requester, and denote it as the historical emergency demand moment of the corresponding historical emergency requester. Immediately, denote the set of historical emergency demand moments of each historical emergency requester in the second set as the historical emergency demand moment set, and denote the moment when the emergency dispatch center receives the emergency information of the target emergency requester as the target moment. Then, in the historical emergency demand moment set, obtain the set of all characteristic moments greater than the target moment and denote it as the subset, and obtain the characteristic moment with the most frequent occurrence in the subset as the moment to be analyzed for the target moment. And if the moments in the subset are all non-repeating, then take the characteristic moment closest to the target moment in the subset as the moment to be analyzed for the target moment. After that, denote the reciprocal of the time interval between the target moment and the moment to be analyzed as the third index value. The time interval between the target moment and the moment to be analyzed is the absolute value of the time difference between the target moment and the moment to be analyzed. That is, the larger the third index value, the greater the probability that there are other emergency requesters with risk level values greater than the target emergency requester in the future time period relatively close to the target moment.For example, if there are 3 historical emergency requesters in the second set, the time when the emergency dispatch center receives the emergency information of the 1st historical emergency requester is 14:00, the time when the emergency dispatch center receives the emergency information of the 2nd historical emergency requester is 18:00, and the time when the emergency dispatch center receives the emergency information of the 3rd historical emergency requester is also 18:00. The time when the emergency dispatch center receives the emergency information of the target emergency requester is 13:00. That is, when recording the time, it is recorded according to the 24-hour time system. Based on the above analysis, the time greater than the time when the emergency dispatch center receives the emergency information of the target emergency requester and with the most occurrences is 18:00. Then the time to be analyzed is 18:00. At this time, the time interval between the target time and the time to be analyzed is 5 hours, and it also indicates that the probability of the hospital receiving more serious emergency patients than the target emergency requester at 18:00 is relatively high. If there are also 3 historical emergency requesters in the second set, but the time when the emergency dispatch center receives the emergency information of the 1st historical emergency requester is 14:00, the time when the emergency dispatch center receives the emergency information of the 2nd historical emergency requester is 15:00, the time when the emergency dispatch center receives the emergency information of the 3rd historical emergency requester is 18:00, and the time when the emergency dispatch center receives the emergency information of the target emergency requester is still 13:00. At this time, there is no repeated time among the times when the emergency dispatch center receives the emergency information of all historical emergency requesters in the second set. However, at this time, the time when the emergency dispatch center receives the emergency information of the 1st historical emergency requester is the closest to the time when the emergency dispatch center receives the emergency information of the target emergency requester. Then the time to be analyzed at this time is 14:00, and the time interval between the target time and the time to be analyzed is 1 hour. Finally, the average value of the first index value, the second index value, and the third index value is used as the medical contradiction risk characterization value corresponding to Hospital K. The larger the medical contradiction risk characterization value corresponding to Hospital K, the greater the real-time risk score of Hospital K if it receives the target emergency requester or the greater the medical contradiction risk. The medical contradiction risk refers to the contradiction that may exist between receiving this target emergency requester and expecting to receive a more serious emergency requester.

[0042] In this embodiment, the specific process of obtaining the target preference degree corresponding to each hospital in the to-be-selected hospital set according to the distance score value, the medical contradiction risk characterization value corresponding to each hospital, and the medical resource characterization value corresponding to each hospital in the to-be-selected hospital set is as follows: For any hospital K in the to-be-selected hospital set, the average value of the medical resource characterization value and the medical contradiction risk characterization value corresponding to Hospital K is used as the risk characterization value of Hospital K for receiving the target emergency requester. That is, the risk characterization value of Hospital K for receiving the target emergency requester is where R Kis the medical contradiction risk characterization value corresponding to Hospital K. Subsequently, the weighted sum of the negative correlation mapping value of the risk characterization value of Hospital K receiving the target first-aid requester and the distance score value of Hospital K is used as the target preference degree corresponding to Hospital K. That is, the negative correlation mapping value of the risk characterization value of Hospital K receiving the target first-aid requester is exp(-X K ), where exp() is the exponential function with the constant e as the base, and X K is the risk characterization value of Hospital K receiving the target first-aid requester. And because first aid has the highest requirement for time. Therefore, when calculating the weighted sum of the negative correlation mapping value of the risk characterization value of Hospital K receiving the target first-aid requester and the distance score value of Hospital K, it is required that the weight of the distance score value of Hospital K is greater than the weight of the negative correlation mapping value of the risk characterization value of Hospital K receiving the target first-aid requester. For example, the weight of the distance score value of Hospital K is set to 0.6, and the negative correlation mapping value of the risk characterization value of Hospital K receiving the target first-aid requester is set to 0.4.

[0043] Therefore, through the above process, this embodiment obtains the target preference degree corresponding to each hospital in the set of hospitals to be selected. And the greater the target preference degree, the smaller the probability that the target first-aid requester will not receive effective first aid within the best treatment time when going to the corresponding hospital for treatment. Therefore, the hospital corresponding to the maximum target matching degree is the emergency matching hospital for the target first-aid requester and is also the emergency hospital recommended by the platform for the target emergency requester. After determining the emergency matching hospital for the target first-aid requester, the platform plans the shortest traffic path to the ambulance display screen. The doctor confirms going to the recommended hospital. After confirmation, the platform sends the various physical sign data of the target first-aid requester to the corresponding hospital, notifies the hospital to make first-aid preparations. After sending the target first-aid requester to the hospital for first aid, the physical sign data of the target first-aid requester is sent to the internal medical system of the hospital, and the internal medical system of the hospital conducts subsequent treatment for the first-aid data of the target first-aid requester.

[0044] Thus, this embodiment completes the process of matching the emergency hospital for the first-aid requester.

[0045] In summary, the present embodiment includes a first acquisition module, which is used to acquire a target emergency data set of a target emergency demander, a historical emergency data set of a historical emergency demander, and a set of hospitals to be matched for the target emergency demander; a second acquisition module, which is used to obtain the influence degree values ​​of different emergency data types according to the historical emergency data set, obtain the risk level value of the target emergency demander according to the influence degree values ​​of different emergency data types and the target emergency data set, obtain the target matching degree corresponding to each hospital in the set of hospitals to be selected according to the time from the location of the target emergency demander to each hospital in the set of hospitals to be selected, the medical resource occupancy rate of each hospital in the set of hospitals to be selected, and the risk level value of the target emergency demander, and use the hospital corresponding to the maximum target matching degree as the emergency matching hospital for the target emergency demander. Moreover, the present embodiment combines multiple factors to analyze the target matching degree corresponding to each hospital, and then determines the emergency matching hospital for the target emergency demander according to the size of the target matching degree corresponding to each hospital, which can reduce the probability that the emergency demander cannot get effective emergency treatment within the optimal treatment time as much as possible, that is, the present embodiment can increase the probability that the emergency demander can get effective emergency treatment within the optimal treatment time.

[0046] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent management and sharing platform for first aid data based on the Internet of Things, characterized in that, The intelligent management and sharing platform for first-aid data based on the Internet of Things includes: A first acquisition module, configured to acquire a target first-aid data set of a target first-aid requester, a historical first-aid data set of a historical first-aid requester, and a set of hospitals to be matched for the target first-aid requester; A second acquisition module, configured to obtain an influence degree value of different first-aid data types according to the historical first-aid data set, obtain a risk level value of the target first-aid requester according to the influence degree value of different first-aid data types and the target first-aid data set, and obtain a target matching degree corresponding to each hospital in the set of hospitals to be selected according to the time from the location of the target first-aid requester to each hospital in the set of hospitals to be selected, the occupancy rate of medical resources of each hospital in the set of hospitals to be selected, and the risk level value of the target first-aid requester, and use the hospital corresponding to the maximum target matching degree as the emergency matching hospital of the target first-aid requester.

2. The intelligent management and sharing platform for first aid data based on the Internet of Things according to claim 1, wherein The first-aid data in the first-aid data set is composed of first-aid data of different first-aid data types monitored by medical staff accompanying the ambulance using monitoring equipment, and the set of hospitals to be matched is composed of all hospitals in the area where the target first-aid requester is located that have the ability to receive the target first-aid requester.

3. The intelligent management and sharing platform for first aid data based on the Internet of Things according to claim 1, characterized in that The method for obtaining the influence degree value of different first-aid data types according to the historical first-aid data set includes: Count all the first-aid data types that appear in all the historical first-aid data sets, and in all the historical first-aid data sets, divide the first-aid data belonging to the same first-aid data type into the same set to obtain a set to be screened corresponding to different first-aid data types, and obtain the deviation degree of each first-aid data in the set to be screened according to the normal value range corresponding to different first-aid data types. Denote the set reconstructed from all the first-aid data with non-zero deviation degrees in the set to be screened corresponding to different first-aid data types as the set to be analyzed corresponding to the corresponding first-aid data type, and denote each first-aid data in the set to be analyzed as a data to be analyzed; According to the set to be analyzed and the historical first-aid requesters to which the data to be analyzed in the set to be analyzed belong, obtain the reference weight value and the lethal risk coefficient corresponding to each data to be analyzed in the set to be analyzed; denote the product of the reference weight value corresponding to each data to be analyzed in the set to be analyzed and the lethal risk coefficient corresponding to the corresponding data to be analyzed as the weighted lethal risk coefficient corresponding to the corresponding data to be analyzed, and use the sum of the weighted lethal risk coefficients corresponding to all the data to be analyzed in the set to be analyzed corresponding to the first-aid data type as the comprehensive weighted lethal risk coefficient corresponding to the corresponding first-aid data type, and denote the normalized value of the comprehensive weighted lethal risk coefficient as the influence degree value of the corresponding first-aid data type.

4. The intelligent management and sharing platform for first-aid data based on the Internet of Things according to claim 3, characterized in that, The method for obtaining the reference weight value and the lethal risk coefficient corresponding to each data to be analyzed in the set to be analyzed includes: For any data to be analyzed f in the set to be analyzed corresponding to any first-aid data type F: Denote the historical first-aid requester to which the data f to be analyzed belongs as first-aid requester V. Denote all the sets to be analyzed corresponding to other first-aid data types except the set to be analyzed corresponding to the first-aid data type F as feature sets. Denote all the first-aid data in the historical first-aid data set of the first-aid requester V as feature data. In all the feature sets, obtain the number of feature sets containing the feature data, and denote it as the frequency characterization value of the historical first-aid requester to which the data f to be analyzed belongs. Denote the normalized value of the frequency characterization value of the historical first-aid requester to which the data f to be analyzed belongs as the correlation degree of the data f to be analyzed. Denote the sum of the correlation degree of the data f to be analyzed and a preset first constant as the correlation characterization value of the data f to be analyzed. Denote the accumulated sum of the correlation characterization values of all the data to be analyzed in the set to be analyzed corresponding to the first-aid data type F as the comprehensive correlation characterization value of the first-aid data type F. Denote the normalized value of the ratio of the comprehensive correlation characterization value of the first-aid data type F to the correlation characterization value of the data f to be analyzed as the reference weight value of the data f to be analyzed. In the emergency medical record of the first-aid requester V, obtain all the types of diseases diagnosed by the first-aid requester V, and denote the set constructed by all the types of diseases diagnosed by the first-aid requester V as the diagnosed disease set of the first-aid requester V. In the diagnosed disease set of the first-aid requester V, obtain the fatality rate of the disease related to the data f to be analyzed, and denote it as the fatality risk coefficient of the data f to be analyzed.

5. The intelligent management and sharing platform for first-aid data based on the Internet of Things according to claim 3, characterized in that, The method for obtaining the deviation degree of each first-aid data in the set to be screened includes: For any first-aid data a in any set to be screened: Denote the first-aid data type corresponding to the first-aid data a as first-aid data type A. Obtain the normal value range corresponding to the first-aid data type A, and denote the maximum value and the minimum value in the normal value range corresponding to the first-aid data type A as the maximum normal value and the minimum normal value corresponding to the first-aid data type A respectively. Denote the difference between the maximum value and the minimum value in the normal value range corresponding to the first-aid data type A as the extreme difference. If the first-aid data a belongs to the normal value range corresponding to the first-aid data type A, then take 0 as the deviation degree of the first-aid data a. If the first-aid data a is greater than the maximum normal value corresponding to the first-aid data type A, then take the ratio of the result of subtracting the maximum normal value from the first-aid data a to the extreme difference as the deviation degree of the first-aid data a. If the first-aid data a is less than the minimum normal value corresponding to the first-aid data type A, then take the ratio of the result of subtracting the first-aid data a from the minimum normal value to the extreme difference as the deviation degree of the first-aid data a.

6. The intelligent management and sharing platform for first aid data based on the Internet of Things according to claim 5, characterized in that, The method for obtaining the risk level value of the target first-aid requester includes: Each first aid data in the first aid data set of the target first aid requester is recorded as the first data, and the deviation degree of the first data is obtained. The method for obtaining the deviation degree of the first data is the same as the method for obtaining the deviation degree of the first aid data a. The product of the deviation degree of the first data and the influence degree value of the first aid data type to which the first data belongs is recorded as the weighted deviation degree of the first data. The sum of the weighted deviation degrees of all the first data in the first aid data set of the target first aid requester is recorded as the first aid risk coefficient of the target first aid requester. The value range of the first aid risk coefficient is obtained and recorded as the target value range. The target value range is divided to obtain each sub-value range corresponding to the target value range. The risk level values are assigned to each sub-value range corresponding to the target value range in ascending order of the level values, and the risk level values corresponding to each sub-value range are obtained. The risk level value corresponding to the sub-value range to which the first aid risk coefficient of the target first aid requester belongs is used as the risk level value of the target first aid requester.

7. The intelligent management and sharing platform for first-aid data based on the Internet of Things according to claim 1, characterized in that, The method for obtaining the target matching degree corresponding to each hospital in the to-be-selected hospital set includes: The position of the target first aid requester obtained when the first aid dispatching center receives the first aid information of the target first aid requester is recorded as the starting position. When the ambulance arrives at the starting position, the expected time for the ambulance to travel from the starting position to each hospital in the to-be-selected hospital set is obtained and recorded as the time representation value of the corresponding hospital. The sum of the time representation values of all the hospitals in the to-be-selected hospital set is recorded as the comprehensive time representation value. The normalized value of the ratio of the comprehensive time representation value to the time representation value of the hospital is recorded as the distance score value of the corresponding hospital. When the ambulance arrives at the starting position, the number of idle ambulances, the number of in-hospital patients, and the equipment occupancy rate in each hospital in the to-be-selected hospital set are obtained. According to the number of idle ambulances, the number of in-hospital patients, and the equipment occupancy rate in each hospital, the medical resource representation value corresponding to each hospital is obtained. The historical emergency requester set corresponding to each hospital in the to-be-selected hospital set and the risk level values of each historical emergency requester in the historical emergency requester set are obtained. According to the historical emergency requester set and the risk level values of each historical emergency requester in the historical emergency requester set, the medical conflict risk representation value corresponding to each hospital is obtained. The method for obtaining the risk level value of the historical emergency requester is the same as the method for obtaining the risk level value of the target first aid requester. The historical emergency requester set corresponding to any hospital consists of all the emergency requesters received by the corresponding hospital in the preset recent historical time period. According to the distance score value, the medical conflict risk representation value, and the medical resource representation value corresponding to each hospital, the target preference degree corresponding to each hospital is obtained.

8. The intelligent management and sharing platform for first-aid data based on the Internet of Things according to claim 7, characterized in that, The method for obtaining the medical resource representation value corresponding to each hospital includes: For any hospital in the set of hospitals to be selected, the reciprocal of the result obtained by adding the number of idle ambulances in the hospital to a preset first constant is denoted as the first eigenvalue, the ratio of the number of in-patient in the hospital to the maximum number of patients that the corresponding hospital can accommodate is denoted as the second eigenvalue, the equipment occupancy rate in the hospital is denoted as the third eigenvalue, and the weighted sum value of the first eigenvalue, the second eigenvalue, and the third eigenvalue is denoted as the medical resource characterization value corresponding to the hospital.

9. The intelligent management and sharing platform for first aid data based on the Internet of Things according to claim 7, characterized in that, The method for obtaining the medical contradiction risk characterization value corresponding to each hospital includes: For any hospital in the set of hospitals to be selected: Denote the set constructed by the risk level values of each historical emergency requester in the corresponding historical emergency requester set of the hospital as the risk level value set, take the mode in the risk level value set as the comparison risk level value, and denote the result of subtracting the risk level value of the target emergency requester from the comparison risk level value as the risk level difference. Denote Max(0, D) as the first index value, where Max() is the maximum value function and D is the risk level difference; Denote the location of the historical emergency requester obtained when the emergency dispatch center receives the emergency information of the historical emergency requester as the emergency location of the corresponding historical emergency requester; In the corresponding historical emergency requester set of the hospital, denote the set constructed by all historical emergency requesters whose emergency locations are within the preset neighborhood range of the hospital as the first set, and denote the set constructed by all historical emergency requesters in the first set whose risk level values are greater than the risk level value of the target emergency requester as the second set. Denote the ratio of the number of historical emergency requesters in the second set to the number of historical emergency requesters in the first set as the second index value; Denote the moment when the emergency dispatch center receives the emergency information of the historical emergency requester as the historical emergency demand moment of the corresponding historical emergency requester, denote the set constructed by the historical emergency demand moments of each historical emergency requester in the second set as the historical emergency demand moment set, and denote the moment when the emergency dispatch center receives the emergency information of the target emergency patient as the target moment; In the historical emergency demand moment set, denote the set constructed by all historical emergency demand moments greater than the target moment as the subset, and take the historical emergency demand moment with the most occurrences in the subset as the moment to be analyzed of the target moment; Denote the reciprocal of the time interval between the target moment and the moment to be analyzed as the third index value; Denote the mean value of the first index value, the second index value, and the third index value as the medical contradiction risk characterization value corresponding to the hospital.

10. The intelligent management and sharing platform for first-aid data based on the Internet of Things according to claim 7, characterized in that, The method for obtaining the target preference degree corresponding to each hospital according to the distance score value of each hospital, the medical contradiction risk characterization value corresponding to each hospital, and the medical resource characterization value corresponding to each hospital includes: For any hospital in the set of hospitals to be selected, the mean of the medical resource characterization value and the medical contradiction risk characterization value corresponding to the hospital is used as the risk characterization value for the hospital to receive the target emergency patient, and the weighted sum result of the negative correlation mapping value of the risk characterization value for the hospital to receive the target emergency patient and the distance score value of the hospital is used as the corresponding target preference degree of the hospital.

Images