Emergency treatment data quick response management method and system

Abstract

The invention relates to the technical field of medical data processing, in particular to an emergency data quick response management method and system, and the method comprises the steps: obtaining emergency case information, carrying out basic diagnosis, and obtaining a case pre-diagnosis result; accessing a case file system according to the emergency case information, and matching the emergency case information to obtain case matching information; the case matching information is classified, each classification result corresponds to a case data field, and a plurality of case data field sets correspond to single emergency cases; distributing weights to the plurality of case data fields according to a case pre-diagnosis result, obtaining response association weights, and establishing an emergency treatment quick response queue according to the response association weights; task allocation is carried out on the quick response queue to multiple response ends, and the multiple response ends make plan preparation for the allocated tasks at the same time and wait for calling of the emergency quick response queue. According to the invention, the flexibility and the automation degree in the aspects of case information matching and dynamic resource allocation are met.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a management method and system for rapid response to emergency data. Background Art

[0002] In the modern medical system, emergency medical services are a key component. Their efficiency and effectiveness are directly related to the timeliness and effectiveness of patient treatment. Emergency rooms face a variety of acute cases, which are usually life-threatening and require immediate diagnosis and treatment. Therefore, quickly and accurately obtaining and processing emergency case information is the key to improving emergency response efficiency and treatment success rate.

[0003] Traditional emergency data processing methods often rely on manual operations and linear workflows, which can lead to information processing delays when handling cases during peak hours and fail to meet the urgency of emergency care needs. These systems often exhibit inefficiencies, especially when faced with sudden and large numbers of emergency cases. Furthermore, these systems lack flexibility and automation in matching case information and dynamically allocating resources, and are unable to optimize in real time based on case urgency and specific needs. This limits the responsiveness and overall effectiveness of emergency services, impacting patient outcomes and safety.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0005] The present invention provides a management method and system for rapid response to emergency data, which can effectively solve the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: A management method for rapid response to emergency data, the method comprising: Obtain emergency case information, perform basic diagnosis on the emergency case information, and obtain case pre-diagnosis results; Accessing the case file system according to the emergency case information, matching the emergency case information, and obtaining case matching information; Classifying the case matching information, each classification result corresponds to a case data field, and a plurality of sets of the case data fields correspond to a single emergency case; Assigning weights to the plurality of case data fields according to the case pre-diagnosis results and obtaining response association weights, and establishing an emergency rapid response queue according to the response association weights; The rapid response queue is assigned tasks to multiple response terminals, and the multiple response terminals simultaneously prepare for the assigned tasks and wait for the call of the emergency rapid response queue.

[0007] Furthermore, weights are assigned to a number of the case data fields according to the case pre-diagnosis results to obtain response association weights, including: Selecting the case data field for the first execution according to the case pre-diagnosis result, and setting time slices for the case data field for the first execution, with each case data field corresponding to one time slice; Setting a decision engine, wherein the decision engine stores and dynamically calls single-dimensional priority weights; The single-dimensional priority weight adapted by the decision engine is called in the current time slice, and the single-dimensional priority weights of the decisions in each time slice are sequentially integrated to generate the response association weight.

[0008] Furthermore, calling the adapted single-dimensional priority weight according to the decision engine within the current time slice includes: The time slice and the time response segment are staggered and overlapped, wherein the time response segment is the actual response time of the case data field; The time slice connects the two time response segments and sets a connection time period within the time slice, and calls the single-dimensional priority weight according to the decision engine within the connection time period.

[0009] Furthermore, tasks are assigned to multiple response terminals from the rapid response queue, and the multiple response terminals simultaneously prepare for the assigned tasks and wait for the call of the emergency rapid response queue, including: Allocating tasks in the emergency rapid response queue to multiple response terminals according to predetermined rules; After receiving the assigned tasks, the multiple responders simultaneously prepare contingency plans for their respective tasks, including deploying corresponding personnel, equipment, and resources according to task requirements; After completing the emergency plan preparation, the multiple response terminals are in a standby state, waiting for the call of the emergency rapid response queue, so as to immediately execute the corresponding emergency response operation when receiving the call instruction.

[0010] Furthermore, the case file system is accessed according to the emergency case information, and the emergency case information is matched to obtain case matching information, including: Establishing a case file database, wherein the case file database includes personal historical medical information, historical case symptom information, and historical case diagnosis information; Constructing a case matching model, retrieving the historical case symptom information and the historical case diagnosis information, and training and evaluating the case matching model; According to the case matching model, deep learning is performed on the case archive database to obtain a mapping relationship between the historical case symptom information and the historical case diagnosis information, and emergency case information is matched according to the mapping relationship to obtain case matching information.

[0011] Furthermore, a case file database is established, and the method includes: Collect personal historical medical information, historical case symptom information, and historical case diagnosis information; Constructing a case symptom index to reflect the mapping relationship between the historical case symptom information and the historical case diagnosis information, and the historical case symptom information and the historical case diagnosis information have a one-to-one correspondence; Integrate historical diagnostic data and classify and manage the historical diagnostic data for use by the case archive database.

[0012] Furthermore, the number of cases in the emergency case information is identified, where the identification result includes unilateral emergency or multilateral emergency, and the association weight of the multilateral emergency is adaptively adjusted, including: Identifying the number of cases in the emergency case information, analyzing the severity of the emergency cases contained in each of the emergency case information and their mutual relevance, and determining the priority of each of the emergency cases; Classifying the identification results into unilateral emergency cases or multilateral emergency cases according to the priority of each emergency case and the number of cases included in each emergency medical record information, wherein the difference between the unilateral emergency case and the multilateral emergency case is the number of cases included in the emergency case; Assigning initial association weights to the case data fields of each case included in the unilateral emergency department and the multilateral emergency department; The initial correlation weight is adjusted according to the correlation of each emergency case to generate a correlation weight, and the emergency rapid response queue is updated according to the result of the adjusted correlation weight.

[0013] Furthermore, adjusting the initial correlation weight according to the correlation of each emergency case to generate a correlation weight, and updating the emergency rapid response queue according to the result of the adjusted correlation weight, including: Performing a detailed evaluation of the strength of the correlation between the plurality of emergency cases to determine a correlation level between the emergency cases, wherein the higher the correlation level, the stronger the correlation between the emergency medical records; Combined with the resource requirements of each emergency case, the initial association weights are adjusted hierarchically according to the degree of resource shortage and the resource occupation priority of each emergency case to generate association weights, and the weights are redistributed; Calculate the weight difference between the association weights, adjust the priority response order of multiple tasks according to the weight difference, establish a priority task allocation mechanism for cases with higher association strength, and update the order of the emergency rapid response queue.

[0014] A management system for rapid response to emergency data, comprising: A case information acquisition module is used to obtain emergency case information, perform basic diagnosis on the emergency case information, and obtain case pre-diagnosis results; An emergency medical record matching module accesses the case file system according to the emergency case information, matches the emergency case information, and obtains case matching information; A case data classification module classifies the case matching information, each classification result corresponds to a case data field, and a plurality of case data field sets correspond to a single emergency case; a weighted queue establishment module, which assigns weights to a number of the case data fields according to the case pre-diagnosis results and obtains response-related weights, and establishes an emergency rapid response queue according to the response-related weights; The allocation plan calling module allocates tasks of the rapid response queue to multiple response terminals, and the multiple response terminals simultaneously prepare plans for the assigned tasks and wait for the call of the emergency rapid response queue.

[0015] Furthermore, the weighted queue establishment module includes: a field selection unit, which selects the case data field of the first execution according to the case pre-diagnosis result, and sets a time slice for the case data field of the first execution, and each case data field corresponds to one time slice; A decision engine unit is provided, wherein a decision engine is provided, and the decision engine stores and dynamically calls a single-dimensional priority weight; The weight generation unit calls the adapted single-dimensional priority weight according to the decision engine in the current time slice, and sequentially integrates the single-dimensional priority weights of the decisions in each time slice to generate the response association weight.

[0016] The technical solution of the present invention can achieve the following technical effects: It effectively solves the problem that traditional emergency data processing methods often rely on manual operations and linear workflows, which leads to information processing delays when handling cases during peak hours and cannot meet the urgency of the actual needs of emergency care. Especially when faced with sudden and large-scale emergency situations, these systems often show low processing efficiency.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A flowchart of the management method for rapid response to emergency data; Figure 2 Schematic diagram of the structure for assigning response association weights; Figure 3 A schematic diagram of the structure for generating case matching information; Figure 4 This is a flowchart of the emergency rapid response queue; Figure 5 Schematic diagram of the process for establishing a priority response order. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0021] 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 pertains. The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0022] Example 1 like Figure 1 As shown, the present application provides a management method for rapid response of emergency data, including: S10: Obtain emergency case information, perform basic diagnosis on the emergency case information, and obtain case pre-diagnosis results; S20: Accessing the case file system according to the emergency case information, matching the emergency case information, and obtaining case matching information; S30: classifying the case matching information, each classification result corresponds to a case data field, and a set of several case data fields corresponds to a single emergency case; S40: assigning weights to a number of case data fields according to the case pre-diagnosis results and obtaining response association weights, and establishing an emergency rapid response queue according to the response association weights; S50: Assign tasks from the quick response queue to multiple response terminals. The multiple response terminals simultaneously prepare plans for the assigned tasks and wait for the call of the emergency quick response queue.

[0023] Specifically, first obtain relevant case information from emergency patients, including the patient's personal information, medical history, symptom description, etc., then perform a preliminary basic diagnosis on the obtained case information, and generate case pre-diagnosis results to assess the severity and urgency of the patient's condition, and provide a reference for subsequent response processes. After obtaining the emergency case information, the case files will be accessed and historical case files will be searched. By comparing the emergency case information with the case data in the historical files, possible matching case information will be found. This matching is based on factors such as symptoms, medical history, and diagnostic results, which can better analyze the potential treatment plans for the current emergency case, and classify the case matching information. Each classification result corresponds to one or more case data fields, including medical history fields, symptom fields, examination result fields, etc. The case information is classified It is decomposed into multiple data fields, and different types of data are processed and analyzed. Weights are assigned to multiple case data fields according to the case pre-diagnosis results. The weight assignment takes into account the urgency and severity of the case and the relative importance of different fields. Through the reasonable assignment of weights, response association weights are generated. The weight reflects the priority of each case data field in the emergency response. According to the generated response association weights, an emergency rapid response queue is established, and the cases in the queue are sorted from high to low according to the weight, so that cases with higher urgency can be responded to and processed first. After the emergency rapid response queue is established, tasks are assigned to multiple response terminals. Each response terminal will prepare contingency plans according to the assigned tasks and wait for calls. Once the weight of a case is high and needs to be processed immediately, the corresponding response terminal will be called for a rapid response.

[0024] The technical solution of the present invention effectively solves the problem that traditional emergency data processing methods often rely on manual operations and linear workflows, which leads to information processing delays when processing cases during peak hours and cannot meet the urgency of actual emergency needs, especially when facing sudden and large-scale emergency situations, and often exhibit low processing efficiency.

[0025] Further, if Figure 2 As shown in the figure, weights are assigned to several case data fields according to the case pre-diagnosis results and response association weights are obtained, including: Selecting a first executed case data field according to the case pre-diagnosis result, and setting a time slice for the first executed case data field, wherein each case data field corresponds to a time slice; Set up a decision engine that stores and dynamically calls single-dimensional priority weights; In the current time slice, the adapted single-dimensional priority weight is called according to the decision engine, and the single-dimensional priority weights of the decisions in each time slice are sequentially integrated to generate the response association weight.

[0026] As a preferred embodiment of the above, several case data fields are selected for priority execution based on the pre-diagnosis results of the case, and fields based on factors such as the urgency of the patient's condition and potential danger are given priority for processing. For each case data field selected for execution, a time slice is assigned to it. The time slice refers to the time period in which the field is processed and analyzed. Different case data fields may require different processing times. The setting of the time slice can ensure that each field is processed in an orderly manner without causing waste or delays in resources. For example, the patient's blood pressure data may need to be updated more frequently, while the processing frequency of medical history data can be lower. After completing the above work, a decision engine is configured, which stores and can dynamically call single-dimensional priority weights. The single-dimensional priority weight refers to the priority of each case data field in a specific dimension, for example, the severity of the disease. , fluctuations in vital signs, etc. may serve as different dimensions, and each dimension will affect the priority processing order of the corresponding case data fields. The decision engine dynamically adjusts these weights according to the pre-diagnosis results of the current case and related dimensions. In each time slice, the decision engine will call the appropriate single-dimensional priority weight according to the current situation. For example, in a time slice, if the patient's heart rate fluctuates greatly, the priority weight of the field may be increased so that it can get more resources or a faster response in the next time slice. At the end of each time slice, the single-dimensional priority weights in the time period are integrated, and the priority weights in all time slices are sorted. In this process, the single-dimensional priority weights in each time slice are accumulated in sequence to form the final response association weight, which determines the overall response order and resource allocation priority for emergency cases.

[0027] Specifically, the decision engine calls the adapted single-dimensional priority weights within the current time slice, including: The time slice and the time response segment are staggered and superimposed, where the time response segment is the actual response time of the case data field; The time slice connects two time response segments and sets a connection time period within the time slice, and calls a single-dimensional priority weight according to the decision engine within the connection time period.

[0028] As a preferred embodiment of the above, the staggered superposition of time slices and time response segments is achieved by dividing the response time of each case data field into multiple time segments. Each case data field has its own unique time response segment, which is usually associated with the data update frequency or monitoring requirements of the field. Time slices are used for weight allocation and response priority decision-making. Unlike response segments, they can span multiple fields within a time period. Through staggered superposition, the start or end of a time slice does not strictly depend on the time response segment of a specific field, but allows the response time of multiple fields to partially overlap with the slice. When processing the current field, preparations are made for weight allocation for the field to be started. In each time slice, the previous response segment is The end of the segment and the beginning of the next response segment are connected to ensure that there will be no response delay due to the switching of time slices. The connection time period is a buffer period, during which the priority of the time response segment to be entered can be evaluated. In each connection time period, the decision engine will dynamically call the adapted single-dimensional priority weight according to the current case status and resource requirements. This process takes into account multiple dimensions, such as changes in disease condition, resource availability and emergency response needs. After all time slices and response segments are completed, the tasks will be reordered according to the dynamically adjusted weight results. Through the design of staggered stacking and connection time periods, a smooth transition to the next response task can be achieved without delaying the emergency response due to processing gaps or weight calculations.

[0029] Furthermore, tasks are assigned to multiple responders from the quick response queue. Multiple responders simultaneously prepare for the assigned tasks and wait for the call from the emergency quick response queue, including: Allocate tasks in the emergency rapid response queue to multiple response terminals according to predetermined rules; After receiving the assigned tasks, multiple responders simultaneously prepare contingency plans for their respective tasks. The contingency plan preparation includes deploying corresponding personnel, equipment, and resources according to the task requirements. After completing the plan preparation, multiple response terminals are in standby state, waiting for the call of the emergency rapid response queue, so as to immediately execute the corresponding emergency response operation when receiving the call instruction.

[0030] As a preferred embodiment of the above, after the emergency rapid response queue is generated, the task is assigned to multiple responders according to predetermined rules. The predetermined rules may include the priority of the task, resource availability, professional skills of the responder, etc. The task assignment rules can be configured according to the specific situation of the hospital, such as considering the real-time workload of each responder, the current available resources of the emergency room, the expertise of the medical staff and the response efficiency, etc. By combining these factors, it is ensured that each task is assigned to the most suitable responder. After receiving the assigned task, each responder will immediately enter the emergency plan preparation stage. The emergency plan preparation includes the deployment of necessary personnel, equipment and resources. Each responder will The task will undergo comprehensive contingency plan preparation, and all key factors will be ready before the task is called. After the contingency plan preparation is completed, multiple responders will be on standby. The standby state means that the personnel, equipment and resources of each responder are in a ready state that can be called immediately, but the actual operation has not yet started. During the standby period, the responder will continue to monitor the task status in the task queue and wait for the call instruction at any time. In the standby state, the call instruction can be issued at any time. According to the urgency of the task in the queue and the preparation of the responder, the responder that has completed the preparation and has a higher task priority will be called first. When the call instruction is issued, the responder in the standby state will immediately perform the corresponding emergency operation. In the process of executing the task, multiple responders will continue to monitor the progress of their operations and adjust the task preparation of other uncalled responders according to the real-time situation.

[0031] Further, if Figure 3 As shown, the case file system is accessed according to the emergency case information, and the emergency case information is matched to obtain case matching information, including: Establish a case file database, which includes personal historical medical information, historical case symptom information, and historical case diagnosis information; Build a case matching model, retrieve historical case symptom information and historical case diagnosis information, and train and evaluate the case matching model; Based on the case matching model, deep learning is performed on the case archive database to obtain the mapping relationship between historical case symptom information and historical case diagnosis information, and emergency case information is matched based on the mapping relationship to obtain case matching information.

[0032] As a preferred embodiment of the above, a case file database is established, which contains personal historical medical information, historical case symptom information, and historical case diagnosis information. The case file database is dynamically updated through long-term accumulation and patient medical records to ensure the comprehensiveness and accuracy of the data. After the database is established, a case matching model is constructed. The purpose of this model is to automatically identify the similarity between current emergency cases and previous cases by analyzing historical case data. The symptom information and diagnosis information of historical cases are retrieved from the case file database. This information is used as training data for the model. The case matching model is trained using the retrieved historical case data. The model learns the mapping relationship between symptoms and diagnoses through a deep learning algorithm. Through repeated training and evaluation, the accuracy of the model is gradually improved, enabling it to better match current emergency cases with historical cases. The case matching model is further optimized through deep learning methods. Based on the retrieved historical case symptom information and diagnosis information, the deep learning model is used to automatically construct a mapping relationship between symptoms and diagnoses. During the matching process, the current emergency case information is analyzed using the learned symptom and diagnosis mapping relationship. After the model is trained and learns a large number of mapping relationships, the case file database can be matched according to the emergency case information. The matching process includes comparing the symptoms, medical history and other information of the current emergency case with the historical case data, and outputting matching information of historical cases similar to the current case. For example, if a historical case is matched with the current emergency case in terms of symptoms and medical history, the matching information will be provided as a reference to make diagnostic decisions.

[0033] Furthermore, a case file database is established, including the following methods: Collect personal historical medical information, historical case symptom information, and historical case diagnosis information; Construct a case symptom index to reflect the mapping relationship between historical case symptom information and historical case diagnosis information, and the historical case symptom information and historical case diagnosis information are one-to-one corresponding; Integrate historical diagnostic data and classify and manage the historical diagnostic data for access to the case archive database.

[0034] As a preferred embodiment of the above embodiment, personal historical medical information, historical case symptom information, and historical case diagnosis information are collected and stored through various channels such as hospital information, electronic medical records, and medical device records. This data collection includes personal historical medical information, historical case symptom information, and historical case diagnosis information. A case symptom index is constructed to improve the retrieval efficiency of historical case data. A mapping relationship is established between historical case symptom information and historical case diagnosis information. Symptom descriptions are extracted from historical cases and mapped one-to-one with the doctor's final diagnosis of the disease. To improve retrieval speed, the symptom index adopts a multi-level classification structure. By integrating historical diagnosis data, all historical case information is classified, organized, and managed. When integrating historical diagnosis data, various types of data are cleaned and standardized, and classified and managed according to the type and severity of the diagnosis data. The classified management of historical diagnosis data can quickly retrieve the corresponding historical diagnosis information when matching emergency cases. Through this mechanism, the most similar historical case can be found based on the symptoms and medical history information of the emergency case in the shortest possible time, providing a diagnostic reference for the doctor.

[0035] Further, if Figure 4 As shown in the figure, the number of cases with emergency case information is identified. The identification results include unilateral emergency or multilateral emergency, and the association weight of multilateral emergency is adaptively adjusted, including: Identify the number of cases in the emergency case information, analyze the severity of the emergency cases contained in each emergency case information and their mutual correlation, and determine the priority of each emergency case; According to the priority of each emergency case and the number of cases included in each emergency medical record information, the identification results are divided into unilateral emergency or multilateral emergency. The difference between unilateral emergency and multilateral emergency is the number of cases included in the emergency situation; Initial association weights were assigned to the case data fields for each case included in the unilateral ED and the multilateral ED; The initial correlation weight is adjusted according to the correlation of each emergency case to generate the correlation weight, and the emergency rapid response queue is updated according to the result after the correlation weight adjustment.

[0036] As a preferred embodiment of the above embodiment, emergency case information is first received and analyzed. Each piece of emergency case information may contain one or more emergency cases. By analyzing the number of patients in each piece of emergency case information, it is determined whether the current emergency situation is a unilateral emergency or a multilateral emergency. For each identified emergency case, the severity of the case and its correlation with other cases will be further analyzed. For example, the severity of the condition will be judged based on the patient's vital signs, symptom description, preliminary diagnosis and other information, and the correlation between different emergency cases will be evaluated. For example, in a multilateral emergency situation, multiple patients may seek emergency medical treatment due to the same event (such as a traffic accident or an infectious disease). The correlation between these cases will be evaluated, and a priority will be assigned to each case based on the severity and correlation of the emergency case. Cases with more serious conditions or cases that are highly correlated with other cases will be given a higher priority. For example, patients with severe heart attacks may be assigned the highest priority, while cases with milder conditions will receive a lower priority. Based on the number and priority of identified cases, the emergency situation is divided into a unilateral emergency or a multilateral emergency, and the response is further determined based on this classification result. For example, unilateral emergencies can be handled directly based on the severity of the case, while multilateral emergencies need to consider the priority and relevance of multiple cases. For each case in both unilateral and multilateral emergencies, an initial relevance weight is assigned to its case data field based on the analysis results. The initial weight reflects the initial priority of the case in the emergency response queue. For unilateral emergencies, the weight only considers the severity of the patient; for multilateral emergencies, the relevance and importance of multiple cases are simultaneously considered. In the case of multilateral emergencies, the initial relevance weight is adjusted based on the relevance between different cases. Cases with higher relevance will receive higher weights. Especially when multiple cases come from the same event or the progression of the disease may affect each other, these related cases will be handled first. The emergency rapid response queue is updated in real time based on the adjusted relevance weights. Cases in the queue are sorted from high to low according to weight, and cases with higher weights are handled first. For multilateral emergencies, cases with strong relevance and high priority are ensured to be at the top. The queue is updated dynamically, and the queue order is continuously adjusted as the status of the case changes or the availability of resources.

[0037] Further, if Figure 5 As shown, the initial correlation weight is adjusted according to the correlation of each emergency case to generate the correlation weight, and the emergency rapid response queue is updated according to the result after the correlation weight adjustment, including: Conduct a detailed assessment of the strength of the correlation between multiple emergency cases and determine the correlation level between each emergency case. The higher the correlation level, the stronger the correlation between the emergency medical records. Combined with the resource requirements of each emergency case, the initial association weights are adjusted hierarchically according to the degree of resource shortage and the resource occupation priority of each emergency case to generate association weights, and the weights are redistributed; Calculate the weight difference between the associated weights, adjust the priority response order of multiple tasks according to the weight difference, establish a priority task allocation mechanism for cases with higher association intensity, and update the sorting of the emergency rapid response queue.

[0038] As a preferred embodiment of the above, first, a detailed analysis is performed on the correlation between multiple emergency cases. The correlation evaluation includes multiple factors, such as whether the cases are caused by the same event, the similarity of the conditions, and whether there is a potential need for sharing medical resources between cases. Based on these factors, a correlation level is assigned to each case. The higher the correlation level, the stronger the mutual influence between multiple emergency cases. After evaluating the case correlation level, further analysis is performed in combination with the resource demand of each emergency case. According to the current availability of medical resources, it is evaluated whether the resources are tight. The degree of resource tension determines how to prioritize resource allocation. The resource demand of each emergency case is different. For example, some cases may require emergency surgery, while other cases may only require routine treatment. The resource occupation priority of each case is used to judge the degree of demand for existing medical resources of the case. The higher the resource occupation priority, the more critical resources the case needs to occupy. Based on the correlation level and resource occupation priority, the initial correlation weight is hierarchically adjusted. The higher the resource tension, the more it tends to be allocated to high-priority and highly correlated cases. The correlation weight of cases with high correlation and high resource occupation priority will increase accordingly, while for cases with low correlation and low resource demand, the correlation weight will increase accordingly. The weight of cases with fewer requests will be reduced accordingly, and the cases will be stratified. The first tier is cases with high relevance and high resource occupation priority, the second tier is cases with low relevance but large resource demand, and the third tier is cases with low relevance and small resource demand. Through this stratification mechanism, it is ensured that urgent and important cases are handled first, and the difference between the relevance weights of each case is calculated. The weight difference value refers to the relative difference in weights between different cases, which is used to decide which cases should be responded to first. For example, after calculating the relevance weights of multiple cases, these weight values ​​will be compared to calculate which cases have significant priority differences and which cases can be responded to first. They are processed together and the priority response order of multiple tasks is readjusted according to the calculated weight difference value. Cases with larger weight difference values ​​will be responded to first, while cases with smaller weights or insignificant weight differences can be delayed or processed in parallel. After determining the priority response order, a priority task allocation mechanism will be established for cases with higher correlation intensity. Resources will be concentrated on cases with strong correlation. According to the reallocated correlation weights, the ranking of the emergency rapid response queue will be updated. Through the adjustment of the correlation weights, the cases in the emergency queue will be updated according to the new priority order, and the order in the queue will be adjusted according to factors such as changes in the condition and resource availability.

[0039] Example 2 Based on the same inventive concept as the management method for rapid response to emergency data in the aforementioned embodiment, the present invention further provides a management system for rapid response to emergency data, the system comprising: Case information acquisition module, which obtains emergency case information, performs basic diagnosis on the emergency case information, and obtains case pre-diagnosis results; The emergency medical record matching module accesses the case file system according to the emergency case information, matches the emergency case information, and obtains case matching information; The case data classification module classifies case matching information. Each classification result corresponds to a case data field, and a set of case data fields corresponds to a single emergency case. The weighted queue establishment module assigns weights to several case data fields according to the case pre-diagnosis results and obtains response-related weights, and establishes an emergency rapid response queue according to the response-related weights; The emergency plan calling module allocates tasks from the quick response queue to multiple response terminals. Multiple response terminals simultaneously prepare emergency plans for the assigned tasks and wait for the call from the emergency quick response queue.

[0040] The above-mentioned adjustment system in the present invention can effectively realize the management method of rapid response to emergency data, and the technical effects that can be achieved are as described in the above-mentioned embodiments and will not be repeated here.

[0041] Specifically, the weighted queue building module includes: A field selection unit, which selects a first executed case data field according to the case pre-diagnosis result, and sets a time slice for the first executed case data field, wherein each case data field corresponds to a time slice; A decision engine unit, which sets a decision engine that stores and dynamically calls single-dimensional priority weights; The weight generation unit calls the adapted single-dimensional priority weight according to the decision engine in the current time slice, and sequentially integrates the single-dimensional priority weights of the decisions in each time slice to generate the response association weight.

[0042] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the corresponding optimization effects of the method in Example 1, which will not be repeated here.

[0043] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and drawings are merely illustrative of the present application as defined herein and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the present application and its equivalents.

Claims

1. A management method for rapid response of emergency data, characterized in that: The method comprises: Obtain emergency case information, perform basic diagnosis on the emergency case information, and obtain case pre-diagnosis results; Accessing the case file system according to the emergency case information, and matching the emergency case information to obtain case matching information; Classifying the case matching information, each classification result corresponds to a case data field, and a plurality of case data field sets correspond to a single emergency case; According to the case pre-diagnosis result, weights are assigned to the case data fields to obtain response-related weights, and an emergency rapid response queue is established according to the response-related weights; The quick response queue is assigned tasks to multiple responding ends, and the multiple responding ends simultaneously prepare plans for the assigned tasks and wait for the call of the emergency quick response queue.

2. The management method for rapid response of emergency data according to claim 1, characterized in that: According to the case pre-diagnosis result, weights are assigned to a number of the case data fields and response association weights are obtained, including: Selecting the case data field of the first execution according to the case pre-diagnosis result, and setting a time slice for the case data field of the first execution, and each case data field corresponds to one time slice; Setting a decision engine, wherein the decision engine stores and dynamically calls single-dimensional priority weights; The single-dimensional priority weight adapted by the decision engine is called in the current time slice, and the single-dimensional priority weights of the decisions in each time slice are sequentially integrated to generate the response association weight.

3. The management method for rapid response of emergency data according to claim 2, characterized in that: Invoking the adapted single-dimension priority weight according to the decision engine within the current time slice includes: The time slice and the time response segment are staggered and overlapped, wherein the time response segment is the actual response time of the case data field; The time slice connects the two time response segments and sets a connection time period within the time slice, and calls the single-dimensional priority weight according to the decision engine within the connection time period.

4. The management method for rapid response of emergency data according to claim 3, characterized in that: The quick response queue is assigned tasks to multiple response terminals, and the multiple response terminals simultaneously prepare plans for the assigned tasks and wait for the call of the emergency quick response queue, including: Allocating tasks in the emergency rapid response queue to multiple response terminals according to predetermined rules; After receiving the assigned tasks, the multiple responders simultaneously prepare plans for their respective tasks, wherein the plan preparation includes deploying corresponding personnel, equipment and resources according to task requirements; After completing the plan preparation, the multiple response ends are in a standby state, waiting for the call of the emergency rapid response queue, so as to immediately execute the corresponding emergency response operation when receiving the call instruction.

5. The management method for rapid response of emergency data according to claim 1, characterized in that: Access the case file system according to the emergency case information, match the emergency case information, and obtain case matching information, including: Establishing a case file database, the case file database includes personal historical medical information, historical case symptom information, and historical case diagnosis information; Constructing a case matching model, retrieving the historical case symptom information and the historical case diagnosis information, and training and evaluating the case matching model; According to the case matching model, deep learning is performed on the case archive database to obtain the mapping relationship between the historical case symptom information and the historical case diagnosis information, and the emergency case information is matched according to the mapping relationship to obtain case matching information.

6. The management method for rapid response of emergency data according to claim 5, characterized in that: Establishing a case file database, the method comprises: Collect personal historical medical information, historical case symptom information, and historical case diagnosis information; Constructing a case symptom index to reflect the mapping relationship between the historical case symptom information and the historical case diagnosis information, and the historical case symptom information and the historical case diagnosis information correspond one to one; Integrate historical diagnostic data, and classify and manage the historical diagnostic data for use by the case archive database.

7. The management method for rapid response of emergency data according to claim 1, characterized in that: Identify the number of cases of the emergency case information, where the identification result includes unilateral emergency or multilateral emergency, and adaptively adjust the association weight of the multilateral emergency, including: Identify the number of cases in the emergency case information, analyze the severity of the emergency cases contained in each of the emergency case information and their interrelationships, and determine the priority of each of the emergency cases; According to the priority of each emergency case and the number of cases included in each emergency medical record information, the identification results are divided into unilateral emergency or multilateral emergency, and the difference between the unilateral emergency and multilateral emergency is the emergency situation including the number of cases; Assigning initial association weights to the case data fields of each case included in the unilateral emergency department and the multilateral emergency department; The initial association weight is adjusted according to the association of each emergency case to generate an association weight, and the emergency rapid response queue is updated according to the result of the adjustment of the association weight.

8. The management method for rapid response of emergency data according to claim 7, characterized in that: Adjusting the initial association weight according to the association of each of the emergency cases to generate an association weight, and updating the emergency rapid response queue according to the result after the association weight adjustment, including: Conduct a detailed evaluation of the strength of the correlation between the multiple emergency cases to determine the correlation level between the emergency cases, wherein the higher the correlation level, the stronger the correlation between the emergency medical records; Combined with the resource requirements of each emergency case, the initial association weights are adjusted hierarchically according to the resource intensity and resource occupation priority of each emergency case to generate association weights, and the weights are redistributed; The weight difference value between the association weights is calculated, and the priority response order of multiple tasks is adjusted according to the weight difference value, a priority task allocation mechanism for cases with higher association strength is established, and the ranking of the emergency rapid response queue is updated.

9. Emergency data rapid response management system, characterized by: The system comprises: A case information acquisition module is used to acquire emergency case information, and to perform basic diagnosis on the emergency case information to obtain case pre-diagnosis results; An emergency medical record matching module accesses the case file system according to the emergency case information, matches the emergency case information, and obtains case matching information; A case data classification module is used to classify the case matching information, each classification result corresponds to a case data field, and a plurality of case data field sets correspond to a single emergency case; A weighted queue establishment module, which assigns weights to a number of case data fields according to the case pre-diagnosis results and obtains response-related weights, and establishes an emergency rapid response queue according to the response-related weights; The allocation plan calling module allocates tasks from the rapid response queue to multiple responding ends, and the multiple responding ends simultaneously prepare plans for the allocated tasks and wait for the call of the emergency rapid response queue.

10. The management system for rapid response of emergency data according to claim 9, characterized in that: The weight queue establishment module includes: A field selection unit, which selects the case data field of the first execution according to the case pre-diagnosis result, and sets a time slice for the case data field of the first execution, and each case data field corresponds to one time slice; A decision engine unit, which is used to set a decision engine, wherein the decision engine stores and dynamically calls a single-dimensional priority weight; The weight generating unit calls the adapted single-dimensional priority weight according to the decision engine in the current time slice, and sequentially integrates the single-dimensional priority weights of the decisions in each time slice to generate the response association weight.

Images