CN115101180A

CN115101180A - Medical resource configuration method based on big data and electronic equipment

Info

Publication number: CN115101180A
Application number: CN202210738573.9A
Authority: CN
Inventors: 秦铁岭; 王想想; 孟祥伟
Original assignee: Beijing Ziyun Intelligent Technology Co ltd
Current assignee: Beijing Ziyun Intelligent Technology Co ltd
Priority date: 2022-06-24
Filing date: 2022-06-24
Publication date: 2022-09-23

Abstract

The application discloses a medical resource configuration method and electronic equipment based on big data, wherein the method comprises the following steps: determining medical resources consumed by medical health institutions at all levels in quarantine, isolation observation, suspected case diagnosis and treatment and confirmed case treatment; constructing an emergent infectious disease epidemic situation prediction model based on different prevention and control measures and regional and time-interval division, and determining an optimized prediction model of intervention measures with the least medical resource consumption; and formulating a medical resource supply and configuration mode based on the SEIAPHR optimization model prediction value.

Description

Medical resource configuration method based on big data and electronic equipment

Technical Field

The application relates to the technical field of big data, in particular to a medical resource configuration method based on big data and electronic equipment.

Background

In view of the late stage of epidemic control, the epidemic situation is in an intermittent and regional situation, for example, in some developed cities (especially in cities with many international flights), the potential possibility of epidemic recurrence exists. Therefore, allocation of medical resources is an urgent problem to be solved at present. The problems and defects of the prior art are as follows: the total quantity of the sanitary resource allocation resources is insufficient, the service quality is not high, the sanitary resource allocation between cities and countryside and between different regions is unbalanced, and the allocation efficiency is low;

(2) the medical resource allocation is only allocated based on the current situation of epidemic situation prevalence, and short-term and long-term accurate dynamic adjustment is carried out without considering the influence of intervention measures and regional differences, so that the shortage of emergency medical resources in part of time periods of parts of regions is caused, and the phenomena of surplus and waste of medical resources occur in part of regions;

(3) the medical resources consumed by the patient cannot be accurately determined, and the medical resources cannot be accurately supplied and allocated in different regions and different time intervals.

How to rapidly and accurately allocate medical resources becomes a technical problem to be solved urgently.

Disclosure of Invention

The application provides a medical resource configuration method based on big data and an electronic device, which are used for at least solving the technical problems in the related art.

According to a first aspect of the present application, there is provided a big data-based medical resource configuration method, including: determining medical resources consumed by medical health institutions of all levels in quarantine, isolation observation, suspected case diagnosis and treatment and confirmed case treatment; constructing a sudden infectious disease epidemic situation prediction model based on different prevention and control measures and regional and time-interval division, and determining an optimized prediction model of intervention measures with minimum medical resource consumption; and formulating a medical resource supply and configuration mode based on the SEIAPHR optimization model prediction value.

Optionally, the expended medical resources include: human resources; the human resource consumption calculation method comprises the following steps: calculating the time required by each medical service flow by adopting an operation cost method, and calculating the labor time cost of detailed work of the diagnosis and treatment flow; calculating the number of medical staff required by various groups of service unit number according to the per-person service time calculated by determining the diagnosis and treatment process; simultaneously determining the effective working time of each medical staff every year; and calculating the cost of per-person manpower, time and money required to be invested for completing each type of diagnosis and treatment process.

Optionally the expended medical resources include: medical supplies; the medical material consumption calculation method comprises the following steps: medical material consumption is measured and calculated from medical facility equipment and consumables which need to be invested in various medical service processes; the medical staff who carries out the relevant medical service and the financial management department are investigated to collect the investment of medical materials.

Optionally the expended medical resources include: prevention and control cost; the prevention and control cost consumption calculation method comprises the following steps: respectively collecting a plurality of case data of centralized medical isolation, suspected cases, confirmed common cases, severe cases and critical cases, and collecting medical cost data of an investigation object in the whole diagnosis and treatment process; calculating the average medical resource consumption of various cases; the medical costs include direct medical costs and indirect medical costs; the direct medical costs include out-patient costs and hospitalization costs; the hospitalization cost comprises diagnosis detection cost, health detection cost, medication cost, cost for treating related complications and hospitalization cost; the indirect medical cost comprises the food and lodging cost and the work error cost during the isolation period and medical resources occupied by blocking nosocomial infection.

Optionally, the establishment of the emergent infectious disease epidemic situation prediction model based on different prevention and control measures and regional and time-interval division comprises the following steps: obtaining a real footprint chain of a positive patient by using the mobile phone signaling data; determining a high risk area by taking each point on the patient footprint chain as a search origin; updating the high-risk area every day to obtain each closed unit in the high-risk area; according to the obtained medical resource investment required by each high-risk area on the same day, the fastest distribution time and the optimal distribution scheme are obtained by combining the space distribution condition and the real-time traffic condition of the medical resource suppliers, and single-center distribution and multi-center distribution of the medical resources are carried out.

Alternatively the footprint chain of positive patients is derived as follows: obtaining a dictation footprint chain and a mobile phone signaling footprint chain of a positive patient; and checking whether the dictation footprint chain and the mobile phone signaling footprint chain are completely matched, if so, the mobile phone signaling footprint chain is the real footprint chain of the patient, otherwise, on the basis of the mobile phone signaling footprint chain, adding the positions and the corresponding times which are contained in the dictation chain but not contained in the mobile phone signaling footprint chain into the patient footprint chain, and obtaining the mobile phone signaling footprint chain by traversing all the points in the dictation chain, namely the real footprint chain of the patient.

Optionally, the method for determining the cell phone signaling footprint chain is as follows: obtaining mobile phone signaling data, wherein the mobile phone signaling data comprises a user ID, longitude, latitude and a timestamp; preprocessing the mobile phone signaling data, reserving a first piece of repeated data for the repeated data, and deleting the rest of the repeated data; supplementing missing data by adopting an averaging method; counting the number of points in a neighborhood by taking a single trip point with the earliest timestamp as an initial search position and taking a preset radius r and timestamp time as a neighborhood search position data set; if the number of points in the neighborhood is greater than the preset minimum number of points minpoints, classifying the points in the neighborhood into one class, otherwise, marking the points as noise points until the whole data set is traversed; calculating core points of all points in a cluster formed by the neighborhood to replace all stop points in the cluster, and arranging a series of core points according to the time dimension to obtain a mobile phone signaling footprint chain of the positive patient; the core point is the point where the center of the neighborhood is located.

Optionally, the method for distribution of medical resources comprises the following steps: the travel time of a plurality of medical resource suppliers under different configuration schemes for distributing medical resources to each high-risk area is measured, and if the total amount of the medical resources of a single medical resource supplier is insufficient, n medical resource suppliers can be coordinated to distribute the medical resources to the same target at the same time, so that the obtained optimal-time scheme is the adopted distribution scheme.

According to a second aspect of the present application, an embodiment of the present application further provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the big data based medical resource configuring method of any one of the above first aspects.

According to a third aspect of the present application, there is also provided a computer-readable storage medium storing a computer program, which when executed by a processor implements the big data based medical resource configuring method according to any one of the first aspect.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is a schematic flow chart of a medical resource configuration method based on big data according to the present application.

Detailed Description

In order to more clearly explain the overall concept of the present application, the following detailed description is given by way of example in conjunction with the accompanying drawings.

In order to make the technical solutions of the present application better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the accompanying drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the application provides a public resource management method based on trauma big data, and with reference to fig. 1, the method may include the following steps:

s11, determining medical resources consumed by medical and health institutions of all levels in quarantine, isolation observation, suspected case diagnosis and treatment and confirmed case treatment.

S12, establishing a sudden infectious disease epidemic situation prediction model based on different prevention and control measures and regional and time-interval division, and determining an optimized prediction model of intervention measures with minimum medical resource consumption. S13, formulating medical resource supply and configuration mode based on SEIAPHR optimization model predicted value

Determining medical resources consumed by medical health institutions at all levels in quarantine, isolation observation, suspected case diagnosis and treatment and confirmed case treatment by adopting a data collection and management method, a questionnaire survey and interview survey method, a group discussion method, a Delphi method and a data statistical analysis method; constructing an emergent infectious disease epidemic situation prediction model based on different prevention and control measures and regional and time-interval division, and determining an optimized prediction model of intervention measures with the least medical resource consumption;

and formulating a medical resource supply and configuration mode based on the SEIAPHR optimization model prediction value.

The medical resources consumed by the embodiment of the invention comprise: human resources, medical supplies and prevention and control costs; (1) the human resource consumption calculation method comprises the following steps:

firstly, calculating the time required by each medical service flow by adopting an operation cost method, and calculating the labor time cost of detailed work of the diagnosis and treatment flow;

secondly, calculating the number of medical staff required by various groups of service unit numbers according to the per-person service time calculated by determining the completion of the diagnosis and treatment process; simultaneously determining the effective working time of each medical staff every year;

finally, calculating the per-capita manpower time and currency cost required to be invested for completing each type of diagnosis and treatment process;

(2) the medical material consumption calculation method comprises the following steps: medical material consumption is calculated from medical facility equipment and consumables which need to be invested in various medical service processes; collecting the input of medical materials by surveying medical staff who carry out related medical services and a financial management department;

(3) the prevention and control cost consumption calculation method comprises the following steps: retrospectively collecting the case data of centralized medical isolation, suspected cases, confirmed common cases (including 50 cases with mild symptoms), 100 cases with severe cases and 50 cases with severe cases respectively, and collecting the medical cost data of the investigation object in the whole diagnosis and treatment process; calculating the average medical resource consumption of various cases;

the medical costs include direct medical costs and indirect medical costs; the direct medical costs include out-patient costs and hospitalization costs; the hospitalization cost comprises diagnosis detection cost, health detection cost, medication cost, cost for treating related complications and hospitalization cost; the indirect medical cost comprises the food and lodging cost and the work error cost during the isolation period and medical resources occupied by blocking nosocomial infection.

The embodiment of the invention provides an optimized prediction model for constructing a sudden infectious disease epidemic situation prediction model based on different prevention and control measures and regional and time-sharing intervals and determining an intervention measure with minimum medical resource consumption, which comprises the following steps:

1) collecting relevant epidemiological data and sorting abnormal values;

2) determining factors for inclusion into the model: factors of the traditional SEIR model are included: time lag factors, infectivity, latency, disease return, and factors affecting medical resource consumption: different stages of disease prevalence, regional factors, population changes, changes of prevention and control policy measures, tracking and isolation of close contacts, suspected cases and disease critical degree;

3) determining main indexes of model prediction: the number of isolated persons and suspected cases is centralized, and the hospitalization cases are isolated after confirmed diagnosis;

4) constructing a SEAPIHR model; constructing a SEAPIHR optimization model;

5) performing parameter inversion and trend prediction on the SEIAPHR model in an epidemic process, combining a least square method and a Markov Monte Carlo algorithm to perform the parameter inversion of the SEIAPHR model, selecting the parameter distribution as normal distribution, and utilizing a Metropolis-Hastings algorithm; solving the differential equation by using an implicit Runge-Kutta rigid differential equation solving algorithm;

6) on the basis of the SEIAPRS infectious disease cabin model, cases and personnel migration between different regions, namely epidemic origin regions, bordering regions and non-bordering regions, population change, change of prevention and control policy measures, lag factors of implementation time of the prevention and control measures and use related factors of vaccines are introduced, and the SEIAPRS cabin model is improved.

The SEIAPHR model construction method provided by the embodiment of the invention comprises the following steps:

firstly, dividing the total number of people in a considered area into 11 types, a susceptible type S, a latent type E in a free environment, a diseased type I and an asymptomatic infected type A, tracking to perform medical observation, wherein the susceptible type Sq and the asymptomatic latent type Eq are respectively obtained by intensively isolating medical observation S1q and domestic medical observation S2q, the suspected case is P, the diagnosed and hospitalized isolated treated type is H, the recovered type is R and the dead type is D;

the total weight of the human body at the moment t is represented by the following general formula (I), (t), S1q (t), S2q (t), E (t), I (t), A (t), Sq (t), S1q (t) and S2q (t)), Eq (t), P (t), H (t), R (t) and D (t) respectively, and the general formula (I) is shown in the specification:

N(t)＝S(t)+E(t)+I(t)+A(t)+H(t)+R(t)

the number of confirmed medical treatment cases H is divided into three categories: the general and light confirmed disease humans I1, the severe confirmed disease humans I2, and the severe confirmed disease humans I3, and the number of the three groups of people at time t, day t, and further H (t) I1(t) + I2(t) + I3(t) are respectively recorded by Ii (t) (I ═ 1,2, 3);

secondly, determining input and output relations of a susceptible class, an isolated class and a latent class; due to the implementation of close-tracking isolation measures, the population in close contact with infected persons is divided into an isolated susceptible class Sq, and a latent class Eq. Tracking by close contact of the infected, assuming that the contacter class of q1+ q2(═ q) proportion is isolated, wherein the isolated individual of q2 proportion is isolated in the Eq bin if infected, otherwise in the Sq bin; q1 proportion of isolated individuals will be isolated to the P compartment by the fever clinic if infected, otherwise isolated in the Sq compartment; the Sq chamber comprises a household medical observer S1q and a centralized isolation medical observer S2q, wherein r proportion of close contacts in the Sq chamber are centralized and medically isolated in the S1q chamber, and 1-r proportion of close contacts are household isolated in the S2q chamber; if a proportion of 1-q contacts are missed in the tracking, once effectively infected, move to E-chamber, otherwise remain in S-chamber; assuming a probability of propagation per contact of β and a number of contacts of c, assuming that the isolated individual, if infected, moves to bin P and bin Eq at rates of β cq1 and β cq2, respectively; otherwise, the cells are moved to bins Sq and E at rates of (1-. beta.) cq and β c (1-q).

The method for formulating the medical resource supply and configuration mode based on the SEIAPHR optimization model prediction value comprises the following steps:

firstly, establishing a medical resource allocation optimization model by combining the number of people needing isolation, the number of suspected cases and the number of people who are confirmed to be treated, which are predicted by the obtained prediction model, with medical technicians, medical materials and medical expenses which need to be input by various people in each case, so as to obtain the allocation number of medical resources in different areas and different time periods;

secondly, comparing the quantity of medical resource consumption measured and calculated by the model with the medical resource actually input by the investigation region, evaluating the scientificity and accuracy of the medical resource measuring and calculating method, modifying the model, finally determining the weight coefficient of the intervention force, and making an optimization scheme which has practical value and is used for dealing with the medical resource allocation of the emergent public health incident;

and finally, dividing the measured medical resource demand into an emergency medical resource storage part and a part needing emergency allocation of medical resources, and performing emergency medical resource allocation.

When a small-scale epidemic situation outbreak occurs, a process for quickly arranging medical resources is as follows: after positive patients are found, footprint chains (hereinafter, abbreviated as dictation footprint chains) with time dimension dictated by the patients and communication big data are obtained by using a traditional investigation means, and information of the footprint chains (hereinafter, abbreviated as mobile signaling footprint chains) with time dimension calculated by using mobile signaling data is subjected to cross verification and revision to obtain approximately real patient footprint chains. And then, a high-risk area searching model considering the road network structure is adopted, and the high-risk area is quickly locked and closed unit extraction is carried out by combining the virus day toxicity, the patient footprint center point group, the road network structure and the accessibility. And finally, combining network map service and a path planning algorithm to obtain a final medical resource distribution scheme of each closed unit.

The premise of accurately judging the high-risk area is to master the accurate footprint chain information of positive patients. The model utilizes the dictation footprint chain and the mobile phone signaling footprint chain of the patient simultaneously to jointly determine the action track of the patient. When oral information of a patient is acquired, the method mainly works to determine the activity track of the positive patient, determine the related information such as travel history, contact history and exposure history, and particularly pay attention to the retention time of a case exposed to intensive places of people such as farmer markets, shopping malls, supermarkets and hospitals, the number of people or the intensive degree and other indexes, so that the possible infection range and susceptible people are determined.

Accurate acquisition of the mobile phone signaling footprint chain is a precondition for mastering accurate footprint chain information of positive patients. The format of the handset signaling data includes user ID, longitude, latitude, and timestamp, examples of which are shown in table 1. In order to eliminate the adverse effect of data errors on subsequent analysis, data needs to be preprocessed. The method comprises the following steps: (1) for the repeated data, the first piece of data of the repeated data is reserved, and the rest of the repeated data is deleted. (2) And for missing data, replacing by using an averaging method. As known from the data format, the mobile signaling data is data based on the location of the base station. Therefore, the individual position location can be completed by utilizing a trigonometric formula estimation algorithm, and the position data set Point with the longitude and latitude data of the single trip Point and the timestamp data of the single trip Point is obtained.

The steps of the footprint chain extraction algorithm based on the mobile phone signaling data set are as follows: (1) sequencing the position data sets according to time sequence, and determining a time interval t, wherein a plurality of stop points are possible in t, but a core point is required to be calculated by utilizing the plurality of stop points to construct a footprint chain, (2) setting a geographical clustering radius r and a minimum point number minpoints, wherein the radius r represents the maximum moving distance of a user in the time interval t, the minimum point number minpoints represents the minimum number of the stop points which should appear in the time interval t, if the minimum number is less than the minimum number, the pseudo-stop points caused by data drift of the communication base station can be regarded as pseudo-stop points, and related pseudo-stop points can be deleted; if it is larger than the minimum number minpoints, it will be considered as real stopover points, and the core points will be calculated from these stopover points. 3) And (4) sequencing according to the time latitude by using the obtained core points, and constructing a positive patient footprint chain, namely a mobile phone signaling footprint chain.

There are also the following methods for extraction of footprint chains: (1) and extracting the user travel track by using a Bayesian network and a hidden Markov model based on the mobile phone positioning data. (2) Travel parameters are extracted based on the data of the mobile phone sensor by applying wavelet analysis, neural network and other mining technologies. (3) And extracting travel stop points by utilizing vehicle-mounted GPS data and a K-means clustering algorithm. (4) And extracting a stop point based on the time clustering of the GPS, the base station and the Wi-Fi data, and extracting a footprint chain in a time characteristic and map superposition mode. Compared with the method, the path point clustering extraction algorithm provided by the model has the following advantages: (1) the extraction result of the footprint chain is insensitive to abnormal points in the data set, and the abnormal points can be found while the footprint chain is extracted. (2) The selection of the initial value of the extraction algorithm has little influence on the result. (3) Footprint chain extraction can be performed on the position data set which is distributed randomly, and a clustering algorithm like K-means extracts the footprint chain only suitable for the convex set.

The process of obtaining the positive patient real footprint chain according to the dictation footprint chain and the mobile phone signaling footprint chain is as follows: and (1) checking whether the dictation footprint chain is completely matched with the mobile phone signaling footprint chain, and jumping to the step (2). (2) And (4) if the real footprint chain is completely matched with the real footprint chain of the patient, the mobile phone signaling footprint chain is the real footprint chain of the patient, and if the real footprint chain is not completely matched with the real footprint chain of the patient, the step (3) is skipped. (3) And adding the positions and the corresponding time of the positions which are contained in the dictation chain but not contained in the mobile phone signaling footprint chain into the patient footprint chain on the basis of the mobile phone signaling footprint chain until all the points in the dictation chain are traversed, wherein the mobile phone signaling footprint chain at the moment is the real footprint chain of the patient.

The measurement and calculation of the delivery time of the medical resources are the key points for improving the efficiency of medical resource allocation. The model measures and calculates the travel time from the medical resource supplier to the medical resource demander under different configuration schemes by utilizing the map API and based on the massive real-time road network data provided by the digital map, and determines the most suitable supplier to provide medical service for the demander in the shortest time. In order to rate the optimal corresponding relation between the medical resource supply and demand parties, the following operations are carried out on the supply parties capable of providing the medical resource: (1) and if the total amount Souk of the investable medical resources of a certain single supplier k is larger than the medical resource requirement Soui of the demander i, adding k into the to-be-paired set M of i. (2) And sequentially measuring travel time between the supplier and the demander for the suppliers in the M set, and selecting the supplier j with the shortest travel time as a matched supplier of the demander i. (3) The remaining medical resource of donor j, Resouj-Soii, is calculated. (4) And replacing Souj with Resouj, and performing the next round of search. And performing multi-center distribution until a single supplier cannot meet the requirement of the demander. The scheme of multi-center distribution is as follows: and calculating the combined distribution scheme of all the satisfied demanders i in the rest suppliers, calculating the distribution time between each group of schemes and the demander i, and selecting the final distribution scheme with the shortest time. Thus, the calculation of the theoretical medical resource input amount and the travel time between the medical resource supply and demand parties is completed.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disk, ROM, RAM, magnetic or optical disk, and the like.

The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a storage medium, and including instructions for causing one or more computer devices (which may be personal computers, servers, network devices, or the like) to execute all or part of the steps of the method described in the embodiments of the present application.

In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, and may also be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

Where not mentioned in this application, can be accomplished using or referencing existing technology.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A medical resource allocation method based on big data is characterized by comprising the following steps:

determining medical resources consumed by medical health institutions at all levels in quarantine, isolation observation, suspected case diagnosis and treatment and confirmed case treatment;

constructing a sudden infectious disease epidemic situation prediction model based on different prevention and control measures and regional and time-interval division, and determining an optimized prediction model of intervention measures with minimum medical resource consumption;

2. The big-data based medical resource configuration method according to claim 1, wherein the consumed medical resource comprises: human resources;

the human resource consumption calculation method comprises the following steps:

calculating the time required by each medical service flow by adopting an operation cost method, and calculating the labor time cost of detailed work of the diagnosis and treatment flow;

calculating the number of medical staff required by various groups of service unit number according to the per-person service time calculated by determining the diagnosis and treatment process; simultaneously determining the effective working time of each medical staff every year;

and calculating the cost of per-person manpower, time and money required to be invested for completing each type of diagnosis and treatment process.

3. The big-data based medical resource configuration method according to claim 1, wherein the consumed medical resource comprises: medical supplies;

the medical material consumption calculation method comprises the following steps:

medical material consumption is measured and calculated from medical facility equipment and consumables which need to be invested in various medical service processes;

the medical staff who carries out the relevant medical service and the financial management department are investigated to collect the investment of medical materials.

4. The big-data based medical resource configuration method according to claim 1, wherein the consumed medical resource comprises: prevention and control costs;

the prevention and control cost consumption calculation method comprises the following steps:

respectively collecting a plurality of case data of centralized medical isolation, suspected cases, confirmed common cases, severe cases and critical cases, and collecting medical cost data of an investigation object in the whole diagnosis and treatment process;

calculating the average medical resource consumption of various cases;

the medical costs include direct medical costs and indirect medical costs; the direct medical costs include out-patient costs and hospitalization costs; the hospitalization cost comprises diagnosis detection cost, health detection cost, medication cost, cost for treating related complications and hospitalization cost; the indirect medical cost comprises food and lodging fees and labor error fees during isolation, and medical resources occupied by blocking nosocomial infection.

5. The medical resource allocation method based on big data as claimed in claim 1, wherein constructing the prediction model of epidemic situation of sudden infectious disease based on different prevention and control measures and regional and time-sharing comprises:

obtaining a real footprint chain of a positive patient by using the mobile phone signaling data;

determining a high risk area by taking each point on the patient footprint chain as a search origin;

updating the high-risk area every day to obtain each closed unit in the high-risk area;

according to the obtained medical resource investment required by each high-risk area on the same day, the fastest distribution time and the optimal distribution scheme are obtained by combining the space distribution condition and the real-time traffic condition of the medical resource suppliers, and single-center distribution and multi-center distribution of the medical resources are carried out.

6. The big-data based medical resource configuration method of claim 1, wherein the footprint chain of the positive patient is obtained by:

obtaining a dictation footprint chain and a mobile phone signaling footprint chain of a positive patient;

and checking whether the dictation footprint chain is completely matched with the mobile phone signaling footprint chain, if so, determining the mobile phone signaling footprint chain as the real footprint chain of the patient, otherwise, adding the position which is contained in the dictation footprint chain but not contained in the mobile phone signaling footprint chain and the corresponding time into the patient footprint chain on the basis of the mobile phone signaling footprint chain until all the points in the dictation chain are traversed to obtain the mobile phone signaling footprint chain which is the real footprint chain of the patient.

7. The big-data based medical resource configuration method according to claim 6, wherein the determination method of the cell phone signaling footprint chain is as follows:

obtaining mobile phone signaling data, wherein the mobile phone signaling data comprises a user ID, longitude, latitude and a timestamp;

preprocessing the mobile phone signaling data, and deleting the rest repeated data for the first data of the repeated data retention repeated data; supplementing missing data by adopting an averaging method;

counting the number of points in a neighborhood by taking a single trip point with the earliest timestamp as an initial search position and taking a preset radius r and timestamp time as a neighborhood search position data set;

if the number of points in the neighborhood is greater than the preset minimum number of points minpoints, classifying the points in the neighborhood into one class, otherwise, marking the points as noise points until the whole data set is traversed;

calculating core points of all points in a cluster formed by the neighborhood to replace all stop points in the cluster, and arranging a series of core points according to the time dimension to obtain a mobile phone signaling footprint chain of the positive patient; the core point is the point where the center of the neighborhood is located.

8. The epidemic situation medical resource distribution method of claim 1, wherein the distribution method of medical resources comprises the following steps:

the travel time of a plurality of medical resource suppliers under different configuration schemes for distributing medical resources to each high-risk area is measured, and if the total amount of the medical resources of a single medical resource supplier is insufficient, n medical resource suppliers can be coordinated to distribute the medical resources to the same target at the same time, so that the obtained optimal-time scheme is the adopted distribution scheme.

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the big data based medical resource configuring method of any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the big data based medical resource configuring method according to any one of claims 1 to 8.