Medical resource allocation method and device for pre-hospital first aid, electronic equipment and storage medium

Abstract

The invention relates to the technical field of medical resource management, in particular to a medical resource allocation method and device for pre-hospital first aid, electronic equipment and a storage medium. And importing the scoring result of each evaluation sub-item to each medical resource allocation scoring model to obtain an allocation scoring result of each medical resource, obtaining various medical resource scoring results of other patients to be subjected to resource allocation at the current moment, and determining the recommendation probability of the target patient in various medical resources based on a recommendation probability function. Compared with an existing mode of obtaining allocation results of various medical resources by using the same model, the medical resource allocation method disclosed by the embodiment of the invention fully considers influence factors of various medical resources, so that allocation of various medical resources is more reasonable and accurate, idle or overuse of part of medical resources is avoided, and the medical resource allocation efficiency is improved. The effectiveness of patient rescue is ensured, and the rescue success rate is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical resource management, and is a method, device, electronic device and storage medium for allocating medical resources for pre-hospital emergency care. Background Art

[0002] Pre-hospital emergency care is an important part of the emergency treatment process, referring to the medical treatment that a patient receives from the onset of the disease until being admitted to the hospital after receiving the alarm. It is necessary to quickly evaluate the patient's condition, and quickly, accurately and efficiently allocate medical resources according to the condition and other factors, reduce the waiting time of critically ill patients, improve the success rate of rescue of critically ill patients, optimize the utilization of medical resources, improve the quality of medical services, and ensure the safety of patients.

[0003] In the existing medical system, the allocation of resources for pre-hospital emergency care mainly relies on the experience of emergency medical staff to complete through manual decision-making. Therefore, the following problems exist:

[0004] (1) Uneven distribution of medical resources: The professional levels and experiences of emergency medical staff are different. In an emergency environment such as first aid, relying on methods based on professional level, experience and intuition is likely to lead to uneven, inaccurate and untimely distribution of medical resources, resulting in the idling or overuse of some medical resources, so that some patients cannot obtain corresponding medical resources, hindering the effectiveness of treatment, causing some critically ill patients to miss the best treatment opportunity, and reducing the success rate of rescue.

[0005] (2) Slow response speed: In an emergency environment such as first aid, the manual allocation of medical resources takes a long time and cannot quickly respond to the needs of patients, affecting the treatment efficiency.

[0006] (3) Insufficient training of emergency medical staff: There are differences in the training quality and professional levels of emergency personnel. In some areas, there is a lack of emergency personnel who have received professional training and certification, which affects the allocation of medical resources and thus affects the quality and effect of first aid.

[0007] With the rapid development of Internet and artificial intelligence technologies, more and more computer technologies are used in the allocation of resources for pre-hospital emergency care or the allocation of resources in the medical system. For example:

[0008] Existing publicly disclosed patent document 1, with a publication number of CN115831335A, discloses a resource scheduling method and system based on multi-dimensional diagnosis and treatment data, including: for a target area, obtaining a set of diagnosis and treatment data for each dimension within the current seasonal cycle that matches the target area; wherein, the set of diagnosis and treatment data includes patient diagnosis and treatment data in the patient dimension, department diagnosis and treatment data in the department dimension, doctor diagnosis and treatment data in the doctor dimension, and hospital diagnosis and treatment data in the hospital dimension; for the diagnosis and treatment data of each dimension in the set of diagnosis and treatment data, calculating the total score value corresponding to the diagnosis and treatment data of this dimension based on the weight corresponding to the diagnosis and treatment data of this dimension and the score corresponding to the diagnosis and treatment data of this dimension; combining the total score value and the seasonal index corresponding to the historical diagnosis and treatment data to predict the diagnosis and treatment level of the next seasonal cycle; determining the medical resources that match the diagnosis and treatment level, and outputting the medical resources to allocate medical resources to the target area. The present invention can improve the scheduling effect of medical resources.

[0009] Existing publicly disclosed patent document 2, with a publication number of CN118471456B, discloses a scheduling method, system, device and storage medium for emergency medical resources, relating to the technical field of resource allocation, including the steps of: obtaining the scheduling status information and related actions of medical resources in the emergency department; estimating the related actions through a deep reinforcement learning model; using a particle swarm optimization algorithm to optimize the parameters of the deep reinforcement learning model, randomly initializing the position and velocity of each particle in the particle swarm; updating the velocity and position of each particle according to the individual historical best position and the global historical best position; selecting the optimal particle to update the parameters of the deep reinforcement learning model to obtain an optimized deep reinforcement learning model; inputting the scheduling status information and related actions of medical resources into the optimized deep reinforcement learning model to obtain the optimal resource scheduling strategy. The present invention uses a particle swarm optimization algorithm to improve the method of optimizing the training of a deep reinforcement learning model, and improves the speed and accuracy of obtaining the best parameters in resource scheduling.

[0010] However, in the above resource allocation process, it does not target the differences of various types of medical resources to achieve targeted allocation of various types of medical resources, but uses the same model to obtain the allocation results of various types of medical resources. Therefore, there is a problem that the allocation of various types of medical resources is inaccurate. Summary of the Invention

[0011] The present invention provides a method, device, electronic device and storage medium for allocating medical resources for pre-hospital emergency treatment, overcoming the above-mentioned deficiencies of the prior art, and effectively solving the problems existing in the existing medical resource allocation method, that is, using the same model to allocate various types of medical resources, resulting in inaccurate allocation results and easily causing some medical resources to be idle or overused.

[0012] One of the technical solutions of the present invention is achieved by the following measures: A method for allocating medical resources for pre-hospital emergency treatment, including:

[0013] Score the sub - items of the score based on the scoring rules and the basic data set of the target patient. The basic data set includes the distance data from the location of the target patient to the hospital, the vital sign data, the disease condition data, and the medical history data of the target patient. The sub - items of the score are factors related to the allocation of medical resources;

[0014] Import the scoring results of each sub - item of the score into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource. Each medical resource allocation scoring model is constructed by setting the weights of different sub - items of the score in combination with the characteristics of each medical resource;

[0015] Obtain the scoring results of various medical resources of other patients waiting for allocation at the current moment, and determine the recommendation probability of the target patient in various medical resources based on the recommendation probability function. The recommendation probability function is as follows:

[0016]

[0017] where, T i is the allocation scoring result of a certain medical resource of the target patient; T j is the allocation scoring result of a certain medical resource of the patient waiting for allocation; n is the total number of patients waiting for allocation.

[0018] The following is a further optimization or / and improvement of the above - mentioned technical solution of the invention:

[0019] The above also includes, after the allocation of medical resources for the target patient, in response to the fact that not all of the actual allocation feedback data of the target patient is less than the corresponding threshold, using an optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model. The actual allocation feedback data of the target patient includes the success rate of treatment, the utilization efficiency of medical resources, and the waiting time for medical treatment of the target patient.

[0020] The above use of the optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model includes:

[0021] Construct a loss function based on the actual allocation feedback data and the predicted allocation feedback data of the target patient;

[0022] Use the gradient descent algorithm to adjust the weights of each item in the medical resource allocation scoring model through multiple iterations, so that the loss function is continuously reduced until the optimization stop condition is met.

[0023] The above also includes obtaining the resource allocation result of the target patient by combining the allocation rules and the recommendation probabilities of various medical resources. The allocation rules include:

[0024] If the recommendation probability in a certain type of medical resource exceeds the threshold, it is allowed to obtain that medical resource;

[0025] Allocate medical resources in a class of medical resources in descending order of recommended probability.

[0026] The above-mentioned scoring sub-items and corresponding scoring rules include:

[0027] Disease condition assessment details score: Score the disease condition assessment details according to the scoring rules, where each symptom keyword and its corresponding score are set in the scoring rules;

[0028] Disease condition assessment performance score: Score the dynamic performance of symptoms according to the scoring rules, where various dynamic symptom manifestations and their corresponding scores are set in the scoring rules;

[0029] Disease emergency level score: Score the disease emergency level according to the scoring rules, where various disease emergency levels and their corresponding scores are set in the scoring rules;

[0030] Vital sign score: Score various vital signs according to the scoring rules and obtain the total score after weighting, where the scores corresponding to various vital signs at different stages are set in the scoring rules;

[0031] Physical examination abnormality score: Score the physical examination abnormalities according to the scoring rules, where various physical examination abnormalities and their corresponding scores are set in the scoring rules;

[0032] Medical history assessment score: Score the medical history assessment results according to the scoring rules, where various diseases and their corresponding scores are set in the scoring rules;

[0033] Distance to hospital score: Score the distance from the target patient to the hospital according to the scoring rules, where the scores corresponding to kilometers are set in the scoring rules;

[0034] Route congestion score: Calculate the congestion index and score the difference between the congestion index and the basic threshold according to the scoring rules. Different differences and their corresponding scores are set in the scoring rules. The congestion index calculation formula is as follows:

[0035]

[0036] Among them, C is the congestion index, RS is the normal traffic running speed, and CS is the actual traffic running speed.

[0037] The above-mentioned medical resource allocation scoring model is as follows:

[0038] T = D×w_D + M×w_M + E×w_E + V×w_V + P×w_P + H×w_H - L×w_L - C×w_C

[0039] Among them, T is the total score of a certain type of medical resource; D, M, E, V, P, H, L, and C are the scoring results of the sub - scoring items, which are the scoring results of the disease condition assessment details, the scoring results of the disease condition assessment performance, the scoring results of the disease emergency level, the scoring results of the vital signs, the scoring results of the abnormal physical examination, the scoring results of the medical history assessment, the scoring results of the distance to the hospital, and the scoring results of the road congestion; w_D, w_M, w_E, w_V, w_P, w_H, w_L, and w_C are the weights of each sub - scoring item in this type of medical resource.

[0040] The second technical solution of the present invention is achieved through the following measures: A medical resource allocation device for pre - hospital first aid, including:

[0041] A sub - item scoring unit that scores the sub - scoring items by combining the scoring rules and the basic data set of the target patient, where the basic data set includes the road data from the location of the target patient to the hospital, the vital signs data, the disease condition data, and the medical history data of the target patient, and the sub - scoring items are factors related to medical resource allocation;

[0042] A model scoring unit that imports the scoring results of each sub - scoring item into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource, where each medical resource allocation scoring model is constructed by setting different weights for each sub - scoring item in combination with the characteristics of each medical resource;

[0043] A recommended probability calculation unit that obtains the scoring results of various medical resources of other patients with resources to be allocated at the current moment, and determines the recommended probability of the target patient in various medical resources based on the recommended probability function, where the recommended probability function is as follows:

[0044]

[0045] Among them, T i is the allocation scoring result of a certain medical resource for the target patient; T j is the allocation scoring result of a certain medical resource for the patient with resources to be allocated; n is the total number of patients with resources to be allocated.

[0046] The following is a further optimization and / or improvement of the above - mentioned invention technical solution:

[0047] The above also includes:

[0048] A resource allocation unit that obtains the resource allocation result of the target patient by combining the allocation rules and the recommended probabilities of various medical resources, where the allocation rules include:

[0049] If the recommended probability in a certain type of medical resource exceeds the threshold, it is allowed to obtain this medical resource;

[0050] Allocate medical resources in a class of medical resources in descending order of recommended probability;

[0051] A feedback optimization unit, after the allocation of medical resources for the target patient is completed, in response to the fact that not all of the actual allocation feedback data of the target patient is less than the corresponding threshold, uses an optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model, where the actual allocation feedback data of the target patient includes the success rate of treatment, the utilization efficiency of medical resources, and the waiting time for medical treatment of the target patient.

[0052] The above also includes:

[0053] A sub-project construction unit constructs evaluation sub-projects and corresponding scoring rules, including:

[0054] Disease condition assessment detail scoring: Score the disease condition assessment details according to the scoring rules, where each symptom keyword and its corresponding score are set in the scoring rules;

[0055] Disease condition assessment performance scoring: Score the dynamic performance of symptoms according to the scoring rules, where various dynamic symptoms and their corresponding scores are set in the scoring rules;

[0056] Disease urgency scoring: Score the disease urgency according to the scoring rules, where various disease urgencies and their corresponding scores are set in the scoring rules;

[0057] Vital sign scoring: Score various vital signs according to the scoring rules and obtain the total score after weighting, where the scores corresponding to various vital signs at different stages are set in the scoring rules;

[0058] Physical examination abnormality scoring: Score the physical examination abnormalities according to the scoring rules, where various physical examination abnormalities and their corresponding scores are set in the scoring rules;

[0059] Medical history assessment scoring: Score the medical history assessment results according to the scoring rules, where various diseases and their corresponding scores are set in the scoring rules;

[0060] Distance to the hospital scoring: Score the distance of the target patient to the hospital according to the scoring rules, where the scores corresponding to kilometers are set in the scoring rules;

[0061] Route congestion scoring: Calculate the congestion index and score the difference between the congestion index and the base threshold according to the scoring rules, where different differences and their corresponding scores are set in the scoring rules. The congestion index calculation formula is as follows:

[0062]

[0063] Among them, C is the congestion index, RS is the normal traffic operation speed, and CS is the actual traffic operation speed;

[0064] A model construction unit that constructs various medical resource allocation scoring models. The medical resource allocation scoring model is as follows:

[0065] T = D×w_D + M×w_M + E×w_E + V×w_V + P×w_P + H×w_H - L×w_L - C×w_C

[0066] Among them, T is the total score of a certain type of medical resource; D, M, E, V, P, H, L, and C are the scoring results of the sub - scoring items, which are the scoring results of the detailed condition assessment, the scoring results of the condition assessment performance, the scoring results of the degree of urgency of the condition, the scoring results of the vital signs, the scoring results of the abnormal rapid physical examination, the scoring results of the medical history assessment, the scoring results of the distance to the hospital, and the scoring results of the journey congestion; w_D, w_M, w_E, w_V, w_P, w_H, w_L, and w_C are the weights of each sub - scoring item in this type of medical resource.

[0067] The third technical solution of the present invention is achieved by the following measures: An electronic device includes a processor and a memory. A computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the steps in the medical resource allocation method for pre - hospital emergency.

[0068] The fourth technical solution of the present invention is achieved by the following measures: A storage medium stores a computer program that can be read by a computer. The computer program is set to execute the steps in the medical resource allocation method for pre - hospital emergency when running.

[0069] The present invention separately sets up medical resource allocation scoring models according to the characteristics of each medical resource, adaptively scores various medical resources for target patients according to the medical resource allocation scoring models, and determines the demand degree of target patients for a certain type of medical resource among all patients waiting for allocated resources based on the recommendation probability function, providing support for reasonable medical resource allocation. Compared with the existing method of obtaining the allocation results of various medical resources using the same model, the medical resource allocation method disclosed in the present invention fully considers the influencing factors of various medical resources, making the allocation of various medical resources more reasonable and accurate, avoiding the idleness or over - use of some medical resources, ensuring the effectiveness of patient treatment, and improving the success rate of rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Attached Figure 1 is a schematic diagram of an implementation environment provided by the present invention.

[0071] Attached Figure 2Schematic diagram of a medical resource allocation method provided by the present invention.

[0072] Appendix Figure 3 Another schematic diagram of a medical resource allocation method provided by the present invention.

[0073] Appendix Figure 4 Another schematic diagram of a medical resource allocation method provided by the present invention.

[0074] Appendix Figure 5 Schematic diagram of the structure of a medical resource allocation device provided by the present invention.

[0075] Appendix Figure 6 Another schematic diagram of the structure of a medical resource allocation device provided by the present invention. Detailed implementation manners

[0076] The present invention is not limited by the following embodiments, and the specific implementation manners can be determined according to the technical solution of the present invention and the actual situation.

[0077] Those skilled in the art of the present technology can understand that, unless specifically stated, in the embodiments of the present invention, a "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of that module or unit.

[0078] In addition, in the embodiments of the present invention, "a plurality of" means two or more, and "first" and "second" are used for distinguishing descriptions, and should not be construed as implying relative importance.

[0079] Next, an introduction is given to the architecture of the steam injection boiler collaborative scheduling system based on multiple event states provided by the embodiments of the present invention.

[0080] The embodiments of the present invention provide a medical resource allocation method, device, electronic device and storage medium for pre-hospital first aid. The medical resource allocation device for pre-hospital first aid can be integrated in a computer device, and the computer device can be a server or a terminal device, etc. It can be understood that the medical resource allocation method for pre-hospital first aid in this embodiment can be executed on the server, or on the terminal, or jointly executed by the terminal and the server. The above examples should not be construed as limitations on the present invention.

[0081] As shown in the appendix Figure 1As shown, take the medical resource allocation method for pre-hospital emergency jointly executed by the terminal and the server as an example. The terminal and the server are connected through a network, which can be a wired network or a wireless network connection, etc.

[0082] Among them, the terminal provides an interactive interface for the medical resource allocation method for pre-hospital emergency, which is used to display the basic data set of the target patient based on the interactive interface, display the scoring results of each scoring sub-item after scoring the scoring sub-items based on the scoring rules and the basic data set of the target patient. At this time, manual scoring can also be introduced, and professionals can perform operations such as modifying scores and filling in blank scores. Then, import the scoring results of each scoring sub-item into each medical resource allocation scoring model, view the allocation scoring results of each medical resource, and then view the recommended probability of the target patient in various medical resources and the corresponding medical resource allocation results. At this time, manual adjustment of the medical resource allocation results can also be introduced. For example, when the medical resource allocation result is occupied, the medical resource is manually adjusted. Further, operations such as manually performing real-time viewing of the current occupancy status of various medical resources and directly modifying the scoring results of the scoring sub-items according to the current status of the target patient to re-perform medical resource allocation can also be performed. The terminal here can include mobile phones, wearable intelligent devices, tablet computers, laptop computers, personal computers (PCs), in-vehicle computers, etc., and the present invention does not limit this. Regarding the number of terminal devices, the present invention does not make any restrictions.

[0083] Among them, the server provides processes such as various data extraction, model calculation, recommended probability calculation, medical resource allocation result generation, model update, etc. in the medical resource allocation method for pre-hospital emergency. Specifically, it may include but is not limited to: (1) collecting data such as the voice information self-reported by the target patient, the voice information described by on-site personnel, the pre-judgment information of medical staff, and image information, and using preset algorithms such as image recognition, voice recognition, and semantic analysis to extract the basic data set of the target patient; (2) constructing each scoring sub-item and its corresponding scoring rules, and scoring the scoring sub-items in combination with the scoring rules and the basic data set of the target patient; (3) constructing each medical resource allocation scoring model, and importing the scoring results of each scoring sub-item into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource; (4) obtaining the scoring results of various medical resources of other patients waiting for allocation at the current moment, and determining the recommended probability of the target patient in various medical resources based on the recommended probability function; (5) combining the allocation rules and the recommended probabilities of various medical resources to obtain the resource allocation result of the target patient; (6) after the medical resource allocation of the target patient is completed, collecting the actual allocation feedback data of the target patient, and if the actual allocation feedback data of the target patient is not all less than the corresponding threshold, using the optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model. Here, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The present invention does not limit this.

[0084] Based on this, the technical solutions of the present invention will be introduced and illustrated below with several examples.

[0085] Example 1: As shown in the appendix Figure 2 The embodiment of the present invention discloses a medical resource allocation method for pre-hospital emergency, including:

[0086] Step S110, scoring the scoring sub-items in combination with the scoring rules and the basic data set of the target patient, where the basic data set includes the distance data from the location of the target patient to the hospital, the vital sign data, condition data, and medical history data of the target patient, and the scoring sub-items are factors related to medical resource allocation.

[0087] In the above steps, the basic data set includes the distance data from the location of the target patient to the hospital, the vital sign data, condition data, and medical history data of the target patient. Among them, the distance data from the location of the target patient to the hospital can be automatically collected after navigation based on the location information of the target patient and map data. The vital sign data of the target patient can be collected remotely by terminal devices such as intelligent wearable devices and mobile medical devices. The condition data can be obtained by collecting data such as the voice information described by the target patient himself / herself, the voice information described by on-site personnel, the preliminary judgment information of medical staff, and image information, and extracting them using existing technologies such as image recognition, voice recognition, and semantic analysis. The medical history data can be searched and extracted from the relevant hospital databases through the identity information of the target patient.

[0088] Furthermore, the basic data set can be classified according to the scoring sub-items, which is convenient for improving the scoring speed of subsequent scoring sub-items.

[0089] There can be several scoring sub-items in the above steps. The specific types are not limited in this embodiment, but they need to be factors related to medical resource allocation. The scoring rules for each scoring sub-item need to be set according to the characteristics of the scoring sub-item and in combination with historical medical resource allocation data and professional guidance.

[0090] When scoring each scoring sub-item, the data in the basic data set is matched with each scoring rule to determine the corresponding scoring result. Furthermore, in the case of non-matching, a prompt is given and manual scoring is introduced to ensure that all scoring sub-items have scoring results, avoiding incorrect allocation scoring results output by the subsequent medical resource allocation scoring model and affecting medical resource allocation.

[0091] Step S120, import the scoring results of each scoring sub-item into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource, where each medical resource allocation scoring model is constructed by setting the weights of different scoring sub-items in combination with the characteristics of each medical resource.

[0092] In the above steps, each medical resource allocation scoring model is constructed by setting the weights of different scoring sub-items in combination with the characteristics of each medical resource. Among them, when constructing each medical resource allocation scoring model, the weight allocation for each scoring sub-item can be obtained by analyzing a number of relevant materials such as historical case data and historical emergency data. The analysis process can be divided into training and testing, that is, using a part of the relevant materials to analyze and set the initial weight values of each scoring sub-item, and then bringing the remaining relevant materials into the medical resource allocation scoring model with the initial weight values for accuracy testing, and thus cycling to obtain the accurate weight values of each scoring sub-item. It is also possible to use existing optimization algorithms to determine the weight values of each scoring sub-item.

[0093] Step S130: Obtain the scoring results of various medical resources for patients with other resources to be allocated at the current moment, and determine the recommendation probability of the target patient for various medical resources based on the recommendation probability function, where the recommendation probability function is as follows:

[0094]

[0095] where, T i is the allocation scoring result of the target patient in a certain medical resource; T j is the allocation scoring result of the patient with resources to be allocated in a certain medical resource; n is the total number of patients with resources to be allocated (including the target patient among all patients with resources to be allocated).

[0096] The above steps are used to determine the recommendation probability of the target patient for various medical resources, that is, the recommendation probability of the allocation scoring result of the target patient in a certain medical resource among the allocation scoring results of all patients with resources to be allocated at the current moment. Thus, the demand degree of the target patient for a certain type of medical resource among all patients with resources to be allocated can be determined, which is convenient for subsequently allocating the corresponding medical resources according to the demand degree, making the medical resources more reasonable.

[0097] In summary, the embodiment of the present invention discloses a medical resource allocation method for pre-hospital emergency. Medical resource allocation scoring models are respectively set according to the characteristics of each medical resource. Adaptive scoring of various medical resources is realized for the target patient according to the medical resource allocation scoring model, and the demand degree of the target patient for a certain type of medical resource among all patients with resources to be allocated is determined based on the recommendation probability function, providing support for reasonable medical resource allocation. Compared with the existing method of obtaining the allocation results of various medical resources using the same model, the medical resource allocation method disclosed in this embodiment fully considers the influencing factors of various medical resources, making the allocation of various medical resources more reasonable and accurate, avoiding the idleness or overuse of some medical resources, ensuring the effectiveness of patient treatment, and improving the rescue success rate.

[0098] Embodiment 2: The embodiment of the present invention discloses a medical resource allocation method for pre-hospital emergency, which is a further optimization of the above embodiment. The scoring sub-items and corresponding scoring rules include:

[0099] (1) Detailed scoring of condition assessment: Score the condition assessment details according to the scoring rules, where each symptom keyword and its corresponding score are set in the scoring rules;

[0100] The above-mentioned disease condition assessment details include keywords corresponding to various symptoms such as dyspnea, abdominal pain, toothache, shoulder and back pain, combined with bleeding, combined with heart failure, combined with malignant arrhythmia, etc. The scoring rules can be set according to the severity of various symptoms. For example, dyspnea = 3, abdominal pain = 2, toothache = 1, shoulder and back pain = 1, combined with bleeding = 3, combined with heart failure = 4, combined with malignant arrhythmia = 4.

[0101] (2) Scoring of the manifestation of disease condition assessment, scoring the dynamic manifestations of symptoms according to the scoring rules, where various dynamic manifestations of symptoms and their corresponding scores are set in the scoring rules;

[0102] The above-mentioned dynamic manifestations of symptoms are set according to the dynamic changes of various symptoms. For example, for chest tightness / chest pain, the dynamic manifestations of this symptom include persistent chest tightness / chest pain, intermittent chest tightness / chest pain, chest tightness / chest pain has been relieved, etc. The scoring rules can be set according to the severity of the results caused by various dynamic manifestations of symptoms. For example, persistent chest tightness / chest pain = 3, intermittent chest tightness / chest pain = 2, symptom has been relieved = 1.

[0103] (3) Scoring of the urgency of disease condition, scoring the urgency of the disease condition according to the scoring rules, where various degrees of urgency of the disease condition and their corresponding scores are set in the scoring rules;

[0104] The scoring rules corresponding to the above-mentioned scoring of the urgency of the disease condition can set scores according to the presence or absence of a certain symptom, or can also be set according to different degrees of manifestation of a certain symptom. For example:

[0105] If there is a risk of airway obstruction or potential risk, respiratory disorder, circulatory disorder = 1, if not = 0;

[0106] Scoring for consciousness assessment, such as awake = 1, drowsy = 2, confused = 3, delirious = 3, lethargic = 3, comatose = 4.

[0107] (4) Scoring of vital signs, scoring various vital signs according to the scoring rules and obtaining the total score after weighting, where the scores corresponding to various vital signs at different stages are set in the scoring rules;

[0108] The types of the above-mentioned vital signs are not limited in this embodiment. The scores of various vital signs can be set according to different threshold intervals, and the weights of various vital signs can be set according to the importance of this vital sign among all vital signs or according to the degree to which various vital signs exceed the normal threshold interval during each scoring.

[0109] In this embodiment, the vital signs can include but are not limited to heart rate, blood pressure, respiration, body temperature, SPO2, blood glucose; the weight setting can be as follows:

[0110] Heart rate (HR) weight (w_HR): The normal range is 60 - 100 beats per minute. Heart rates outside this range will affect the weight according to the degree of deviation.

[0111] Blood pressure (BP) weight (w_BP): The normal range is systolic blood pressure 90 - 140 mmHg and diastolic blood pressure 60 - 90 mmHg. The weight is calculated according to the deviation.

[0112] Respiration (R) weight (w_R): The normal range is 12 - 20 breaths per minute. Respiration frequencies outside this range will affect the weight according to the degree of deviation.

[0113] Body temperature (T) weight (w_T): The normal range is 36.5 - 37.2 °C. Body temperatures outside this range will affect the weight according to the degree of deviation.

[0114] SPO2 (w_SPO2) weight: The normal range is 95% - 100%. SPO2 below 95% will affect the weight according to the degree of deviation.

[0115] Blood glucose (GLU) weight (w_GLU): The normal range for fasting is 3.9 - 6.1 mmol / L. Blood glucose outside this range will affect the weight according to the degree of deviation.

[0116] The corresponding vital sign scores can be shown as follows:

[0117] V = HR × w_HR + BP × w_BP + R × w_R + T × w_T + SPO2 × w_SPO2 + GLU × w_GLU

[0118] (5) Physical examination abnormality score: Score the physical examination abnormalities according to the scoring rules, where various physical examination abnormalities and their corresponding scores are set in the scoring rules;

[0119] The above physical examination abnormality scores and scoring rules can be set according to various physical examination abnormalities and their severities in medicine. For example, head and facial features / neck abnormalities = 2, no abnormalities = 0.

[0120] (6) Medical history assessment score: Score the medical history assessment results according to the scoring rules, where various diseases and their corresponding scores are set in the scoring rules;

[0121] The scoring rules for the above medical history assessment scores can be, but are not limited to, cumulative scoring based on the type of medical history, such as brief medical history, past history, allergy history, epidemiological history, family history, etc. Add 1 for each abnormality; record 0 if there is no special case.

[0122] (7) Distance to the hospital score: Score the distance of the target patient to the hospital according to the scoring rules, where the scores corresponding to kilometers are set in the scoring rules;

[0123] The scoring rules for the above-mentioned distance to the hospital score can be but are not limited to cumulative scoring. For example, taking every 1 kilometer as a unit, with a base of 0 and adding 1 for every 1 kilometer.

[0124] (8) Score for traffic congestion on the journey, calculate the congestion index, and score the difference between the congestion index and the base threshold according to the scoring rules, where different differences and corresponding scores are set in the scoring rules. The congestion index calculation formula is as follows:

[0125]

[0126] Among them, C is the congestion index, RS is the normal traffic running speed, and CS is the actual traffic running speed.

[0127] In the above steps, different degrees of differences and corresponding scores are set in the scoring rules. For example, for every 1% increase in congestion, 0.1 points are deducted. That is, if the difference between the congestion index and the base threshold is 3%, then 0.3 points are deducted.

[0128] Example 3: The embodiment of the present invention discloses a medical resource allocation method for pre-hospital emergency, which is a further optimization of the above embodiment. The medical resource allocation scoring model is as follows:

[0129] T = D × w_D + M × w_M + E × w_E + V × w_V + P × w_P + H × w_H - L × w_L - C × w_C

[0130] Among them, T is the total score of a certain type of medical resource; D, M, E, V, P, H, L, C are the scoring results of the sub-items of the score, which are the scoring results of the disease condition assessment details, the scoring results of the disease condition assessment performance, the scoring results of the disease emergency level, the scoring results of the vital signs, the scoring results of the abnormal physical examination, the scoring results of the medical history assessment, the scoring results of the distance to the hospital score, and the scoring results of the traffic congestion score on the journey; w_D, w_M, w_E, w_V, w_P, w_H, w_L, w_C are the weights of each sub-item of the score in this type of medical resource.

[0131] When setting w_D, w_M, w_E, w_V, w_P, w_H, w_L, w_C, the following rules can be followed:

[0132] w_D: The weight factor for the disease condition assessment details score, dynamically adjusted according to the importance of the disease condition assessment details;

[0133] w_M: The weight factor for the disease condition assessment type score, considering the persistence and intermittence of the disease condition;

[0134] w_E: The weight factor for the emergency assessment weighting, considering the emergency levels of the airway, breathing, circulation, and consciousness;

[0135] w_V: The weight factor of the vital sign score, considering the deviation degree of indicators such as heart rate, blood pressure, and respiration;

[0136] w_P: The weight factor of the weighted abnormal rapid physical examination, considering abnormal conditions such as the head, facial features, and neck;

[0137] w_H: The weight factor of the medical history assessment score, considering information such as the chief complaint and past medical history;

[0138] w_L: The weight factor of the patient's distance to the hospital score, considering the impact of distance on the treatment time;

[0139] w_C: The weight factor of the road congestion score, which is dynamically adjusted according to real-time traffic data.

[0140] Example 4: As shown in the appendix Figure 2 The embodiment of the present invention discloses a medical resource allocation method for pre-hospital emergency, which is a further optimization of the above embodiment, including:

[0141] Step S210, score the sub-items of the score according to the scoring rules and the basic data set of the target patient, where the basic data set includes the road data from the location of the target patient to the hospital, the vital sign data, condition data, and medical history data of the target patient, and the sub-items of the score are factors related to medical resource allocation;

[0142] Step S220, import the scoring results of each sub-item of the score into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource, where each medical resource allocation scoring model is constructed by setting different weights for different sub-items of the score in combination with the characteristics of each medical resource;

[0143] Step S230, obtain the scoring results of various medical resources of other patients waiting for allocation at the current moment, and determine the recommended probability of the target patient in various medical resources based on the recommended probability function, where the recommended probability function is as follows:

[0144]

[0145] Among them, T i is the allocation scoring result of a certain medical resource of the target patient; T j is the allocation scoring result of a certain medical resource of the patient waiting for allocation; n is the total number of patients waiting for allocation

[0146] Step S240, obtain the resource allocation result of the target patient by combining the allocation rules and the recommended probabilities of various medical resources, where the allocation rules include:

[0147] If the recommended probability in a certain type of medical resource exceeds the threshold, it is allowed to obtain this medical resource;

[0148] Medical resources are allocated in a class of medical resources in descending order of recommended probability.

[0149] If there are allocated medical resources in the above resource allocation results that are in use, dynamic adjustment can be carried out, including but not limited to: (1) selecting medical resources with a high degree of relevance to the medical resources in use from this class of medical resources for replacement based on the degree of relevance; (2) reallocating medical resources according to the latest basic data set of the target patient.

[0150] It should also be noted that the medical resource allocation process in the present invention is dynamic, and the basic data set of the target patient can be updated according to the set time interval and the judgment of medical staff during the first aid process, and the medical resources can be reallocated.

[0151] According to the method disclosed in the above embodiments, the following applications can be included but not limited to:

[0152] Severity of illness score (S): Endangered 4 points.

[0153] Detailed illness assessment score (D): Dyspnea 3 points + Abdominal pain 2 points + Nausea and vomiting 1 point + Complicated heart failure 4 points = 10 points.

[0154] Illness assessment performance score (M): Persistent symptoms 3 points.

[0155] Illness urgency score (E): Respiratory disorder 1 point + Circulatory disorder 1 point + Confusion 3 points = 5 points.

[0156] Vital sign score (V):

[0157] Heart rate (HR): 120 beats per minute, deviating from the normal range gets 1 point;

[0158] Blood pressure (BP): 180 / 110, diastolic blood pressure deviating from the normal range gets 1.2 points; systolic blood pressure deviating from the normal range gets 0.6 points;

[0159] Respiration (R): 40 breaths per minute, deviating from the normal range gets 1.2 points;

[0160] Respiration (R): 40 breaths per minute, deviating from the normal range gets 1.2 points;

[0161] Body temperature (T): Normal, gets 0 points;

[0162] SPO2: Not provided, gets 0 points;

[0163] Blood glucose (GLU): 13 mmol / L, deviating from the normal range gets 1.38 points;

[0164] After weighting, the total score of V is 5.38 points.

[0165] Physical examination abnormality score (P): The weighted score for open head trauma is 2 points.

[0166] Medical history assessment score (H): Diabetes 1 point, hypertension 1 point, family history 1 point, positive penicillin skin test 1 point, hepatitis B 1 point, total 5 points.

[0167] Distance to the hospital score (L): 5 kilometers, scored 5 points.

[0168] Traffic congestion score (C): 1 kilometer of traffic jam, assuming the congestion index increases by 10%, C = 0.1.

[0169] For medical resources such as operating rooms and catheterization labs, the weight distribution is set as w_S = 0.3; w_D = 0.2; w_M = 0.1; w_E = 0.1; w_V = 0.1; w_P = 0.05; w_H = 0.05; w_L = 0.05; w_C = 0.05. Then the medical resource allocation score result is T = 4.33.

[0170] For medical resources such as operating rooms and catheterization labs, the resource recommendation probability for the target patient is approximately 75.48%. The resource recommendation probability exceeds the threshold of 50% and is at a relatively high level. Therefore, the target patient will be given priority to obtain the resources of the operating room and catheterization lab.

[0171] Example 5: As shown in the appendix Figure 3 The present invention discloses a medical resource allocation method for pre - hospital emergency, which is a further optimization of the above - mentioned embodiments, including:

[0172] Step S310, score the sub - items of the score based on the scoring rules and the basic data set of the target patient. The basic data set includes the distance data from the location of the target patient to the hospital, the vital sign data, the condition data, and the medical history data of the target patient. The sub - items of the score are factors related to medical resource allocation;

[0173] Step S320, import the scoring results of each sub - item of the score into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource. Each medical resource allocation scoring model is constructed by setting different weights for different sub - items of the score in combination with the characteristics of each medical resource;

[0174] Step S330, obtain the scoring results of various medical resources of other patients waiting for resource allocation at the current moment, and determine the recommendation probability of the target patient for various medical resources based on the recommendation probability function. The recommendation probability function is as follows:

[0175]

[0176] Wherein, T iis the allocation score result of a certain medical resource for the target patient; T j is the allocation score result of a certain medical resource for the patient to be allocated; n is the total number of patients to be allocated;

[0177] Step S340: Combine the allocation rules and the recommended probabilities of various medical resources to obtain the resource allocation result for the target patient;

[0178] Step S350: After the medical resource allocation for the target patient is completed, in response to the fact that not all of the actual allocation feedback data of the target patient is less than the corresponding threshold, use an optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model, where the actual allocation feedback data of the target patient includes the rescue success rate, medical resource utilization efficiency, and waiting time for medical treatment of the target patient.

[0179] In this embodiment, the type of the optimization algorithm in step S350 is not limited, and it can be but is not limited to the gradient descent algorithm. The optimization process is as follows:

[0180] (1) Construct a loss function based on the actual allocation feedback data and the predicted allocation feedback data of the target patient. Here, the allocation prediction data is the ideal allocation feedback data that the resource allocation result of the target patient output in step S340 is predicted to achieve.

[0181] For example, select the allocation feedback data of n patients including the target patient, y i is the allocation feedback data, is the allocation prediction data calculated according to the current weight. The mean squared error (MSE) is used as the loss function L, and the formula is:

[0182]

[0183] (2) Use the gradient descent algorithm to adjust the weights of each item in the medical resource allocation scoring model through multiple iterations, so that the loss function is continuously reduced until the optimization stop condition is met.

[0184] The above steps include:

[0185] Gradient calculation: In order to find the direction in which the loss function decreases fastest, the partial derivative of the loss function with respect to each weight w j is calculated to obtain the gradient Taking a linear model as an example (assuming that the predicted allocation effect is a linear combination of the weight w j and the feature x ij , that is where x i0 = 1 corresponds to the bias term), the partial derivative of the mean squared error loss function is calculated as follows:

[0186]

[0187] The above gradient reflects the rate of change of the loss function in the direction of the weight w j The larger the absolute value of the gradient, the more sensitive the loss function is to the change of this weight.

[0188] Updating the weights: After obtaining the gradient, the learning rate α is used to control the step size of each weight update. The weight update formula is as follows: The learning rate α is an important hyperparameter, which determines the magnitude of each weight update. If the value of α is too large, the step size of the weight update will be very large, which may cause the algorithm to oscillate back and forth near the minimum value and even fail to converge. If the value of α is too small, although the algorithm will be relatively stable, the convergence speed will be very slow and more iteration times are required to achieve better results. Therefore, choosing an appropriate learning rate is crucial for the performance of the gradient descent algorithm.

[0189] Iterative optimization: Repeatedly execute the steps of calculating the gradient and updating the weights. Each iteration adjusts the weights in the direction that makes the loss function decrease. As the iteration progresses, the value of the loss function will gradually decrease until the stopping condition is met.

[0190] Embodiment 6: As shown in the appendix Figure 4 This embodiment of the present invention discloses a medical resource allocation device for pre - hospital first aid, including:

[0191] Sub - project scoring unit, which scores the sub - projects of the score by combining the scoring rules and the basic data set of the target patient. The basic data set includes the distance data from the location of the target patient to the hospital, the vital sign data, the condition data and the medical history data of the target patient. The sub - projects of the score are factors related to medical resource allocation;

[0192] Model scoring unit, which imports the scoring results of each sub - project of the score into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource. Each medical resource allocation scoring model is constructed by setting the weights of different sub - projects of the score in combination with the characteristics of each medical resource;

[0193] Recommended probability calculation unit, which obtains the scoring results of various medical resources of other patients waiting for allocation at the current moment, and determines the recommended probability of the target patient in various medical resources based on the recommended probability function. The recommended probability function is as follows:

[0194]

[0195] Where, T i is the allocation scoring result of a certain medical resource of the target patient; T jis the allocation score result of a certain medical resource for a patient waiting for resource allocation; n is the total number of patients waiting for resource allocation.

[0196] Example 7: As shown in the appendix Figure 5 shown, the embodiment of the present invention discloses a medical resource allocation device for pre - hospital first aid, which is a further optimization of the above - mentioned embodiment, and further includes:

[0197] A resource allocation unit, which combines the allocation rules and the recommended probabilities of various medical resources to obtain the resource allocation result of the target patient, where the allocation rules include:

[0198] If the recommended probability in a certain type of medical resource exceeds the threshold, the medical resource is allowed to be obtained;

[0199] In a certain type of medical resource, the medical resources are allocated in order from high to low according to the recommended probability.

[0200] A feedback optimization unit, after the medical resource allocation of the target patient is completed, in response to the fact that not all of the actual allocation feedback data of the target patient is less than the corresponding threshold, uses an optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model, where the actual allocation feedback data of the target patient includes the success rate of treatment, the utilization efficiency of medical resources, and the waiting time for medical treatment of the target patient.

[0201] A sub - project construction unit, which constructs evaluation sub - projects and corresponding scoring rules, including:

[0202] Disease condition assessment detail scoring, scoring the disease condition assessment details according to the scoring rules, where each symptom keyword and its corresponding score are set in the scoring rules;

[0203] Disease condition assessment performance scoring, scoring the dynamic performance of symptoms according to the scoring rules, where various symptom dynamic performances and their corresponding scores are set in the scoring rules;

[0204] Disease condition urgency scoring, scoring the disease condition urgency according to the scoring rules, where various disease condition urgencies and their corresponding scores are set in the scoring rules;

[0205] Vital sign scoring, scoring various vital signs according to the scoring rules and obtaining the total score after weighting, where the scores corresponding to various vital signs at different stages are set in the scoring rules;

[0206] Physical examination abnormality scoring, scoring the physical examination abnormality conditions according to the scoring rules, where various physical examination abnormality conditions and their corresponding scores are set in the scoring rules;

[0207] Medical history assessment scoring, scoring the medical history assessment results according to the scoring rules, where various diseases and their corresponding scores are set in the scoring rules;

[0208] Distance-to-hospital score: The distance from the target patient to the hospital is scored according to the scoring rules, where the score corresponding to each kilometer is set in the scoring rules.

[0209] Route congestion score: Calculate the congestion index and score the difference between the congestion index and the base threshold according to the scoring rules, where different differences and their corresponding scores are set in the scoring rules. The formula for calculating the congestion index is as follows:

[0210]

[0211] where C is the congestion index, RS is the normal traffic speed, and CS is the actual traffic speed.

[0212] Model construction unit: Construct various medical resource allocation scoring models. The medical resource allocation scoring model is as follows:

[0213] T = D×w_D + M×w_M + E×w_E + V×w_V + P×w_P + H×w_H - L×w_L - C×w_C

[0214] where T is the total score of a certain type of medical resource; D, M, E, V, P, H, L, and C are the scoring results of the sub-items of the score, which are the scoring results of the disease assessment details, the scoring results of the disease assessment performance, the scoring results of the disease urgency, the scoring results of the vital signs, the scoring results of the abnormal rapid physical examination, the scoring results of the medical history assessment, the scoring results of the distance-to-hospital score, and the scoring results of the route congestion score, respectively; w_D, w_M, w_E, w_V, w_P, w_H, w_L, and w_C are the weights of each sub-item of the score in this type of medical resource.

[0215] Embodiment 8: An embodiment of the present invention discloses a storage medium, on which a computer program readable by a computer is stored, and the computer program is configured to execute a medical resource allocation method for pre-hospital first aid when running.

[0216] The above storage medium may include, but is not limited to, various media that can store computer programs, such as USB flash drives, read-only memories, mobile hard disks, magnetic disks, or optical discs.

[0217] Embodiment 9: An embodiment of the present invention discloses an electronic device, including a processor and a memory. A computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement a medical resource allocation method for pre-hospital first aid.

[0218] The above-mentioned processor may be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present invention. It can also be a combination that implements computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, and so on. The memory may include, but is not limited to, various media that can store computer programs, such as USB flash drives, read-only memories, external hard drives, magnetic disks, or optical discs.

[0219] Those skilled in the art should understand that the embodiments of the present invention may be provided as a method, a system, or a computer program product. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented in various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0220] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or a combination of multiple flows and / or blocks

[0221] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more of the flows Figure 1 or a combination of multiple flows and / or blocks

[0222] The above content is only a specific implementation manner of the present invention, which has strong adaptability and implementation effects. However, the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A medical resource allocation method for pre-hospital emergency treatment, characterized in that, Including: Scoring the sub - items of the score based on the scoring rules and the basic data set of the target patient. The basic data set includes the distance data from the location of the target patient to the hospital, the vital sign data, the condition data, and the medical history data of the target patient. The sub - items of the score are factors related to the allocation of medical resources; Importing the scoring results of each sub - item of the score into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource. Each medical resource allocation scoring model is constructed by setting the weights of different sub - items of the score in combination with the characteristics of each medical resource; Obtaining the scoring results of various medical resources of other patients to be allocated at the current moment, and determining the recommendation probability of the target patient in various medical resources based on the recommendation probability function. The recommendation probability function is as follows: Among them, T i is the allocation score result of a certain medical resource for the target patient; T j is the allocation score result of a certain medical resource for the patient with the resource to be allocated; n is the total number of all patients with the resource to be allocated.

2. The medical resource allocation method for pre - hospital emergency according to claim 1, wherein It also includes, after the allocation of medical resources for the target patient, in response to the fact that not all of the actual allocation feedback data of the target patient is less than the corresponding threshold, using an optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model. The actual allocation feedback data of the target patient includes the treatment success rate, the medical resource utilization efficiency, and the waiting time for medical treatment of the target patient.

3. The medical resource allocation method for pre-hospital emergency according to claim 2, wherein Using an optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model, including: Constructing a loss function based on the actual allocation feedback data and the predicted allocation feedback data of the target patient; Using the gradient descent algorithm to adjust the weights of each item in the medical resource allocation scoring model through multiple iterations, so that the loss function is continuously reduced until the optimization stop condition is met.

4. The medical resource allocation method for pre-hospital emergency according to claim 1 or 2 or 3, characterized in that It also includes obtaining the resource allocation result of the target patient by combining the allocation rules and the recommendation probabilities of various medical resources. The allocation rules include: If the recommendation probability in a certain type of medical resource exceeds the threshold, it is allowed to obtain this medical resource; In a certain type of medical resource, the medical resources are allocated in order from high to low according to the recommendation probability.

5. The medical resource allocation method for pre-hospital first aid according to claim 1 or 2 or 3, characterized in that The sub - items of the score and the corresponding scoring rules, including: Disease assessment details score: Scoring the disease assessment details according to the scoring rules, where each symptom keyword and its corresponding score are set in the scoring rules; Disease assessment performance score: Scoring the dynamic performance of symptoms according to the scoring rules, where various dynamic performances of symptoms and their corresponding scores are set in the scoring rules; Disease urgency score: Scoring the disease urgency according to the scoring rules, where various disease urgencies and their corresponding scores are set in the scoring rules; Vital sign score: Scoring various vital signs according to the scoring rules and obtaining the total score after weighting. The scores corresponding to various vital signs at different stages are set in the scoring rules; Abnormal physical examination score: Scoring the abnormal physical examination conditions according to the scoring rules, where various abnormal physical examination conditions and their corresponding scores are set in the scoring rules; Medical history assessment score: Scoring the medical history assessment results according to the scoring rules, where various diseases and their corresponding scores are set in the scoring rules; Distance to the hospital score: Scoring the distance from the target patient to the hospital according to the scoring rules, where the scores corresponding to kilometers are set in the scoring rules; Route congestion score. Calculate the congestion index and score the difference between the congestion index and the basic threshold according to the scoring rules. Different differences and corresponding scores are set in the scoring rules. The congestion index calculation formula is as follows: Where C is the congestion index, RS is the normal traffic operation speed, and CS is the actual traffic operation speed.

6. The medical resource allocation method for pre-hospital first aid according to any one of claims 1 to 5, characterized in that The medical resource allocation scoring model is as follows: T = D×w_D + M×w_M + E×w_E + V×w_V + P×w_P + H×w_H - L×w_L - C×w_C Where T is the total score of a certain type of medical resource; D, M, E, V, P, H, L, C are the scoring results of the sub - scoring items, which are the scoring results of the disease condition assessment details, the scoring results of the disease condition assessment performance, the scoring results of the disease emergency level, the scoring results of the vital signs, the scoring results of the physical examination abnormalities, the scoring results of the medical history assessment, the scoring results of the distance to the hospital, and the scoring results of the route congestion; w_D, w_M, w_E, w_V, w_P, w_H, w_L, w_C are the weights of each sub - scoring item in this type of medical resource.

7. A medical resource allocation device for pre-hospital emergency treatment, which applies the method according to any one of claims 1 to 6, characterized in that Including: Sub - item scoring unit. Score the sub - scoring items by combining the scoring rules and the basic data set of the target patient. The basic data set includes the route data from the location of the target patient to the hospital, the vital sign data, the disease condition data, and the medical history data of the target patient. The sub - scoring items are factors related to medical resource allocation. Model scoring unit. Import the scoring results of each sub - scoring item into each medical resource allocation scoring model to obtain the allocation scoring results of each medical resource. Each medical resource allocation scoring model is constructed by setting different weights for each sub - scoring item according to the characteristics of each medical resource. Recommended probability calculation unit. Obtain the scoring results of various medical resources of other patients waiting for allocation at the current moment, and determine the recommended probability of the target patient in various medical resources based on the recommended probability function. The recommended probability function is as follows: Among them, T i is the allocation score result of a certain medical resource for the target patient; T j is the allocation score result of a certain medical resource for the patient to be allocated; n is the total number of all patients to be allocated.

8. The medical resource allocation device for pre-hospital emergency according to claim 7, characterized in that, Also including: Resource allocation unit. Obtain the resource allocation result of the target patient by combining the allocation rules and the recommended probabilities of various medical resources. The allocation rules include: If the recommended probability in a certain type of medical resource exceeds the threshold, the target patient is allowed to obtain this medical resource. Allocate medical resources in a certain type of medical resource in descending order of the recommended probability. Feedback optimization unit. After the medical resource allocation of the target patient is completed, if the actual allocation feedback data of the target patient is not all less than the corresponding thresholds, use the optimization algorithm to optimize and adjust the weights in each medical resource allocation scoring model. The actual allocation feedback data of the target patient includes the success rate of treatment, the utilization efficiency of medical resources, and the waiting time for medical treatment of the target patient.

9. The medical resource allocation device for pre-hospital emergency according to claim 7, characterized in that, Also including: Sub - item construction unit. Construct the sub - scoring items and corresponding scoring rules, including: Disease condition assessment details scoring. Score the disease condition assessment details according to the scoring rules. Different symptom keywords and corresponding scores are set in the scoring rules. Disease assessment performance score: The dynamic manifestations of symptoms are scored according to the scoring rules, where various dynamic manifestations of symptoms and their corresponding scores are set in the scoring rules; Disease urgency score: The disease urgency is scored according to the scoring rules, where various disease urgencies and their corresponding scores are set in the scoring rules; Vital sign score: Various vital signs are scored according to the scoring rules, and the total score is obtained after weighting, where the scores corresponding to various vital signs at different stages are set in the scoring rules; Physical examination abnormality score: The physical examination abnormalities are scored according to the scoring rules, where various physical examination abnormalities and their corresponding scores are set in the scoring rules; Medical history assessment score: The medical history assessment results are scored according to the scoring rules, where various diseases and their corresponding scores are set in the scoring rules; Distance to hospital score: The distance from the target patient to the hospital is scored according to the scoring rules, where the scores corresponding to kilometers are set in the scoring rules; Route congestion score: For the route congestion score, the congestion index is calculated, and the difference between the congestion index and the basic threshold is scored according to the scoring rules, where different differences and their corresponding scores are set in the scoring rules. The congestion index calculation formula is as follows: Where C is the congestion index, RS is the normal traffic operation speed, and CS is the actual traffic operation speed; Model construction unit: Construct various medical resource allocation scoring models. The medical resource allocation scoring model is as follows: T = D×w_D + M×w_M + E×w_E + V×w_V + P×w_P + H×w_H - L×w_L - C×w_C Where T is the total score of a certain type of medical resource; D, M, E, V, P, H, L, C are the scoring results of the sub - scoring items, which are the scoring results of the disease assessment details, disease assessment performance, disease urgency, vital signs, rapid physical examination abnormalities, medical history assessment, distance to hospital, and route congestion scoring results in sequence; w_D, w_M, w_E, w_V, w_P, w_H, w_L, w_C are the weights of each sub - scoring item in this type of medical resource.

10. An electronic device, characterized in that, It includes a processor and a memory. A computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the steps in the method according to any one of claims 1 to 6.

11. A storage medium, characterized in that, A computer program that can be read by a computer is stored on the storage medium, and the computer program is set to execute the steps in the method according to any one of claims 1 to 6 when running.

Images